{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Credit Approval Tutorial\n", "This tutorial illustrates the use of several methods in the AI Explainability 360 Toolkit to provide different kinds of explanations suited to different users in the context of a credit approval process enabled by machine learning. We use data from the [FICO Explainable Machine Learning Challenge](https://community.fico.com/s/explainable-machine-learning-challenge) as [described below](#intro). The three types of users (a.k.a. consumers) that we consider are a data scientist, who evaluates the machine learning model before deployment, a loan officer, who makes the final decision based on the model's output, and a bank customer, who wants to understand the reasons for their application result. \n", "\n", "For the [data scientist](#rule-based-models), we present two directly interpretable rule-based models that provide global understanding of their behavior. These models are produced by the [Boolean Rule Column Generation](#BRCG) (BRCG, class `BooleanRuleCG`) and [Logistic Rule Regression](#LogRR) (LogRR, class `LogisticRuleRegression`) algorithms in AIX360. The former yields very simple OR-of-ANDs classification rules while the latter gives weighted combinations of rules that are more accurate and still interpretable.\n", "\n", "For the [loan officer](#prototypes), we demonstrate a different way of explaining machine learning predictions by showing examples, specifically _prototypes_ or representatives in the training data that are similar to a given loan applicant and receive the same class label. We use the ProtoDash method (class `ProtodashExplainer`) to find these prototypes.\n", "\n", "For the [bank customer](#contrastive), we consider the Contrastive Explanations Method (CEM, class `CEMExplainer`) for explaining the predictions of black box models to end users. CEM builds upon the popular approach of highlighting features present in the input instance that are responsible for the model's classification. In addition to these, CEM also identifies features that are (minimally) absent in the input instance, but whose presence would have altered the classification.\n", "\n", "The tutorial is organized around these three types of consumers, following an introduction to the dataset.\n", "1. [Introduction to FICO HELOC Dataset](#intro)\n", "2. [Data Scientist: Boolean Rules and Logistic Rule Regression models](#rule-based-models)\n", "3. [Loan Officer: Similar samples as explanations for predictions based on HELOC Dataset](#prototypes)\n", "4. [Customer: Contrastive Explanations for predictions based on HELOC Dataset](#contrastive)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 1. Introduction to FICO HELOC Dataset\n", "\n", "The FICO HELOC dataset contains anonymized information about home equity line of credit (HELOC) applications made by real homeowners. A HELOC is a line of credit typically offered by a US bank as a percentage of home equity (the difference between the current market value of a home and the outstanding balance of all liens, e.g. mortgages). The customers in this dataset have requested a credit line in the range of USD 5,000 - 150,000. The machine learning task we are considering is to use the information about the applicant in their credit report to predict whether they will make timely payments over a two year period. The machine learning prediction can then be used to decide whether the homeowner qualifies for a line of credit and, if so, how much credit should be extended. \n", "\n", "The HELOC dataset and more information about it, including instructions to download, can be found [here](https://community.fico.com/s/explainable-machine-learning-challenge?tabset-3158a=2).\n", "\n", "The table below reproduces part of the data dictionary that comes with the HELOC dataset, explaining the predictor variables and target variable. For example, NumSatisfactoryTrades is a predictor variable that counts the number of past credit agreements with the applicant, which resulted in on-time payments. The target variable to predict is a binary variable called RiskPerformance. The value “Bad” indicates that an applicant was 90 days past due or worse at least once over a period of 24 months from when the credit account was opened. The value “Good” indicates that they have made their payments without ever being more than 90 days overdue. The relationship between a predictor variable and the target is indicated in the last column of the table. If a predictor variable is monotonically decreasing with respect to probability of bad = 1, it \n", "means that as the value of the variable increases, the probability of the loan application being \"Bad\" decreases, i.e. it becomes more \"good\". For example, ExternalRiskEstimate and NumSatisfactoryTrades are shown as monotonically decreasing. Monotonically increasing has the opposite meaning.\n", "\n", "\n", "|Field | Meaning |Monotonicity Constraint (with respect to probability of bad = 1)|\n", "|------|---------|----------------------------------------------------------------|\n", "|ExternalRiskEstimate |\tConsolidated version of risk markers |Monotonically Decreasing| \n", "|MSinceOldestTradeOpen\t| Months Since Oldest Trade Open | Monotonically Decreasing|\n", "|MSinceMostRecentTradeOpen | Months Since Most Recent Trade Open |Monotonically Decreasing\n", "|AverageMInFile\t| Average Months in File |Monotonically Decreasing|\n", "|NumSatisfactoryTrades |\tNumber Satisfactory Trades |Monotonically Decreasing|\n", "|NumTrades60Ever2DerogPubRec |\tNumber Trades 60+ Ever |Monotonically Decreasing|\n", "|NumTrades90Ever2DerogPubRec | Number Trades 90+ Ever |Monotonically Decreasing| \n", "|PercentTradesNeverDelq\t| Percent Trades Never Delinquent|Monotonically Decreasing|\n", "|MSinceMostRecentDelq\t| Months Since Most Recent Delinquency|Monotonically Decreasing|\n", "|MaxDelq2PublicRecLast12M |\tMax Delq/Public Records Last 12 Months. See tab \"MaxDelq\" for each category|Values 0-7 are monotonically decreasing|\n", "|MaxDelqEver |\tMax Delinquency Ever. See tab \"MaxDelq\" for each category|Values 2-8 are monotonically decreasing|\n", "|NumTotalTrades\t| Number of Total Trades (total number of credit accounts)|No constraint|\n", "|NumTradesOpeninLast12M\t| Number of Trades Open in Last 12 Months|Monotonically Increasing| \n", "|PercentInstallTrades\t| Percent Installment Trades|No constraint|\n", "|MSinceMostRecentInqexcl7days |\tMonths Since Most Recent Inq excl 7days|Monotonically Decreasing| \n", "|NumInqLast6M\t| Number of Inq Last 6 Months|Monotonically Increasing|\n", "|NumInqLast6Mexcl7days\t| Number of Inq Last 6 Months excl 7days. Excluding the last 7 days removes inquiries that are likely due to price comparision shopping. |Monotonically Increasing|\n", "|NetFractionRevolvingBurden\t| Net Fraction Revolving Burden. This is revolving balance divided by credit limit |Monotonically Increasing|\n", "|NetFractionInstallBurden\t| Net Fraction Installment Burden. This is installment balance divided by original loan amount |Monotonically Increasing| \n", "|NumRevolvingTradesWBalance\t| Number Revolving Trades with Balance |No constraint|\n", "|NumInstallTradesWBalance\t| Number Installment Trades with Balance |No constraint|\n", "|NumBank2NatlTradesWHighUtilization\t| Number Bank/Natl Trades w high utilization ratio |Monotonically Increasing|\n", "|PercentTradesWBalance\t| Percent Trades with Balance |No constraint\n", "|RiskPerformance\t| Paid as negotiated flag (12-36 Months). String of Good and Bad | Target |\n", "\n", "\n", "#### Storing HELOC dataset to run this notebook\n", "- In this notebook, we assume that the HELOC dataset is saved as `./aix360/data/heloc_data/heloc_dataset.csv`, where \".\" is the root directory of the Git repository before running a pip install of aix360 library. \n", "- If the data is downloaded after installation, please place the file within the respective folder under site-packages of your virtual environment `path-to-your-virtual-env/lib/python3.6/site-packages/aix360/data/heloc_data/heloc_dataset.csv`\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 2. Data scientist: Boolean Rule and Logistic Rule Regression models\n", "In evaluating a machine learning model for deployment, a data scientist would ideally like to understand the behavior of the model as a whole, not just in specific instances (e.g. specific loan applicants). This is especially true in regulated industries such as banking where higher standards of explainability may be required. For example, the data scientist may have to present the model to: 1) technical and business managers for review before deployment, 2) a lending expert to compare the model to the expert's knowledge, or 3) a regulator to check for compliance. Furthermore, it is common for a model to be deployed in a different geography than the one it was trained on. A global view of the model may uncover problems with overfitting and poor generalization to other geographies before deployment.\n", "\n", "Directly interpretable models can provide such global understanding because they have a sufficiently simple form for their workings to be transparent. Below we present two directly interpretable models in the form of a [Boolean rule (BR)](#BRCG) and a [logistic rule regression (LogRR)](#LogRR) model. The former is produced by the Boolean Rule Column Generation (BRCG) algorithm while the latter is a generalized linear rule model (GLRM), both implemented in AIX360. While both models are interpretable, they provide different trade-offs between model simplicity and accuracy in predicting loan repayment. BRCG yields a very simple set of rules that has reasonable accuracy. LogRR achieves higher accuracy, higher even than some uninterpretable models, while retaining the form of a linear model. Its interpretation is enhanced by [plots as demonstrated below](#visualize)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 2.1. Load and process data for BRCG and LogRR\n", "We use the `HELOCDataset` class in AIX360 to load the FICO HELOC data as a DataFrame. The setting `custom_preprocessing=nan_preprocessing` converts special values in the data (coded as negative integers) to `np.nan`, which can be handled properly by BRCG and LogRR, as opposed to replacing them with zeros or mean values. The data is then split into training and test sets using a fixed random seed." ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
89608403194948864998
ExternalRiskEstimate64.057.059.065.065.0
MSinceOldestTradeOpen175.047.0168.0228.0117.0
MSinceMostRecentTradeOpen6.09.03.05.07.0
AverageMInFile97.035.038.069.048.0
NumSatisfactoryTrades29.05.021.024.07.0
NumTrades60Ever2DerogPubRec9.01.00.03.01.0
NumTrades90Ever2DerogPubRec9.00.00.02.01.0
PercentTradesNeverDelq63.050.0100.085.078.0
MSinceMostRecentDelq2.016.0NaN3.036.0
MaxDelq2PublicRecLast12M4.06.07.00.06.0
MaxDelqEver4.05.08.02.04.0
NumTotalTrades41.010.021.027.09.0
NumTradesOpeninLast12M1.01.012.01.02.0
PercentInstallTrades63.030.038.031.056.0
MSinceMostRecentInqexcl7days0.00.00.07.07.0
NumInqLast6M1.02.01.00.00.0
NumInqLast6Mexcl7days1.02.01.00.00.0
NetFractionRevolvingBurden16.066.085.013.054.0
NetFractionInstallBurden94.070.090.066.069.0
NumRevolvingTradesWBalance1.02.010.03.02.0
NumInstallTradesWBalance1.02.05.02.03.0
NumBank2NatlTradesWHighUtilizationNaN0.04.00.01.0
PercentTradesWBalance50.057.094.046.083.0
\n", "
" ], "text/plain": [ " 8960 8403 1949 4886 4998\n", "ExternalRiskEstimate 64.0 57.0 59.0 65.0 65.0\n", "MSinceOldestTradeOpen 175.0 47.0 168.0 228.0 117.0\n", "MSinceMostRecentTradeOpen 6.0 9.0 3.0 5.0 7.0\n", "AverageMInFile 97.0 35.0 38.0 69.0 48.0\n", "NumSatisfactoryTrades 29.0 5.0 21.0 24.0 7.0\n", "NumTrades60Ever2DerogPubRec 9.0 1.0 0.0 3.0 1.0\n", "NumTrades90Ever2DerogPubRec 9.0 0.0 0.0 2.0 1.0\n", "PercentTradesNeverDelq 63.0 50.0 100.0 85.0 78.0\n", "MSinceMostRecentDelq 2.0 16.0 NaN 3.0 36.0\n", "MaxDelq2PublicRecLast12M 4.0 6.0 7.0 0.0 6.0\n", "MaxDelqEver 4.0 5.0 8.0 2.0 4.0\n", "NumTotalTrades 41.0 10.0 21.0 27.0 9.0\n", "NumTradesOpeninLast12M 1.0 1.0 12.0 1.0 2.0\n", "PercentInstallTrades 63.0 30.0 38.0 31.0 56.0\n", "MSinceMostRecentInqexcl7days 0.0 0.0 0.0 7.0 7.0\n", "NumInqLast6M 1.0 2.0 1.0 0.0 0.0\n", "NumInqLast6Mexcl7days 1.0 2.0 1.0 0.0 0.0\n", "NetFractionRevolvingBurden 16.0 66.0 85.0 13.0 54.0\n", "NetFractionInstallBurden 94.0 70.0 90.0 66.0 69.0\n", "NumRevolvingTradesWBalance 1.0 2.0 10.0 3.0 2.0\n", "NumInstallTradesWBalance 1.0 2.0 5.0 2.0 3.0\n", "NumBank2NatlTradesWHighUtilization NaN 0.0 4.0 0.0 1.0\n", "PercentTradesWBalance 50.0 57.0 94.0 46.0 83.0" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Load FICO HELOC data with special values converted to np.nan\n", "from aix360.datasets.heloc_dataset import HELOCDataset, nan_preprocessing\n", "data = HELOCDataset(custom_preprocessing=nan_preprocessing).data()\n", "# Separate target variable\n", "y = data.pop('RiskPerformance')\n", "\n", "# Split data into training and test sets using fixed random seed\n", "from sklearn.model_selection import train_test_split\n", "dfTrain, dfTest, yTrain, yTest = train_test_split(data, y, random_state=0, stratify=y)\n", "dfTrain.head().transpose()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "BRCG and LogRR require non-binary features to be binarized using the provided `FeatureBinarizer` class. We use the default of nine quantile thresholds (i.e. 10 bins) to binarize ordinal (including continuous-valued) features, include all negations (e.g. '>' comparisons as well as '<='), and also return standardized versions of the original unbinarized ordinal features, which are used by LogRR but not BRCG. Below is the result of binarizing the first 'ExternalRiskEstimate' feature. " ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Applications/anaconda3/lib/python3.7/site-packages/aix360/algorithms/rbm/features.py:154: RuntimeWarning: invalid value encountered in less_equal\n", " Anew = (data[c].values[:, np.newaxis] <= thresh[c]).astype(int)\n", "/Applications/anaconda3/lib/python3.7/site-packages/aix360/algorithms/rbm/features.py:154: RuntimeWarning: invalid value encountered in less_equal\n", " Anew = (data[c].values[:, np.newaxis] <= thresh[c]).astype(int)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
operation<=>==!=
value59.063.066.069.072.075.078.082.086.059.063.066.069.072.075.078.082.086.0NaNNaN
896000111111111000000001
840311111111100000000001
194911111111100000000001
488600111111111000000001
499800111111111000000001
\n", "
" ], "text/plain": [ "operation <= > \\\n", "value 59.0 63.0 66.0 69.0 72.0 75.0 78.0 82.0 86.0 59.0 63.0 66.0 69.0 \n", "8960 0 0 1 1 1 1 1 1 1 1 1 0 0 \n", "8403 1 1 1 1 1 1 1 1 1 0 0 0 0 \n", "1949 1 1 1 1 1 1 1 1 1 0 0 0 0 \n", "4886 0 0 1 1 1 1 1 1 1 1 1 0 0 \n", "4998 0 0 1 1 1 1 1 1 1 1 1 0 0 \n", "\n", "operation == != \n", "value 72.0 75.0 78.0 82.0 86.0 NaN NaN \n", "8960 0 0 0 0 0 0 1 \n", "8403 0 0 0 0 0 0 1 \n", "1949 0 0 0 0 0 0 1 \n", "4886 0 0 0 0 0 0 1 \n", "4998 0 0 0 0 0 0 1 " ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Binarize data and also return standardized ordinal features\n", "from aix360.algorithms.rbm import FeatureBinarizer\n", "fb = FeatureBinarizer(negations=True, returnOrd=True)\n", "dfTrain, dfTrainStd = fb.fit_transform(dfTrain)\n", "dfTest, dfTestStd = fb.transform(dfTest)\n", "dfTrain['ExternalRiskEstimate'].head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### 2.2. Run Boolean Rule Column Generation (BRCG)\n", "First we consider BRCG, which is designed to produce a very simple OR-of-ANDs rule (known more formally as disjunctive normal form, DNF) or alternatively an AND-of-ORs rule (conjunctive normal form, CNF) to predict whether an applicant will repay the loan on time (Y = 1). For a binary classification problem such as we have here, a DNF rule is equivalent to a *rule set*, where AND clauses in the DNF correspond to individual rules in the rule set. Furthermore, it can be shown that a CNF rule for Y = 1 is equivalent to a DNF rule for Y = 0 [[1]](https://ieeexplore.ieee.org/document/7738856). BRCG is distinguished by its use of the optimization technique of column generation to search the space of possible clauses, which is exponential in size. To learn more about column generation, please see our NeurIPS paper [[2]](http://papers.nips.cc/paper/7716-boolean-decision-rules-via-column-generation). \n", "\n", "For this dataset, we find that a CNF rule for Y = 1 (i.e. a DNF for Y = 0, enabled by setting `CNF=True`) is slightly better than a DNF rule for Y = 1. The model complexity parameters `lambda0` and `lambda1` penalize the number of clauses in the rule and the number of conditions in each clause. We use the default values of 1e-3 for `lambda0` and `lambda1` (decreasing them did not increase accuracy here) and leave other parameters at their defaults as well. The model is then trained, evaluated, and printed." ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Learning CNF rule with complexity parameters lambda0=0.001, lambda1=0.001\n", "Initial LP solved\n", "Iteration: 1, Objective: 0.2895\n", "Iteration: 2, Objective: 0.2895\n", "Iteration: 3, Objective: 0.2895\n", "Iteration: 4, Objective: 0.2895\n", "Iteration: 5, Objective: 0.2864\n", "Iteration: 6, Objective: 0.2864\n", "Iteration: 7, Objective: 0.2864\n", "Training accuracy: 0.719573146021883\n", "Test accuracy: 0.696515397082658\n", "Predict Y=0 if ANY of the following rules are satisfied, otherwise Y=1:\n", "['ExternalRiskEstimate <= 75.00 AND NumSatisfactoryTrades <= 17.00', 'ExternalRiskEstimate <= 72.00 AND NumSatisfactoryTrades > 17.00']\n" ] } ], "source": [ "# Instantiate BRCG with small complexity penalty and large beam search width\n", "from aix360.algorithms.rbm import BooleanRuleCG\n", "br = BooleanRuleCG(lambda0=1e-3, lambda1=1e-3, CNF=True)\n", "\n", "# Train, print, and evaluate model\n", "br.fit(dfTrain, yTrain)\n", "from sklearn.metrics import accuracy_score\n", "print('Training accuracy:', accuracy_score(yTrain, br.predict(dfTrain)))\n", "print('Test accuracy:', accuracy_score(yTest, br.predict(dfTest)))\n", "print('Predict Y=0 if ANY of the following rules are satisfied, otherwise Y=1:')\n", "print(br.explain()['rules'])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The returned DNF rule for Y = 0 is indeed very simple with only two clauses, each involving the same two features. It is interesting to see that such a rule can already achieve 69.7% accuracy. 'ExternalRiskEstimate' is a consolidated version of some risk markers (higher is better), while 'NumSatisfactoryTrades' is the number of satisfactory credit accounts. It makes sense therefore that for applicants with more than 17 satisfactory accounts, the ExternalRiskEstimate threshold dividing good (Y = 1) and bad (Y = 0) credit risk is slightly lower (more lenient) than for applicants with fewer satisfactory accounts.\n", "\n", "We note that AIX360 includes only a heuristic beam search version of BRCG. The published version of BRCG [[2]](http://papers.nips.cc/paper/7716-boolean-decision-rules-via-column-generation) (not implemented in AIX360) uses integer programming to yield slightly more complex rules that are also more accurate (close to 72% test accuracy)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### 2.3. Run Logistic Rule Regression (LogRR)\n", "Next we consider a LogRR model, which can improve accuracy at the cost of a more complex but still interpretable model. Specifically, LogRR fits a logistic regression model using rule-based features, where column generation is again used to generate promising candidates from the space of all possible rules. Here we are also including unbinarized ordinal features (`useOrd=True`) in addition to rules. Similar to BRCG, the complexity parameters `lambda0`, `lambda1` penalize the number of rules included in the model and the number of conditions in each rule. the The values for `lambda0`, `lambda1` below strike a good balance between accuracy and model complexity, based on our published experience with the FICO HELOC dataset [[3]](http://proceedings.mlr.press/v97/wei19a.html)." ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training accuracy: 0.742536809401594\n", "Test accuracy: 0.7260940032414911\n", "Probability of Y=1 is predicted as logistic(z) = 1 / (1 + exp(-z))\n", "where z is a linear combination of the following rules/numerical features:\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
rule/numerical featurecoefficient
0(intercept)-0.0684696
1MSinceMostRecentInqexcl7days > 0.000.680258
2ExternalRiskEstimate0.654171
3NetFractionRevolvingBurden-0.554063
4NumSatisfactoryTrades0.551644
5NumInqLast6M-0.463222
6NumBank2NatlTradesWHighUtilization-0.448346
7AverageMInFile <= 52.00-0.434366
8NumRevolvingTradesWBalance <= 5.000.421533
9MaxDelq2PublicRecLast12M <= 5.00-0.418156
10PercentInstallTrades > 50.00-0.317581
11NumSatisfactoryTrades <= 12.00-0.31248
12MSinceMostRecentDelq <= 21.00-0.301572
13PercentTradesNeverDelq <= 95.00-0.273936
14ExternalRiskEstimate > 75.000.263452
15AverageMInFile <= 84.00-0.182134
16PercentTradesNeverDelq0.166524
17AverageMInFile0.150683
18PercentInstallTrades > 42.00-0.148731
19NumBank2NatlTradesWHighUtilization <= 0.000.135388
20MSinceOldestTradeOpen <= 122.00-0.132505
21PercentTradesNeverDelq <= 91.00-0.117713
22NumSatisfactoryTrades <= 17.00-0.110228
23ExternalRiskEstimate > 72.000.107617
24NumInqLast6M > 0.00-0.0993614
25MSinceOldestTradeOpen <= 146.00-0.0966503
26PercentInstallTrades <= 42.000.0916733
27MSinceMostRecentInqexcl7days <= 0.00-0.0900543
28AverageMInFile <= 61.00-0.0794703
29AverageMInFile <= 76.00-0.072278
30NetFractionRevolvingBurden <= 39.000.0627657
31MSinceOldestTradeOpen > 122.000.060358
32NetFractionRevolvingBurden <= 50.000.0455664
33MSinceOldestTradeOpen0.0421272
34ExternalRiskEstimate > 69.000.0354293
35PercentTradesWBalance <= 73.00-0.0345454
36MSinceOldestTradeOpen > 146.000.024503
\n", "
" ], "text/plain": [ " rule/numerical feature coefficient\n", "0 (intercept) -0.0684696\n", "1 MSinceMostRecentInqexcl7days > 0.00 0.680258\n", "2 ExternalRiskEstimate 0.654171\n", "3 NetFractionRevolvingBurden -0.554063\n", "4 NumSatisfactoryTrades 0.551644\n", "5 NumInqLast6M -0.463222\n", "6 NumBank2NatlTradesWHighUtilization -0.448346\n", "7 AverageMInFile <= 52.00 -0.434366\n", "8 NumRevolvingTradesWBalance <= 5.00 0.421533\n", "9 MaxDelq2PublicRecLast12M <= 5.00 -0.418156\n", "10 PercentInstallTrades > 50.00 -0.317581\n", "11 NumSatisfactoryTrades <= 12.00 -0.31248\n", "12 MSinceMostRecentDelq <= 21.00 -0.301572\n", "13 PercentTradesNeverDelq <= 95.00 -0.273936\n", "14 ExternalRiskEstimate > 75.00 0.263452\n", "15 AverageMInFile <= 84.00 -0.182134\n", "16 PercentTradesNeverDelq 0.166524\n", "17 AverageMInFile 0.150683\n", "18 PercentInstallTrades > 42.00 -0.148731\n", "19 NumBank2NatlTradesWHighUtilization <= 0.00 0.135388\n", "20 MSinceOldestTradeOpen <= 122.00 -0.132505\n", "21 PercentTradesNeverDelq <= 91.00 -0.117713\n", "22 NumSatisfactoryTrades <= 17.00 -0.110228\n", "23 ExternalRiskEstimate > 72.00 0.107617\n", "24 NumInqLast6M > 0.00 -0.0993614\n", "25 MSinceOldestTradeOpen <= 146.00 -0.0966503\n", "26 PercentInstallTrades <= 42.00 0.0916733\n", "27 MSinceMostRecentInqexcl7days <= 0.00 -0.0900543\n", "28 AverageMInFile <= 61.00 -0.0794703\n", "29 AverageMInFile <= 76.00 -0.072278\n", "30 NetFractionRevolvingBurden <= 39.00 0.0627657\n", "31 MSinceOldestTradeOpen > 122.00 0.060358\n", "32 NetFractionRevolvingBurden <= 50.00 0.0455664\n", "33 MSinceOldestTradeOpen 0.0421272\n", "34 ExternalRiskEstimate > 69.00 0.0354293\n", "35 PercentTradesWBalance <= 73.00 -0.0345454\n", "36 MSinceOldestTradeOpen > 146.00 0.024503" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Instantiate LRR with good complexity penalties and numerical features\n", "from aix360.algorithms.rbm import LogisticRuleRegression\n", "lrr = LogisticRuleRegression(lambda0=0.005, lambda1=0.001, useOrd=True)\n", "\n", "# Train, print, and evaluate model\n", "lrr.fit(dfTrain, yTrain, dfTrainStd)\n", "print('Training accuracy:', accuracy_score(yTrain, lrr.predict(dfTrain, dfTrainStd)))\n", "print('Test accuracy:', accuracy_score(yTest, lrr.predict(dfTest, dfTestStd)))\n", "print('Probability of Y=1 is predicted as logistic(z) = 1 / (1 + exp(-z))')\n", "print('where z is a linear combination of the following rules/numerical features:')\n", "lrr.explain()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The test accuracy of LogRR is significantly better than that of BRCG and even better than the neural network in the [Loan Officer](#c2) and [Customer](#contrastive) sections. The LogRR model remains directly interpretable as it is a logistic regression model that uses the 36 rule-based and ordinal features shown above (in addition to an intercept term). Rules are distinguished by having one or more conditions on feature values (e.g. AverageMInFile <= 52.0) while ordinal features are marked by just the feature name without conditions (e.g. ExternalRiskEstimate). Being a linear model, feature importance is naturally given by the model coefficients and thus the list is sorted in order of decreasing coefficient magnitude. The list can be truncated if the user wishes to display fewer features.\n", "\n", "Since the rules in this LogRR model happen to all be single conditions on individual features, the model contains no interactions between features. It is therefore a kind of [generalized additive model (GAM)](https://en.wikipedia.org/wiki/Generalized_additive_model), i.e. a sum of functions of individual features, where these functions are themselves sums of step function components from rules and linear components from unbinarized ordinal features. Thus a better way to visualize the model is by plotting the univariate functions that make up the GAM, as we do next." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### 2.4. Visualize LogRR model as a Generalized Additive Model (GAM)\n", "We use the `visualize()` method of `LogisticRuleRegression` to plot the functions in the GAM that corresponds to the LogRR model (more generally, `visualize()` plots the GAM part of a LogRR model, excluding higher-degree rules). The plots show the sizes and shapes of the model's dependences on individual features. These can then be compared to a lending expert's knowledge. In the present case, all plots indicate that the model behaves as we would expect with some interesting nuances. \n", "\n", "The 36 features shown above involve only 14 of the original features in the data (not including the intercept), as verified below. For example, ExternalRiskEstimate appears in its unbinarized form in row 2 above and also in 3 rules (rows 14, 23, 34)." ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "15" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfx = lrr.explain()\n", "# Separate 1st-degree rules into (feature, operation, value) to count unique features\n", "dfx2 = dfx['rule/numerical feature'].str.split(' ', expand=True)\n", "dfx2.columns = ['feature','operation','value']\n", "dfx2['feature'].nunique() # includes intercept" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It follows that there are 14 functions to plot, which we organize into semantic groups below to ease interpretation." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### ExternalRiskEstimate\n", "As expected from the BRCG Boolean rule above, 'ExternalRiskEstimate' is an important feature positively correlated with good credit risk. The jumps in the plot indicate that applicants with above average 'ExternalRiskEstimate' (the mean is 72) get an additional boost." ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['ExternalRiskEstimate']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Credit inquiries\n", "The next two plots illustrate the dependence on the applicant's credit inquiries. The first plot shows a significant penalty for having less than one month since the most recent inquiry ('MSinceMostRecentInqexcl7days' = 0)." ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "scrolled": false }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['MSinceMostRecentInqexcl7days']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The second shows that predicted risk increases with the number of inquiries in the last six months ('NumInqLast6M')." ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['NumInqLast6M']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Debt level\n", "The following four plots relate to the applicant's debt level. 'NetFractionRevolvingBurden' is the ratio of revolving debt (e.g. credit card) balance to credit limit, expressed as a percentage, and has a large negative impact on the probability of good credit. A small fraction of applicants (less than 1%) actually have NetFractionRevolvingBurden greater than 100%, i.e. more revolving debt than their credit limit. This might be investigated further by the data scientist." ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['NetFractionRevolvingBurden']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The second 'NumBank2NatlTradesWHighUtilization' plot shows that the number of accounts (\"trades\") with high utilization (high balance relative to credit limit for each account) also has a large impact, with a drop as soon as one account has high utilization." ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkIAAAGwCAYAAABFFQqPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOzdd3QVdf7/8ddNQgolCSWFQGihhI6CYEBUIBpEBYRVwIKIirCKtFVhf18BK7iWRRAFRUB2LaggroIoQigiEAUiKCHSWxKCYBqQPr8/2NwlpJCb3Jvbno9z7jnJ3Jm573FM8mLm856PyTAMQwAAAG7Iw94FAAAA2AtBCAAAuC2CEAAAcFsEIQAA4LYIQgAAwG0RhAAAgNsiCAEAALflZe8CHF1hYaGSkpJUp04dmUwme5cDAAAqwDAMZWZmKiwsTB4eZV/3IQhdRVJSksLDw+1dBgAAqIQTJ06ocePGZb5PELqKOnXqSLr0H9Lf39/O1QAAgIrIyMhQeHi4+e94WQhCV1F0O8zf358gBACAk7nasBYGSwMAALdFEAIAAG6LIAQAANwWQQgAALgtghAAAHBbBCEAAOC2CEIAAMBtEYQAAIDbIggBAAC3RRACAABuiyAEAADcFkEIAAC4LYKQneTmF2rT72fsXQYAAG6NIGQnb6z7XQ8ujtM3e5PtXQoAAG6LIGQHhmHo+4TTkqQDqVl2rgYAAPdFELIDk8mk7s3r2bsMAADcHkEIAAC4LYIQAABwWwQhAADgtghCAADAbRGEAACA2yIIAQAAt0UQAgAAbosgBAAA3BZBCAAAuC2CEAAAcFsEIQAA4LYIQgAAwG0RhAAAgNsiCAEAALdFEAIAAG6LIAQAANwWQQgAALgtgpCdXcwrsHcJAAC4LS97F+CuAvxqSJIWbjokD5M0oV9reXuRSwEAqE785bWTJ/q01F+6NlahIc2PPaQh72zVwdRMe5cFAIBbIQjZSS0fL712d2e9c9+1CqxZQ7+eytDtc3/QBz8elWEY9i4PAAC3QBCys9s6NtS3E2/Uja2DlJNfqBn/+U2jlvyk1Ixse5cGAIDLIwg5gBB/X33w0HV6bmB7+Xh5aNPvZxQzZ7PW/pps79IAAHBpBCEHYTKZ9GDPZlr95A1qH+avPy/kaey/d+lvn/2izOw8e5cHAIBLIgg5mJbBdfTFX3vprzdHyMMkfb7zpG57c4t+OnrO3qUBAOByCEIOyNvLQ0/3j9Tyx6LUuK6fTv55UcMWbtOr3+5Xbn6hvcsDAMBlEIQc2HXN6umbCb1pswcAwEYIQg6ujm8N2uwBALARgpCTKK3N/sElP+k0bfYAAFQaQciJXNlmv5k2ewAAqoQg5GSubLNPo80eAIBKIwg5KdrsAQCoOoKQEyurzf4fa2mzBwCgIghCLuDKNvu3N9JmDwBARThdEJo/f76aNWsmX19f9ejRQ3FxceWu/9lnnykyMlK+vr7q2LGj1qxZU02VVi/a7AEAsJxTBaHly5dr8uTJmjFjhnbt2qXOnTsrJiZGqamppa7/448/asSIEXr44Ye1e/duDR48WIMHD9avv/5azZVXH9rsAQCoOJPhRJcLevTooeuuu05vvfWWJKmwsFDh4eEaP368pk6dWmL9YcOG6fz58/r666/Ny66//np16dJFCxYsKPUzcnJylJOTY/4+IyND4eHhSk9Pl7+/v5WPyHYMw9Cybcf08poE5eQXKrBmDc26q6Nu69jQ3qUBAGBzGRkZCggIuOrfb6e5IpSbm6udO3cqOjravMzDw0PR0dHatm1bqdts27at2PqSFBMTU+b6kjRr1iwFBASYX+Hh4dY5gGp2eZt9h0aX2uzHfUibPQAAl3OaIPTHH3+ooKBAISEhxZaHhIQoJSWl1G1SUlIsWl+Spk2bpvT0dPPrxIkTVS/ejloG19HKcbTZAwBQGqcJQtXFx8dH/v7+xV7OjjZ7AABK5zRBqEGDBvL09NTp06eLLT99+rRCQ0NL3SY0NNSi9V0dbfYAABTnNEHI29tbXbt21fr1683LCgsLtX79ekVFRZW6TVRUVLH1JWndunVlru8OitrsF9xPmz0AAE4ThCRp8uTJeu+99/TBBx8oISFB48aN0/nz5/XQQw9JkkaOHKlp06aZ158wYYLWrl2r119/Xfv379fMmTP1888/64knnrDXITiM/h1oswcAwKmC0LBhw/Taa69p+vTp6tKli+Lj47V27VrzgOjjx48rOfl/M7H37NlTH330kd5991117txZn3/+uVatWqUOHTrY6xAcSlmz2X+zl9nsAQDuwameI2QPFX0OgbM7mJqpicvj9eupDEnS0Gsba+bAdqrjW8POlQEAYDmXe44QbKuozf7xPpfa7Ffsos0eAOD6CEIw8/by0FMxtNkDANwHQQgl0GYPAHAXBCGU6vI2+7qXtdkv3XqENnsAgMsgCKFcV7bZz/xqH232AACXQRDCVQXTZg8AcFEEIVRIWbPZT/mU2ewBAM6LIASLlNVmH3eENnsAgPMhCMFiRW32nz4WpfB6/22zf5c2ewCA8yEIodK6NaunNU9earM3aLMHADghghCqhDZ7AIAzIwjBKora7G+6rM1+5OI42uwBAA6NIASrCfb31dKHrtPzgy612W858Adt9gAAh0YQglWZTCaNjKLNHgDgHAhCsAna7AEAzsBqQejPP//UsmXLrLU7uICy2uxfoc0eAOAgrBaEjh8/roceeshau4MLKWqzv/u/bfbvbDyku96mzR4AYH8VDkIZGRnlvjIz+aOGstXxraFXL2uz/y2JNnsAgP2ZjAr+FfLw8JDJZCrzfcMwZDKZVFBQYLXiHEFGRoYCAgKUnp4uf39/e5fjElIzsvXU53u06fczkqTerRrotbs7K8Tf186VAQBcRUX/flc4CAUEBOj//b//px49epT6/oEDB/TYY48RhFAhhmHoX9uP6aXVCcrJL1RgzRp6+a6OGtCxob1LAwC4gIr+/faq6A6vvfZaSdJNN91U6vuBgYHc4kCFFbXZ94xooInLd+vXUxn664e7NPTaxpo5sJ3q+Nawd4kAADdQ4TFC9957r3x9y751ERoaqhkzZlilKLiPlsG1abMHANhNhW+NuStujVWfn4+e06RP43Xi3EWZTNLYmyI0Kbq1vL143BUAwDIV/fvNXxg4jLLa7A+cpiMRAGAblQpCW7duVU5OTomvgaoqrc3+jnm02QMAbKNSQei2227TqVOnSnwNWAuz2QMAqkOlgtDl/zLnX+mwlbJms1/DbPYAACthjBAc2v9ms++tjo0ClHYhT39lNnsAgJUQhOAUWgbX1opxPfVEn5a02QMArIYgBKfh7eWhv8W0YTZ7AIDVEITgdGizBwBYC0EITqm8NvvCQgbwAwAqhiAEp1Zam/2DS2izBwBUTKWC0MKFCxUSElLia8AeaLMHAFRWhecaMwxDJpPJ1vU4HOYacy4HU7M0aXm89p5KlyRmswcAN2X1ucZ69eqlgwcPWqU4wFZoswcAWKLCQahx48bq0qWL5s+fb8t6gCqjzR4AUFEVDkKffvqplixZoueff1633HKLTp48acu6gCqjzR4AcDUVHiNU5MyZM3r88ce1bt06PfDAA/Ly8ir2/htvvGHVAu2NMUKuYe2vyZq2cq/+vJAnHy8PTbstUiOjmsnDw/3GvQGAO6jo32+vMt8pQ7169dS2bVt98cUX2r17d7Eg5I6DqeEc+ndoqGub1NVTn+/Rpt/PaOZX+7R+f6peu7uzQvx97V0eAMBOLLoi9Ntvv2nkyJE6d+6cFi9erD59+tiyNofAFSHXYhiG/r39mF5cnaCc/EIF1qyhl+/qqAEdG9q7NACAFVm9a2z27Nnq2rWrOnfurD179rhFCILrMZlMeoDZ7AEA/1XhK0INGzbUu+++qzvvvNPWNTkUrgi5rtz8Qs1df0BvbzyoQkNqXNdPb9zTRd2b17N3aQCAKqro3+8KB6GzZ8+qfv36VivQWRCEXN/PR89p0qfxOnHuokwmaexNEZoU3VreXsxAAwDOyuq3xtwxBME9dGtWT99MuJE2ewBwQ/yTF5BU28eL2ewBwA0RhIDLMJs9ALiXCgWhyZMn6/z585KkzZs3Kz8/36ZFAfZUNJv9C8xmDwAur0KDpWvUqKGTJ08qJCREnp6eSk5OVnBwcHXUZ3cMlnZvV85mP+TaRnpuYHtmswcAB2fVJ0s3a9ZMc+fO1a233irDMLRt2zbVrVu31HVvvPHGylUMOKCi2eyL2uxX7jqluCPnaLMHABdRoStCq1at0tixY5WamiqTyaSyNjGZTCooKLB6kfbEFSEUoc0eAJyH1Z8jJElZWVny9/dXYmJimbfGAgICLK/WgRGEcLmsnHw995/f9NnOk5Kk9mH+mjOsi1qF1LFzZQCAy9kkCEnSpk2b1KtXrxKzzrsqghBKw2z2AODYbBaEJKmgoECrVq1SQkKCJKldu3YaNGiQPD09K1+xgyIIoSypGdnm2ewlqXerBsxmDwAOwmZB6ODBg7r99tt18uRJtWnTRpKUmJio8PBwrV69WhEREVWr3MEQhFCeotnsX1qToOw8ZrMHAEdhsyA0YMAAGYahDz/8UPXqXeqaOXv2rO6//355eHho9erVVavcwRCEUBGltdnPHNhe/rTZA4Bd2CwI1apVS9u3b1fHjh2LLf/ll1/Uq1cvZWVlVa5iB0UQQkVdOZt9o0A//XMYbfYAYA9Wn3S1iI+PjzIzS05GmZWVJW9vb0t3B7gMby8P/S2mjT59LErh9fx0Ku2ihr27Ta+s3a/c/EJ7lwcAKIXFQeiOO+7QmDFjtGPHDhmGIcMwtH37do0dO1YDBw60RY2AUymazf6ebsxmDwCOzuIgNHfuXEVERCgqKkq+vr7y9fVVr1691LJlS7355pu2qBFwOrV9vPSPv3TWgvu7Mps9ADiwSrXPS5e6x4ra59u2bauWLVtatTBHwRghVBVt9gBQ/Wz6HCF3QhCCNdBmDwDVy2aDpQFYzmQy6YGoZvp6fG91bBSgtAt5+uuHuzT503hlZOfZuzwAcFsEIaAatQyurZV/7akn+rSUh0laueuUbpuzRXFHztm7NABwS04ThM6dO6f77rtP/v7+CgwM1MMPP3zVZxbdfPPNMplMxV5jx46tpoqB0tXwpM0eAByF0wSh++67T7/99pvWrVunr7/+Wps3b9aYMWOuut2jjz6q5ORk8+sf//hHNVQLXB1t9gBgfxYHobVr1+qHH34wfz9//nx16dJF9957r/7880+rFlckISFBa9eu1aJFi9SjRw/dcMMNmjdvnj755BMlJSWVu23NmjUVGhpqfjHgGY6krDb7JbTZA0C1sDgIPfXUU8rIyJAk7d27V1OmTNGAAQN05MgRTZ482eoFStK2bdsUGBiobt26mZdFR0fLw8NDO3bsKHfbDz/8UA0aNFCHDh00bdo0Xbhwodz1c3JylJGRUewF2Fr/DqH6duKNuql1kHLyC/XcV/v04JI4nc7ItndpAODSLA5CR44cUbt27SRJK1as0B133KGXX35Z8+fP1zfffGP1AiUpJSVFwcHBxZZ5eXmpXr16SklJKXO7e++9V//+978VGxuradOm6V//+pfuv//+cj9r1qxZCggIML/Cw8OtcgzA1QT7+2rpQ9fphUHt5VvDQ1sO/KGYOZu1Zm+yvUsDAJdlcRDy9vY2X1X5/vvvdeutt0qS6tWrZ/HVk6lTp5YYzHzla//+/ZaWaDZmzBjFxMSoY8eOuu+++7Rs2TJ98cUXOnToUJnbTJs2Tenp6ebXiRMnKv35gKVosweA6uVl6QY33HCDJk+erF69eikuLk7Lly+XJP3+++9q3LixRfuaMmWKRo0aVe46LVq0UGhoqFJTU4stz8/P17lz5xQaGlrhz+vRo4ekS0/FjoiIKHUdHx8f+fj4VHifgC0UtdnPXX9A82MPauWuU9px+Byz2QOAlVkchN566y399a9/1eeff6533nlHjRo1kiR988036t+/v0X7CgoKUlBQ0FXXi4qKUlpamnbu3KmuXbtKkjZs2KDCwkJzuKmI+Ph4SVLDhjzNF46vhqeHptzaRje3CdLE5fE6ce5Sm/3YmyI0Kbq1vL2cpukTAByW00yxcdttt+n06dNasGCB8vLy9NBDD6lbt2766KOPJEmnTp1Sv379tGzZMnXv3l2HDh3SRx99pAEDBqh+/fras2ePJk2apMaNG2vTpk0V/lym2IAjyMrJ1/Nf/aZPfz4pSWof5q85w7qoVUgdO1cGAI6pon+/K3RFyJKxP7YKCx9++KGeeOIJ9evXTx4eHho6dKjmzp1rfj8vL0+JiYnm8Uve3t76/vvvNWfOHJ0/f17h4eEaOnSo/u///s8m9QG2VNRm3zcyRNNW7jG32U+9LVIPRjWTh4fJ3iUCgFOq0BUhDw8PmUwV+0VbUFBQ5aIcCVeE4GhSM7L19Io92pj4v9nsX/1LZ4UGMJs9ABSx6hWh2NhY89dHjx7V1KlTNWrUKEVFRUm69JyfDz74QLNmzapi2QCuJtjfV0tGXWeezb6ozX7WEGazBwBLWTxGqF+/fnrkkUc0YsSIYss/+ugjvfvuu9q4caM167M7rgjBkR1MzdKk5fHaeypdkjTk2kaaObC9/H1r2LkyALCviv79trjtZNu2bcWe8FykW7duiouLs3R3AKqgqM1+fF9msweAyrA4CIWHh+u9994rsXzRokU8hRmwg6I2+8/GRqlJvZrm2exnf8Ns9gBwNRbfGluzZo2GDh2qli1bmp/hExcXpwMHDmjFihUaMGCATQq1F26NwZlc2WbfrqG/3hxOmz0A91PRv9+Veo7QiRMn9M4775inv2jbtq3Gjh3rkleECEJwRmt/TdG0lXv054U8+Xh50GYPwO3YNAi5E4IQnBVt9gDcmVWD0J49eyr8wZ06darwus6AIARnZhiGuc0+O69QAX419PJdHXV7J9rsAbg2qwahogcqGoZR7MGKRZtevowHKgKO59CZLE38hDZ7AO7Dqu3zR44c0eHDh3XkyBGtWLFCzZs319tvv634+HjFx8fr7bffVkREhFasWGG1AwBgPRFBtNkDQGksHiPUvXt3zZw5s0R32Jo1a/Tss89q586dVi3Q3rgiBFez89g5TVr+i46fuyCTSXrsxghNvoXZ7AG4Fps9UHHv3r1q3rx5ieXNmzfXvn37LN0dgGrWtWk9rZnQW/d0ayzDkBZsOqTB87fq99OZ9i4NAKqdxUGobdu2mjVrlnJzc83LcnNzNWvWLLVt29aqxQGwjaLZ7Bc+0FV1a9bQvuRLs9kv2XpEhYU0kgJwHxbfGouLi9Odd94pwzDMHWJ79uyRyWTSV199pe7du9ukUHvh1hhcHW32AFyRTZ8jdP78eX344YfFHqh47733qlatWpWv2EERhOAOaLMH4Gp4oKKVEITgTg6duTSb/Z6T/22zv6aRZg6izR6A87HZYGlJOnTokMaPH6/o6GhFR0drwoQJOnToUKWLBeAYIoJqa8W4y9rsd9NmD8C1WRyEvv32W7Vr105xcXHq1KmTOnXqpO3bt6t9+/Zat26dLWoEUI2YzR6AO7H41tg111yjmJgYzZ49u9jyqVOn6rvvvtOuXbusWqC9cWsM7qy02eznDO+i1sxmD8DB2WyMkK+vr/bu3atWrVoVW/7777+rU6dOys7OrlzFDoogBEjf/paiaSv36tz5XHl7eWhq/0iN6sls9gAcl83GCAUFBSk+Pr7E8vj4eAUHB1u6OwBOIKZ9qNZO7K2b2wQpN79Qz3+9Tw8uiVNKumv9wweA+/GydINHH31UY8aM0eHDh9WzZ09J0tatW/XKK69o8uTJVi8QgGMIruOrJaOuM7fZbznwh2LmbKbNHoBTs/jWmGEYmjNnjl5//XUlJSVJksLCwvTUU0/pySefLDYTvSvg1hhQEm32ABxdtTxHKDPz0txEdeq47sBJghBQuryCQs1df0DzYw+q0JAaBfrpjXs6q0eL+vYuDQBs+xyhIvPnz1dBQUFVdgHASZXWZj/8ve202QNwKlUKQi+//LLOneNBa4A7YzZ7AM6sSkGI2TkASMVns69Xy9s8m/3iH5jNHoBjq1IQAoDL0WYPwNlUKQjt27dPTZs2tVYtAFxAUZv9C4M7yLeGh7nNfvWeZHuXBgAlVCkIhYeHy9PT01q1AHARJpNJD1zfVKuf7K1OjQOUfjFPj3+0S5OXxysjO8/e5QGAmcXt83Xr1i31WUEmk0m+vr5q2bKlRo0apYceeshqRdoT7fNA1dBmD8AebNY+P336dHl4eOj222/Xc889p+eee0633367PDw89Pjjj6t169YaN26c3nvvvSodAADXUFab/axvEpSTz+M3ANiXxVeEhg4dqltuuUVjx44ttnzhwoX67rvvtGLFCs2bN0/vvvuu9u7da9Vi7YErQoD1ZOXk64Wv9mn5zyckMZs9ANux2ZOla9eurfj4eLVs2bLY8oMHD6pLly7KysrSoUOH1KlTJ50/f75y1TsQghBgfcxmD8DWbHZrrF69evrqq69KLP/qq69Ur149SdL58+ddetoNAFVDmz0AR2Hx7PPPPvusxo0bp9jYWHXv3l2S9NNPP2nNmjVasGCBJGndunW66aabrFspAJdins1+x3G9tHqfuc3+pbs66I5OYfYuD4CbqNSkq1u3btVbb72lxMRESVKbNm00fvx49ezZ0+oF2hu3xgDbYzZ7ANZWLbPPuwOCEFA9aLMHYE02DUIFBQVatWqVEhISJEnt27fXwIEDXfLhigQhoHrtPHZOk5b/ouPnLshkksbc2EKTb2ktHy/X+/0CwHZsFoQOHjyoAQMG6NSpU2rTpo0kKTExUeHh4Vq9erUiIiKqVrmDIQgB1e/KNvu2Df31Jm32ACxgsyA0YMAAGYahDz/80NwldvbsWd1///3y8PDQ6tWrq1a5gyEIAfZDmz2AyrJZEKpVq5a2b9+ujh07Flv+yy+/qFevXsrKyqpcxQ6KIATYV2pmtp7+fI82Jp6RJPVu1UCv/qWzQgN87VwZAEdms+cI+fj4KDMzs8TyrKwseXt7W7o7AChXWbPZf70nyd6lAXABFgehO+64Q2PGjNGOHTtkGIYMw9D27ds1duxYDRw40BY1AnBzpc1m/8RHuzWJ2ewBVJHFQWju3LmKiIhQVFSUfH195evrq169eqlly5Z68803bVEjAEiSIoJqa8W4nnqyb0t5mKQvdp/SbXO2aMfhs/YuDYCTqvRzhA4cOKD9+/dLktq2bVti7jFXwRghwDHRZg+gPDxQ0UoIQoDjos0eQFmsGoQmT55c4Q9+4403KryuMyAIAY6PNnsAV6ro3+8KTbq6e/fuCn2oycQvHQDVL6Z9qK5pEqhnPt+j2MQzev7rfdqwP1Wv3U2bPYDycWvsKrgiBDgPwzDMs9ln5xUqwK8Gs9kDbspmzxECAEdFmz0ASxGEALgc2uwBVBRBCIBLquHpocm3ttFnY3uqSb2aOpV2UcPf265Z3yQoJ7/A3uUBcBAEIQAurWvTulozobeGdQuXYUgLNx3W4Pk/6vfTJacKAuB+CEIAXF5tHy+98pdOWvhAV9Wr5a2E5AzdMe8HLf7hiAoL6RcB3FmlusYOHTqkOXPmKCEhQZLUrl07TZgwQREREVYv0N7oGgNcS2pmtrnNXpJuaNmANnvABdmsa+zbb79Vu3btFBcXp06dOqlTp07asWOH2rdvr3Xr1lWpaACwteA6vlo86jq9+N/Z7H84yGz2gDuz+IrQNddco5iYGM2ePbvY8qlTp+q7777Trl27rFqgvXFFCHBdh85kadLyeO05mS5JuuuaRnpuUHv5+9awc2UAqspmc435+vpq7969atWqVbHlv//+uzp16qTs7OzKVeygCEKAa8srKNS89Qf0VuxBFRpSo0A/vXFPZ/VoUd/epQGoApvdGgsKClJ8fHyJ5fHx8QoODrZ0dwBgV5e32TetT5s94G4qNNfY5R599FGNGTNGhw8fVs+ePSVJW7du1SuvvGLR5KwA4Ei6Nq2rNU/21gtf79MnP53Qwk2Htfn3P5jNHnBxFt8aMwxDc+bM0euvv66kpEuDC8PCwvTUU0/pySefdLmJV7k1BrgfZrMHnJ/NxghdLjPz0gPJ6tRx3X8tEYQA90SbPeDcbDZGqG/fvkpLS5N0KQAVhaCMjAz17du3kuUCgGOhzR5wDxYHoY0bNyo3N7fE8uzsbG3ZssUqRZXmpZdeUs+ePVWzZk0FBgZWaBvDMDR9+nQ1bNhQfn5+io6O1oEDB2xWIwDXYjKZdD+z2QMurcJBaM+ePdqzZ48kad++febv9+zZo927d+v9999Xo0aNbFZobm6u7r77bo0bN67C2/zjH//Q3LlztWDBAu3YsUO1atVSTEyMy7X4A7AtZrMHXFeFxwh5eHiYB0KXtomfn5/mzZun0aNHW7fCKyxdulQTJ040354ri2EYCgsL05QpU/S3v/1NkpSenq6QkBAtXbpUw4cPr9DnMUYIwOV2HvtTkz+N17GzF2QySWNubKHJt7SWj5envUsDcJmK/v2ucPv8kSNHZBiGWrRoobi4OAUFBZnf8/b2VnBwsDw9HecXwZEjR5SSkqLo6GjzsoCAAPXo0UPbtm0rMwjl5OQoJyfH/H1GRobNawXgPGizB1xLhYNQ06ZNJUmFhYU2K8aaUlJSJEkhISHFloeEhJjfK82sWbP03HPP2bQ2AM6tlo+XZg/tpL6RwZq6cq95Nvtn+kfqIdrsAadi8WBpa5o6dapMJlO5r/3791drTdOmTVN6err5deLEiWr9fADO49b2oVo7sbf6tAlSbn6hXvh6n0YujlNKOuMQAWdh8ZOlrWnKlCkaNWpUueu0aNGiUvsODQ2VJJ0+fVoNGzY0Lz99+rS6dOlS5nY+Pj7y8fGp1GcCcD9FbfYf7jiuF1fvM7fZv3RXB93RKcze5QG4CrsGoaCgoGJjjaypefPmCg0N1fr1683BJyMjQzt27LCo8wwArqaozb5nRH1NWh6vX06m64mPdmt9Qiqz2QMOzq63xixx/PhxxcfH6/jx4yooKFB8fLzi4+OVlWii2owAACAASURBVJVlXicyMlJffPGFpEu/mCZOnKgXX3xR//nPf7R3716NHDlSYWFhGjx4sL0OA4ALaxFUW5+P66kn+7Uq1ma/nTZ7wGFV+opQbm6uUlNTSwyebtKkSZWLKs306dP1wQcfmL+/5pprJEmxsbG6+eabJUmJiYlKT083r/P000/r/PnzGjNmjNLS0nTDDTdo7dq18vXlEfkAbKOGp4cm39JaN7UOMrfZj3hvO232gIOyeK6xAwcOaPTo0frxxx+LLTcMQyaTSQUFBVYt0N54jhCAyjqfk29us5ektg39abMHqonNJl3t1auXvLy8NHXqVDVs2LDEbPOdO3euXMUOiiAEoKq++y1FUy+bzZ42e8D2bBaEatWqpZ07dyoyMrLKRToDghAAa7hyNvteLevrtbs7q2GAn50rA1yTzWafb9eunf74448qFQcA7ubK2ey3Hjyr/nO2MJs9YGcWB6FXXnlFTz/9tDZu3KizZ88qIyOj2AsAULqiNvs1T/ZWZ2azBxyCxbfGPDwuZacrxwYxWBoAKi6voFDzNhzUWxsOqNCQGgX66fV7Ouv6FvXtXRrgEqw+6WqR2NjYKhUGAKDNHnAUFl8RcjdcEQJga7TZA9Zns64xSUpLS9P777+vhIQESVL79u01evRoBQQEVL5iB0UQAlBdaLMHrMdmQejnn39WTEyM/Pz81L17d0nSTz/9pIsXL+q7777TtddeW7XKHQxBCEB1OpOZo2dW7NGG/amSaLMHKstmQah3795q2bKl3nvvPXl5XRpilJ+fr0ceeUSHDx/W5s2bq1a5gyEIAahuhmGYZ7PPziuUv6+XXh7SkdnsAQvYLAj5+flp9+7dJR6ouG/fPnXr1k0XLlyoXMUOiiAEwF4On8kyz2YvSXdd04jZ7IEKstkDFf39/XX8+PESy0+cOKE6dRjYBwDWwmz2gO1ZHISGDRumhx9+WMuXL9eJEyd04sQJffLJJ3rkkUc0YsQIW9QIAG6rqM3+83E91bR+TZ1Ku6gR723XrDUJysl3ree2AfZg8a2x3NxcPfXUU1qwYIHy8/MlSTVq1NC4ceM0e/Zs+fj42KRQe+HWGABHUVqb/ZxhXdQmlKvxwJVs2j4vSRcuXNChQ4ckSREREapZs2blKnVwBCEAjoY2e+DqbB6E3AVBCIAjos0eKJ9Vg9CQIUO0dOlS+fv7a8iQIeWuu3LlSsurdWAEIQCOyjAMfRR3XC9+naCLeQXy9/XSS3d11J2dabMHrDrXWEBAgHmSVX9//xITrgIAqp/JZNJ9PZoqqkV9c5v9+I93a8P+VNrsgQri1thVcEUIgDNgNnugOJs9R6hv375KS0sr9QP79u1r6e4AAFZAmz1QORYHoY0bNyo3N7fE8uzsbG3ZssUqRQEAKufaJnW15sneGn5duAxDWrj5sAbP/1GJKZn2Lg1wSBUaIyRJe/bsMX+9b98+paSkmL8vKCjQ2rVr1ahRI+tWBwCwWC0fL80e2kn92obomRV7lJCcoTvf+oE2e6AUFR4j5OHhYR4kXdomfn5+mjdvnkaPHm3dCu2MMUIAnBlt9nBXVn+O0LFjx2QYhlq0aKG4uDgFBQWZ3/P29lZwcLA8PT2rXrmDIQgBcHa02cMd8UBFKyEIAXAVV85mP7hLmJ4b1EEBfrTZw/XYLAgtW7as3PdHjhxpye4cHkEIgCu5ss0+LMBXr9/TRVERtNnDtdgsCNWtW7fY93l5ebpw4YK8vb1Vs2ZNnTt3rnIVOyiCEABXtOv4n5q0PF7Hzl6QySSN6d1Ck29tLR8v1xviAPdks+cI/fnnn8VeWVlZSkxM1A033KCPP/64SkUDAKoHbfbAJVYbI/Tzzz/r/vvv1/79+62xO4fBFSEArm7dvtOaumKPzv53NvunY9podK/mtNnDqdnsilBZvLy8lJSUZK3dAQCqyS3tQrR24o3qGxms3PxCvbg6QQ8s3qHk9Iv2Lg2wOYuvCP3nP/8p9r1hGEpOTtZbb72l8PBwffPNN1Yt0N64IgTAXdBmD1dis8HSHh7FLyKZTCYFBQWpb9++ev3119WwYcPKVeygCEIA3A1t9nAFPEfISghCANxRUZv9/NiDKig0aLOH06mWMUKGYZQ63QYAwLkVzWb/2dgoNa1fU0np2bp3EbPZw/VUKgi9//776tChg3x9feXr66sOHTpo0aJF1q4NAGBntNnD1VkchKZPn64JEybozjvv1GeffabPPvtMd955pyZNmqTp06fbokYAgB0VzWb/3shuql/L2zyb/aIth1VYyF0BODeLxwgFBQVp7ty5GjFiRLHlH3/8scaPH68//vjDqgXaG2OEAOB/mM0ezsJmY4Ty8vLUrVu3Esu7du2q/Px8S3cHAHAiQXV89P6D3fTSXR3kV8NTWw+eVcw/N+urX3iOHJyTxUHogQce0DvvvFNi+bvvvqv77rvPKkUBAByXyWTSfT2aavWTN6hz4wBlZOdr/Me7NfGT3Uq/mGfv8gCLeFVkpcmTJ5u/NplMWrRokb777jtdf/31kqQdO3bo+PHjLjfzPACgbC2CauvzcT3Nbfar4pMUd+QcbfZwKhUaI9SnT5+K7cxk0oYNG6pclCNhjBAAXN2Vs9k/2ruFpjCbPeyIBypaCUEIACrmfE6+Xly9Tx/HnZAkRYbW0ZvDr1Gb0Dp2rgzuqNonXQUAuLdaPl6aNeR/bfb7UzJps4fDq9AVoSFDhmjp0qXy9/fXkCFDyl135cqVVivOEXBFCAAsR5s97M2qV4QCAgJkMpnMX5f3AgCgrDb7/9BmDwdj0RghwzB04sQJBQUFyc/PPVI9V4QAoGoOn8nSpE9/0S8n0iQxmz2qh03GCBmGoZYtW+rkyZNVLhAA4B5aBNXW52Oj9GS/VvL0MGlVfJJum7NZ2w6dtXdpgGVByMPDQ61atdLZs/zPCwCouLJms3+Z2exhZxZ3jc2ePVtPPfWUfv31V1vUAwBwYUWz2Y/ofmk2+3c3H9agt7Zqf0qGvUuDm7L4OUJ169bVhQsXlJ+fL29v7xJjhc6dO2fVAu2NMUIAYBvr9p3W1BV7dPZ8rry9PPR0TBuN7tVcHh4me5cGF1DRv98VmmLjcv/85z/NHWQAAFTWLe1C1CX8RnOb/YurExSbmEqbPaoVT5a+Cq4IAYBtGYahj+KO68WvE3Qxr0D+vl568a6OGtg5zN6lwYnZ7MnSnp6eSk1NLbH87Nmz8vRkThkAgGWKzWYfHqiM7Hw9+fFuTWA2e1QDi4NQWReQcnJy5O3tXeWCAADuqajNfsJ/2+y/pM0e1aDCY4Tmzp0r6VJyX7RokWrXrm1+r6CgQJs3b1ZkZKT1KwQAuI0anh6adEtr3dQmyDyb/b2LtjObPWymwmOEmjdvLkk6duyYGjduXOw2mLe3t5o1a6bnn39ePXr0sE2ldsIYIQCwj9Jms58zvIsiQ/ldjKur6N9viwdL9+nTRytXrlTdunWrXKQzIAgBgH0Va7P39NDT/Wmzx9XZLAi5G4IQANjfmcwcTV2xR+v/O5t9z4j6ev0e2uxRNpsFoYKCAi1dulTr169XamqqCgsLi72/YcOGylXsoAhCAOAYaLOHJWz2QMUJEyZo6dKluv3229WhQwcerggAqBZFbfZRLeqbZ7N/8uPdWp9wWs8zmz0qyeIrQg0aNNCyZcs0YMAAW9XkULgiBACOJ6+gUG9tOKi3Yg+qoNBQWICvXruns3pGNLB3aXAQNnugore3t1q2bFml4gAAqIqiNvvPx0ap2X9ns79v0Q5ms4fFLA5CU6ZM0ZtvvlnmgxUBAKgu1zSpq9XMZo8qsPjW2F133aXY2FjVq1dP7du3V40axe/Jrly50qoF2hu3xgDAOdBmj8vZbLB0YGCg7rrrrioVBwCAtRXNZl/UZv/i6gRt2H9pNvuwQNrsUTqneY7QSy+9pNWrVys+Pl7e3t5KS0u76jajRo3SBx98UGxZTEyM1q5dW+HP5YoQADgXwzD0cdwJvfD1Ptrs3ZjNBksXOXPmjH744Qf98MMPOnPmTGV3U2G5ubm6++67NW7cOIu269+/v5KTk82vjz/+2EYVAgAcgclk0r09mjCbPSrE4ltj58+f1/jx47Vs2TLzwxQ9PT01cuRIzZs3TzVr1rR6kZL03HPPSZKWLl1q0XY+Pj4KDQ2t8Po5OTnKyckxf5+RwYA7AHBGRbPZF7XZfxmfpJ+OnKPNHsVYfEVo8uTJ2rRpk7766iulpaUpLS1NX375pTZt2qQpU6bYosYq2bhxo4KDg9WmTRuNGzdOZ8+eLXf9WbNmKSAgwPwKDw+vpkoBANZGmz2uplIPVPz888918803F1seGxure+65x+a3yZYuXaqJEydWaIzQJ598opo1a6p58+Y6dOiQ/v73v6t27dratm2bPD09S92mtCtC4eHhjBECACd3aTb7BH0cd1wSs9m7OpuNEbpw4YJCQkJKLA8ODtaFCxcs2tfUqVNlMpnKfe3fv9/SEs2GDx+ugQMHqmPHjho8eLC+/vpr/fTTT9q4cWOZ2/j4+Mjf37/YCwDg/Gr5eGnWkI56b2Q31a/lrf0pmRo4b6sWbTmswkKn6BuCDVgchKKiojRjxgxlZ2ebl128eFHPPfecoqKiLNrXlClTlJCQUO6rRYsWlpZYphYtWqhBgwY6ePCg1fYJAHAut7QL0dqJN6pfZLByCwr14uoE3f/+DiWlXbR3abADiwdLv/nmm4qJiVHjxo3VuXNnSdIvv/wiX19fffvttxbtKygoSEFBQZaWUGknT57U2bNn1bBhw2r7TACA4wmq46NFD3Yzt9n/eOis+s/ZTJu9G7L4ilCHDh104MABzZo1S126dFGXLl00e/ZsHThwQO3bt7dFjZKk48ePKz4+XsePH1dBQYHi4+MVHx+vrKws8zqRkZH64osvJElZWVl66qmntH37dh09elTr16/XoEGD1LJlS8XExNisTgCAcyhqs18zoTdt9m7MaR6oWNrDEaVLg7SLBm6bTCYtWbJEo0aN0sWLFzV48GDt3r1baWlpCgsL06233qoXXnih1DFOZeGBigDg+pjN3vVU9O+3xUFo1qxZCgkJ0ejRo4stX7x4sc6cOaNnnnmmchU7KIIQALiP3cf/1KTl8Tp69oJMJunR3i005dbW8vEqvdMYjstmXWMLFy5UZGRkieXt27fXggULLN0dAAAO43+z2TdhNns3YXEQSklJKXWwcVBQkJKTk61SFAAA9lLUZr+INnu3YHEQCg8P19atW0ss37p1q8LCGGkPAHAN0bTZuwWLg9Cjjz6qiRMnasmSJTp27JiOHTumxYsXa9KkSXr00UdtUSMAAHZR1Gb/8l0d5VfD09xm/59fkuxdGqzE4sHShmFo6tSpmjt3rnJzcyVJvr6+euaZZzR9+nSbFGlPDJYGAEjSkT/Oa9LyeMWfuDTF06AuYXp+UAcF+NWwc2Uojc26xopkZWUpISFBfn5+atWqlXx8fCpdrCMjCAEAiuQXFOqt2IOat4E2e0dn8yDkLghCAIAr0Wbv+GzWPg8AgLujzd51EIQAAKgE2uxdA0EIAIAqoM3euRGEAACoItrsnRdBCAAAK7h8NvsuzGbvNAhCAABYUfMGtfT52ChNjG4lTw+TvoxP0m1zNuvHQ3/YuzSUgiAEAICVeXl6aGJ0a30+NkrN6tdUUnq27lu0Qy+t3qec/AJ7l4fLEIQAALCRK9vs39tyhDZ7B0MQAgDAhmizd2wEIQAAqkF0uxB9O+lGRbelzd6REIQAAKgmDWr76L2R3TRrCG32joIgBABANTKZTBrRnTZ7R0EQAgDADmizdwwEIQAA7IQ2e/sjCAEAYGe02dsPQQgAAAdAm719EIQAAHAgtNlXL4IQAAAOhjb76kMQAgDAAdFmXz0IQgAAODDa7G2LIAQAgIOjzd52CEIAADiJa5rU1ZoJvXVvD9rsrYUgBACAE6np7aWX76LN3loIQgAAOCHa7K2DIAQAgJMqq83+y/hT9i7NaRCEAABwYqW12U/4JF5PfkybfUUQhAAAcAFXttn/5xfa7CuCIAQAgIugzd5yBCEAAFwMbfYVRxACAMAFXd5m36A2bfZlIQgBAODCotuFaO1E2uzLQhACAMDF0WZfNoIQAABuoNw2+wvu22ZPEAIAwI2U1mbf/033bbMnCAEA4GaubLNPduM2e4IQAABuijZ7ghAAAG6trDb79za7R5s9QQgAAJRos39pTYLuW+T6bfYEIQAAIKlkm/22w67fZk8QAgAAZu7WZk8QAgAAJZTZZn/QtdrsCUIAAKBUl7fZN29QS8np2brXxdrsCUIAAKBc1zSpq9VP3qB7ezSR5Fpt9gQhAABwVa7aZk8QAgAAFeZqbfYEIQAAYJHL2+xrel9qs49x0jZ7ghAAALCYuc3+yUtt9plO2mZPEAIAAJXWzMnb7AlCAACgSspqs3/x633KznPsNnuCEAAAsIor2+wX/XBEg+c7dps9QQgAAFhNUZv9+w86R5s9QQgAAFhdv7bO0WZPEAIAADbhDG32BCEAAGAzjt5mTxACAAA2V9RmPym6tUO12ROEAABAtfDy9NCE6FYl2uwXbDpkt5oIQgAAoFpd3mbvYZKubVLXbrU4RRA6evSoHn74YTVv3lx+fn6KiIjQjBkzlJubW+522dnZevzxx1W/fn3Vrl1bQ4cO1enTp6upagAAUJaiNvvvJ9+k7s3r2a0OpwhC+/fvV2FhoRYuXKjffvtN//znP7VgwQL9/e9/L3e7SZMm6auvvtJnn32mTZs2KSkpSUOGDKmmqgEAwNW0CKpt1883GYbheE83qoBXX31V77zzjg4fPlzq++np6QoKCtJHH32kv/zlL5IuBaq2bdtq27Ztuv766yv0ORkZGQoICFB6err8/f2tVj8AALCdiv79doorQqVJT09XvXplX0rbuXOn8vLyFB0dbV4WGRmpJk2aaNu2bWVul5OTo4yMjGIvAADgmpwyCB08eFDz5s3TY489VuY6KSkp8vb2VmBgYLHlISEhSklJKXO7WbNmKSAgwPwKDw+3Wt0AAMCx2DUITZ06VSaTqdzX/v37i21z6tQp9e/fX3fffbceffRRq9c0bdo0paenm18nTpyw+mcAAADH4GXPD58yZYpGjRpV7jotWrQwf52UlKQ+ffqoZ8+eevfdd8vdLjQ0VLm5uUpLSyt2Vej06dMKDQ0tczsfHx/5+PhU7AAAAIBTs2sQCgoKUlBQUIXWPXXqlPr06aOuXbtqyZIl8vAo/2JW165dVaNGDa1fv15Dhw6VJCUmJur48eOKioqqcu0AAMD5OcUYoVOnTunmm29WkyZN9Nprr+nMmTNKSUkpNtbn1KlTioyMVFxcnCQpICBADz/8sCZPnqzY2Fjt3LlTDz30kKKioircMQYAAFybXa8IVdS6det08OBBHTx4UI0bNy72XlH3f15enhITE3XhwgXze//85z/l4eGhoUOHKicnRzExMXr77bertXYAAOC4nPY5QtWF5wgBAOB8XP45QgAAAFVFEAIAAG6LIAQAANwWQQgAALgtp+gas6eiseTMOQYAgPMo+rt9tZ4wgtBVZGZmShJzjgEA4IQyMzMVEBBQ5vu0z19FYWGhkpKSVKdOHZlMJqvtNyMjQ+Hh4Tpx4oTbteVz7O537O563BLH7o7H7q7HLTnWsRuGoczMTIWFhZU7GwVXhK7Cw8OjxEMcrcnf39/u/7PYC8fufsfursctcezueOzuetyS4xx7eVeCijBYGgAAuC2CEAAAcFueM2fOnGnvItyVp6enbr75Znl5ud8dSo7d/Y7dXY9b4tjd8djd9bgl5zt2BksDAAC3xa0xAADgtghCAADAbRGEAACA2yIIAQAAt0UQsqH58+erWbNm8vX1VY8ePRQXF1fu+p999pkiIyPl6+urjh07as2aNdVUqfXMmjVL1113nerUqaPg4GANHjxYiYmJ5W6zdOlSmUymYi9fX99qqth6Zs6cWeI4IiMjy93GFc65JDVr1qzEsZtMJj3++OOlru+s53zz5s268847FRYWJpPJpFWrVhV73zAMTZ8+XQ0bNpSfn5+io6N14MCBq+7X0t8V9lDesefl5emZZ55Rx44dVatWLYWFhWnkyJFKSkoqd5+V+Zmpblc756NGjSpxDP3797/qfp39nEsq9WfeZDLp1VdfLXOfjnjOCUI2snz5ck2ePFkzZszQrl271LlzZ8XExCg1NbXU9X/88UeNGDFCDz/8sHbv3q3Bgwdr8ODB+vXXX6u58qrZtGmTHn/8cW3fvl3r1q1TXl6ebr31Vp0/f77c7fz9/ZWcnGx+HTt2rJoqtq727dsXO44ffvihzHVd5ZxL0k8//VTsuNetWydJuvvuu8vcxhnP+fnz59W5c2fNnz+/1Pf/8Y9/aO7cuVqwYIF27NihWrVqKSYmRtnZ2WXu09LfFfZS3rFfuHBBu3bt0rPPPqtdu3Zp5cqVSkxM1MCBA6+6X0t+Zuzhaudckvr371/sGD7++ONy9+kK51xSsWNOTk7W4sWLZTKZNHTo0HL363Dn3IBNdO/e3Xj88cfN3xcUFBhhYWHGrFmzSl3/nnvuMW6//fZiy3r06GE89thjNq3T1lJTUw1JxqZNm8pcZ8mSJUZAQEA1VmUbM2bMMDp37lzh9V31nBuGYUyYMMGIiIgwCgsLS33fFc65JOOLL74wf19YWGiEhoYar776qnlZWlqa4ePjY3z88cdl7sfS3xWO4MpjL01cXJwhyTh27FiZ61j6M2NvpR33gw8+aAwaNMii/bjqOR80aJDRt2/fctdxxHPOFSEbyM3N1c6dOxUdHW1e5uHhoejoaG3btq3UbbZt21ZsfUmKiYkpc31nkZ6eLkmqV69euetlZWWpadOmCg8P16BBg/Tbb79VR3lWd+DAAYWFhalFixa67777dPz48TLXddVznpubq3//+98aPXp0uRMVu8o5L3LkyBGlpKQUO6cBAQHq0aNHmee0Mr8rnEV6erpMJpMCAwPLXc+SnxlHtXHjRgUHB6tNmzYaN26czp49W+a6rnrOT58+rdWrV+vhhx++6rqOds4JQjbwxx9/qKCgQCEhIcWWh4SEKCUlpdRtUlJSLFrfGRQWFmrixInq1auXOnToUOZ6bdq00eLFi/Xll1/q3//+twoLC9WzZ0+dPHmyGqutuh49emjp0qVau3at3nnnHR05ckS9e/dWZmZmqeu74jmXpFWrViktLU2jRo0qcx1XOeeXKzpvlpzTyvyucAbZ2dl65plnNGLEiHIn3rT0Z8YR9e/fX8uWLdP69ev1yiuvaNOmTbrttttUUFBQ6vques4/+OAD1alTR0OGDCl3PUc8587x/Gs4pccff1y//vrrVe//RkVFKSoqyvx9z5491bZtWy1cuFAvvPCCrcu0mttuu838dadOndSjRw81bdpUn376aYX+leQq3n//fd12220KCwsrcx1XOecoKS8vT/fcc48Mw9A777xT7rqu8DMzfPhw89cdO3ZUp06dFBERoY0bN6pfv352rKx6LV68WPfdd99Vmx4c8ZxzRcgGGjRoIE9PT50+fbrY8tOnTys0NLTUbUJDQy1a39E98cQT+vrrrxUbG6vGjRtbtG2NGjV0zTXX6ODBgzaqrnoEBgaqdevWZR6Hq51zSTp27Ji+//57PfLIIxZt5wrnvOi8WXJOK/O7wpEVhaBjx45p3bp15V4NKs3VfmacQYsWLdSgQYMyj8HVzrkkbdmyRYmJiRb/3EuOcc4JQjbg7e2trl27av369eZlhYWFWr9+fbF/BV8uKiqq2PqStG7dujLXd1SGYeiJJ57QF198oQ0bNqh58+YW76OgoEB79+5Vw4YNbVBh9cnKytKhQ4fKPA5XOeeXW7JkiYKDg3X77bdbtJ0rnPPmzZsrNDS02DnNyMjQjh07yjynlfld4aiKQtCBAwf0/fffq379+hbv42o/M87g5MmTOnv2bJnH4ErnvMj777+vrl27qnPnzhZv6xDn3N6jtV3VJ598Yvj4+BhLly419u3bZ4wZM8YIDAw0UlJSDMMwjAceeMCYOnWqef2tW7caXl5exmuvvWYkJCQYM2bMMGrUqGHs3bvXXodQKePGjTMCAgKMjRs3GsnJyebXhQsXzOtceezPPfec8e233xqHDh0ydu7caQwfPtzw9fU1fvvtN3scQqVNmTLF2Lhxo3HkyBFj69atRnR0tNGgQQMjNTXVMAzXPedFCgoKjCZNmhjPPPNMifdc5ZxnZmYau3fvNnbv3m1IMt544w1j9+7d5s6o2bNnG4GBgcaXX35p7Nmzxxg0aJDRvHlz4+LFi+Z99O3b15g3b575+6v9rnAU5R17bm6uMXDgQKNx48ZGfHx8sZ/9nJwc8z6uPPar/cw4gvKOOzMz0/jb3/5mbNu2zThy5Ijx/fffG9dee63RqlUrIzs727wPVzznRdLT042aNWsa77zzTqn7cIZzThCyoXnz5hlNmjQxvL29je7duxvbt283v3fTTTcZDz74YLH1P/30U6N169aGt7e30b59e2P16tXVXHHVSSr1tWTJEvM6Vx77xIkTzf+dQkJCjAEDBhi7du2q/uKraNiwYUbDhg0Nb29vo1GjRsawYcOMgwcPmt931XNe5NtvvzUkGYmJiSXec5VzHhsbW+r/30XHVlhYaDz77LNGSEiI4ePjY/Tr16/Ef4+mTZsaM2bMKLasvN8VjqK8Yz9y5EiZP/uxsbHmfVx57Ff7mXEE5R33hQsXjFtvvdUICgoyatSoYTRt2tR49NFHSwQaVzznRRYuXGj4+fkZaWlppe7DGc65yTAMw6aXnAAAABwUY4QAAIDbIggBAAC3RRACAABuiyAEAADcFkEIAAC4LYIQAABwWwQhAADgtghCAADAbRGEABd09OhRmUwmxcfH27uUct18eddVLwAAETFJREFU882aOHGiXT47OztbJpNJa9eutcvnW2rBggUWT8o5fPjwYrOjW9vatWtlMpmUnZ0tqWSNU6dO1fXXX2+zz5ek/fv3y2Qyaf/+/Tb9HLgughDcyqhRo2QymTR79uxiy1etWiWTyWTzzzeZTOaXl5eXmjRposmTJysnJ8fmn325c+fOafz48WrTpo38/PzUpEkTPfnkk0pPTzevUxSmgoODlZmZWWz7Ll26aObMmRX+vI0bN8pkMiktLa3U94s+q7zX0qVLK3Oo1SI+Pr7U4NmlSxfVqVNH+fn55mVZWVmqUaOGPvzwQ0llh5UrQ8aDDz6ovXv3Wr320NBQLViwoMTyK0PM9ddfr6lTpxZbp2/fvkpOTpavr2+p+/6///s/rVmzxmq1lvbfqlWrVkpOTlarVq2s9jlwLwQhuB1fX1+98sor+vPPP+3y+UuWLFFycrKOHDmit99+W//617/04osvVmsNSUlJSkpK0muvvaZff/1VS5cu1dq1a/Xwww+XWDczM1OvvfaaTesJDw9XcnKy+TVlyhS1b9++2LJhw4aV2K6goECFhYU2ra0iOnXqpHr16mnjxo3mZefOndNvv/0mf39//fzzz+blW7ZsUX5+vvr27WvRZ/j5+SkoKMhaJVuFt7d3uVepateurXr16tm0Bk9PT4WGhsrT09OmnwPXRRCC24mOjlZoaKhmzZpV6vszZ85Uly5dii2bM2eOmjVrZv5+1KhRGjx4sF5++WWFhIQoMDBQzz//vPLz8/XUU0+pXr16aty4sZYsWVJi/4GBgQoNDVV4eLjuuOMODRo0SLt27TK/f+jQIQ0aNEghISGqXbu2rrvuOn3//ffF9tGsWTO9/PLLGj16tOrUqaMmTZro3XffLfOYCwoKNHr0aEVGRur48ePq0KGDVqxYoTvvvFMRERHq27evXnrpJX311VfFrl5I0vjx4/XGG28oNTW1zP3/61//Urdu3VSnTh2Fhobq3nvvNa9/9OhR9enTR5JUt25dmUwmjRo1qtj2RX/Mil61a9eWl5dXsWV+fn7mWy8rVqxQmzZt5OPjo9TUVP3444/q16+f6tevr8DAQPXr10979uwp9hkJCQnq1auXfH191aFDh2KhpcjRo0c1dOhQBQQEqH79+hoyZIhOnDhhfn/dunXq1q2batasqbp166p3795KSkqSh4eHbrrppmL73LRpkzp37qyYmJhiyzdu3Kg2bdqoYcOGZf73LM2Vt50Mw9D06dPVoEED+fv7a+zYsZo8eXKpt6KK/j8NCgrSxIkTVVBQYNFnDx8+XDt27NArr7xivkKXkpJS4qrVlS6/qlR0K/LKV2RkpCQpJydHo0aNUtOmTeXn56fIyEi9/fbbxfa1fPlyLV++3Lzt9u3bS7019v3336tr167y8fFRWFiYnn322WLHfP311+tvf/ubJk2apMDAQIWFhZX5+wCujyAEt+Pp6amXX35Z8+bN08mTJyu9nw0bNigpKUmbN2/WG2+8oRkzZuiOO+5Q3bp1tWPHDo0dO1aPPfZYuZ/x+++/a8OGDerRo4d5WVZWlgYMGKD169dr9+7d6t+/v+68804dP3682Lavv/66unXrpt27d+uvf/2rxo0bp8TExBKfkZOTo7vvvlvx8fHasmWLmjRpUmot6enp8vf3l5eXV7HlI0aMUMuWLfX888+XeRx5eXl64YUX9Msvv2jVqlU6evSoOeyEh4drxYoVkqTExEQlJyfrzTffLHNfV5OWlqY5c+Zo2bJl2rt3r+rWrausrCw98sgj+vHHH7V161Y1atRIAwYM0MWLFyVdCoKDBg1SQECA4uLiNHfuXD399NPF9puTk6Po6GgFBwdr69at2rx5s7y8vHT77beroKBA2dnZuuuuu9S/f3/9+uuv2rp1qx566CHz9n369NHmzZvNV6hiY2N1880366abblJsbKx5vdjYWHMwrIrFixfr9df/f3v3H9R0/ccB/DkVRreBGoxBxWbeBOcay2HqjF/Zj3kLWliXgXXY6rwzpFJnqFicRB1WRhcRGdk5k6zzguCoeXkpxM9aIEQ1thQ8rgwFgviRibTX9w9un68fhj9Iy2zvx93u+Lz3/rzf789nnw+89v7xYQfy8vLwzTffICgoCLt27fLIZ7VacfLkSXz55ZcoKirC22+/jQ8++GBSde3cuRNarRZr167leuiCg4MnVYafnx+vh8/hcEAulyM2NhYAMDo6itmzZ6OkpAQ//PADNm/ejA0bNqC8vBzA2DCb0WiE0WjkyoiKivKo5/jx40hISEBsbCxaWlqQn5+PgoICvPLKK7x8RUVFCA4Ohs1mQ3Z2NrZs2YLq6upJHRPzH3H1/vE9w/zzUlNTyWg0EhHR4sWLyWQyERFRaWkpuW+HrKws0mg0vP3y8vJILpfzypHL5fTnn39yaRERERQTE8Ntj46Okkgkon379nFpAMjPz49EIhEJhUICQAkJCTQyMnLBdqtUKsrPz+e25XI5PfLII9y2y+Wi4OBgKiwsJCKijo4OAkDV1dV05513UnR0NPX395+3/O7ubpLJZLRlyxYuzV3GkSNH6MCBA+Tj40NHjx4lIiKNRkNZWVnnLc9msxEAGhwcJCKiw4cPEwDq6+vj5YuLi6Onn37aY/+JPgMiosLCQgJAbW1t562biGhkZIT8/Pzo4MGDRERUVlZGQqGQuru7uTzuz9xqtRIRUVFRkUedv//+O/n4+FBVVRX9/PPPBIAaGhomrLO1tZUAUFNTExERqdVqKi8vp/b2dhKJRHT27FkaGBigqVOn0kcffcTtt2LFCpo2bRqJRCLey8/PjwDQ6dOnuWOXSqXcfhqNhjZs2MBrQ1RUFC1atIhX9pw5c8jlcnFpiYmJlJqaym1LpVLuujlXRkYGr6xFixZRRkYGL4/Var1gG8eX4TY6OkoGg4F0Oh398ccfE5zNMY8//jitXLmSdzwrVqzg5bHb7QSA7HY7ERGtX7+eIiMjeXl27NhBgYGBvGO56667eHnUavUFr2nmv4v1CDFea/v27bBYLLDb7X9pf5VKhSlT/n8LSaVSqNVqbnvq1KkIDAz0GFLKy8tDc3MzWlpaUFFRAafTiUcffZR7f2hoCGazGUqlEjNmzIBYLIbdbvfoEYqMjOR+FggECAkJ8agrOTkZw8PD+PzzzzF9+vQJj2NgYAD33nsv5s2bd94J0Hq9HtHR0XjuuecmfL+xsRGJiYmQyWTw9/dHXFwcAHi0+UoQi8WIiIjgpZ04cQImkwkKhQIBAQGYOXMmzpw5w9Vvt9sxe/ZsBAUFcfvodDpeGS0tLfj+++8hFou5l0QiwejoKI4dO4YbbrgBDz/8MO644w4YjUbk5+fj5MmT3P4qlQoSiQSVlZXo7e2F3W5HTEwMbr75Zlx//fWw2Wyorq6Gy+VCfHw8r269Xo/m5mbe69xhoYk4nU4sXLiQlzZ+GwDUajVvIUBoaOgFhzn/CWazGd9++y1KS0shFAq59Ndffx1arRZBQUEQi8XYs2fPpK8hu92OJUuW8NJuv/129Pb28o773PsH+HecF+bqmHbxLAzz3xQbGwu9Xo/Nmzfz5qxMmTIFRMTLe/bsWY/9fXx8eNsCgWDCtPGTeUNCQqBQKAAAERERGBwcRHJyMnJycqBQKGA2m3Hw4EG8+uqrUCgUuO666/Dggw9iZGTkovWPr8tgMGDv3r2or6+fcHLu4OAgli1bBn9/f5SWlnqUea7c3FzodDps3LiRlz48PAy9Xg+9Xo/i4mJIJBJ0dnZCr9d7tPlKEIlEHmkpKSk4c+YM3nzzTYSFhUEoFEKr1U6q/qGhIeh0Orz33nse77mHgfbt24fGxkYcOHAAe/fuxdatW3H48GFotVoIBAJuGEwmk0GtVmPGjBkAwKX39fVBpVJ5DCuJxWLumnA7evToJbf9Qi52nQQEBPBWC7r19/efN3i+HO+++y527tyJmpoaSKVSLn337t3IzMxEXl4ebrvtNvj7+yMnJ+dvWxZ/KfcP4x1YIMR4tdzcXNx66628HgaJRIKuri4QEfdN+u98Ho97tYt7PkttbS1WrVqFpKQkAGN/oI8fP/6Xyl6zZg1uueUW3Hffffj000+5nhpgrCdIr9dDKBSivLz8vEug3RYuXIjly5d7LKFua2tDb28vcnNzERYWBgC8VVLA2OoiAJOepHspiAh1dXUoLi7GsmXLAIwFEecu+VcqlWhvb0dPTw/XK9TQ0MArR6vV4rPPPkNoaOiEwZZbVFQUoqKikJmZifnz5+PDDz+EVqsFMDZPKDMzE2FhYbxen9jYWOzfvx99fX1XZH4QAISHh8Nms+Ghhx7i0mw226RXT0VERKCxsdEjvampiTd3zdfX97I/v6qqKqSlpcFisXDnzK22thbx8fFYvXo1lzY+GPT19eXuk/NRKpUeiwtqa2sRGBg46XlNjHdgQ2OMV1Or1Vi5ciXeeOMNLi0+Ph7d3d14+eWXcezYMRQUFMBqtV6xOvv7+9HV1YUTJ06gqqoK2dnZCA8Ph1KpBDD2XJSSkhJu+CwlJeWyvqmmp6cjJycHCQkJqKmpATAWBN1zzz0YHh7Grl27MDAwgK6uLnR1dV3wj92LL76IQ4cO8SZly2Qy+Pr6Ij8/H+3t7SgvL8cLL7zA208ul0MgEKCiogLd3d0YGhr6y8cznkAggEKhgMVigcPhQF1dHVJTU3lDLgaDAWFhYdyzeCorK5GVlcUrJzU1FSKRCElJSaitrUVHRwcOHTqEtLQ0nDp1Cg6HA1u3bkVDQwM6OzthtVrR0dHBfW7AWCDU39+P999/nxd0xsXFoaamBkeOHLligVB6ejoKCwtRXFwMp9OJ559/Hk6nc9LPw1q3bh1KSkqwfft2tLW1obW1FRs3bkRLSwvS09O5fLNmzUJ9fT06OzvR09Pj0Wt6MT/99BMeeOABrFq1CvHx8dz11tPTA2Dsuq+vr8cXX3wBp9OJjIwMj+cmzZo1C83Nzfjxxx/R09PjscLRfV4cDgfWr18Ph8OBjz/+GDk5OTCbzZNqL+M9WCDEeL3s7GxeoKFUKvHWW2+hoKAAGo0GX3/99RX9JfrYY48hNDQUN910E5KTk6FSqWC1WrnVWq+99hpmzpyJJUuWIDExEXq93uPb82Q988wz2LZtGwwGA+rq6tDU1ISvvvoKra2tUCgUCA0N5V7nLhcfLzw8HCaTibdcWiKRYPfu3di/fz/mzZuH3Nxcj+cO3Xjjjdi2bRs2bdoEqVSKtWvXXtbxjGexWPDLL79Ao9HAZDLh2Wef5YalAGDatGn45JNP8Ouvv2LBggV48sknPZZLBwQEoLq6GsHBwTAajVAqlVi9ejVcLhdEIhHEYjFaW1uRlJSEOXPmIC0tDWazmTesqlQqERISguHhYW41lPu8TZ8+HS6XixcgXQ6TyYR169bhqaeewoIFC3Dq1CmkpKRctGdvvKVLl6KsrAxlZWVYvHgxli5diqamJlRWViI8PJzLt2nTJoyMjGDu3LmQSCS8+VGX4rvvvkNvby/eeecd3vUWHR0NYCyAMRgMWL58OXQ6HU6fPo0nnniCV8aaNWsgk8kwf/58SCQSj55HYCxYqqioQFVVFSIjI5Geno60tDSPIV2GcRPQZMN6hmEY5l8pJiYGc+fORVFR0dVuCsNcM9gcIYZhmGvQb7/9BovFgrvvvhsAsGfPHtTU1OCll166yi1jmGsL6xFiGIa5Bg0MDOD+++9Hc3MzN2SVlZWFxMTEq900hrmmsECIYRiGYRivxSZLMwzDMAzjtVggxDAMwzCM12KBEMMwDMMwXosFQgzDMAzDeC0WCDEMwzAM47VYIMQwDMMwjNdigRDDMAzDMF6LBUIMwzAMw3it/wEBUZHdn2qCMwAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['NumBank2NatlTradesWHighUtilization']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ " The third plot shows that the model gives a bonus to applicants who carry balances on no more than five revolving debt accounts." ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['NumRevolvingTradesWBalance']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The fourth shows an effect from the percentage of accounts with a balance that is much smaller than those from other features." ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['PercentTradesWBalance']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Number and type of accounts\n", "The number of \"satisfactory\" accounts (\"trades\") has a significant positive effect on the predicted probability of good credit, with jumps at 12 and 17 accounts." ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['NumSatisfactoryTrades']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "However, having more than 40% as installment debt accounts (e.g. car loans) is seen as a negative." ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['PercentInstallTrades']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Length of credit history\n", "The 'AverageMInFile' plot shows that most of the benefit of having a longer average credit history accrues between average ages of 52 and 84 months (four to seven years). " ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAk0AAAG1CAYAAADk08CxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOzdeVRTd94/8HcSSBDZRAhJEKuCVUAJUxXq0tqqdUGT6bTPb6x1SrWtTjvVtuJ0hGemrc48U3S6uf7K1Hba+jv66HQnVlHrUltLtdUSXAD3ooSwCmGRLbm/P8AgA9hEg1l4v87hHPK99yYfOtPy5ubmfUWCIAggIiIiohsSO3sAIiIiInfA0ERERERkA4YmIiIiIhswNBERERHZgKGJiIiIyAYMTUREREQ2YGgiIiIisgFDExEREZENGJqIiIiIbMDQRERERGQDtwtNGzZswKBBg+Dj44PExEQcOXLkhvtXVVXh2WefhVKphEwmw5133okdO3bcpmmJiIjIU3g5ewB7bNu2DSkpKcjIyEBiYiJWr16NadOmoaCgAHK5vNP+TU1NeOCBByCXy/Hxxx8jPDwcP//8M4KCgpwwPREREbkzkTvdsDcxMRFjxozB+vXrAQAWiwURERFYvHgxUlNTO+2fkZGB1157Dfn5+fD29r6p17RYLDAYDPD394dIJLql+YmIiOj2EAQBNTU1UKlUEIsd88aa24SmpqYm+Pr64uOPP8aDDz5oXX/88cdRVVWFL774otMxSUlJCA4Ohq+vL7744guEhobi0UcfxbJlyyCRSLp8ncbGRjQ2NlofFxUVISYmxvE/EBEREfW4S5cuYcCAAQ55Lrd5e668vBxmsxlhYWEd1sPCwpCfn9/lMefPn8e+ffswd+5c7NixA2fPnsUf/vAHNDc345VXXunymPT0dKxYsaLT+qVLlxAQEHDrPwgRERH1OJPJhIiICPj7+zvsOd0mNN0Mi8UCuVyOd955BxKJBKNGjUJRURFee+21bkNTWloaUlJSrI+v/UMPCAhgaCIiInIzjry0xm1CU0hICCQSCUpKSjqsl5SUQKFQdHmMUqmEt7d3h7fioqOjYTQa0dTUBKlU2ukYmUwGmUzm2OGJiIjI7blN5YBUKsWoUaOwd+9e65rFYsHevXsxduzYLo8ZP348zp49C4vFYl07ffo0lEpll4GJiIiIqDtuE5oAICUlBRs3bsSHH36IvLw8PPPMM6irq8P8+fMBAMnJyUhLS7Pu/8wzz6CyshLPP/88Tp8+jS+//BKvvvoqnn32WWf9CEREROSm3ObtOQCYPXs2ysrK8PLLL8NoNCI+Ph5ZWVnWi8MLCws7fKwwIiICu3btwpIlSxAXF4fw8HA8//zzWLZsmbN+BCIiInJTblM54CwmkwmBgYGorq7mheBERERuoid+f7vV23NEREREzsLQRERERGQDhiYiIiIiGzA0EREREdmAoYmIiIjIBgxNRERERDZgaCIiIiKyAUMTEREROYXFIuDHi5VoaDY7exSbuFUjOBEREbk3QRBw0mBCpt6A7XoDDNUN+OdjozAtVuHs0X4RQxMRERH1uLOlNcjUF2O73oDz5XXWdT+ZF0pNDU6czHYMTURERNQjLlXWY3tuMTL1BuQVm6zrMi8xpkSHQaNW4r5hcvh4S5w4pe0YmoiIiMhhSmsa8GVuMXR6A44VVlnXvcQi3HtnKLRqFabEhMFP5n4RxP0mJiIiIpdSVd+ErBNGZOoN+P58BSxC67pIBNw9uD+08SpMj1WgX1+pcwe9RQxNREREZLe6xhbsOVUCnd6Ag2fK0GwWrNt+NTAImjgVZsUpIQ/wceKUjsXQRERERDZpaDbjQEEZdHoD9uaXoKHZYt02XOEPbbwKmjgVIoJ9nThlz2FoIiIiom41my347lwFMnMM2H3SiJrGFuu2Qf19oVWroFGrMDTM34lT3h4MTURERNSBxSLgh4uV0OUasOO4EZV1TdZtykAfzIpTQqsOx4jwAIhEIidOensxNBEREREEQcDxompk5hiwPbcYxuu6k/r3lSJppBIatQqj7+gHsbj3BKXrMTQRERH1YqdLaqDTG6DTG3Cxot667i/zwrQRCmjVKoyL7A8vCe+8xtBERETUyxRW1EOX2xqU8o011nUf72ulkypMvDPUbUonbxeGJiIiol6gxNSA7W2lkzmX2ksnvSUiTLwzFBq1ClOiw9DXDUsnbxf+kyEiIvJQV+qasPOEEZn6Ihy+UAmhrUpJLALGRvaHVq3CtFgFgnzdu3TydmFoIiIi8iC1jS3YfdIInd6Ab86Uo8XSXjo56o5+0MQpkRSnhNzfc0onbxeGJiIiIjfX0GzG/vxSZOoN2JdfisaW9tLJGGUAtPEqzByp9NjSyduFoYmIiMgNNZst+PZsOXQ5Buw+VYLa60onh4T0haatdDJK7ufEKT0LQxMREZGbMFsEHLnQWjq583gxrtQ3W7eFB/XBLLUSmjgVYlW9q3TydmFoIiIicmGCIEB/ubV08svjBpSYGq3bQvykmNlWOnnXwN5bOnm7MDQRERG5oHyjqa10shiFldeVTvp4YcYIBbTqcNw9JJilk7cRQxMREZGLuFhe1xqUcg04XVJrXe/jLcEDMa2lk/feGQKZF0snnYGhiYiIyImM1Q3Y3tbOrb9cbV2XSsSYOCwUWrUKk6Pl8JXyV7az8X8BIiKi26yitrGtdNKAHy52LJ0cHxUCTVvpZGAfb+cOSh0wNBEREd0GpoZm7D5ZAp3egG/PlsN8XenkmEH9oFGrkDRSiRA/mROnpBthaCIiIuohV5vM2Jdfikx9EfYXlKHputLJEeEB0KpVmBmnQnhQHydOSbZiaCIiInKgphYLvjlTBp3egD2nSlDXZLZuiwztC606HBq1EkNCWTrpbhiaiIiIbpHZIuDw+YrW0skTRlRdVzo5oF+f1nbuOBWilf4snXRjDE1EREQ3QRAE/HSpqq10shhlNe2lk6H+sutKJ4MYlDyE24WmDRs24LXXXoPRaIRarca6deuQkJDwi8dt3boVc+bMwa9//Wt8/vnnt2FSIiLyNIIgIK+4Brq2ioDLV65atwX28W4rnVQhcUh/SNjO7XHcKjRt27YNKSkpyMjIQGJiIlavXo1p06ahoKAAcrm82+MuXryIP/7xj7jnnntu47REROQpLpTXITOntXTybGl76aSvVIKpbaWT9wwNhdSL7dyeTCQIgvDLu7mGxMREjBkzBuvXrwcAWCwWREREYPHixUhNTe3yGLPZjHvvvRdPPPEEvvnmG1RVVdl1pslkMiEwMBDV1dUICAhwyM9BRESuz1B1FdtzDcjUG3CiyGRdl3qJcf+wUGjV4Zg0XI4+UrZzu6Ke+P3tNmeampqacPToUaSlpVnXxGIxpkyZguzs7G6P++tf/wq5XI4nn3wS33zzzS++TmNjIxob29+XNplMN9ibiIg8SXltI3YeL24rnbxiXZeIRZjQVjo5NTYMAT4sneyN3CY0lZeXw2w2IywsrMN6WFgY8vPzuzzm22+/xXvvvYecnBybXyc9PR0rVqy4pVmJiMh9VF9txq6TRuj0Bnx3rqJD6WTC4ODW0skRCvRn6WSv5zahyV41NTV47LHHsHHjRoSEhNh8XFpaGlJSUqyPTSYTIiIiemJEIiJykvqmFuzNK0Wm3oCvC8rQZG4vnYwbENhWOqmEMpClk9TObUJTSEgIJBIJSkpKOqyXlJRAoVB02v/cuXO4ePEiNBqNdc1iaf2XwsvLCwUFBYiMjOx0nEwmg0zGvyaIiDxNY4sZB0+XQ6c34Ku8EtRfVzo5VO4HrVoFjVqFQSF9nTgluTK3CU1SqRSjRo3C3r178eCDDwJoDUF79+7FokWLOu0/fPhwHD9+vMPaX/7yF9TU1GDNmjU8e0RE1AuYLQKyz1VApzdg54limBparNsigvtYg9JwBT/oQ7/MbUITAKSkpODxxx/H6NGjkZCQgNWrV6Ourg7z588HACQnJyM8PBzp6enw8fHBiBEjOhwfFBQEAJ3WiYjIc1gsAn66dKWtdNKI8tr2D/fI/WWYFaeCNl4F9YBAlk6SXdwqNM2ePRtlZWV4+eWXYTQaER8fj6ysLOvF4YWFhRCL2ZFBRNTbCIKAkwYTdLkGbNcXo6iqvXQyyNcbM0YooVWrkDA4mKWTdNPcqqfJGdjTRETkus6V1VpLJ8+X1VnX+0olmBargEatwoShIfCW8A/q3qZX9zQREREBwOUr9dieW4zMHANOFXcsnZw8XA6tWoX7h8vh483SSXIshiYiInJ5ZTWN2NFWOnn05/bSSS+xCPcMbS2dfCAmDP4snaQexNBEREQuqbq+GVkni6HTF+O7c+W41jkpEgGJbaWTM0YoEdxX6txBqddgaCIiIpdR19iCr/JKoNMb8PXpMjSb2y+7jY8IgkatwsyRSigCfZw4JfVWDE1ERORUjS1mHCgog05vwN68Ulxtbi+dHK7wh0atgiZOhYH9fZ04JRFDExEROUGL2YLvzlUgU2/ArpNG1FxXOnlHf19r6eSdYf5OnJKoI4YmIiK6LSwWAUcLW0sndxwvRkVdk3WbIsAHs+KU0MarMDKcpZPkmhiaiIioxwiCgBNF10onDTBUN1i3BfeVImmkApo4FcYMCoaYpZPk4hiaiIjI4c6W1rSVThbjQnl76aS/zAtTYxXQxqswLrI/SyfJrTA0ERGRQ1yqrIcu14DMHAPyjTXWdZmXGFOiw6BRq3DfsFCWTpLbYmgiIqKbVmpqwJdtpZM/FVZZ173EIky8MxQatQpTYsLgJ+OvG3J//H8xERHZpaq+CTtPGKHTG/D9+YoOpZNjh/SHVq3C9BEKBPmydJI8C0MTERH9otrGFnx1qgSZegMOni5Di6W9dPKuge2lk/IAlk6S52JoIiKiLjU0m3GgoBQ6fTH25pegodli3RatDIBWrcKsOCUiglk6Sb0DQxMREVk1my04dLYcmXoDdp8sQW1je+nk4JC+0KhV0KqViJKzdJJ6H4YmIqJezmIR8MPFSmTqDdh5wojK60onlYE+bUFJhVhVAEsnqVdjaCIi6oUEQUDu5Wro9AZszy2G0dReOtm/rxQz45TQqFUYNbAfSyeJ2jA0ERH1IqdLrpVOGvBzRb113d/HC9PbSifHDukPL5ZOEnXC0ERE5OEKK9pLJwtK2ksnfbxbSye1ahUmDguFzIulk0Q3wtBEROSBSkwN0Olbb2Oiv9ReOuktEWHinXJo1EpMiQ5DX5ZOEtmM/7YQEXmIyrom7DxRDJ3egMMXKiG0VSmJRcC4yBBo1SpMi1Ug0NfbuYMSuSmGJiIiN1bT0Iw9baWT354p71A6OfqOftCoVUgaqUSov8yJUxJ5BoYmIiI309Bsxr78Uuj0BuzLL0VjS3vpZKyqtXRyZpwSA/qxdJLIkRwWmq5cuQKdTofk5GRHPSUREbVpNlvw7ZlrpZNG1DWZrduGhPaFVq2CRq1CZKifE6ck8mwiQRCEX97tl+n1etx1110wm82/vLMbMZlMCAwMRHV1NQICApw9DhH1ImaLgCMXrpVOFqOqvtm6LTyoD2apldCqVYhRsnSS6D/1xO9vm880mUymG26vqam54XYiIvplgiAg51IVdPpibM81oLSm0botxE+GWXFKaNRK/CqCpZNEt5vNoSkoKOiGf8kIgsC/dIiIboIgCCi4rnTyUuVV67YAHy/MGKGENl6FxMHBLJ0kciKbQ5O/vz/+/Oc/IzExscvtZ86cwe9//3uHDUZE5OkultdBpzcgU2/AmdJa67qvVIIHYsKgiVPh3jtDIfViUCJyBTaHprvuugsAMHHixC63BwUFwUGXRxEReazi6qvYri+GLteA3MvV1nWpRIz7hoVCo1ZhcrQcvlJ+uJnI1dj8b+Wjjz6Kq1evdrtdoVDglVdecchQRESepKK2ETtOGKHTG/DDxfbSSYlYhHGR/aFVqzA1VoHAPiydJHJlDvv0nKfip+eI6GaYGpqx64QRutxiHDpbDvN1pZMJg4KhUSsxY6QSIX4snSTqCU799BwREd3Y1SYz9uaXQKc3YH9BGZquK50cGR5oLZ1UBfVx4pREdLNuKjQdOnQIo0ePhkwm6/A9EVFv09RiwTdnypCpN2DPqRLUX1c6GSX3s5ZODg7p68QpicgRburtuYCAAOTk5GDIkCEdvvdEfHuOiP6T2SLg+/MV0OkN2HnCiOqr7aWTA/r1gUatglatwnCFP6tYiJzEZd6euz5n8ZIoIuoNBEHAscIq6PQGfHm8GGXXlU6G+l8rnVThVxE37rQjIvfFa5qIiLohCALyimuQqTdApzegqKr9E8SBfbyRNFIBjVqFxMH9IWE7N5HHc7vQtGHDBrz22mswGo1Qq9VYt24dEhISutx348aN2LRpE06cOAEAGDVqFF599dVu9yciAoDzZbXQ6YuRqS/CubI663pfqQRTYxXQqJWYEMXSSaLexq1C07Zt25CSkoKMjAwkJiZi9erVmDZtGgoKCiCXyzvtf+DAAcyZMwfjxo2Dj48PVq1ahalTp+LkyZMIDw93wk9ARK6qqOoqtutbb2Nyoqj9XptSLzEmDZNDo1Zh0nA5+kglTpySiJzppi4E9/f3h16vx5AhQzp839MSExMxZswYrF+/HgBgsVgQERGBxYsXIzU19RePN5vN6NevH9avX4/k5GSbXpMXghN5rrKaRuw8UYzMHAN+/PmKdV0iFmFCVAi0ahUeiA1DgA9LJ4ncjctcCO4MTU1NOHr0KNLS0qxrYrEYU6ZMQXZ2tk3PUV9fj+bmZgQHB3e7T2NjIxob2y/wNJlM3e5LRO6n+uq10kkDDp0tx7XOSZHoWumkCkkjlQjuK3XuoETkctwmNJWXl8NsNiMsLKzDelhYGPLz8216jmXLlkGlUmHKlCnd7pOeno4VK1bc0qxE5Frqm1rwVV4pMnMMOHi6DE3m9tJJ9YBAaNQqzIpTQRHo48QpicjV3VRo+uc//2kNL9d/78pWrlyJrVu34sCBA/Dx6f4/jGlpaUhJSbE+NplMiIiIuB0jEpEDNbaYcfB0OTL1Bnx1qgRXm9tLJ+8May+dvKM/SyeJyDY2hyZBEKzdI48++qh1/frve1JISAgkEglKSko6rJeUlEChUNzw2Ndffx0rV67EV199hbi4uBvuK5PJ2G5O5KZazBZkt5VOZp0wwtTQYt02MNgXGrUSWnU4hin8nTglEbkrm0PT+PHjsWnTJkRFRfXkPN2SSqUYNWoU9u7diwcffBBA64Xge/fuxaJFi7o97h//+Af+/ve/Y9euXRg9evTtGpeIbhOLRcCxwivI1Buw43gxymubrNvCAmSYFdd6Rkk9IJClk0R0S2wOTQMGDEB8fDxWrVqFZ599tidn6lZKSgoef/xxjB49GgkJCVi9ejXq6uowf/58AEBycjLCw8ORnp4OAFi1ahVefvllbNmyBYMGDYLRaAQA+Pn5wc/Pzyk/AxHdOkEQcNJggk5vwPbc4g6lk/18vTFjpBJatQpjBgWzdJKIHMbm0PTvf/8bH330ERYtWoTPP/8c77//PgYMGNCTs3Uye/ZslJWV4eWXX4bRaER8fDyysrKs11QVFhZCLG4vm3v77bfR1NSE//qv/+rwPK+88gqWL19+O0cnIgc4W1oLXVs79/ny9tJJP5kXpsaGQaNWYUJUCLwlLJ0kIsezu6eprKwMzz77LPbs2YPHHnsMXl4dc9ebb77p0AGdjT1NRM51+Uo9dPpi6PQGnCpurwCReYkxOVoOrVqF+4bJ4ePN0kkiaucSPU3BwcGIjo7GZ599hp9++qlDaOL1AkTkCKU1DdiRW4xMvQHHCqus615iEe4ZGgJtvApTosPgz9JJIrqN7ApNJ0+eRHJyMiorK7F7927cf//9PTUXEfUy1fXN2HmiGLpcA7LPVXQonbx7cH9o1CrMGKFAP5ZOEpGT2ByaVq5cieXLl+PRRx/FmjVr4O/Pj+wS0a2pa2zBV3klraWTZ8rQbG6/WiA+IghatQoz45QIC2DpJBE5n82hac2aNfjoo4+g0Wh6ch4i8nANzWZ8fboMmXoD9uaVoKG5vZ17uMIfGrUKWrUKEcG+TpySiKgzm0PTiRMn0L9//56chYg8VIvZgkPnWksnd50woqaxvXRyUH9fa1AaGsYz2ETkumwOTQxMRGQPi0XAjz9fQaa+CDuPG1FR1146qQz0waw4JTRqFUaGs3SSiNyD29ywl4hcnyAIOF5UbS2dLK5usG4L7itF0kgFtOpwjL6jH8QsnSQiN8PQRES37ExJDTLbSicvVtRb1/1lXpg2QgGNWoXxkf3hxdJJInJjNoWmlJQU/O1vf0Pfvn1x8OBBjBs3rlOpJRH1Lpcq661BKd9YY1338RZjcnQYtGoVJt4ZytJJIvIYNjWCe3t74/LlywgLC4NEIkFxcTHkcvntmM/p2AhO1K7E1IAv20oncy61l056S0S4d2iotXSyr4x/VBGRczmtEXzQoEFYu3Ytpk6dCkEQkJ2djX79+nW577333uuQwYjINVypa8LOE0bo9AZ8f6EC1/7MEouAsZH9oYlTYfoIBYJ8WTpJRJ7NpjNNn3/+OZ5++mmUlpZCJBKhu0NEIhHMZrPDh3Qmnmmi3qi2sQV7ThmRmWPAN2fK0WJp/3f+roGtpZNJcUrI/Vk6SUSuqSd+f9t1w97a2loEBASgoKCg27fnAgMDHTKYq2Boot6iodmMAwWlbaWTpWhsaS+djFEGQKNWYVackqWTROQWnH7DXj8/P+zfvx+DBw/mheBEHqDZbMG3Z8uh0xuw+2QJaq8rnRwS0hcatQoatRJRcpZOEhHZnXwmTpwIs9mMTz75BHl5eQCAmJgY/PrXv4ZEwk/JELk6i0XAkYuVyNQbsPN4Ma7UN1u3qQJ92oKSCrGqAJZOEhFdx+7QdPbsWcycOROXL1/GsGHDAADp6emIiIjAl19+icjISIcPSUS3RhAE6C9fK500oMTUaN0W4idF0kgltGoV7hrI0kkiou7YdU0TACQlJUEQBGzevBnBwcEAgIqKCvzud7+DWCzGl19+2SODOguvaSJ3VmCsQaa+CDp9MQorryud9PHCjLbSybFDWDpJRJ7H6dc0AcDXX3+N77//3hqYgNb70q1cuRLjx493yFBEdPN+rqiDTm+ATl+MgpL20sk+3hJMiWktnbz3zhDIvPh2OhGRPewOTTKZDDU1NZ3Wa2trIZWyp4XIGYzVDdie29rOrb9cbV33logw8U55W+mkHL5SfoCDiOhm2f1f0FmzZmHhwoV47733kJCQAAA4fPgwnn76aWi1WocPSERdq6xrwo7jxdDpDThysbJD6eT4qBBo1CpMi1Eg0NfbuYMSEXkIu0PT2rVr8fjjj2Ps2LHw9m79j3FLSwu0Wi3WrFnj8AGJqF1NQzN2nyxBpt6Ab8+Ww3xd6eToO/pBG6/CjBFKhPrLnDglEZFnsjs0BQUF4YsvvsDZs2etlQPR0dGIiopy+HBE1Fo6uS+/FJk5BuwrKEXTdaWTI8IDoIlTYZZahfCgPk6ckojI8930BQ5RUVEMSkQ9pKnFgm/PlkGnL8buk0bUNbXfnigytC+06nDMUisRGernxCmJiHoXXhVK5CLMFgGHL1RApzdg5wkjqq4rnQwP6gONWgWtWoVopT9LJ4mInIChiciJBEHAT5eqoNMb8GVuMUprri+dlGFWnBIatQp3DQxiUCIicjKGJqLbTBAE5BtrkKlvrQi4fOWqdVtgH29r6eTdQ/pDwnZuIiKXwdBEdJtcKG8tnczUG3C2tNa67iuV4IG20sl7hoZC6sV2biIiV2R3aMrKyoKfnx8mTJgAANiwYQM2btyImJgYbNiwAf369XP4kETuylB1FV/mFiNTb8DxovbSSalEjPuHh0KjVmHy8DD0kbKdm4jI1dl977mRI0di1apVSEpKwvHjxzFmzBikpKRg//79GD58ON5///2emtUpeO85sldFbSN2HG8NSj9cvGJdl4hFGB8VAq1ahamxYQjwYekkEVFPcYl7z124cAExMTEAgE8++QSzZs3Cq6++imPHjiEpKckhQxG5m+qrzdh90ohMvQHfnavoUDqZMCgYmngVkkYo0N+PpZNERO7K7tAklUpRX996t/SvvvoKycnJAIDg4GCYTCbHTkfkwq42mfFVXgl0egMOFJShydxeOhk3ILCtdFIJZSBLJ4mIPIHdoWnChAlISUnB+PHjceTIEWzbtg0AcPr0aQwYMMDhAxK5kqYWCw6eLoMu14A9p0pQf13p5FC5H7Tq1nbuwSF9nTglERH1BLtD0/r16/GHP/wBH3/8Md5++22Eh4cDAHbu3Inp06c7fEAiZzNbBHx/vgKZOQbsPFEMU0OLdVtEcB9o4lTQxqswLIylk0REnszuC8F7G14I3jsJgoBjhVeg0xdje24xymvbSyfl/jLMilNBo1YiPoKlk0RErshpF4Lbc60SgwW5K0EQcKrYhEy9Adv1xSiqai+dDPL1xowRSmjVKiQMDmbpJBFRL2RTaAoKsv2vabPZ/Ms7EbmQ82W11nbuc2V11vW+UgmmxiqgVaswPiqEpZNERL2cTaFp//791u8vXryI1NRUzJs3D2PHjgUAZGdn48MPP0R6enrPTHmdDRs24LXXXoPRaIRarca6deuQkJDQ7f4fffQRXnrpJVy8eBFDhw61dkxR71ZUdRXb29q5Txraz6RKvcSYPFwOjVqFScPl8PFm6SQREbWy+5qmyZMn46mnnsKcOXM6rG/ZsgXvvPMODhw44Mj5Oti2bRuSk5ORkZGBxMRErF69Gh999BEKCgogl8s77f/dd9/h3nvvRXp6OmbNmoUtW7Zg1apVOHbsGEaMGGHTa/KaJs/zw8VKzHnne7S0dSl5iUWYMLS1dPKBmDD4s3SSiMjt9cTvb7tDk6+vL/R6PYYOHdph/fTp04iPj7d2OPWExMREjBkzBuvXrwcAWCwWREREYPHixUhNTe20/+zZs1FXV4ft27db1+6++27Ex8cjIyPDptdkaPI8/y/7Il764iTCg/rgD/dHYsYIJYL7Sp09FhEROVBP/P62+yKNiIgIbNy4sdP6u/aYkVcAACAASURBVO++i4iICIcM1ZWmpiYcPXoUU6ZMsa6JxWJMmTIF2dnZXR6TnZ3dYX8AmDZtWrf7A0BjYyNMJlOHL/JM6ohAzE28g4GJiIhsYndP01tvvYWHH34YO3fuRGJiIgDgyJEjOHPmDD755BOHD3hNeXk5zGYzwsLCOqyHhYUhPz+/y2OMRmOX+xuNxm5fJz09HStWrLj1gYmIiMij2H2mKSkpCadPn4ZGo0FlZSUqKyuh0Whw+vRpj7jAOi0tDdXV1davS5cuOXskIiIicgF2n2kCWt+ie/XVVx09yw2FhIRAIpGgpKSkw3pJSQkUCkWXxygUCrv2BwCZTAaZjDdVJSIioo5sCk25ubk2P2FcXNxND3MjUqkUo0aNwt69e/Hggw8CaL0QfO/evVi0aFGXx4wdOxZ79+7FCy+8YF3bs2ePtSqBiIiIyFY2hab4+HiIRCIIgtCh5PLaB++uX+vJcsuUlBQ8/vjjGD16NBISErB69WrU1dVh/vz5AIDk5GSEh4db+6Kef/55TJw4EW+88QZmzpyJrVu34scff8Q777zTYzMSERGRZ7IpNF24cMH6/U8//YQ//vGPePHFFzuUW77xxhv4xz/+0TNTtpk9ezbKysrw8ssvw2g0Ij4+HllZWdaLvQsLCyEWt1+mNW7cOGzZsgV/+ctf8N///d8YOnQoPv/8c5s7moiIiIiusbunKSEhAcuXL+900feOHTvw0ksv4ejRow4d0NnY0+R5rvU0JY1U4P/OHeXscYiIqAe4RE/T8ePHMXjw4E7rgwcPxqlTpxwyFBEREZGrsTs0RUdHIz09HU1NTda1pqYmpKenIzo62qHDEREREbkKuysHMjIyoNFoMGDAAOsn5XJzcyESiaDT6Rw+IBEREZErsDs0JSQk4Pz589i8ebO1iXv27Nl49NFH0bdvX4cPSEREROQKbqrcsm/fvli4cKGjZyEiIiJyWTcVms6dO4fVq1cjLy8PABAbG4vnnnsOkZGRDh2OiIiIyFXYfSH4rl27EBMTgyNHjiAuLg5xcXH4/vvvERsbiz179vTEjEREREROZ/eZptTUVCxZsgQrV67stL5s2TI88MADDhuOiIiIyFXYfaYpLy8PTz75ZKf1J554gj1NRERE5LHsDk2hoaHIycnptJ6TkwO5XO6QoYiIiIhcjd1vzy1YsAALFy7E+fPnMW7cOADAoUOHsGrVKqSkpDh8QCIiIiJXYHdoeumll+Dv74833ngDaWlpAACVSoXly5fjueeec/iARERERK7A7tAkEomwZMkSLFmyBDU1NQAAf39/hw9GRERE5Ersvqbpehs2bIDZbHbULEREREQu65ZC06uvvorKykpHzUJERETksm4pNAmC4Kg5iIiIiFzaLYUmIiIiot7ipu49d82pU6egUqkcNQsRERGRy7ql0BQREeGoOYiIiIhcmt2hqV+/fhCJRJ3WRSIRfHx8EBUVhXnz5mH+/PkOGZCIiIjIFdgdml5++WX8/e9/x4wZM5CQkAAAOHLkCLKysvDss8/iwoULeOaZZ9DS0oIFCxY4fGAiIiIiZ7A7NH377bf4n//5Hzz99NMd1v/5z39i9+7d+OSTTxAXF4e1a9cyNBEREZHHsPvTc7t27cKUKVM6rU+ePBm7du0CACQlJeH8+fO3Ph0RERGRi7A7NAUHB0On03Va1+l0CA4OBgDU1dXx1ipERETkUW7qhr3PPPMM9u/fb72m6YcffsCOHTuQkZEBANizZw8mTpzo2EmJiIiInMju0LRgwQLExMRg/fr1+PTTTwEAw4YNw9dff41x48YBAJYuXerYKYmIiIic7KZ6msaPH4/x48c7ehYiIiIil3VToclsNuPzzz9HXl4eACA2NhZarRYSicShwxERERG5CrtD09mzZ5GUlISioiIMGzYMAJCeno6IiAh8+eWXiIyMdPiQRERERM5m96fnnnvuOURGRuLSpUs4duwYjh07hsLCQgwePBjPPfdcT8xIRERE5HR2n2n6+uuv8f3331vrBQCgf//+WLlyJa9zIiIiIo9l95kmmUyGmpqaTuu1tbWQSqUOGYqIiIjI1dgdmmbNmoWFCxfi8OHDEAQBgiDg+++/x9NPPw2tVtsTMxI5VLNZcPYIRETkhux+e27t2rV4/PHHMXbsWHh7ewMAWlpaoNVqsWbNGocPSOQI1fXNyDpZjEy9AdnnKgAAXmK7/2YgIqJezO7QFBQUhC+++AJnzpxBfn4+ACA6OhpRUVEOH47oVtQ1tuCrvBLo9AZ8fbqswxkmdUQQnpgw2InTERGRu7mpniYAGDp0KIYOHerIWW6osrISixcvhk6ng1gsxsMPP4w1a9bAz8+v2/1feeUV7N69G4WFhQgNDcWDDz6Iv/3tbwgMDLxtc9Pt1dhixoGCMmTqDdibV4KGZot123CFPzRqFTRxKgzs7+vEKYmIyB3ZFJpSUlJsfsI333zzpoe5kblz56K4uBh79uxBc3Mz5s+fj4ULF2LLli1d7m8wGGAwGPD6668jJiYGP//8M55++mkYDAZ8/PHHPTIjOd+8f/2A7PMV1seD+vtCq1ZBo1ZhaBhvIk1ERDdPJAjCL14Ve//999v2ZCIR9u3bd8tD/ae8vDzExMTghx9+wOjRowEAWVlZSEpKwuXLl6FSqWx6no8++gi/+93vUFdXBy8v206ymUwmBAYGorq6GgEBATf9M9DtEbd8F0wNLXg0cSDmjBmIEeEBEIlEzh6LiIhus574/W1Tcti/f79DXuxmZWdnIygoyBqYAGDKlCkQi8U4fPgwfvOb39j0PNf+wdkamMh9PTlhMCJDu37rloiI6Ga4RXowGo2Qy+Ud1ry8vBAcHAyj0WjTc5SXl+Nvf/sbFi5ceMP9Ghsb0djYaH1sMpnsH5iIiIg8jlM/c52amgqRSHTDr2uf0LsVJpMJM2fORExMDJYvX37DfdPT0xEYGGj9ioiIuOXXJyIiIvfn1DNNS5cuxbx58264z5AhQ6BQKFBaWtphvaWlBZWVlVAoFDc8vqamBtOnT4e/vz8+++wza7dUd9LS0jpc+G4ymRiciIiIyLmhKTQ0FKGhob+439ixY1FVVYWjR49i1KhRAIB9+/bBYrEgMTGx2+NMJhOmTZsGmUyGzMxM+Pj4/OJryWQyyGQy238IIiIi6hXcohI5Ojoa06dPx4IFC3DkyBEcOnQIixYtwiOPPGL95FxRURGGDx+OI0eOAGgNTFOnTkVdXR3ee+89mEwmGI1GGI1GmM1mZ/44RERE5IZu6kzTuXPnsHr1auTl5QEAYmJi8PzzzyMyMtKhw11v8+bNWLRoESZPnmwtt1y7dq11e3NzMwoKClBfXw8AOHbsGA4fPgwAndrKL1y4gEGDBvXYrEREROR57A5Nu3btglarRXx8PMaPHw8AOHToEGJjY6HT6fDAAw84fEgACA4O7rbIEgAGDRqE6yun7rvvPthQQUVERERkE7tDU2pqKpYsWYKVK1d2Wl+2bFmPhSYiIiIiZ7L7mqa8vDw8+eSTndafeOIJnDp1yiFDEREREbkau0NTaGgocnJyOq3n5OR0KqAkIiIi8hR2vz23YMECLFy4EOfPn8e4ceMAtF7TtGrVKrtu7EtERETkTuwOTS+99BL8/f3xxhtvIC0tDQCgUqmwfPlyPPfccw4fkIiIiMgV2B2aRCIRlixZgiVLlqCmpgYA4O/v7/DBiIiIiFyJ3dc0TZo0CVVVVQBaw9K1wGQymTBp0iTHTkdERETkIuw+03TgwAE0NTV1Wm9oaMA333zjkKGI7HG1yYy9+SXIzDGgprHF2eMQEZGHsjk05ebmWr8/deoUjEaj9bHZbEZWVhbCw8MdOx1RN5paLDh4ugy6XAP2nCpBfVP7rXHuGhiEgcG+TpyOiIg8kc2hKT4+HiKRCCKRqMu34fr06YN169Y5dDii65ktAr4/XwGd3oCdJ4yovtps3RYR3AeaOBU0ahWGK/whEomcOCkREXkim0PThQsXIAgChgwZgiNHjiA0NNS6TSqVQi6XQyKR9MiQ1HsJgoBjhVXQ6Q3YnluM8tpG6za5vwwz45TQqlWIjwhiUCIioh5lc2i64447AAAWi6XHhiECWoPSqWITdPpi6PQGFFVdtW4L8vXGjBFKaNRKJA7uD4mYQYmIiG4Puy8EJ+op58tqkak3QKc34FxZnXW9r1SCqbEKaNRKTIgKhdTL7g99EhER3TKGJnIJb+wuwLp9Z62PpV5iTBomhzZehfuHydFHyrd+iYjIuRiayCV8e7YcADD6jn6YkzAQU2PD4O/j7eSpiIiI2jE0kUv5/cRIPBAT5uwxiIiIOrnp0NTU1ITS0tJOF4YPHDjwlociIiIicjV2h6YzZ87giSeewHfffddhXRAEiEQimM3mbo4kIiIicl92h6Z58+bBy8sL27dvh1KpZDcOERER9Qp2h6acnBwcPXoUw4cP74l5iIiIiFyS3YU3MTExKC8v74lZiIiIiFyW3aFp1apV+NOf/oQDBw6goqICJpOpwxcRERGRJ7L77bkpU6YAACZPntxhnReCExERkSezOzTt37+/J+YgIiIicml2h6aJEyf2xBxERERELu2myi2rqqrw3nvvIS8vDwAQGxuLJ554AoGBgQ4djoiIiMhV2H0h+I8//ojIyEi89dZbqKysRGVlJd58801ERkbi2LFjPTEjERERkdPZfaZpyZIl0Gq12LhxI7y8Wg9vaWnBU089hRdeeAEHDx50+JBEREREzmZ3aPrxxx87BCYA8PLywp/+9CeMHj3aocMRERERuQq7354LCAhAYWFhp/VLly7B39/fIUMRERERuRq7Q9Ps2bPx5JNPYtu2bbh06RIuXbqErVu34qmnnsKcOXN6YkYiIiIip7P77bnXX38dIpEIycnJaGlpAQB4e3vjmWeewcqVKx0+IHk+QRBgsQjOHoOIiOiG7A5NUqkUa9asQXp6Os6dOwcAiIyMhK+vr8OHI892sbwOOr0BmXoDzpTWAgC8xCInT0VERNS1m+ppAgBfX1+MHDnSkbNQL1BcfRXb9cXI1BtwvKjaui6ViDE1NgwJg4OdOB0REVH3bApNDz30ED744AMEBATgoYceuuG+n376qUMGI89RUduIHSeM0OUYcORipXVdIhZhXGR/aNUqTBuhQICPtxOnJCIiujGbQlNgYCBEota3TQICAqzfE92Ioeoq/vuz4/jmTDnM112zlDAoGBq1EjNGKhHiJ3PihERERLYTCYLgFlfgVlZWYvHixdDpdBCLxXj44YexZs0a+Pn5/eKxgiAgKSkJWVlZ+Oyzz/Dggw/a/LomkwmBgYGorq5GQEDArfwIvc7bB85hVVY+AGBkeCC0ahVmximhCurj5MmIiMjT9cTvb7srByZNmoSqqqouh5s0aZJDhurK3LlzcfLkSezZswfbt2/HwYMHsXDhQpuOXb16Nc+OOUGL2QIA+D+jBkC3eAIW3DuEgYmIiNyW3ReCHzhwAE1NTZ3WGxoa8M033zhkqP+Ul5eHrKws/PDDD9bW8XXr1iEpKQmvv/46VCpVt8fm5OTgjTfewI8//gilUtkj89GNeUnszuZEREQux+bQlJuba/3+1KlTMBqN1sdmsxlZWVkIDw937HRtsrOzERQU1OE2LVOmTIFYLMbhw4fxm9/8psvj6uvr8eijj2LDhg1QKBQ9MhsRERH1DjaHpvj4eIhEIohEoi7fhuvTpw/WrVvn0OGuMRqNkMvlHda8vLwQHBzcIbz9pyVLlmDcuHH49a9/bfNrNTY2orGx0frYZDLZPzARERF5HJtD04ULFyAIAoYMGYIjR44gNDTUuk0qlUIul0Mikdj14qmpqVi1atUN98nLy7PrOa/JzMzEvn378NNPP9l1XHp6OlasWHFTr0lERESey+bQdMcddwAALBaLw1586dKlmDdv3g33GTJkCBQKBUpLSzust7S0oLKystu33fbt24dz584hKCiow/rDDz+Me+65BwcOHOjyuLS0NKSkpFgfm0wmRERE/PIPQ0RERB7N7gvBN23adMPtycnJNj9XaGhohzNW3Rk7diyqqqpw9OhRjBo1CkBrKLJYLEhMTOzymNTUVDz11FMd1kaOHIm33noLGo2m29eSyWSQydgdRERERB3ZHZqef/75Do+bm5tRX18PqVQKX19fu0KTraKjozF9+nQsWLAAGRkZaG5uxqJFi/DII49YPzlXVFSEyZMnY9OmTUhISIBCoejyLNTAgQMxePBgh89IREREns3uz4JfuXKlw1dtbS0KCgowYcIE/O///m9PzAgA2Lx5M4YPH47JkycjKSkJEyZMwDvvvGPd3tzcjIKCAtTX1/fYDERERNR73fQNe683dOhQrFy5Er/73e+Qn5/viKfsJDg4GFu2bOl2+6BBg/BL5eZuUn5ORERELshhrYNeXl4wGAyOejoiIiIil2L3mabMzMwOjwVBQHFxMdavX4/x48c7bDAiIiIiV2J3aPrPm92KRCKEhoZi0qRJeOONNxw2GBEREZErsTs0ObKniYiIiMhd3NI1TYIg8OJqIiIi6hVuKjS99957GDFiBHx8fODj44MRI0bg3XffdfRsRERERC7D7rfnXn75Zbz55ptYvHgxxo4dCwDIzs7GkiVLUFhYiL/+9a8OH5KIiIjI2ewOTW+//TY2btyIOXPmWNe0Wi3i4uKwePFihiYiIiLySHa/Pdfc3IzRo0d3Wh81ahRaWlocMhQRERGRq7E7ND322GN4++23O62/8847mDt3rkOGIiIiInI1Nr09l5KSYv1eJBLh3Xffxe7du3H33XcDAA4fPozCwsIeuVkvERERkSuwKTT99NNPHR6PGjUKAHDu3DkAQEhICEJCQnDy5EkHj0dERETkGmwKTfv37+/pOYiIiIhcmsNu2EtERETkyWw60/TQQw/hgw8+QEBAAB566KEb7vvpp586ZDAiIiIiV2JTaAoMDIRIJLJ+T0RERNTb2BSa3n//fQCt95pbsWIFQkND0adPnx4djIiIiMiV2HVNkyAIiIqKwuXLl3tqHiIiIiKXZFdoEovFGDp0KCoqKnpqHiIiIiKXZPen51auXIkXX3wRJ06c6Il5iIiIiFyS3TfsTU5ORn19PdRqNaRSaadrmyorKx02HBEREZGrsDs0vfXWW9ZP0hERERH1FnaHpnnz5vXAGERERESuze5rmiQSCUpLSzutV1RUQCKROGQoIiIiIldjd2gSBKHL9cbGRkil0lseiIiIiMgV2fz23Nq1awEAIpEI7777Lvz8/KzbzGYzDh48iOHDhzt+QiIiIiIXYHNoeuuttwC0nmnKyMjo8FacVCrFoEGDkJGR4fgJiYiIiFyAzaHpwoULAID7778fn376Kfr169djQxERERG5Grs/Pbd///6emIOIiIjIpdkdmsxmMz744APs3bsXpaWlsFgsHbbv27fPYcMRERERuQq7Q9Pzzz+PDz74ADNnzsSIESNYdElERES9gt2haevWrfj3v/+NpKSknpiHiIiIyCXZ3dMklUoRFRXVE7MQERERuSy7Q9PSpUuxZs2abksuiYiIiDyR3W/Pffvtt9i/fz927tyJ2NhYeHt7d9j+6aefOmw4IiIiIldhd2gKCgrCb37zm56YhYiIiMhl2R2a3n///Z6Y4xdVVlZi8eLF0Ol0EIvFePjhh7FmzZoOt3PpSnZ2Nv785z/j8OHDkEgkiI+Px65du9CnT5/bNDkRERF5ArtD0zVlZWUoKCgAAAwbNgyhoaEOG6orc+fORXFxMfbs2YPm5mbMnz8fCxcuxJYtW7o9Jjs7G9OnT0daWhrWrVsHLy8v6PV6iMV2X8pFREREvZzdoamurg6LFy/Gpk2brMWWEokEycnJWLduHXx9fR0+ZF5eHrKysvDDDz9g9OjRAIB169YhKSkJr7/+OlQqVZfHLVmyBM899xxSU1Ota8OGDXP4fEREROT57D7lkpKSgq+//ho6nQ5VVVWoqqrCF198ga+//hpLly7tiRmRnZ2NoKAga2ACgClTpkAsFuPw4cNdHlNaWorDhw9DLpdj3LhxCAsLw8SJE/Htt9/2yIxERETk2ewOTZ988gnee+89zJgxAwEBAQgICEBSUhI2btyIjz/+uCdmhNFohFwu77Dm5eWF4OBgGI3GLo85f/48AGD58uVYsGABsrKycNddd2Hy5Mk4c+ZMt6/V2NgIk8nU4YuIiIjI7tBUX1+PsLCwTutyuRz19fV2PVdqaipEItENv/Lz8+0dEQCsbx3+/ve/x/z58/GrX/0Kb731FoYNG4Z//etf3R6Xnp6OwMBA61dERMRNvT4RERF5FruvaRo7dixeeeUVbNq0CT4+PgCAq1evYsWKFRg7dqxdz7V06VLMmzfvhvsMGTIECoUCpaWlHdZbWlpQWVkJhULR5XFKpRIAEBMT02E9OjoahYWF3b5eWloaUlJSrI9NJhODExEREdkfmtasWYNp06ZhwIABUKvVAAC9Xg8fHx/s2rXLrucKDQ216VN3Y8eORVVVFY4ePYpRo0YBAPbt2weLxYLExMQujxk0aBBUKpX1E37XnD59GjNmzOj2tWQyGWQymR0/BREREfUGdoemESNG4MyZM9i8ebP1rbM5c+Zg7ty5PdZ9FB0djenTp2PBggXIyMhAc3MzFi1ahEceecT6ybmioiJMnjwZmzZtQkJCAkQiEV588UW88sorUKvViI+Px4cffoj8/Pweu/aKiIiIPNdN9TT5+vpiwYIFjp7lhjZv3oxFixZh8uTJ1nLLtWvXWrc3NzejoKCgw3VVL7zwAhoaGrBkyRJUVlZCrVZjz549iIyMvK2zExERkfuzOzSlp6cjLCwMTzzxRIf1f/3rXygrK8OyZcscNtz1goODb1hkOWjQoC5vIpyamtqhp4mIiIjoZtj96bl//vOfGD58eKf12NhYZGRkOGQoIiIiIldjd2gyGo3WT6ZdLzQ0FMXFxQ4ZioiIiMjV2B2aIiIicOjQoU7rhw4d6vZ2JkRERETuzu5rmhYsWIAXXngBzc3NmDRpEgBg7969+NOf/tRjt1EhIiIicja7Q9OLL76IiooK/OEPf0BTUxMAwMfHB8uWLUNaWprDByQiIiJyBXaHJpFIhFWrVuGll15CXl4e+vTpg6FDh7IQkoiIiDzaTfU0AYCfnx/GjBnjyFmIiIiIXJbdF4ITERER9UYMTUREREQ2YGgiIiIisgFDExEREZENGJqIiIiIbMDQRERERGQDhiYiIiIiGzA0EREREdmAoYmIiIjIBgxNRERERDZgaCIiIiKyAUMTERERkQ0YmoiIiIhswNBEREREZAOGJiIiIiIbMDQRERER2YChiYiIiMgGDE1ERERENmBoIiIiIrIBQxMRERGRDRiaiIiIiGzA0ERERERkA4YmIiIiIhswNBERERHZgKGJiIiIyAYMTUREREQ2YGgiIiIisgFDExEREZENGJqIiIiIbOA2oamyshJz585FQEAAgoKC8OSTT6K2tvaGxxiNRjz22GNQKBTo27cv7rrrLnzyySe3aWIiIiLyJG4TmubOnYuTJ09iz5492L59Ow4ePIiFCxfe8Jjk5GQUFBQgMzMTx48fx0MPPYTf/va3+Omnn27T1EREROQp3CI05eXlISsrC++++y4SExMxYcIErFu3Dlu3boXBYOj2uO+++w6LFy9GQkIChgwZgr/85S8ICgrC0aNHb+P0RERE5AncIjRlZ2cjKCgIo0ePtq5NmTIFYrEYhw8f7va4cePGYdu2baisrITFYsHWrVvR0NCA++677zZMTURERJ7Ey9kD2MJoNEIul3dY8/LyQnBwMIxGY7fH/fvf/8bs2bPRv39/eHl5wdfXF5999hmioqK6PaaxsRGNjY3WxyaT6dZ/ACIiInJ7Tj3TlJqaCpFIdMOv/Pz8m37+l156CVVVVfjqq6/w448/IiUlBb/97W9x/Pjxbo9JT09HYGCg9SsiIuKmX5+IiIg8h1PPNC1duhTz5s274T5DhgyBQqFAaWlph/WWlhZUVlZCoVB0edy5c+ewfv16nDhxArGxsQAAtVqNb775Bhs2bEBGRkaXx6WlpSElJcX62GQyMTgRERGRc0NTaGgoQkNDf3G/sWPHoqqqCkePHsWoUaMAAPv27YPFYkFiYmKXx9TX1wMAxOKOJ9MkEgksFku3ryWTySCTyWz9EagLgiDgWGEVvr9Q4exRiIiIHMYtrmmKjo7G9OnTsWDBAmRkZKC5uRmLFi3CI488ApVKBQAoKirC5MmTsWnTJiQkJGD48OGIiorC73//e7z++uvo378/Pv/8c2tlATmWIAjIK65Bpt4And6Aoqqr1m0Dg32dOBkREZFjuEVoAoDNmzdj0aJFmDx5MsRiMR5++GGsXbvWur25uRkFBQXWM0ze3t7YsWMHUlNTodFoUFtbi6ioKHz44YdISkpy1o/hcc6X1UKnL0amvgjnyuqs632lEkyNVUCjVuL+YfIbPAMREZF7EAmCIDh7CFdmMpkQGBiI6upqBAQEOHscl1BUdRXb9Qbocg04UdT+6UKplxiThsmhjVfh/mFy9JFKnDglERH1Zj3x+9ttzjSRc5XVNGLniWJk5hjw489XrOsSsQj3DA2BJk6FqbFh8PfxduKUREREPYehibpVfbUZu04Yocs14NDZcljazkmKREDCoGBo41WYMUKJ4L5S5w5KRER0GzA0UQf1TS34Kq8UmTkGHDxdhiZz+ycN1RFB0MQpMStOBUWgjxOnJCIiuv0YmgiNLWYcPF2OTL0BX50qwdVms3XbsDB/aNRKaNQq3NG/rxOnJCIici6Gpl6qxWxB9vkK6PQGZJ0wwtTQYt02MNgXWrUKGrUKwxT+TpySiIjIdTA09SIWi4BjhVeQqTdgx/FilNc2WbeFBcgwK04FrVqFuAGBEIlETpyU6BLNwwAAFYdJREFUiIjI9TA0eThBEHDSYIJOb8D23OIOpZP9fL2RNLL1rbeEQcEQixmUiIiIusPQ5KHOltZC19bOfb68vXTST+aFqbFh0KpVGB8VAm+JU+/ZTERE5DYYmjzI5Sv10OmLodMbcKq4vXRS5iXG5Gg5tGoV7hsmh483SyeJiIjsxdDk5kprGrAjtxiZegOOFVZZ173EItx7Zyg0aiUeiFHAT8b/qYmIiG4Ff5O6oer6Zuw8UQxdrgHZ5yo6lE7ePbg/tPEqTI9VoB9LJ4mIiByGoclN1DW24Ku8ktbSyTNlaDa33zLwVwP/f3t3HxTVdYYB/Fm+VVxWAdlF+fQDkwIqGgkmURsoYgiKdYxB0kG0OlpMY5JaTWzVmklNm7bTtM3Q1qA2Ew1NEzSJRQ1VIdEQFAQEtUQYFBNZUAgCCirs2z8cbroCconAAvv8ZnaGvefsvefZs7DvcO+e1SEm2BNPBhswSstFJ4mIiHoDi6Z+rPl2K7K+vIKPCi/j8LkqNN/+dnXuifrhiJl0Z4kAr5FDLThKIiIi68CiqZ9paTXheNmdRScPFRvRcPPbRSd9Xb9ddHK8BxedJCIi6kssmvoBk0mQe/EbfFT4NdKLjKi9/u2ikwYXJzwZbMC8SaMROFrLRSeJiIgshEWThYgIir6+piw6WXmtWWlzHeagLDo5zWcEF50kIiLqB1g0Wcjqd07h4Bmjcn+4ox3mBOoxb5InZox1hR0XnSQiIupXWDRZyBRvHTK/rEb4A3dW5541wZ2LThIREfVjLJosZEmoN5552AfDuOgkERHRgMB3bAsZ7mRv6SEQERFRN/DCGSIiIiIVWDQRERERqcCiiYiIiEgFFk1EREREKrBoIiIiIlKBRRMRERGRCiyaiIiIiFRg0URERESkAosmIiIiIhVYNBERERGpwKKJiIiISAUWTUREREQqsGgiIiIiUsHO0gPo70QEAFBfX2/hkRAREZFabe/bbe/jPYFFUxcaGhoAAF5eXhYeCREREXVXQ0MDXFxcemRfGunJEmwQMplMuHz5MoYPHw6NRvOd91NfXw8vLy9cunQJWq22B0fY/1hTVsC68lpTVsC68lpTVsC68lpTVuDbvBUVFdBoNPD09ISNTc9cjcT/NHXBxsYGY8aM6bH9abVaq3jRAtaVFbCuvNaUFbCuvNaUFbCuvNaUFQBcXFx6PC8vBCciIiJSgUUTERERkQq2W7Zs2WLpQVgLW1tbzJ49G3Z2g/+sqDVlBawrrzVlBawrrzVlBawrrzVlBXovLy8EJyIiIlKBp+eIiIiIVGDRRERERKQCiyYiIiIiFVg0EREREanAoqkPvPnmm/D19YWTkxNCQ0Nx4sQJSw/pvm3ZsgUajcbsNnHiRKW9ubkZSUlJcHV1hbOzMxYuXIiqqioLjrh7Pv30U8TExMDT0xMajQb79u0zaxcRbNq0CQaDAUOGDEFERATOnz9v1qe2thbx8fHQarXQ6XRYvnw5Ghsb+zKGal3lXbp0abv5joqKMuszUPJu27YNDz30EIYPH45Ro0YhNjYWJSUlZn3UvH4rKioQHR2NoUOHYtSoUVi3bh1aWlr6MkqX1GSdPXt2u7ldtWqVWZ+BkBUAkpOTERwcrCziGBYWhgMHDijtg2Vega6zDqZ5vdtrr70GjUaDtWvXKtv6bG6FelVqaqo4ODjIjh075MyZM7JixQrR6XRSVVVl6aHdl82bN8v3vvc9qaysVG5XrlxR2letWiVeXl5y+PBhyc3NlYcfflhmzJhhwRF3T3p6umzcuFHS0tIEgOzdu9es/bXXXhMXFxfZt2+fFBYWyrx588TPz0+ampqUPlFRUTJp0iT54osv5LPPPpNx48ZJXFxcX0dRpau8CQkJEhUVZTbftbW1Zn0GSt45c+bIzp07pbi4WAoKCuSJJ54Qb29vaWxsVPp09fptaWmRwMBAiYiIkPz8fElPTxc3Nzd56aWXLBGpU2qyzpo1S1asWGE2t9euXVPaB0pWEZGPPvpI/v3vf8uXX34pJSUl8vLLL4u9vb0UFxeLyOCZV5Gusw6mef1/J06cEF9fXwkODpbnnntO2d5Xc8uiqZdNnz5dkpKSlPutra3i6ekp27Zts+Co7t/mzZtl0qRJHbbV1dWJvb29/Otf/1K2nTt3TgBIdnZ2Xw2xx9xdRJhMJtHr9fL6668r2+rq6sTR0VHeffddERE5e/asAJCTJ08qfQ4cOCAajUa+/vrrvhv8d9BZ0TR//vxOHzOQ81ZXVwsAycrKEhF1r9/09HSxsbERo9Go9ElOThatVis3b97s2wDdcHdWkTtvrv//5nO3gZq1zYgRI+Stt94a1PPapi2ryOCc14aGBhk/frxkZGSY5evLueXpuV5069Yt5OXlISIiQtlmY2ODiIgIZGdnW3BkPeP8+fPw9PSEv78/4uPjUVFRAQDIy8vD7du3zXJPnDgR3t7egyJ3eXk5jEajWT4XFxeEhoYq+bKzs6HT6TBt2jSlT0REBGxsbJCTk9PnY+4JmZmZGDVqFAICArB69WrU1NQobQM577Vr1wAAI0eOBKDu9ZudnY2goCB4eHgofebMmYP6+nqcOXOmD0ffPXdnbbN79264ubkhMDAQL730Em7cuKG0DdSsra2tSE1NxfXr1xEWFjao5/XurG0G27wmJSUhOjrabA6Bvv2dtY6lQS3k6tWraG1tNZskAPDw8MB///tfC42qZ4SGhmLXrl0ICAhAZWUlfvWrX+Gxxx5DcXExjEYjHBwcoNPpzB7j4eEBo9FooRH3nLYMHc1rW5vRaMSoUaPM2u3s7DBy5MgB+RxERUXhhz/8Ifz8/FBWVoaXX34Zc+fORXZ2NmxtbQdsXpPJhLVr1+KRRx5BYGAgAKh6/RqNxg7nv62tP+ooKwAsWbIEPj4+8PT0xOnTp7F+/XqUlJQgLS0NwMDLWlRUhLCwMDQ3N8PZ2Rl79+7Fgw8+iIKCgkE3r51lBQbfvKampuLUqVM4efJku7a+/J1l0UTfydy5c5Wfg4ODERoaCh8fH7z33nsYMmSIBUdGveHpp59Wfg4KCkJwcDDGjh2LzMxMhIeHW3Bk9ycpKQnFxcU4duyYpYfS6zrLunLlSuXnoKAgGAwGhIeHo6ysDGPHju3rYd63gIAAFBQU4Nq1a3j//feRkJCArKwsSw+rV3SW9cEHHxxU83rp0iU899xzyMjIgJOTk0XHwtNzvcjNzQ22trbtruCvqqqCXq+30Kh6h06nw4QJE1BaWgq9Xo9bt26hrq7OrM9gyd2W4V7zqtfrUV1dbdbe0tKC2traQfEc+Pv7w83NDaWlpQAGZt41a9Zg//79OHr0KMaMGaNsV/P61ev1Hc5/W1t/01nWjoSGhgKA2dwOpKwODg4YN24cpk6dim3btmHSpEl44403BuW8dpa1IwN5XvPy8lBdXY2QkBDY2dnBzs4OWVlZ+NOf/gQ7Ozt4eHj02dyyaOpFDg4OmDp1Kg4fPqxsM5lMOHz4sNl558GgsbERZWVlMBgMmDp1Kuzt7c1yl5SUoKKiYlDk9vPzg16vN8tXX1+PnJwcJV9YWBjq6uqQl5en9Dly5AhMJpPyx2sg++qrr1BTUwODwQBgYOUVEaxZswZ79+7FkSNH4OfnZ9au5vUbFhaGoqIis0IxIyMDWq1WOT3SH3SVtSMFBQUAYDa3AyFrZ0wmE27evDmo5rUzbVk7MpDnNTw8HEVFRSgoKFBu06ZNQ3x8vPJzn81tj1zSTp1KTU0VR0dH2bVrl5w9e1ZWrlwpOp3O7Ar+gejFF1+UzMxMKS8vl+PHj0tERIS4ublJdXW1iNz5+Ke3t7ccOXJEcnNzJSwsTMLCwiw8avUaGhokPz9f8vPzBYD84Q9/kPz8fLl48aKI3FlyQKfTyYcffiinT5+W+fPnd7jkwJQpUyQnJ0eOHTsm48eP75cfwRe5d96Ghgb52c9+JtnZ2VJeXi7/+c9/JCQkRMaPHy/Nzc3KPgZK3tWrV4uLi4tkZmaafRz7xo0bSp+uXr9tH1+OjIyUgoICOXjwoLi7u/e7j2t3lbW0tFS2bt0qubm5Ul5eLh9++KH4+/vLzJkzlX0MlKwiIhs2bJCsrCwpLy+X06dPy4YNG0Sj0cgnn3wiIoNnXkXunXWwzWtH7v50YF/NLYumPvDnP/9ZvL29xcHBQaZPny5ffPGFpYd03xYvXiwGg0EcHBxk9OjRsnjxYiktLVXam5qa5Cc/+YmMGDFChg4dKgsWLJDKykoLjrh7jh49KgDa3RISEkTkzrIDv/zlL8XDw0McHR0lPDxcSkpKzPZRU1MjcXFx4uzsLFqtVhITE6WhocECabp2r7w3btyQyMhIcXd3F3t7e/Hx8ZEVK1a0K/wHSt6OcgKQnTt3Kn3UvH4vXLggc+fOlSFDhoibm5u8+OKLcvv27T5Oc29dZa2oqJCZM2fKyJEjxdHRUcaNGyfr1q0zW89HZGBkFRFZtmyZ+Pj4iIODg7i7u0t4eLhSMIkMnnkVuXfWwTavHbm7aOqrudWIiHT7f2VEREREVobXNBERERGpwKKJiIiISAUWTUREREQqsGgiIiIiUoFFExEREZEKLJqIiIiIVGDRRERERKQCiyYion6mpaUFGo0G+/fvB3Dn+8I0Gg2Ki4stPDIi68aiiYi+k+zsbNja2iI6OtrSQ+lxS5cuhUajwapVq9q1JSUlQaPRYOnSpWb9Y2Nju3UMX19faDQas1vbl+na2dmhsrISP/jBD+4rBxH1LBZNRPSdpKSk4Nlnn8Wnn36Ky5cv9+qxbt261av774iXlxdSU1PR1NSkbGtubsaePXvg7e3dI8fYunUrKisrlVt+fr7Sptfr4ejo2CPHIaKewaKJiLqtsbER//znP7F69WpER0dj165dAO58y/qYMWOQnJxs1j8/Px82Nja4ePEiAKCurg4//vGP4e7uDq1Wi8cffxyFhYVK/y1btmDy5Ml466234OfnBycnJwDAwYMH8eijj0Kn08HV1RVPPvkkysrKzI71+eefY/LkyXBycsK0adOwb98+aDQa5VveAaC4uBhz586Fs7MzPDw88KMf/QhXr141209ISAi8vLyQlpambEtLS4O3tzemTJlyz+dn9uzZ+OlPf4qf//znGDlyJPR6PbZs2dKu3/Dhw6HX65Wbu7s7gPan5zpSVFSEOXPmYNiwYdDr9UhISEBNTc09x0VE94dFExF123vvvYeJEyciICAAzzzzDHbs2AERgY2NDeLi4rBnzx6z/rt378YjjzwCHx8fAMCiRYtQXV2NAwcOIC8vDyEhIQgPD0dtba3ymNLSUnzwwQdIS0tTCp7r16/jhRdeQG5uLg4fPgwbGxssWLAAJpMJAFBfX4+YmBgEBQXh1KlTeOWVV7B+/XqzsdTV1eHxxx/HlClTkJubi4MHD6KqqgpPPfVUu5zLli3Dzp07lfs7duxAYmKiqufoH//4B4YNG4acnBz89re/xdatW5GRkaHqsV2pra3F97//fUyfPh2nTp1Ceno6vvrqK8TFxfXI/omoE/f/XcNEZG1mzJghf/zjH0VE5Pbt2+Lm5iZHjx4VEZH8/HzRaDRy8eJFERFpbW2V0aNHS3JysoiIfPbZZ6LVaqW5udlsn2PHjpW//e1vIiKyefNmsbe3l+rq6nuO48qVKwJAioqKREQkOTlZXF1dpampSemzfft2ASD5+fkiIvLKK69IZGSk2X4uXbokAKSkpERERBISEmT+/PlSXV0tjo6OcuHCBblw4YI4OTnJlStXZP78+ZKQkKA8vq1/m1mzZsmjjz5qdoyHHnpI1q9fr9xv+4b6YcOGKbc33nhDeU4ByMcffywiIufPnzfLuXnzZnniiSfM9l9eXi4ApKys7J7PGRF9d3aWLNiIaOApKSnBiRMnsHfvXgB3LlpevHgxUlJSMHv2bEyePBkPPPAA9uzZgw0bNiArKwvV1dVYtGgRAKCwsBCNjY1wdXU1229TU5PZqTYfHx/ldFWb8+fPY9OmTcjJycHVq1eV/zBVVFQgMDAQJSUlCA4OVk7nAcD06dPN9lFYWIijR4/C2dm5XbaysjJMmDBBue/u7q6cfhQRREdHw83NTdXzFBwcbHbfYDCgurrabNu6devMLihXu+/CwkJkZGR0msHf31/Vfoioe1g0EVG3pKSkoKWlBZ6enso2EYGjoyP+8pe/wMXFBfHx8UrRtGfPHkRFRSlFUmNjIwwGAzIzM9vtW6fTKT8PGzasXXtMTAx8fHywfft2eHp6wmQyITAwsFsXijc2NiImJga/+c1v2rUZDIZ225YtW4Y1a9YAAN58803Vx7G3tze7r9FolCKvjZubG8aNG6d6n20aGxsRGxuLX//61+3a/n9eiKhnsWgiItVaWlrw9ttv4/e//z0iIyPN2mJjY/Huu+9i1apVWLJkCX7xi18gLy8P77//Pv76178q/UJCQmA0GmFnZwdfX1/Vx66pqUFJSQm2b9+Oxx57DABw7Ngxsz4BAQF45513cPPmTeWTZydPnjTrExISgg8++AC+vr6ws+v6T2BUVBRu3boFjUaDOXPmqB5vbwoJCcH+/fvh5+cHW1tbSw+HyGrwQnAiUm3//v345ptvsHz5cgQGBprdFi5ciJSUFAB31iCaMWMGli9fjtbWVsybN0/ZR0REBMLCwhAbG4tPPvkEFy5cwOeff46NGzciNze302OPGDECrq6u+Pvf/47S0lIcOXIEL7zwglmfJUuWwGQyYeXKlTh37hwOHTqE3/3udwDu/KcHuLPOUm1tLeLi4nDy5EmUlZXh0KFDSExMRGtra7vj2tra4ty5czh79my/KVCeffZZVFVVIT4+Hrm5uSgrK8PBgweRkJBg6aERDWosmohItZSUFERERMDFxaVd28KFC5Gbm4vTp08DAOLj41FYWIgFCxZgyJAhSj+NRoP09HTMnDkTiYmJmDBhAp5++mlcvHgRHh4enR7bxsYGqampyMvLQ2BgIJ5//nm8/vrrZn20Wi0+/vhjFBQUYPLkydi4cSM2bdoEAMp1Tp6enjh+/DhaW1sRGRmJoKAgrF27FjqdDjY2Hf9J1Gq10Gq13XuyetGYMWNw/Phx3Lx5ExEREQgKCsLzzz/f7joxIupZGhERSw+CiKi37N69G4mJibh27ZpZ8UZE1F28pomIBpW3334b/v7+GD16NAoLC7F+/Xo89dRTLJiI6L6xaCKiQcVoNGLTpk0wGo0wGAxYtGgRXn31VUsPi4gGAZ6eIyIiIlKBF4ITERERqcCiiYiIiEgFFk1EREREKrBoIiIiIlKBRRMRERGRCiyaiIiIiFRg0URERESkAosmIiIiIhVYNBERERGp8D/4194DyKufqQAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['AverageMInFile']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Similar but smaller gains come when the age of the oldest account ('MSinceOldestTradeOpen') exceeds 122 and 146 months (10-12 years)." ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkIAAAGwCAYAAABFFQqPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOzdeXjU5b3//9ckYbKQTCYhhBBIwlr2NREa8RSqqSi4VY8HPRwBoVgtCIJfK7RH1LYaPLUqqIWqVdrf0YO14tqKtQi4FEESIrKjYBKWsGWZLGSb3L8/kMFhWDIwk8lkno/rmutKPnPP5P1xNHn5+bzv+7YYY4wAAABCUFigCwAAAAgUghAAAAhZBCEAABCyCEIAACBkEYQAAEDIIggBAICQRRACAAAhKyLQBbR2TU1NOnDggOLi4mSxWAJdDgAAaAZjjCorK5WamqqwsLNf9yEInceBAweUlpYW6DIAAMAFKC4uVteuXc/6PEHoPOLi4iSd+Adps9kCXA0AAGgOh8OhtLQ019/xsyEIncfJ22E2m40gBABAkDlfWwvN0gAAIGQFXRB69tln1a1bN0VFRWnkyJHasGHDWcc+//zz+rd/+zclJCQoISFBOTk55xwPAABCS1AFoVdffVVz587Vgw8+qPz8fA0ZMkRjx47V4cOHzzh+zZo1uvXWW7V69WqtW7dOaWlpuvLKK7V///4WrhwAALRGFmOMCXQRzTVy5EhdcskleuaZZySdmNqelpamu+++W/PmzTvv651OpxISEvTMM89o0qRJzfqZDodD8fHxqqiooEcIAIAg0dy/30FzRai+vl55eXnKyclxHQsLC1NOTo7WrVvXrPeoqalRQ0ODEhMTzzqmrq5ODofD7QEAANqmoAlCR48eldPpVKdOndyOd+rUSSUlJc16j/vvv1+pqaluYep0ubm5io+Pdz1YQwgAgLYraILQxVq4cKGWL1+uN954Q1FRUWcdN3/+fFVUVLgexcXFLVglAABoSUGzjlBSUpLCw8N16NAht+OHDh1SSkrKOV/7+OOPa+HChfrnP/+pwYMHn3NsZGSkIiMjL7peAADQ+gXNFSGr1arMzEytWrXKdaypqUmrVq1Sdnb2WV/3P//zP/r1r3+tlStXKisrqyVKBQAAQSJorghJ0ty5czV58mRlZWVpxIgReuqpp1RdXa3bb79dkjRp0iR16dJFubm5kqTHHntMCxYs0CuvvKJu3bq5eoliY2MVGxsbsPMAAACtQ1AFoQkTJujIkSNasGCBSkpKNHToUK1cudLVQF1UVOS2w+ySJUtUX1+vf//3f3d7nwcffFAPPfRQS5YOAABaoaBaRygQWEcIAIDg0+bWEQIAAG2Ls8lo+0GHHLUNAashqG6NAQCA4OWobVBBUbnyCsuUX1SmTUXlqqpr1O8nDte4QZ0DUhNBCAAA+JwxRoXHapRXWKa8ojLlF5Zp56FKnd6Q094armNVdYEpUgQhAADgA7UNTn25v+JE8Ck8EXyOVdd7jEtPjFFmRoKGZyQoMz1BfVLiFB5mCUDFJxCEAACA1w45al2hJ6+wTFsPVKjB6X65xxoepkFd408En/QEDc+wKznu7Ls7BAJBCAAAnFOjs0k7SiqVX3Qq+OwrO+4xLik2UlkZCa4rPgO72BQZER6AipuPIAQAANxU1DQov/jE7a28wjIVFJerpt7pNibMIvVNsSnz2+CTmZGgrgnRslgCd5vrQhCEAAAIYcYY7Tla7errySss0+7DVR7j4qIiNDz9VOgZkmZXbGTwx4jgPwMAANBsx+ud+mJfuSv45BeVqazGcx2f7knt3YJP7+RYhQWwqdlfCEIAALRhB8qPn5rJVVSmbQccamxyb2qOjAjTkK72EzO5MhI0PN2uDrGRAaq4ZRGEAABoIxqcTdp+0KG8wjJt/PaKz8GKWo9xnWyRyspIdAWf/p1tskaE5mYTBCEAAIJUWXW920yuL/aVq7ahyW1MeJhF/TvbTq3dk5Gg1PiooGtq9heCEAAAQaCpyejrI1Wn1u4pKtOeI9Ue4+Kj27n6eoanJ2hIWrxirPy5Pxv+yQAA0ApV1zXqi+Jyty0qHLWNHuN6JccqM/3U2j09ktq3yaZmfyEIAQAQYMYY7Ss77naba/tBh07raVZ0u3ANSYt3XfEZlpaghPbWwBTdRhCEAABoYXWNTm094HCt25NXWKbDlZ4bj3axR3+7J5ddmRmJ6ts5Tu3CQ7Op2V8IQgAA+NnRqroToaeoTHnflGnz/grVN7o3NUeEWTSgS/x3bnPZ1Tk+OkAVhw6CEAAAPuRsMtp9uNJtF/ZvjtV4jEtsb3VbsHBw13hFtWvd+3K1RQQhAAAuQmVtgwpONjUXlqmgqFyVde5NzRaL9L3kONf09cyMBHXrEMMU9laAIAQAQDMZY1RUWnNqCnthmXYeqpQ5ram5vTVcw9JPrdszNM2u+Oh2gSka50QQAgDgLGobnNqyv8Jti4qjVfUe49ISo92msPfpFKcImpqDAkEIAIBvHXbUui1YuGV/hRqc7pd7rOFhGtjF5rZoYbItKkAV42IRhAAAIanR2aSdhypdU9g3FpZpX9lxj3FJsVZX6MnMSNCAVJqa2xKCEAAgJFQcb9Cmb1dozis60dRcXe90G2OxSH1TbMrMsJ8IPumJSkuMpqm5DSMIAQDaHGOM9h6tdvX15BWWadehKo9xcZERGpaR4OrvGZIWr7gomppDCUEIABD0jtc7tXlfuWtPrrzCMpXVNHiM69YhRsMzEpSVkajMjAT1So5VOPtyhTSCEAAg6BysOO62YOHWAw41nrYxlzUiTEO6xn+7RcWJ2VxJsZEBqhitFUEIANCqNTibtONgpfIKS5VXVK78wjLtL/dsak6Oi1RWtwTXas0DUuNljWAKO86NIAQAaFXKquu1qfjUgoVfFFfoeIN7U3N4mEX9Ose5rvRkZiSoi52mZniPIAQACJimJqM9R6vcVmr++ki1xzhbVMSpdXsyEjSkq13tI/kThovHv0UAgBZTU9+oguJyV0NzflG5Ko57NjX37Njebe2eHkmxCqOpGX5AEAIA+IUxRvvLj7samvOKyrT9YKWcpzU1R7UL05CuJ9btyeqWoGFpCUpobw1Q1Qg1BCEAgE/UNzZp20GHNn5T6lq755CjzmNcanyU2y7s/Trb1I59uRAgBCEAwAU5VlWn/KJy1xWfL/aVq66xyW1MRJhFA1JtruAzPD1BqfboAFUMeCIIAQDOq6nJaPfhKrdd2Pce9WxqTohp52pozkxP0OCudkVb2ZcLrRdBCADgoaquUQXfXu3JKyrTpqIyVdY2eoz7XqdY15WezIwEdU9qzxR2BBWCEACEOGOMikuPK6+o9NsrPuXaWeLQaT3NirGGa2ia3XXFZ3haguJj2JcLwY0gBAAhprbBqa0HKr6zdk+5jlZ5NjV3TYg+tXZPeoL6psQpgqZmtDEEIQBo4w5X1iq/sPzEFhWFZdqy36F6p3tTc7twiwZ2iXftwj48I0GdbFEBqhhoOQQhAGhDnE1GO0sq3XZhLyqt8RiXFGt19fVkZiRoYJd4RbWjqRmhhyAEAEGs4niDCopPTWHfVFSm6nr3fbksFqlPpzi3lZrTE2NoagZEEAKAoGGM0TfHak5NYS8s067DlTKnNTXHRkZoWLrdFXqGpNlli6KpGTgTghAAtFK1DU5t3lfhtnZPaXW9x7iMDjFuu7B/r1OcwtmXC2gWghAAtBIlFbWnZnIVlWnr/go1njaH3RoRpsFd4k9NYU9PUMe4yABVDAQ/ghAABECjs0k7SiqVV1imjd/e5tpfftxjXMe4SGVlnJrJNSDVpsgImpoBXyEIAUALKK+p16aTKzUXlqmguFzHG9ybmsMsUr/ONre1e7omRNPUDPgRQQgAfMwYo6+PVLumr+cVlemrw1Ue42xREa49uU42NbeP5Ncy0JL4Lw4ALlJNfaO+KK5QftGppubymgaPcT2S2rtNYe/ZMVZhNDUDAUUQAgAvGGN04Num5pNXfLYddMh5WlNzZESYhny7L9fJGV2J7a0BqhrA2RCEAOAc6hubtO2gwy34lDhqPcal2KKU2e3Uba5+nW2yRrAvF9DaEYQA4DtKq+tPBJ5vb3N9UVyuukb3fbnCwywakGpz26Ii1R4doIoBXAyCEICQ1dRk9NWRKreVmvccrfYYZ49p57Zg4eCu8Yqx8usTaAv4LxlAyKiqa9QXxeVuKzVX1jZ6jOudHOtatyczI0E9ktozhR1oowhCANokY4z2lR0/tVJzYZl2lDh0Wk+zotuFa2iaXVndTgSfYWl22WNoagZCBUEIQJtQ1+jUlv0Ot7V7jlTWeYzrYo92m8LeNyVOEeE0NQOhiiAEICgdqaxz3d7KKyzTl/sqVO90b2puF27RgNR4t5WaU+KjAlQxgNaIIASg1XM2Ge06VHlqCntRmQqP1XiM69De6urrycxI0KAu8Ypqx75cAM6OIASg1XHUNqjg23258ovKtKmoXFV17k3NFovUp1Oc2xYVGR1iaGoG4BWCEICAMsao8FiNq68nv7BMOw9VypzW1BwbGaFh6XbX2j1D0+2yRbULTNEA2gyCEIAWVdvg1Jf7K9zW7jlWXe8xLj0xxjWFPSsjQd/rFKdw9uUC4GMEIQB+dchR6zaFfeuBCjU43S/3WMPDNKhrvKuheXiGXclxNDUD8D+CEACfaXQ2aUdJpWsmV15hmfaVHfcYlxQbqayTM7kyEjSwi02RETQ1A2h5BCEAF6yipkH5xac2Iy0oLldNvdNtTJhF6ptic1u7p2tCNE3NAFoFghCAZjHGaM/Rardd2HcfrvIYFxcV4bYZ6ZA0u2Ij+VUDoHXy2W+nsrIyvfPOO5o0aZKv3vKMnn32Wf32t79VSUmJhgwZoqefflojRow449itW7dqwYIFysvLU2FhoZ588kndc889fq0PaCuO1zv1xb5yV/DJLypTWU2Dx7geSe3d1u7p1TFWYTQ1AwgSPgtCRUVFuv322/0ahF599VXNnTtXS5cu1ciRI/XUU09p7Nix2rlzp5KTkz3G19TUqEePHrr55ps1Z84cv9UFtAUHyo+7bUa67YBDjadtzBUZEaYhXe2u4DM83a4OsZEBqhgALl6zg5DD4Tjn85WVlRddzPk88cQTmj59um6//XZJ0tKlS/W3v/1NL774oubNm+cx/pJLLtEll1wiSWd8/kzq6upUV3dqf6LznTcQjBqcTdp+0KG8wjJt/PaKz8GKWo9xnWyRyspIdAWf/p1tskawLxeAtqPZQchut5+zudEY49fmx/r6euXl5Wn+/PmuY2FhYcrJydG6det89nNyc3P18MMP++z9gNagrLrebSbXF/vKVdvgvi9XeJhF/TvbXDO5MjMSlBofRVMzgDat2UEoLi5Ov/zlLzVy5MgzPr9792799Kc/9Vlhpzt69KicTqc6derkdrxTp07asWOHz37O/PnzNXfuXNf3DodDaWlpPnt/wN+amoy+PlJ1au2eojLtOVLtMS4+up3bZqRD0uIVY6WpGUBoafZvveHDh0uSRo8efcbn7Xa7zOlr4gehyMhIRUbS84DgUV3XqC+Ky922qHDUNnqM65Uc69qTa3hGgnoktaepGUDIa3YQ+s///E8dP+65MNpJKSkpevDBB31S1JkkJSUpPDxchw4dcjt+6NAhpaSk+O3nAq2JMUb7yo673ebaftCh03qaFd0uXEPT7K4rPsPS7bLHWANTNAC0Ys0OQtOnTz/n8506dfJrELJarcrMzNSqVat0ww03SJKampq0atUqzZw5028/Fwikukanth5wuNbtySss0+HKOo9xXezR3+7CbldmRqL6dY5TRDhNzQBwPkHVEDB37lxNnjxZWVlZGjFihJ566ilVV1e7ZpFNmjRJXbp0UW5urqQTDdbbtm1zfb1//34VFBQoNjZWvXr1Cth5AGdztKruROgpKlPeN2XavL9C9Y3uTc0RYRYN6BL/ndtcdnWOjw5QxQAQ3C4oCH366afKyspSZGSk29f+NmHCBB05ckQLFixQSUmJhg4dqpUrV7oaqIuKihQWdur/gg8cOKBhw4a5vn/88cf1+OOPa/To0VqzZo3f6wXOxdlktPtwpdsu7N8cq/EYl9je6rZS8+Cu8Ypqx75cAOALFnMBHc42m00FBQXq0aOH29dtkcPhUHx8vCoqKmSz2QJdDoJYZW2DCk42NReWqaCoXJV17k3NFov0veQ4t5Wau3WIYQo7AHipuX+/L+iK0HezU1uYKQb4mjFGRaU1p6awF5Zp56FKnf6fS3truIaln1q3Z2iaXfHR7QJTNACEoKDqEQJaq9oGp7bsr3DbouJoVb3HuLTEaLcp7H060dQMAIFEEAIuwGFHrduChVv2V6jB6X65xxoepoFdbG6LFibbogJUMQDgTAhCwHk0Opu081Clawr7xsIy7SvzXFMrKTZSmRmn1u4ZkEpTMwC0dgQh4DQVxxu06dsVmvOKTjQ1V9c73caEWaQ+KbZTwSc9UWmJ0TQ1A0CQIQghpBljtPdotauvJ6+wTLsOVXmMi4uM0LCMBFd/z5C0eMVF0dQMAMGOIISQcrzeqc37yl17cuUVlqmspsFjXLcOMRqekaCsjERlZiSoV3KswtmXCwDanAsKQn/4wx9cixh+92ugtTlYcdxtwcKtBxxqPG1jLmtEmIZ0jf92i4oTs7mSYtl4FwBCQbMXVDTGhGT/AwsqBo8GZ5O2H3S4BZ8DFbUe45LjIpXVLcG1WvOA1HhZI5jCDgBtic8XVBw1apT+/Oc/s0cXWg1jjD7afVQb9h5TXmGZviiu0PEG96bm8DCL+nWOc13pycxIUBc7Tc0AgBOaHYS6du2qoUOH6rHHHtOMGTP8WRPQLP/fZ4Va8NZWt2O2qIhT6/ZkJGhIV7vaR9IKBwA4s2b/hfjLX/6i1157TTNnztSbb76pl156SV27dvVnbcA5HSg/cdtrYBebbvt+hjIzEtQjKVZhNDUDAJrJq/9VvvnmmzVmzBjNmDFDgwYN0m233aaICPe3eOKJJ3xaIHA+3+/eQRMuSQ90GQCAIOT1PYPExET169dPb7zxhjZt2uQWhOi7AAAAwcSrILR161ZNmjRJpaWl+sc//qEf/vCH/qoLAADA75o9Z3jhwoXKzMzUkCFDtHnzZkIQAAAIes2+IrRo0SK99tpruvbaa/1ZDwAAQItpdhDasmWLOnTo4M9aAAAAWlSzb40RggAAQFvDvgIAACBkEYQAAEDIalYQmjt3rqqrqyVJH330kRobG/1aFAAAQEtoVhB6+umnVVVVJUn64Q9/qNLSUr8WBQAA0BKaNWusW7duWrx4sa688koZY7Ru3TolJCSccewPfvADnxYIAADgL80KQr/97W915513Kjc3VxaLRT/+8Y/POM5iscjpdPq0QAAAAH9pVhC64YYbdMMNN6iqqko2m007d+5UcnKyv2sDAADwK6/2GouNjdXq1avVvXt3j13nAQAAgo3XaWb06NFyOp16/fXXtX37dklS//79df311ys8PNznBQIAAPiL10Hoq6++0vjx47Vv3z716dNHkpSbm6u0tDT97W9/U8+ePX1eJAAAgD94vaDirFmz1KNHDxUXFys/P1/5+fkqKipS9+7dNWvWLH/UCAAA4BdeXxFau3atPvvsMyUmJrqOdejQQQsXLtSoUaN8WhwAAIA/eX1FKDIyUpWVlR7Hq6qqZLVafVIUAABAS/A6CF1zzTW64447tH79ehljZIzRZ599pjvvvFPXXXedP2oEAADwC6+D0OLFi9WzZ09lZ2crKipKUVFRGjVqlHr16qVFixb5o0YAAAC/8LpHyG6366233tJXX33lmj7fr18/9erVy+fFAQAA+NMFr4rYq1cvwg8AAAhqXt8aAwAAaCsIQgAAIGQRhAAAQMgiCAEAgJDldRBauXKlPvnkE9f3zz77rIYOHar//M//VFlZmU+LAwAA8Cevg9B9990nh8MhSfryyy917733aty4cdq7d6/mzp3r8wIBAAD8xevp83v37lX//v0lSa+//rquueYaPfroo8rPz9e4ceN8XiAAAIC/eH1FyGq1qqamRpL0z3/+U1deeaUkKTEx0XWlCAAAIBh4fUXosssu09y5czVq1Cht2LBBr776qiRp165d6tq1q88LBAAA8Bevrwg988wzioiI0F//+lctWbJEXbp0kSS99957uuqqq3xeIAAAgL94fUUoPT1d7777rsfxJ5980icFAQAAtJRmBSFven9sNtsFFwMAANCSmhWE7Ha7LBZLs97Q6XReVEEAAAAtpVlBaPXq1a6vv/nmG82bN09TpkxRdna2JGndunX605/+pNzcXP9UCQAA4AfNCkKjR492ff2rX/1KTzzxhG699VbXseuuu06DBg3Sc889p8mTJ/u+SgAAAD/wetbYunXrlJWV5XE8KytLGzZs8ElRAAAALcHrIJSWlqbnn3/e4/gLL7ygtLQ0nxQFAADQEryePv/kk0/qpptu0nvvvaeRI0dKkjZs2KDdu3fr9ddf93mBAAAA/uL1FaFx48Zp165duvbaa1VaWqrS0lJde+212rVrF3uNAQCAoOL1FSHpxO2xRx991Ne1AAAAtKhmBaHNmzc3+w0HDx58wcUAAAC0pGYFoaFDh8piscgY47awojFGktyOsaAiAAAIFs3qEdq7d6/27NmjvXv36vXXX1f37t31+9//XgUFBSooKNDvf/979ezZk2ZpAAAQVJp1RSgjI8P19c0336zFixe7NUYPHjxYaWlpeuCBB3TDDTf4vkoAAAA/8HrW2Jdffqnu3bt7HO/evbu2bdvmk6IAAABagtdBqF+/fsrNzVV9fb3rWH19vXJzc9WvXz+fFgcAAOBPXk+fX7p0qa699lp17drVNUNs8+bNslgseuedd3xeIAAAgL94fUVoxIgR2rNnj37zm99o8ODBGjx4sB555BHt2bNHI0aM8EeNbp599ll169ZNUVFRGjly5Hn3N3vttdfUt29fRUVFadCgQfr73//u9xoBAEBwuKAFFdu3b6877rjD17Wc16uvvqq5c+dq6dKlGjlypJ566imNHTtWO3fuVHJyssf4f/3rX7r11luVm5ura665Rq+88opuuOEG5efna+DAgS1ePwAAaF28viIkSV9//bXuvvtu5eTkKCcnR7Nnz9bXX3/t69o8PPHEE5o+fbpuv/129e/fX0uXLlVMTIxefPHFM45ftGiRrrrqKt13333q16+ffv3rX2v48OF65pln/F4rAABo/bwOQu+//7769++vDRs2uG6NffbZZxowYIA++OADf9Qo6URDdl5ennJyclzHwsLClJOTo3Xr1p3xNevWrXMbL0ljx44963hJqqurk8PhcHsAAIC2yetbY/PmzdOcOXO0cOFCj+P333+/fvSjH/msuO86evSonE6nOnXq5Ha8U6dO2rFjxxlfU1JScsbxJSUlZ/05ubm5evjhhy++YAAA0Op5fUVo+/btmjZtmsfxqVOntol1hObPn6+KigrXo7i4ONAlAQAAP/H6ilDHjh1VUFCg3r17ux0vKCg4Y8OyryQlJSk8PFyHDh1yO37o0CGlpKSc8TUpKSlejZekyMhIRUZGXnzBAACg1fP6itD06dN1xx136LHHHtPHH3+sjz/+WAsXLtRPf/pTTZ8+3R81SpKsVqsyMzO1atUq17GmpiatWrVK2dnZZ3xNdna223hJ+uCDD846HgAAhBavrwg98MADiouL0+9+9zvNnz9fkpSamqqHHnpIs2bN8nmB3zV37lxNnjxZWVlZGjFihJ566ilVV1fr9ttvlyRNmjRJXbp0UW5uriRp9uzZGj16tH73u99p/PjxWr58uTZu3KjnnnvOr3UCAIDg4HUQslgsmjNnjubMmaPKykpJUlxcnM8LO5MJEyboyJEjWrBggUpKSjR06FCtXLnS1RBdVFSksLBTF7kuvfRSvfLKK/rv//5v/eIXv1Dv3r315ptvsoYQAACQJFmMMeZCX7xw4ULdeeedstvtvqypVXE4HIqPj1dFRYVsNlugy8F3LHxvh5au/Vo/uay7/vua/oEuBwDQijT37/cFLah40qOPPqrS0tKLeQsAAICAuaggdBEXkwAAAALuooIQAABAMLugTVdP2rZtm1JTU31VCwAAQIu6qCCUlpbmqzoAAABanNdBKCEhQRaLxeO4xWJRVFSUevXqpSlTprjW9gEAAGitvA5CCxYs0COPPKKrr75aI0aMkCRt2LBBK1eu1IwZM7R3717dddddamxs9OtK0wAAABfL6yD0ySef6De/+Y3uvPNOt+N/+MMf9I9//EOvv/66Bg8erMWLFxOEAABAq+b1rLH3339fOTk5HsevuOIKvf/++5KkcePGac+ePRdfHQAAgB95HYQSExP1zjvveBx/5513lJiYKEmqrq5usW03AAAALtQFbbp61113afXq1a4eoc8//1x///vftXTpUkkndngfPXq0bysFAADwMa+D0PTp09W/f38988wzWrFihSSpT58+Wrt2rS699FJJ0r333uvbKgEAAPzggtYRGjVqlEaNGuXrWgAAAFrUBQUhp9OpN998U9u3b5ckDRgwQNddd53Cw8N9WhwAAIA/eR2EvvrqK40bN0779+9Xnz59JEm5ublKS0vT3/72N/Xs2dPnRQIAAPiD17PGZs2apZ49e6q4uFj5+fnKz89XUVGRunfvrlmzZvmjRgAAAL/w+orQ2rVr9dlnn7mmyktShw4dtHDhQvqGAABAUPH6ilBkZKQqKys9jldVVclqtfqkKAAAgJbgdRC65pprdMcdd2j9+vUyxsgYo88++0x33nmnrrvuOn/UCAAA4BdeB6HFixerZ8+eys7OVlRUlKKiojRq1Cj16tVLixYt8keNAAAAfuF1j5Ddbtdbb72l3bt3a8eOHZKkfv36qVevXj4vDgAAwJ8uaB0hSerdu7d69+7ty1oAAABaVLOC0Ny5c5v9hk888cQFFwMAANCSmhWENm3a1Kw3s1gsF1UMAABAS2pWEFq9erW/6wAAAGhxXs8aAwAAaCsuuFkaaGmNzibtKKlUflGZ8grL9Mnuo/JLRlIAACAASURBVIEuCQAQ5AhCaLUqahqUX1ym/MITwaeguFw19U63Me3CLfp+jw4BqhAAEOwIQmgVjDHac7RaeYWngs/uw1Ue4+IiIzQsI0GZ6QnKzEjQkLR4xUW1C0DFAIC2gCCEgDPG6Oal67SxsMzjue5J7TX829CTmZGg3smxCgtjdiIAwDcuKAh9/fXXeuqpp7R9+3ZJUv/+/TV79mz17NnTp8UhNBxvcLpCUFZGgrK6JSozI0HD0+3qEBsZ4OoAAG2Z10Ho/fff13XXXaehQ4dq1KhRkqRPP/1UAwYM0DvvvKMf/ehHPi8SoePP00YoxsqFSgBAy/D6L868efM0Z84cLVy40OP4/fffTxACAABBw+t1hLZv365p06Z5HJ86daq2bdvmk6IAAABagtdBqGPHjiooKPA4XlBQoOTkZJ8UBQAA0BK8vjU2ffp03XHHHdqzZ48uvfRSSSd6hB577DGvNmcFAAAINK+D0AMPPKC4uDj97ne/0/z58yVJqampeuihhzRr1iyfFwgAAOAvXgchi8WiOXPmaM6cOaqsrJQkxcXF+bwwAAAAf/O6R+jyyy9XeXm5pBMB6GQIcjgcuvzyy31bHQAAgB95HYTWrFmj+vp6j+O1tbX6+OOPfVIUAABAS2j2rbHNmze7vt62bZtKSkpc3zudTq1cuVJdunTxbXUAAAB+1OwgNHToUFksFlksljPeAouOjtbTTz/t0+IAAAD8qdlBaO/evTLGqEePHtqwYYM6duzoes5qtSo5OVnh4eF+KRIAAMAfmh2EMjIyJElNTU1+KwYAAKAled0sDQAA0FYQhAAAQMgiCAEAgJBFEAIAACHL6y02Tqqvr9fhw4c9mqfT09MvuigAAICW4HUQ2r17t6ZOnap//etfbseNMbJYLHI6nT4rDgAAwJ+8DkJTpkxRRESE3n33XXXu3FkWi8UfdQEAAPid10GooKBAeXl56tu3rz/qAQAAaDFeN0v3799fR48e9UctAAAALcrrIPTYY4/p5z//udasWaNjx47J4XC4PQAAAIKF17fGcnJyJElXXHGF23GapQEAQLDxOgitXr3aH3UAAAC0OK+D0OjRo/1RBwAAQIu7oAUVy8vL9cc//lHbt2+XJA0YMEBTp05VfHy8T4sDAADwJ6+bpTdu3KiePXvqySefVGlpqUpLS/XEE0+oZ8+eys/P90eNAAAAfuH1FaE5c+bouuuu0/PPP6+IiBMvb2xs1E9+8hPdc889+uijj3xeJAAAgD94HYQ2btzoFoIkKSIiQj//+c+VlZXl0+IAAAD8yetbYzabTUVFRR7Hi4uLFRcX55OiAAAAWoLXQWjChAmaNm2aXn31VRUXF6u4uFjLly/XT37yE916663+qBEAAMAvvL419vjjj8tisWjSpElqbGyUJLVr10533XWXFi5c6PMCAQAA/MXrK0JWq1WLFi1SWVmZCgoKVFBQoNLSUj355JOKjIz0R42SpNLSUk2cOFE2m012u13Tpk1TVVXVOV/z3HPPacyYMbLZbLJYLCovL/dbfQAAIPh4HYROiomJ0aBBgzRo0CDFxMT4sqYzmjhxorZu3aoPPvhA7777rj766CPdcccd53xNTU2NrrrqKv3iF7/we30AACD4NOvW2I033qhly5bJZrPpxhtvPOfYFStW+KSw79q+fbtWrlypzz//3DUz7emnn9a4ceP0+OOPKzU19Yyvu+eeeyRJa9asafbPqqurU11dnet7NpIFAKDtatYVofj4eFksFkknZo3Fx8ef9eEP69atk91ud5uen5OTo7CwMK1fv96nPys3N9ftfNLS0nz6/gAAoPVo1hWhl156yfX1smXL/FXLWZWUlCg5OdntWEREhBITE1VSUuLTnzV//nzNnTvX9b3D4SAMAQDQRnndI3T55ZefsenY4XDo8ssv9+q95s2bJ4vFcs7Hjh07vC3xokRGRspms7k9AABA2+T19Pk1a9aovr7e43htba0+/vhjr97r3nvv1ZQpU845pkePHkpJSdHhw4fdjjc2Nqq0tFQpKSle/UwAAICTmh2ENm/e7Pp627ZtbreknE6nVq5cqS5dunj1wzt27KiOHTued1x2drbKy8uVl5enzMxMSdKHH36opqYmjRw50qufCQAAcFKzg9DQoUNdt6vOdAssOjpaTz/9tE+LO6lfv3666qqrNH36dC1dulQNDQ2aOXOmbrnlFteMsf379+uKK67Qn//8Z40YMULSid6ikpISffXVV5KkL7/8UnFxcUpPT1diYqJfagUAAMGj2UFo7969MsaoR48e2rBhg9uVHKvVquTkZIWHh/ulSEl6+eWXNXPmTF1xxRUKCwvTTTfdpMWLF7ueb2ho0M6dO1VTU+M6tnTpUj388MOu73/wgx9IOtH8fb5bcgAAoO2zGGNMoItozRwOh+Lj41VRUUHjtJ/U1Deq/4L3JUnbfjVWMVavW9cAAHDT3L/fXv/F+fOf/3zO5ydNmuTtWwIAAASE10Fo9uzZbt83NDSopqZGVqtVMTExBCEAABA0vF5HqKyszO1RVVWlnTt36rLLLtP//d//+aNGAAAAv7jgTVe/q3fv3lq4cKHH1SIAAIDWzCdBSDqx5cWBAwd89XYAAAB+53WP0Ntvv+32vTFGBw8e1DPPPKNRo0b5rDAAAAB/8zoI3XDDDW7fWywWdezYUZdffrl+97vf+awwAAAAf/M6CDU1NfmjDgAAgBZ3UT1CxhixHiMAAAhWFxSE/vjHP2rgwIGKiopSVFSUBg4cqBdeeMHXtQEAAPiV17fGFixYoCeeeEJ33323srOzJUnr1q3TnDlzVFRUpF/96lc+LxIAAMAfvA5CS5Ys0fPPP69bb73Vdey6667T4MGDdffddxOEAABA0PD61lhDQ4OysrI8jmdmZqqxsdEnRQEAALQEr4PQbbfdpiVLlngcf+655zRx4kSfFAUAANASmnVrbO7cua6vLRaLXnjhBf3jH//Q97//fUnS+vXrVVRUxIarAAAgqDQrCG3atMnt+8zMTEnS119/LUlKSkpSUlKStm7d6uPyAAAA/KdZQWj16tX+rgMAAKDF+WzTVQAAgGDTrCtCN954o5YtWyabzaYbb7zxnGNXrFjhk8IAAAD8rVlBKD4+XhaLxfU1AABAW9CsIPTSSy9JOrG32MMPP6yOHTsqOjrar4UBAAD4m1c9QsYY9erVS/v27fNXPQAAAC3GqyAUFham3r1769ixY/6qBwAAoMV4PWts4cKFuu+++7RlyxZ/1AMAANBivN50ddKkSaqpqdGQIUNktVo9eoVKS0t9VhwAAIA/eR2EnnzySdcMMgAAgGDmdRCaMmWKH8oAAABoeV73CIWHh+vw4cMex48dO6bw8HCfFAUAANASvA5CxpgzHq+rq5PVar3oggAAAFpKs2+NLV68WJJksVj0wgsvKDY21vWc0+nURx99pL59+/q+QgAAAD9pdhB68sknJZ24IrR06VK322BWq1XdunXT0qVLfV8hAACAnzQ7CO3du1eS9MMf/lArVqxQQkKC34oCAABoCV7PGlu9erU/6gAAAGhxXgchp9OpZcuWadWqVTp8+LCamprcnv/www99VhwAAIA/eR2EZs+erWXLlmn8+PEaOHAgiysCAICg5XUQWr58uf7yl79o3Lhx/qgHAACgxXi9jpDValWvXr38UQsAAECL8joI3XvvvVq0aNFZF1YEAAAIFl7fGvvkk0+0evVqvffeexowYIDatWvn9vyKFSt8VhwAAIA/eR2E7Ha7fvzjH/ujFgAAgBbldRB66aWX/FEHAABAi/M6CJ105MgR7dy5U5LUp08fdezY0WdFAQAAtASvm6Wrq6s1depUde7cWT/4wQ/0gx/8QKmpqZo2bZpqamr8USMAAIBfeB2E5s6dq7Vr1+qdd95ReXm5ysvL9dZbb2nt2rW69957/VEjAACAX3h9a+z111/XX//6V40ZM8Z1bNy4cYqOjtZ//Md/aMmSJb6sDwAAwG+8viJUU1OjTp06eRxPTk7m1hgAAAgqXgeh7OxsPfjgg6qtrXUdO378uB5++GFlZ2f7tDgAAAB/8vrW2KJFizR27Fh17dpVQ4YMkSR98cUXioqK0vvvv+/zAgEAAPzF6yA0cOBA7d69Wy+//LJ27NghSbr11ls1ceJERUdH+7xAAAAAf7mgdYRiYmI0ffp0X9cCAADQorzuEcrNzdWLL77ocfzFF1/UY4895pOiAAAAWoLXQegPf/iD+vbt63F8wIABWrp0qU+KAgAAaAleB6GSkhJ17tzZ43jHjh118OBBnxQFAADQErwOQmlpafr00089jn/66adKTU31SVEAAAAtwetm6enTp+uee+5RQ0ODLr/8cknSqlWr9POf/5wtNgAAQFDxOgjdd999OnbsmH72s5+pvr5ekhQVFaX7779f8+fP93mBAAAA/uJ1ELJYLHrsscf0wAMPaPv27YqOjlbv3r0VGRnpj/oAAAD85oLWEZKk2NhYXXLJJb6sBQAAoEV53SwNAADQVhCEAABAyCIIAQCAkEUQAgAAIYsgBAAAQlbQBKHS0lJNnDhRNptNdrtd06ZNU1VV1TnH33333erTp4+io6OVnp6uWbNmqaKiogWrBgAArVnQBKGJEydq69at+uCDD/Tuu+/qo48+0h133HHW8QcOHNCBAwf0+OOPa8uWLVq2bJlWrlypadOmtWDVAACgNbMYY0ygizif7du3q3///vr888+VlZUlSVq5cqXGjRunffv2NXuPs9dee03/9V//perqakVENG8JJYfDofj4eFVUVMhms13wOeDsauob1X/B+5Kkbb8aqxjrBS9vBQCApOb//Q6KK0Lr1q2T3W53hSBJysnJUVhYmNavX9/s9zn5D+NcIaiurk4Oh8PtAQAA2qagCEIlJSVKTk52OxYREaHExESVlJQ06z2OHj2qX//61+e8nSZJubm5io+Pdz3S0tIuuG4AANC6BTQIzZs3TxaL5ZyPHTt2XPTPcTgcGj9+vPr376+HHnronGPnz5+viooK16O4uPiifz4AAGidAtqMce+992rKlCnnHNOjRw+lpKTo8OHDbscbGxtVWlqqlJSUc76+srJSV111leLi4vTGG2+oXbt25xwfGRnJBrIAAISIgAahjh07qmPHjucdl52drfLycuXl5SkzM1OS9OGHH6qpqUkjR4486+scDofGjh2ryMhIvf3224qKivJZ7QAAIPgFRY9Qv379dNVVV2n69OnasGGDPv30U82cOVO33HKLa8bY/v371bdvX23YsEHSiRB05ZVXqrq6Wn/84x/lcDhUUlKikpISOZ3OQJ4OAABoJYJmnvLLL7+smTNn6oorrlBYWJhuuukmLV682PV8Q0ODdu7cqZqaGklSfn6+a0ZZr1693N5r79696tatW4vVDgAAWqegCUKJiYl65ZVXzvp8t27d9N0lkcaMGaMgWCIJAAAEUFDcGgMAAPAHghAAAAhZBCEAABCyCEIAACBkEYQAAEDIIggBAICQRRACAAAhiyAEAABCFkEIAACELIIQAAAIWQQhAAAQsghCAAAgZBGEAABAyCIIAQCAkEUQAgAAIYsgBAAAQhZBCAAAhCyCEAAACFkEIQAAELIIQgAAIGQRhAAAQMgiCAEAgJBFEAIAACGLIISAMsboQPnxQJcBAAhREYEuAKGlrtGprQccyi8sU963j8OVdZKkMIsUZrEEuEIAQCghCMGvjlTWKb+ozBV8Nu+vUH1jk9uYiDCLBnSJ103DuyiqXXiAKgUAhCKCEHzG2WS0+3DliSs935Qpr6hMhcdqPMYltrdqeHqCMjNOPAZ3jScAAQACgiCEC1ZZ26CC4nLXLa6ConJV1jW6jbFYpO8lx2l4xqng061DjCzcAgMAtAIEITSLMUZFpTWu0JNXWKadhypljPu49tZwDUtPcAWfoWl2xUe3C0zRAACcB0EIZ1Tb4NSW/RWu0JNfVKajVfUe49ISo5X57W2u4RkJ6tMpThHhTEYEAAQHghAkSYcdtaeu9hSVacv+CjU43S/3WMPDNLCLzXWLa3h6gpJtUQGqGACAi0cQCkGNzibtPFTpmsm1sbBM+8o81/JJio1UZobdFXwGpNLUDABoWwhCIaDieIM2nZzCXnSiqbm63uk2Jswi9UmxnQo+6YlKS4ymqRkA0KYRhNoYY4z2Hq129fXkFZZp16Eqj3FxkREalpHg6u8ZkhavuCiamgEAoYUgFOSO1zu1eV+58r6zaGFZTYPHuG4dYjQ8I0FZGYnKzEhQr+RYhYdxtQcAENoIQkHmYMXxUzO5Csu09YBDjU2nNTVHhGlI1/gTU9i/ncqeFBsZoIoBAGi9CEKtWIOzSTsOViqvsFR5ReXKLyzT/jNsUJocF6msbgmu1ZoHpMbLGsEUdgAAzocg1IqUVddrU/GpBQu/KK7Q8Qb3pubwMIv6dY5zXenJzEhQFztNzQAAXAiCUIA0NRntOVrltlLz10eqPcbZoiJOrduTkaAhXe1qH8nHBgCAL/AXNUBmvJKv97aUeBzv0bG9ayZXVrcE9UiKVRhNzQAA+AVBKED6dbZp9c7DGtL11IKFw9ITlNjeGujSAAAIGRZjTt82E9/lcDgUHx+viooK2Ww2n71vdV2jrBFhase+XAAA+Fxz/35zRShA6PMBACDwuBwBAABCFkEIAACELIIQAAAIWQQhAAAQsghCAAAgZBGEAABAyCIIAQCAkEUQAgAAIYsgBAAAQhZBCAAAhCyCEAAACFkEIQAAELIIQgAAIGSxBfp5GGMkSQ6HI8CVAACA5jr5d/vk3/GzIQidR2VlpSQpLS0twJUAAABvVVZWKj4+/qzPW8z5olKIa2pq0oEDBxQXFyeLxeKT93Q4HEpLS1NxcbFsNptP3rO1aevnyPkFt7Z+flLbP0fOL/j5+xyNMaqsrFRqaqrCws7eCcQVofMICwtT165d/fLeNputzf4LflJbP0fOL7i19fOT2v45cn7Bz5/neK4rQSfRLA0AAEIWQQgAAISs8IceeuihQBcRisLDwzVmzBhFRLTdu5Nt/Rw5v+DW1s9PavvnyPkFv9ZwjjRLAwCAkMWtMQAAELIIQgAAIGQRhAAAQMgiCAEAgJBFEAqAZ599Vt26dVNUVJRGjhypDRs2BLqkZvnoo4907bXXKjU1VRaLRW+++abb88YYLViwQJ07d1Z0dLRycnK0e/dutzGlpaWaOHGibDab7Ha7pk2bpqqqqpY8jbPKzc3VJZdcori4OCUnJ+uGG27Qzp073cbU1tZqxowZ6tChg2JjY3XTTTfp0KFDbmOKioo0fvx4xcTEKDk5Wffdd58aGxtb8lTOaMmSJRo8eLBr8bLs7Gy99957rueD+dzOZOHChbJYLLrnnntcx4L9HB966CFZLBa3R9++fV3PB/v5SdL+/fv1X//1X+rQoYOio6M1aNAgbdy40fV8MP+e6datm8fnZ7FYNGPGDEnB//k5nU498MAD6t69u6Kjo9WzZ0/9+te/dtvrq1V+fgYtavny5cZqtZoXX3zRbN261UyfPt3Y7XZz6NChQJd2Xn//+9/NL3/5S7NixQojybzxxhtuzy9cuNDEx8ebN99803zxxRfmuuuuM927dzfHjx93jbnqqqvMkCFDzGeffWY+/vhj06tXL3Prrbe29Kmc0dixY81LL71ktmzZYgoKCsy4ceNMenq6qaqqco258847TVpamlm1apXZuHGj+f73v28uvfRS1/ONjY1m4MCBJicnx2zatMn8/e9/N0lJSWb+/PmBOCU3b7/9tvnb3/5mdu3aZXbu3Gl+8YtfmHbt2pktW7YYY4L73E63YcMG061bNzN48GAze/Zs1/FgP8cHH3zQDBgwwBw8eND1OHLkiOv5YD+/0tJSk5GRYaZMmWLWr19v9uzZY95//33z1VdfucYE8++Zw4cPu312H3zwgZFkVq9ebYwJ/s/vkUceMR06dDDvvvuu2bt3r3nttddMbGysWbRokWtMa/z8CEItbMSIEWbGjBmu751Op0lNTTW5ubkBrMp7pwehpqYmk5KSYn7729+6jpWXl5vIyEjzf//3f8YYY7Zt22Ykmc8//9w15r333jMWi8Xs37+/5YpvpsOHDxtJZu3atcaYE+fTrl0789prr7nGbN++3Ugy69atM8acCIthYWGmpKTENWbJkiXGZrOZurq6lj2BZkhISDAvvPBCmzq3yspK07t3b/PBBx+Y0aNHu4JQWzjHBx980AwZMuSMz7WF87v//vvNZZdddtbn29rvmdmzZ5uePXuapqamNvH5jR8/3kydOtXt2I033mgmTpxojGm9nx+3xlpQfX298vLylJOT4zoWFhamnJwcrVu3LoCVXby9e/eqpKTE7dzi4+M1cuRI17mtW7dOdrtdWVlZrjE5OTkKCwvT+vXrW7zm86moqJAkJSYmSpLy8vLU0NDgdo59+/ZVenq62zkOGjRInTp1co0ZO3asHA6Htm7d2oLVn5vT6dTy5ctVXV2t7OzsNnVuM2bM0Pjx493ORWo7n9/u3buVmpqqHj16aOLEiSoqKpLUNs7v7bffVlZWlm6++WYlJydr2LBhev75513Pt6XfM/X19frf//1fTZ06VRaLpU18fpdeeqlWrVqlXbt2SZK++OILffLJJ7r66qsltd7Pr+0uV9kKHT16VE6n0+1fYknq1KmTduzYEaCqfKOkpESSznhuJ58rKSlRcnKy2/MRERFKTEx0jWktmpqadM8992jUqFEaOHCgpBP1W61W2e12t7Gnn+OZ/hmcfC7QvvzyS2VnZ6u2tlaxsbF644031L9/fxUUFAT9uUnS8uXLlZ+fr88//9zjubbw+Y0cOVLLli1Tnz59dPDgQT388MP6t3/7N23ZsqVNnN+ePXu0ZMkSzZ07V7/4xS/0+eefa9asWbJarZo8eXKb+j3z5ptvqry8XFOmTJHUNv79nDdvnhwOh/r27avw8HA5nU498sgjmjhxoqTW+3eCIAScwYwZM7RlyxZ98skngS7Fp/r06aOCggJVVFTor3/9qyZPnqy1a9cGuiyfKC4u1uzZs/XBBx8oKioq0OX4xcn/s5akwYMHa+TIkcrIyNBf/vIXRUdHB7Ay32hqalJWVpYeffRRSdKwYcO0ZcsWLV26VJMnTw5wdb71xz/+UVdffbVSU1MDXYrP/OUvf9HLL7+sV155RQMGDFBBQYHuuecepaamturPj1tjLSgpKUnh4eEeswAOHTqklJSUAFXlGyfrP9e5paSk6PDhw27PNzY2qrS0tFWd/8yZM/Xuu+9q9erV6tq1q+t4SkqK6uvrVV5e7jb+9HM80z+Dk88FmtVqVa9evZSZmanc3FwNGTJEixYtahPnlpeXp8OHD2v48OGKiIhQRESE1q5dq8WLFysiIkKdOnUK+nM8nd1u1/e+9z199dVXbeIz7Ny5s/r37+92rF+/fq7bf23l90xhYaH++c9/6ic/+YnrWFv4/O677z7NmzdPt9xyiwYNGqTbbrtNc+bMUW5urqTW+/kRhFqQ1WpVZmamVq1a5TrW1NSkVatWKTs7O4CVXbzu3bsrJSXF7dwcDofWr1/vOrfs7GyVl5crLy/PNebDDz9UU1OTRo4c2eI1n84Yo5kzZ+qNN97Qhx9+qO7du7s9n5mZqXbt2rmd486dO1VUVOR2jl9++aXbf8gffPCBbDabxy/41qCpqUl1dXVt4tyuuOIKffnllyooKHA9srKyNHHiRNfXwX6Op6uqqtLXX3+tzp07t4nPcNSoUR5LVuzatUsZGRmS2sbvGUl66aWXlJycrPHjx7uOtYXPr6amRmFh7rEiPDxcTU1Nklrx5+eXFmyc1fLly01kZKRZtmyZ2bZtm7njjjuM3W53mwXQWlVWVppNmzaZTZs2GUnmiSeeMJs2bTKFhYXGmBPTIu12u3nrrbfM5s2bzfXXX3/GaZHDhg0z69evN5988onp3bt3q5jWaowxd911l4mPjzdr1qxxm+JaU1PjGnPnnXea9PR08+GHH5qNGzea7Oxsk52d7Xr+5PTWK6+80hQUFJiVK1eajh07torprfPmzTNr1641e/fuNZs3bzbz5s0zFovF/OMf/zDGBPe5nc13Z40ZE/zneO+995o1a9aYvXv3mk8//dTk5OSYpKQkc/jwYWNM8J/fhg0bTEREhHnkkUfM7t27zcsvv2xiYmLM//7v/7rGBPvvGafTadLT083999/v8Vywf36TJ082Xbp0cU2fX7FihUlKSjI///nPXWNa4+dHEAqAp59+2qSnpxur1WpGjBhhPvvss0CX1CyrV682kjwekydPNsacmBr5wAMPmE6dOpnIyEhzxRVXmJ07d7q9x7Fjx8ytt95qYmNjjc1mM7fffruprKwMwNl4OtO5STIvvfSSa8zx48fNz372M5OQkGBiYmLMj3/8Y3Pw4EG39/nmm2/M1VdfbaKjo01SUpK59957TUNDQwufjaepU6eajIwMY7VaTceOHc0VV1zhCkHGBPe5nc3pQSjYz3HChAmmc+fOxmq1mi5dupgJEya4rbET7OdnjDHvvPOOGThwoImMjDR9+/Y1zz33nNvzwf575v333zeSPGo2Jvg/P4fDYWbPnm3S09NNVFSU6dGjh/nlL3/pNrW/NX5+FmO+s+QjAABACKFHCAAAhCyCEAAACFkEIQAAELIIQgAAIGQRhAAAQMgiCAEAgJBFEAIAACGLIAQAAEIWQQgIcRaLRW+++WagyzijZcuWyW63n3PMQw89pKFDh7ZQRS3jlltu0S233BLoMoCQQBACgsyUKVNksVh05513ejw3Y8YMWSwWTZkyRZJ05MgR3XXXXUpPT1dkZKRSUlI0duxYffrpp67XHDx4UFdffXVLle/ypz/9SZdccoliYmIUFxen0aNH6913323xOk53ejAcf5CA3QAADG9JREFUM2aMLBbLWR9jxowJXLGneeGFF5SZmamYmBjZbDb98Ic/1MqVKwNdFtCqEYSAIJSWlqbly5fr+PHjrmO1tbV65ZVXlJ6e7jp20003adOmTfrTn/6kXbt26e2339aYMWN07Ngx15iUlBRFRka2aP3/7//9P/30pz/VhAkTtHnzZm3YsEGXXXaZrr/+ej3zzDMtWsv5rFixQgcPHtTBgwe1YcMGSdI///lP17EVK1ac8XUNDQ0tWaZmzpypWbNm6bbbbtOXX36pdevW6ZJLLtH48eP1/PPPt2gtQFDx2y5mAPxi8uTJ5vrrrzcDBw5025X75ZdfNoMHDzbXX3+9mTx5sikrKzOSzJo1a875fpLMG2+8YYwxZu/evUaSef31182YMWNMdHS0GTx4sPnXv/7l9ppPPvnEjB492kRHRxu73W6uvPJKU1paaow5sbv2o48+arp162aioqLM4MGDzWuvveZ67bp164wks3jxYo9a5s6da9q1a2eKioqMMca89NJLJj4+3m1Mbm6uSU5ONrGxsWbq1Knm/vvvN0OGDHEb8/zzz5u+ffuayMhI06dPH/Pss8+6nqurqzMzZswwKSkpJjIy0qSnp5tHH33UGGNMRkaG24a7GRkZbu978p/Ppk2b3I4fP37cSDLPP/+8a0PM3NxcU1tbayZPnuzahPL0Wowxpr6+3sycOdPYbDbToUMH88tf/tJMmDDBTJgwwTWmsbHRPPzwwyYjI8NER0eboUOHmjfffNP1/Jo1a4wkjw1KjTHmZz/7mYmKijIlJSXGGGOWLFliOnXq9P+3d/8xUdd/HMCfCtznEO6AGxhYTAniR8sLyHadZJFEXF0tm1Iz1iwpFaaSrhpOnTJxK2OAay0RHJdpRUibzqJNGZWytFGgxVDzkFFZnVOy4DwPuOf3D8ZnfDoodd99ky+vx8Z2n8/n/Xn/2mfcc597f+5YV1fHuLg4KorCxx57jOfPn9ecV19fT7PZTEVRGB8fz61bt3JwcFAzXofDQbvdzuDgYCYmJvLTTz/1a1+Im50EISEmmJEgVF5ezqysLHV/VlYWKyoq1CA0MDDA0NBQvvzyy/R4POPWN1YQSk5O5sGDB3n69GkuWrSIM2fOVH/huq2tjYqisKCggO3t7fz+++/51ltv8cKFCyTJ0tJSJicn87PPPqPT6WRtbS0VRVED2erVqxkaGqr5ReoRP//8MwGwoqKCpH8Qqquro6IorKmp4alTp7h+/XoaDAZNENqzZw9jYmLY0NDArq4uNjQ00GQy0eFwkCTffPNNxsbG8ssvv2R3dzePHDnC999/nyTpcrkIgLW1tfzll1/ocrk0/funIBQdHc3du3ezq6uLPT097OvrY0lJCVtbW9nV1UWHw0G9Xs/9+/er55aUlDAyMpL79+9nR0cHn3vuORoMBk0Q2rBhA++66y4eOnSITqeTO3fupE6n41dffUWSXLZsGU0m05i/Qu50OgmA77zzDsnhIKQoCi0WC48fP86vv/6a6enpnD9/vnrOoUOHGB4ezvfee49Op5ONjY2MjY3l66+/rhnvzJkz+dFHH/GHH37g8uXLGR4ezsuXL/v1QYibmQQhISaYkSDkcrmoKAq7u7vZ3d1NvV7PCxcuqEGIJPft28eIiAjq9XrOnTuX69at44kTJzT1jRWEampq1OMdHR0EwM7OTpLk4sWLmZGRMWbfPB4Pp02b5ncHKT8/n4sXLyZJ2mw2vzs4oxmNRhYUFJD0D0JWq5WFhYWa8haLRVNffHy8GmxGbNmyhVarlSS5atUqzp8/nz6fb8z2R8/HX/1TECouLh53XCPy8/OZl5enbptMJs3dMY/Hw+nTp6tB6M8//6Rer+e3336rqScvL48vvPACSTIzM5MWi2XM9nw+H/V6PdesWUNyOAgBYHt7u1qmra2NANRrIyMjg+Xl5Zp6qqurGRcXpxlvaWmpevzixYsEwObm5n+cAyFuJoH/k8/fhBD/dVFRUbDb7XA4HCAJu92OyMhITZmFCxfCbrfjyJEjOHbsGBobG7Ft2zbU1NSoC6rHYjab1dcxMTEAAJfLheTkZLS3tyM3N3fM886ePQu3243s7GzNfq/Xi7S0NHWb5PUOFwDQ2dnpt0jcarWiubkZANDf3w+n04n8/Hy89NJLapnBwUGEhYUBGF5snp2djaSkJNhsNjz++ON45JFHbqg/fzVnzhy/fZWVldi9ezd6enrg8Xjg9Xpx3333AQB+++03XLp0CRaLRS2vKArS09PV7dOnT8Pj8WDevHmaer1eL6xWq7p9PXMaHByMu+++W91OTU1FcHAwOjs7YTabcfLkSXzzzTfYuHGjWmZoaAherxeDg4PqvtHXiclkgk6ng8vluuZ+CHEzkCAkxAS2dOlSrFy5EgDw9ttvj1lGr9cjOzsb2dnZ2LhxI1588UVs2rTpb4NQUFCQ+nrKlCkAAJ/PB2D4TXQ8fX19AIBPPvkEt956q+bYyILsxMREHD16FF6vFzqdTlPm/Pnz+OOPP5CYmDhuG39npP3q6mpNuACAgIAAAEB6ejrOnTuHxsZGHD58GE8//TQefvhh7Nu374baHC0kJESz7XA4sH79elRUVODee++FwWBAaWkpTp06dc11jozp8OHDfkFXr9cDGJ7T+vp6DA4OIjBQ+2/93Llz8Hg81zynPp8P/f39KC8vh91u9zseEBCghqHR1wkwfK2MXCdCTBTy1JgQE5jNZoPX68XAwABycnKu6Zw777wT/f39N9ym2WxGU1PTuHUrioKenh4kJCRo/mJjYwEMf0dOX18fqqqq/M4vKytDUFAQFi5cOGb9KSkpOH78uGbfsWPH1Ne33HILZsyYga6uLr/24+Li1HJGoxHPPPMMqqurUVdXh4aGBly6dAnA8Jv70NDQ9U3KOFpaWpCZmYlly5YhLS0NCQkJOHv2rKa/ERERmjF5vV60tbWp27Nnz0ZgYCB+/PFHvzHddtttAIbntLe3F7W1tX59KCsrg16vx4IFC9R9V65cwcmTJ9XtEydO4MqVK0hJScHUqVORmpqKM2fO+LWXkJCgBmMh/l/IHSEhJrCAgAB0dnaqr0e7ePEicnNzsXTpUpjNZhgMBrS2tmLbtm148sknb7jNdevWYfbs2SgsLMSKFSug0+nQ3NyM3NxcREZG4pVXXsGaNWvg8/lw//334/Lly2hpaYHRaMSSJUtgtVpRVFSEV199FV6vFwsWLMDAwAD27NmD7du3o7KyUg1Nf1VUVITnn38ec+bMQUZGBvbu3YuOjg7cfvvtapmSkhKsXr0aYWFhsNlsuHr1KlpbW9Hb24u1a9eivLwcMTExSEtLw9SpU1FfX4/o6Gj1ixtnzZqFpqYmZGRkQFEURERE3PBc3XHHHWhoaEBTUxNiY2Oxa9cufPfdd0hJSdGMacuWLYiLi0N8fDzeeOMNuN1u9bjJZEJRURFWrlyJq1evwmq14vfff8fRo0cRFRWFZ599Fg899BCWL1+OoqIiuN1uPPHEE/B4PHj33XdRVVWFHTt2IDo6Wq1TURSsWLEC27dvBwAUFBQgMzNT/ahr06ZNWLRoEWbMmIGnnnoKANDe3o4zZ85g8+bNNzwfQtyU/uU1SkKI6zSyWHo8I4ulPR4Pi4uLmZ6ezrCwME6bNo1JSUncsGED3W63Wh5jLJYevRh45DH80YtgP//8c86dO5eKojA8PJw5OTns7e0lObw4t7KykklJSQwKCmJUVBRzcnL4xRdfaPq5a9cu3nPPPdTr9QwJCeG8efN44MABTZmxHp/funUrIyMjGRoayiVLlvC1117zW3y9d+9epqamUqfTMSIigg888AA//vhjkuTOnTuZmprKkJAQGo1GZmVlaRYiHzhwgAkJCQwMDLzux+cbGxs1+91uN/Py8mg0Gmkymbhq1SquXbtWs7DZ6/WysLCQBoOBJpOJxcXFfo/PDw0NsaysjImJiQwKCuL06dP56KOPsqWlRS3j8/lYVVXFtLQ0dU4ffPBBv0faRx6f//DDDzlr1iwqikKbzcaffvpJU+7gwYO0WCzU6/UMCwujxWJhbW3t345XURR+8MEHFGIimULe4KpFIYQQE86OHTuwefNm/Prrr/92V4S4KcgaISGEEEJMWhKEhBBCCDFpyUdjQgghhJi05I6QEEIIISYtCUJCCCGEmLQkCAkhhBBi0pIgJIQQQohJS4KQEEIIISYtCUJCCCGEmLQkCAkhhBBi0pIgJIQQQohJ6z8t3e0AvcAVSwAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['MSinceOldestTradeOpen']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Delinquencies\n", "The last set of plots looks at the effect of delinquencies. The first plot shows that much of the change due to the percentage of accounts that were never delinquent ('PercentTradesNeverDelq') occurs between 90% and 100%." ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['PercentTradesNeverDelq']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "'MaxDelq2PublicRecLast12M' measures the severity of the applicant's worst delinquency from the last 12 months of the public record. A value of 5 or below indicates that some delinquency has occurred, whether of unknown duration, 30/60/90/120 days delinquent, or a derogatory comment. " ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['MaxDelq2PublicRecLast12M']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "According to the last 'MSinceMostRecentDelq' plot, the effect of the most recent delinquency wears off after 21 months." ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "lrr.visualize(data, fb, ['MSinceMostRecentDelq']);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 3. Loan Officer: Prototypical explanations for HELOC use case\n", "\n", "We now show how to generate explanations in the form of selecting prototypical or similar user profiles to an applicant in question that a bank employee such as a loan officer may be interested in. This may help the employee understand the decision of an applicant's HELOC application being accepted or rejected in the context of other similar applications. Note that the selected prototypical applications are profiles that are part of the training set that has been used to train an AI model that predicts good or bad i.e. approved or rejected for these applications. In fact, the method used in this notebook can work even if we are given not just one but a set of user profiles for which we want to find similar profiles from a training dataset. Additionally, the method computes weights for each prototype showcasing its similarity to the user(s) in question.\n", "\n", "The prototypical explanations in AIX360 are obtained using the Protodash algorithm developed in the following work: [ProtoDash: Fast Interpretable Prototype Selection](https://arxiv.org/abs/1707.01212)\n", "\n", "We now provide a brief overview of the method. The method takes as input a datapoint (or group of datapoints) that we want to explain with respect to instances in a training set belonging to the same feature space. The method then tries to minimize the maximum mean discrepancy (MMD metric) between the datapoints we want to explain and a prespecified number of instances from the training set that it will select. In other words, it will try to select training instances that have the same distribution as the datapoints we want to explain. The method does greedy selection and has quality guarantees with it also returning importance weights for the chosen prototypical training instances indicative of how similar/representative they are.\n", "\n", "In this tutorial, we will see two examples of obtaining prototypes, one for a user whose HELOC application was approved and another for a user whose HELOC application was rejected. In each case, we showcase the top five prototypes from the training data along with how similar the feature values were for these prototypes.\n", "\n", "[Example 1. Obtaining similar samples as explanations for a HELOC applicant predicted as \"Good\"](#good)
\n", "[Example 2. Obtaining similar samples as explanations for a HELOC applicant predicted as \"Bad\"](#bad)
\n", "\n", "\n", "###### Why Protodash?\n", "Before we showcase the two examples we provide some motivation for using this method. The method selects applications from the training set that are similar in different ways to the user application we want to explain. For example, a users loan may be rejected justifiably because the number of satisfactory trades he performed were low similar to another rejected user, or because his/her debts were too high similar to a different rejected user. Either of these reasons in isolation may be sufficient for rejection and the method is able to surface a variety of such reasons through the selected prototypes. This is not the case using standard nearest neighbor techniques which use metrics such as euclidean distance, cosine similarity amongst others, where one might get the same type of explanation (i.e. applications with only low number of satisfactory trades). Protodash thus is able to provide a much more well rounded and comprehensive view of why the decision for the applicant may be justifiable.\n", "\n", "Another benefit of the method is that — since it does distribution matching between the user/users in question and those available in the training set — it could, in principle, be applied also in non-iid settings such as for time series data. Other approaches which find similar profiles using standard distance measures (viz. euclidean, cosine) do not have this property. Additionally, we can also highlight important features for the different prototypes that made them similar to the user/users in question.\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Import statements\n", "\n", "Import necessary libraries, frameworks and algorithms." ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import tensorflow as tf\n", "from keras.models import Sequential, Model, load_model, model_from_json\n", "from keras.layers import Dense\n", "import matplotlib.pyplot as plt\n", "from IPython.core.display import display, HTML\n", "\n", "from aix360.algorithms.contrastive import CEMExplainer, KerasClassifier\n", "from aix360.algorithms.protodash import ProtodashExplainer\n", "from aix360.datasets.heloc_dataset import HELOCDataset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Load HELOC dataset and show sample applicants" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/envs/aix360/lib/python3.6/site-packages/aix360/datasets/heloc_dataset.py:31: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df[col][df[col].isin([-7, -8, -9])] = 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Size of HELOC dataset: (10459, 24)\n", "Number of \"Good\" applicants: 5000\n", "Number of \"Bad\" applicants: 5459\n", "Sample Applicants:\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0123456789
ExternalRiskEstimate55616766815954685961
MSinceOldestTradeOpen14458661693331378814832479
MSinceMostRecentTradeOpen4155127117724
AverageMInFile8441247313278376513836
NumSatisfactoryTrades202928123125172419
NumTrades60Ever2DerogPubRec3401000000
NumTrades90Ever2DerogPubRec0401000000
PercentTradesNeverDelq83100100931009192838595
MSinceMostRecentDelq2-7-776-7193155
MaxDelq2PublicRecLast12M3076744644
MaxDelqEver5886866666
NumTotalTrades237930123226182719
NumTradesOpeninLast12M1043013113
PercentInstallTrades43674457254758442626
MSinceMostRecentInqexcl7days0000000000
NumInqLast6M0045104016
NumInqLast6Mexcl7days0044104016
NetFractionRevolvingBurden3305372516289286831
NetFractionInstallBurden-8-8668389937648-886
NumRevolvingTradesWBalance80463127275
NumInstallTradesWBalance1-824147213
NumBank2NatlTradesWHighUtilization1-813032231
PercentTradesWBalance69086918094100409062
RiskPerformanceBadBadBadBadBadBadGoodGoodBadBad
\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 6 7 8 9\n", "ExternalRiskEstimate 55 61 67 66 81 59 54 68 59 61\n", "MSinceOldestTradeOpen 144 58 66 169 333 137 88 148 324 79\n", "MSinceMostRecentTradeOpen 4 15 5 1 27 11 7 7 2 4\n", "AverageMInFile 84 41 24 73 132 78 37 65 138 36\n", "NumSatisfactoryTrades 20 2 9 28 12 31 25 17 24 19\n", "NumTrades60Ever2DerogPubRec 3 4 0 1 0 0 0 0 0 0\n", "NumTrades90Ever2DerogPubRec 0 4 0 1 0 0 0 0 0 0\n", "PercentTradesNeverDelq 83 100 100 93 100 91 92 83 85 95\n", "MSinceMostRecentDelq 2 -7 -7 76 -7 1 9 31 5 5\n", "MaxDelq2PublicRecLast12M 3 0 7 6 7 4 4 6 4 4\n", "MaxDelqEver 5 8 8 6 8 6 6 6 6 6\n", "NumTotalTrades 23 7 9 30 12 32 26 18 27 19\n", "NumTradesOpeninLast12M 1 0 4 3 0 1 3 1 1 3\n", "PercentInstallTrades 43 67 44 57 25 47 58 44 26 26\n", "MSinceMostRecentInqexcl7days 0 0 0 0 0 0 0 0 0 0\n", "NumInqLast6M 0 0 4 5 1 0 4 0 1 6\n", "NumInqLast6Mexcl7days 0 0 4 4 1 0 4 0 1 6\n", "NetFractionRevolvingBurden 33 0 53 72 51 62 89 28 68 31\n", "NetFractionInstallBurden -8 -8 66 83 89 93 76 48 -8 86\n", "NumRevolvingTradesWBalance 8 0 4 6 3 12 7 2 7 5\n", "NumInstallTradesWBalance 1 -8 2 4 1 4 7 2 1 3\n", "NumBank2NatlTradesWHighUtilization 1 -8 1 3 0 3 2 2 3 1\n", "PercentTradesWBalance 69 0 86 91 80 94 100 40 90 62\n", "RiskPerformance Bad Bad Bad Bad Bad Bad Good Good Bad Bad" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "heloc = HELOCDataset()\n", "df = heloc.dataframe()\n", "pd.set_option('display.max_rows', 500)\n", "pd.set_option('display.max_columns', 24)\n", "pd.set_option('display.width', 1000)\n", "print(\"Size of HELOC dataset:\", df.shape)\n", "print(\"Number of \\\"Good\\\" applicants:\", np.sum(df['RiskPerformance']=='Good'))\n", "print(\"Number of \\\"Bad\\\" applicants:\", np.sum(df['RiskPerformance']=='Bad'))\n", "print(\"Sample Applicants:\")\n", "df.head(10).transpose()" ] }, { "cell_type": "code", "execution_count": 54, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Distribution of ExternalRiskEstimate and NumSatisfactoryTrades columns:\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Plot (example) distributions for two features\n", "print(\"Distribution of ExternalRiskEstimate and NumSatisfactoryTrades columns:\")\n", "hist = df.hist(column=['ExternalRiskEstimate', 'NumSatisfactoryTrades'], bins=10)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 1: Process and Normalize HELOC dataset for training\n", "\n", "We will first process the HELOC dataset before using it to train an NN model that can predict the\n", "target variable RiskPerformance. The HELOC dataset is a tabular dataset with numerical values. However, some of the values are negative and need to be filtered. The processed data is stored in the file heloc.npz for easy access. The dataset is also normalized for training.\n", "\n", "The data processing and the type of model built in this case is different from the Data Scientist persona described above where rule based methods are showcased. This is the reason for going through these steps again for the Loan Officer persona." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### a. Process the dataset" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [], "source": [ "# Clean data and split dataset into train/test\n", "(Data, x_train, x_test, y_train_b, y_test_b) = heloc.split()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "\n", "#### b. Normalize the dataset" ] }, { "cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [], "source": [ "Z = np.vstack((x_train, x_test))\n", "Zmax = np.max(Z, axis=0)\n", "Zmin = np.min(Z, axis=0)\n", "\n", "#normalize an array of samples to range [-0.5, 0.5]\n", "def normalize(V):\n", " VN = (V - Zmin)/(Zmax - Zmin)\n", " VN = VN - 0.5\n", " return(VN)\n", " \n", "# rescale a sample to recover original values for normalized values. \n", "def rescale(X):\n", " return(np.multiply ( X + 0.5, (Zmax - Zmin) ) + Zmin)\n", "\n", "N = normalize(Z)\n", "xn_train = N[0:x_train.shape[0], :]\n", "xn_test = N[x_train.shape[0]:, :]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 2. Define and train a NN classifier\n", "\n", "Let us now build a loan approval model based on the HELOC dataset.\n", "\n", "#### a. Define NN architecture\n", "We now define the architecture of a 2-layer neural network classifier whose predictions we will try to interpret. " ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [], "source": [ "# nn with no softmax\n", "def nn_small():\n", " model = Sequential()\n", " model.add(Dense(10, input_dim=23, kernel_initializer='normal', activation='relu'))\n", " model.add(Dense(2, kernel_initializer='normal')) \n", " return model " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### b. Train the NN" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "dense_7 (Dense) (None, 10) 240 \n", "_________________________________________________________________\n", "dense_8 (Dense) (None, 2) 22 \n", "=================================================================\n", "Total params: 262\n", "Trainable params: 262\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Train accuracy: 0.7387545589625827\n", "Test accuracy: 0.7224473257698542\n" ] } ], "source": [ "# Set random seeds for repeatability\n", "np.random.seed(1) \n", "tf.set_random_seed(2) \n", "\n", "class_names = ['Bad', 'Good']\n", "\n", "# loss function\n", "def fn(correct, predicted):\n", " return tf.nn.softmax_cross_entropy_with_logits(labels=correct, logits=predicted)\n", "\n", "# compile and print model summary\n", "nn = nn_small()\n", "nn.compile(loss=fn, optimizer='adam', metrics=['accuracy'])\n", "nn.summary()\n", "\n", "\n", "# train model or load a trained model\n", "TRAIN_MODEL = False\n", "\n", "if (TRAIN_MODEL): \n", " nn.fit(xn_train, y_train_b, batch_size=128, epochs=500, verbose=1, shuffle=False)\n", " nn.save_weights(\"heloc_nnsmall.h5\") \n", "else: \n", " nn.load_weights(\"heloc_nnsmall.h5\")\n", " \n", "\n", "# evaluate model accuracy \n", "score = nn.evaluate(xn_train, y_train_b, verbose=0) #Compute training set accuracy\n", "#print('Train loss:', score[0])\n", "print('Train accuracy:', score[1])\n", "\n", "score = nn.evaluate(xn_test, y_test_b, verbose=0) #Compute test set accuracy\n", "#print('Test loss:', score[0])\n", "print('Test accuracy:', score[1])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 3: Obtain similar samples as explanations for a HELOC applicant predicted as \"Good\" (Example 1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### a. Normalize the data and chose a particular applicant, whose profile is displayed below." ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "p_train = nn.predict_classes(xn_train) # Use trained neural network to predict train points\n", "p_train = p_train.reshape((p_train.shape[0],1))\n", "\n", "z_train = np.hstack((xn_train, p_train)) # Store (normalized) instances that were predicted as Good\n", "z_train_good = z_train[z_train[:,-1]==1, :]\n", "\n", "zun_train = np.hstack((x_train, p_train)) # Store (unnormalized) instances that were predicted as Good \n", "zun_train_good = zun_train[zun_train[:,-1]==1, :]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us now consider applicant 8 whose loan was approved. Note that this applicant was also considered for the contrastive explainer, however, we now justify the approved status in a different manner using prototypical examples, which is arguably a better explanation for a bank employee." ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Chosen Sample: 8\n", "Prediction made by the model: Good\n", "Prediction probabilities: [[-0.1889221 0.29527372]]\n", "\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/envs/aix360/lib/python3.6/site-packages/keras/engine/sequential.py:247: UserWarning: Network returning invalid probability values. The last layer might not normalize predictions into probabilities (like softmax or sigmoid would).\n", " warnings.warn('Network returning invalid probability values. '\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0
ExternalRiskEstimate82
MSinceOldestTradeOpen280
MSinceMostRecentTradeOpen13
AverageMInFile102
NumSatisfactoryTrades22
NumTrades60Ever2DerogPubRec0
NumTrades90Ever2DerogPubRec0
PercentTradesNeverDelq91
MSinceMostRecentDelq26
MaxDelq2PublicRecLast12M6
MaxDelqEver6
NumTotalTrades23
NumTradesOpeninLast12M0
PercentInstallTrades9
MSinceMostRecentInqexcl7days0
NumInqLast6M0
NumInqLast6Mexcl7days0
NetFractionRevolvingBurden3
NetFractionInstallBurden0
NumRevolvingTradesWBalance4
NumInstallTradesWBalance1
NumBank2NatlTradesWHighUtilization1
PercentTradesWBalance42
RiskPerformanceGood
\n", "
" ], "text/plain": [ " 0\n", "ExternalRiskEstimate 82\n", "MSinceOldestTradeOpen 280\n", "MSinceMostRecentTradeOpen 13\n", "AverageMInFile 102\n", "NumSatisfactoryTrades 22\n", "NumTrades60Ever2DerogPubRec 0\n", "NumTrades90Ever2DerogPubRec 0\n", "PercentTradesNeverDelq 91\n", "MSinceMostRecentDelq 26\n", "MaxDelq2PublicRecLast12M 6\n", "MaxDelqEver 6\n", "NumTotalTrades 23\n", "NumTradesOpeninLast12M 0\n", "PercentInstallTrades 9\n", "MSinceMostRecentInqexcl7days 0\n", "NumInqLast6M 0\n", "NumInqLast6Mexcl7days 0\n", "NetFractionRevolvingBurden 3\n", "NetFractionInstallBurden 0\n", "NumRevolvingTradesWBalance 4\n", "NumInstallTradesWBalance 1\n", "NumBank2NatlTradesWHighUtilization 1\n", "PercentTradesWBalance 42\n", "RiskPerformance Good" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "source": [ "idx = 8\n", "\n", "X = xn_test[idx].reshape((1,) + xn_test[idx].shape)\n", "print(\"Chosen Sample:\", idx)\n", "print(\"Prediction made by the model:\", class_names[np.argmax(nn.predict_proba(X))])\n", "print(\"Prediction probabilities:\", nn.predict_proba(X))\n", "print(\"\")\n", "\n", "# attach the prediction made by the model to X\n", "X = np.hstack((X, nn.predict_classes(X).reshape((1,1))))\n", "\n", "Xun = x_test[idx].reshape((1,) + x_test[idx].shape) \n", "dfx = pd.DataFrame.from_records(Xun.astype('double')) # Create dataframe with original feature values\n", "dfx[23] = class_names[X[0, -1]]\n", "dfx.columns = df.columns\n", "dfx.transpose()\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### b. Find similar applicants predicted as \"good\" using the protodash explainer. " ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -2.0000e+04 4e+00 1e+00 1e+00\n", " 1: 1.8207e+01 -2.2985e+05 5e+01 1e+00 1e+00\n", " 2: -1.6771e+00 -1.4132e+06 3e+02 1e+00 1e+00\n", " 3: 6.4653e-01 -7.7669e+06 2e+03 1e+00 1e+00\n", " 4: 9.0963e-01 -1.6930e+08 3e+04 1e+00 1e+00\n", " 5: 6.8400e-01 -8.7461e+10 2e+07 1e+00 1e+00\n", " 6: 2.1065e+08 -1.7700e+18 2e+18 6e-13 9e-03\n", " 7: 2.1065e+08 -1.7700e+16 2e+16 6e-15 1e-03\n", " 8: 2.1065e+08 -1.7700e+14 2e+14 4e-16 3e-05\n", " 9: 2.1065e+08 -1.7706e+12 2e+12 2e-16 5e-07\n", "10: 2.1059e+08 -1.8270e+10 2e+10 2e-16 6e-09\n", "11: 2.0548e+08 -7.3263e+08 9e+08 2e-16 6e-10\n", "12: 5.4547e+06 -5.0769e+08 5e+08 2e-16 2e-11\n", "13: 2.4579e+06 -1.0151e+07 1e+07 3e-16 8e-13\n", "14: 3.9731e+05 -4.8259e+05 9e+05 2e-16 2e-13\n", "15: 5.6807e+04 -6.2926e+04 1e+05 2e-16 4e-14\n", "16: 8.0641e+03 -9.1700e+03 2e+04 1e-16 1e-14\n", "17: 1.1237e+03 -1.3430e+03 2e+03 8e-17 3e-14\n", "18: 1.4817e+02 -2.0491e+02 4e+02 9e-17 2e-15\n", "19: 1.5650e+01 -3.4597e+01 5e+01 2e-16 8e-16\n", "20: -6.5180e-01 -7.5158e+00 7e+00 3e-16 7e-16\n", "21: -2.1215e+00 -2.8262e+00 7e-01 1e-16 6e-17\n", "22: -2.2224e+00 -2.3257e+00 1e-01 5e-17 2e-17\n", "23: -2.2551e+00 -2.2713e+00 2e-02 8e-17 8e-17\n", "24: -2.2583e+00 -2.2599e+00 2e-03 3e-16 7e-17\n", "25: -2.2584e+00 -2.2585e+00 5e-05 9e-17 2e-16\n", "26: -2.2584e+00 -2.2584e+00 5e-07 8e-17 7e-17\n", "Optimal solution found.\n", " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -3.0000e+04 6e+00 1e+00 1e+00\n", " 1: 3.0722e+01 -4.4267e+05 9e+01 1e+00 1e+00\n", " 2: -1.6074e+00 -1.6114e+06 3e+02 1e+00 1e+00\n", " 3: 1.4698e+00 -5.8978e+06 1e+03 1e+00 1e+00\n", " 4: 5.1359e+00 -5.6757e+07 1e+04 1e+00 1e+00\n", " 5: 8.8032e+00 -6.9908e+09 1e+06 1e+00 1e+00\n", " 6: 1.8944e+08 -1.6526e+17 2e+17 6e-13 3e-04\n", " 7: 1.8944e+08 -1.6526e+15 2e+15 6e-15 2e-04\n", " 8: 1.8944e+08 -1.6526e+13 2e+13 2e-16 1e-06\n", " 9: 1.8943e+08 -1.6612e+11 2e+11 2e-16 2e-08\n", "10: 1.8825e+08 -2.5115e+09 3e+09 2e-16 5e-10\n", "11: 1.2280e+08 -5.4548e+08 7e+08 7e-17 1e-07\n", "12: 1.8756e+07 -9.4847e+07 1e+08 4e-16 2e-12\n", "13: 3.6747e+06 -5.2922e+06 9e+06 5e-17 5e-13\n", "14: 5.3007e+05 -5.8496e+05 1e+06 2e-16 2e-13\n", "15: 7.5911e+04 -8.5173e+04 2e+05 2e-16 2e-13\n", "16: 1.0792e+04 -1.2212e+04 2e+04 1e-16 4e-14\n", "17: 1.5104e+03 -1.7838e+03 3e+03 3e-16 7e-15\n", "18: 2.0196e+02 -2.6962e+02 5e+02 2e-16 6e-15\n", "19: 2.2751e+01 -4.4473e+01 7e+01 2e-16 2e-15\n", "20: 1.6485e-01 -9.1332e+00 9e+00 2e-16 4e-16\n", "21: -2.0349e+00 -3.0759e+00 1e+00 3e-16 4e-16\n", "22: -2.1758e+00 -2.4046e+00 2e-01 5e-17 2e-16\n", "23: -2.2521e+00 -2.3210e+00 7e-02 2e-16 7e-17\n", "24: -2.2594e+00 -2.2652e+00 6e-03 2e-16 5e-17\n", "25: -2.2601e+00 -2.2604e+00 3e-04 3e-16 7e-17\n", "26: -2.2601e+00 -2.2601e+00 3e-06 2e-16 9e-17\n", "27: -2.2601e+00 -2.2601e+00 3e-08 1e-16 3e-17\n", "Optimal solution found.\n", " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -4.0000e+04 8e+00 1e+00 1e+00\n", " 1: 4.4367e+01 -7.1824e+05 1e+02 1e+00 1e+00\n", " 2: -2.0468e+00 -3.1903e+06 7e+02 1e+00 1e+00\n", " 3: 1.2538e+01 -1.4991e+07 3e+03 1e+00 1e+00\n", " 4: 1.8503e+01 -3.6431e+08 7e+04 1e+00 1e+00\n", " 5: 1.4872e+01 -4.6590e+11 1e+08 1e+00 1e+00\n", " 6: 1.8484e+08 -7.2574e+18 7e+18 5e-13 9e-03\n", " 7: 1.8484e+08 -7.2574e+16 7e+16 5e-15 5e-03\n", " 8: 1.8484e+08 -7.2574e+14 7e+14 1e-16 8e-05\n", " 9: 1.8484e+08 -7.2586e+12 7e+12 3e-17 7e-07\n", "10: 1.8482e+08 -7.3749e+10 7e+10 2e-16 8e-09\n", "11: 1.8327e+08 -1.8914e+09 2e+09 2e-16 3e-10\n", "12: 6.6101e+07 -3.5884e+08 4e+08 3e-16 3e-08\n", "13: 1.4131e+07 -2.4415e+07 4e+07 2e-16 1e-09\n", "14: 2.0607e+06 -2.3295e+06 4e+06 2e-16 6e-13\n", "15: 2.9628e+05 -3.3354e+05 6e+05 2e-16 3e-13\n", "16: 4.2328e+04 -4.7437e+04 9e+04 2e-16 8e-14\n", "17: 5.9948e+03 -6.8520e+03 1e+04 1e-16 2e-14\n", "18: 8.3044e+02 -1.0092e+03 2e+03 4e-16 1e-14\n", "19: 1.0739e+02 -1.5582e+02 3e+02 3e-16 3e-15\n", "20: 1.0233e+01 -2.7124e+01 4e+01 2e-16 1e-15\n", "21: -1.3211e+00 -6.3304e+00 5e+00 1e-16 3e-16\n", "22: -2.2395e+00 -2.6971e+00 5e-01 2e-16 1e-16\n", "23: -2.2596e+00 -2.2756e+00 2e-02 3e-16 1e-16\n", "24: -2.2616e+00 -2.2630e+00 1e-03 1e-16 1e-16\n", "25: -2.2617e+00 -2.2617e+00 2e-05 9e-17 1e-16\n", "26: -2.2617e+00 -2.2617e+00 2e-07 2e-16 6e-17\n", "Optimal solution found.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/envs/aix360/lib/python3.6/site-packages/cvxopt/coneprog.py:2111: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n", " if 'x' in initvals:\n", "/anaconda3/envs/aix360/lib/python3.6/site-packages/cvxopt/coneprog.py:2116: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n", " if 's' in initvals:\n", "/anaconda3/envs/aix360/lib/python3.6/site-packages/cvxopt/coneprog.py:2131: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n", " if 'y' in initvals:\n", "/anaconda3/envs/aix360/lib/python3.6/site-packages/cvxopt/coneprog.py:2136: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n", " if 'z' in initvals:\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -5.0000e+04 1e+01 1e+00 1e+00\n", " 1: 6.4530e+01 -1.0740e+06 2e+02 1e+00 1e+00\n", " 2: -1.0387e+00 -3.8672e+06 8e+02 1e+00 1e+00\n", " 3: 1.7593e+01 -1.4129e+07 3e+03 1e+00 1e+00\n", " 4: 2.4754e+01 -1.7515e+08 4e+04 1e+00 1e+00\n", " 5: 2.8355e+01 -4.2312e+10 9e+06 1e+00 1e+00\n", " 6: 2.6599e+08 -9.5334e+17 1e+18 4e-13 1e-03\n", " 7: 2.6599e+08 -9.5334e+15 1e+16 4e-15 9e-04\n", " 8: 2.6599e+08 -9.5336e+13 1e+14 1e-16 6e-06\n", " 9: 2.6599e+08 -9.5545e+11 1e+12 1e-16 9e-08\n", "10: 2.6558e+08 -1.1640e+10 1e+10 1e-16 2e-09\n", "11: 2.4039e+08 -2.0164e+09 2e+09 2e-16 2e-08\n", "12: 2.9390e+07 -1.5952e+09 2e+09 2e-16 7e-09\n", "13: 1.0754e+07 -3.7180e+07 5e+07 2e-16 2e-10\n", "14: 1.6461e+06 -1.9697e+06 4e+06 2e-16 2e-12\n", "15: 2.3560e+05 -2.6053e+05 5e+05 1e-16 2e-13\n", "16: 3.3615e+04 -3.7633e+04 7e+04 2e-16 5e-14\n", "17: 4.7521e+03 -5.4485e+03 1e+04 2e-16 2e-14\n", "18: 6.5532e+02 -8.0583e+02 1e+03 1e-16 9e-15\n", "19: 8.3449e+01 -1.2556e+02 2e+02 9e-17 4e-15\n", "20: 7.2389e+00 -2.2354e+01 3e+01 2e-16 7e-16\n", "21: -1.5947e+00 -5.4973e+00 4e+00 2e-16 6e-16\n", "22: -2.2383e+00 -2.5578e+00 3e-01 2e-16 1e-16\n", "23: -2.2526e+00 -2.2903e+00 4e-02 2e-16 7e-17\n", "24: -2.2616e+00 -2.2685e+00 7e-03 3e-16 8e-17\n", "25: -2.2622e+00 -2.2630e+00 8e-04 2e-16 1e-16\n", "26: -2.2622e+00 -2.2622e+00 2e-05 2e-16 2e-16\n", "27: -2.2622e+00 -2.2622e+00 2e-07 2e-16 2e-16\n", "Optimal solution found.\n" ] } ], "source": [ "explainer = ProtodashExplainer()\n", "(W, S, setValues) = explainer.explain(X, z_train_good, m=5) # Return weights W, Prototypes S and objective function values" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### c. Display similar applicant user profiles and the extent to which they are similar to the chosen applicant as indicated by the last row in the table below labelled as \"Weight\"." ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
01234
ExternalRiskEstimate8589778373
MSinceOldestTradeOpen223379338789230
MSinceMostRecentTradeOpen13156265
AverageMInFile8725710910289
NumSatisfactoryTrades233164161
NumTrades60Ever2DerogPubRec00200
NumTrades90Ever2DerogPubRec00200
PercentTradesNeverDelq9110090100100
MSinceMostRecentDelq2606500
MaxDelq2PublicRecLast12M67676
MaxDelqEver68287
NumTotalTrades263214137
NumTradesOpeninLast12M00113
PercentInstallTrades933141718
MSinceMostRecentInqexcl7days10000
NumInqLast6M10112
NumInqLast6Mexcl7days10102
NetFractionRevolvingBurden402159
NetFractionInstallBurden000072
NumRevolvingTradesWBalance40139
NumInstallTradesWBalance10101
NumBank2NatlTradesWHighUtilization00017
PercentTradesWBalance500222353
RiskPerformanceGoodGoodGoodGoodGood
Weight0.7302220.06905620.09785930.04980470.0530578
\n", "
" ], "text/plain": [ " 0 1 2 3 4\n", "ExternalRiskEstimate 85 89 77 83 73\n", "MSinceOldestTradeOpen 223 379 338 789 230\n", "MSinceMostRecentTradeOpen 13 156 2 6 5\n", "AverageMInFile 87 257 109 102 89\n", "NumSatisfactoryTrades 23 3 16 41 61\n", "NumTrades60Ever2DerogPubRec 0 0 2 0 0\n", "NumTrades90Ever2DerogPubRec 0 0 2 0 0\n", "PercentTradesNeverDelq 91 100 90 100 100\n", "MSinceMostRecentDelq 26 0 65 0 0\n", "MaxDelq2PublicRecLast12M 6 7 6 7 6\n", "MaxDelqEver 6 8 2 8 7\n", "NumTotalTrades 26 3 21 41 37\n", "NumTradesOpeninLast12M 0 0 1 1 3\n", "PercentInstallTrades 9 33 14 17 18\n", "MSinceMostRecentInqexcl7days 1 0 0 0 0\n", "NumInqLast6M 1 0 1 1 2\n", "NumInqLast6Mexcl7days 1 0 1 0 2\n", "NetFractionRevolvingBurden 4 0 2 1 59\n", "NetFractionInstallBurden 0 0 0 0 72\n", "NumRevolvingTradesWBalance 4 0 1 3 9\n", "NumInstallTradesWBalance 1 0 1 0 1\n", "NumBank2NatlTradesWHighUtilization 0 0 0 1 7\n", "PercentTradesWBalance 50 0 22 23 53\n", "RiskPerformance Good Good Good Good Good\n", "Weight 0.730222 0.0690562 0.0978593 0.0498047 0.0530578" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfs = pd.DataFrame.from_records(zun_train_good[S, 0:-1].astype('double'))\n", "RP=[]\n", "for i in range(S.shape[0]):\n", " RP.append(class_names[z_train_good[S[i], -1]]) # Append class names\n", "dfs[23] = RP\n", "dfs.columns = df.columns \n", "dfs[\"Weight\"] = np.around(W, 5)/np.sum(np.around(W, 5)) # Calculate normalized importance weights\n", "dfs.transpose()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### d. Compute how similar a feature of a prototypical user is to the chosen applicant.\n", "The more similar the feature of prototypical user is to the applicant, the closer its weight is to 1. We can see below that several features for prototypes are quite similar to the chosen applicant. A human friendly explanation is provided thereafter." ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
01234
ExternalRiskEstimate0.590.290.420.840.21
MSinceOldestTradeOpen0.760.620.760.090.79
MSinceMostRecentTradeOpen1.000.090.830.890.87
AverageMInFile0.790.090.901.000.82
NumSatisfactoryTrades0.950.390.740.390.15
NumTrades60Ever2DerogPubRec1.001.000.081.001.00
NumTrades90Ever2DerogPubRec1.001.000.081.001.00
PercentTradesNeverDelq1.000.150.810.150.15
MSinceMostRecentDelq1.000.360.220.360.36
MaxDelq2PublicRecLast12M1.000.131.000.131.00
MaxDelqEver1.000.410.170.410.64
NumTotalTrades0.800.230.860.260.35
NumTradesOpeninLast12M1.001.000.400.400.06
PercentInstallTrades1.000.050.540.370.33
MSinceMostRecentInqexcl7days0.081.001.001.001.00
NumInqLast6M0.211.000.210.210.04
NumInqLast6Mexcl7days0.261.000.261.000.07
NetFractionRevolvingBurden0.960.880.960.920.09
NetFractionInstallBurden1.001.001.001.000.08
NumRevolvingTradesWBalance1.000.280.380.730.20
NumInstallTradesWBalance1.000.131.000.131.00
NumBank2NatlTradesWHighUtilization0.690.690.691.000.11
PercentTradesWBalance0.670.120.360.380.57
\n", "
" ], "text/plain": [ " 0 1 2 3 4\n", "ExternalRiskEstimate 0.59 0.29 0.42 0.84 0.21\n", "MSinceOldestTradeOpen 0.76 0.62 0.76 0.09 0.79\n", "MSinceMostRecentTradeOpen 1.00 0.09 0.83 0.89 0.87\n", "AverageMInFile 0.79 0.09 0.90 1.00 0.82\n", "NumSatisfactoryTrades 0.95 0.39 0.74 0.39 0.15\n", "NumTrades60Ever2DerogPubRec 1.00 1.00 0.08 1.00 1.00\n", "NumTrades90Ever2DerogPubRec 1.00 1.00 0.08 1.00 1.00\n", "PercentTradesNeverDelq 1.00 0.15 0.81 0.15 0.15\n", "MSinceMostRecentDelq 1.00 0.36 0.22 0.36 0.36\n", "MaxDelq2PublicRecLast12M 1.00 0.13 1.00 0.13 1.00\n", "MaxDelqEver 1.00 0.41 0.17 0.41 0.64\n", "NumTotalTrades 0.80 0.23 0.86 0.26 0.35\n", "NumTradesOpeninLast12M 1.00 1.00 0.40 0.40 0.06\n", "PercentInstallTrades 1.00 0.05 0.54 0.37 0.33\n", "MSinceMostRecentInqexcl7days 0.08 1.00 1.00 1.00 1.00\n", "NumInqLast6M 0.21 1.00 0.21 0.21 0.04\n", "NumInqLast6Mexcl7days 0.26 1.00 0.26 1.00 0.07\n", "NetFractionRevolvingBurden 0.96 0.88 0.96 0.92 0.09\n", "NetFractionInstallBurden 1.00 1.00 1.00 1.00 0.08\n", "NumRevolvingTradesWBalance 1.00 0.28 0.38 0.73 0.20\n", "NumInstallTradesWBalance 1.00 0.13 1.00 0.13 1.00\n", "NumBank2NatlTradesWHighUtilization 0.69 0.69 0.69 1.00 0.11\n", "PercentTradesWBalance 0.67 0.12 0.36 0.38 0.57" ] }, "execution_count": 63, "metadata": {}, "output_type": "execute_result" } ], "source": [ "z = z_train_good[S, 0:-1] # Store chosen prototypes\n", "eps = 1e-10 # Small constant defined to eliminate divide-by-zero errors\n", "fwt = np.zeros(z.shape)\n", "for i in range (z.shape[0]):\n", " for j in range(z.shape[1]):\n", " fwt[i, j] = np.exp(-1 * abs(X[0, j] - z[i,j])/(np.std(z[:, j])+eps)) # Compute feature similarity in [0,1]\n", " \n", "# move wts to a dataframe to display\n", "dfw = pd.DataFrame.from_records(np.around(fwt.astype('double'), 2))\n", "dfw.columns = df.columns[:-1]\n", "dfw.transpose() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Explanation:\n", "The above table depicts the five closest user profiles to the chosen applicant. Based on importance weight outputted by the method, we see that the prototype under column zero is the most representative user profile by far. This is (intuitively) confirmed from the feature similarity table above where more than 50% of the features (12 out of 23) of this prototype are identical to that of the chosen user whose prediction we want to explain. Also, the bank employee looking at the prototypical users and their features surmises that the approved applicant belongs to a group of approved users that have practically no debt (NetFractionInstallBurden). This justification gives the employee more confidence in approving the users application.\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Example 2. Obtaining similar samples as explanations for a HELOC applicant predicted as \"Bad\". \n", "We now consider a user 1272 whose loan was denied. We obtained a contrastive explanation for this user before. Similar to user 8, we now obtain exemplar based explanations for this user to help the bank employee understand the reasons for the rejection. Steps similar to example 1 are followed in this case too, where we first process the data, obtain prototypes and their importance weights, and finally showcase how similar the features are of these prototypes to the user we want to explain." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### a. Normalize the data and chose a particular applicant, whose profile is displayed below." ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [], "source": [ "z_train_bad = z_train[z_train[:,-1]==0, :]\n", "zun_train_bad = zun_train[zun_train[:,-1]==0, :]" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Chosen Sample: 1272\n", "Prediction made by the model: Bad\n", "Prediction probabilities: [[ 0.40682057 -0.391679 ]]\n", "\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0
ExternalRiskEstimate65
MSinceOldestTradeOpen256
MSinceMostRecentTradeOpen15
AverageMInFile52
NumSatisfactoryTrades17
NumTrades60Ever2DerogPubRec0
NumTrades90Ever2DerogPubRec0
PercentTradesNeverDelq100
MSinceMostRecentDelq0
MaxDelq2PublicRecLast12M7
MaxDelqEver8
NumTotalTrades19
NumTradesOpeninLast12M0
PercentInstallTrades29
MSinceMostRecentInqexcl7days2
NumInqLast6M5
NumInqLast6Mexcl7days5
NetFractionRevolvingBurden57
NetFractionInstallBurden79
NumRevolvingTradesWBalance2
NumInstallTradesWBalance4
NumBank2NatlTradesWHighUtilization2
PercentTradesWBalance60
RiskPerformanceBad
\n", "
" ], "text/plain": [ " 0\n", "ExternalRiskEstimate 65\n", "MSinceOldestTradeOpen 256\n", "MSinceMostRecentTradeOpen 15\n", "AverageMInFile 52\n", "NumSatisfactoryTrades 17\n", "NumTrades60Ever2DerogPubRec 0\n", "NumTrades90Ever2DerogPubRec 0\n", "PercentTradesNeverDelq 100\n", "MSinceMostRecentDelq 0\n", "MaxDelq2PublicRecLast12M 7\n", "MaxDelqEver 8\n", "NumTotalTrades 19\n", "NumTradesOpeninLast12M 0\n", "PercentInstallTrades 29\n", "MSinceMostRecentInqexcl7days 2\n", "NumInqLast6M 5\n", "NumInqLast6Mexcl7days 5\n", "NetFractionRevolvingBurden 57\n", "NetFractionInstallBurden 79\n", "NumRevolvingTradesWBalance 2\n", "NumInstallTradesWBalance 4\n", "NumBank2NatlTradesWHighUtilization 2\n", "PercentTradesWBalance 60\n", "RiskPerformance Bad" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "idx = 1272 #another user to try 2385\n", "\n", "X = xn_test[idx].reshape((1,) + xn_test[idx].shape)\n", "print(\"Chosen Sample:\", idx)\n", "print(\"Prediction made by the model:\", class_names[np.argmax(nn.predict_proba(X))])\n", "print(\"Prediction probabilities:\", nn.predict_proba(X))\n", "print(\"\")\n", "\n", "X = np.hstack((X, nn.predict_classes(X).reshape((1,1))))\n", "\n", "# move samples to a dataframe to display\n", "Xun = x_test[idx].reshape((1,) + x_test[idx].shape)\n", "dfx = pd.DataFrame.from_records(Xun.astype('double'))\n", "dfx[23] = class_names[X[0, -1]]\n", "dfx.columns = df.columns\n", "dfx.transpose()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### b. Find similar applicants predicted as \"bad\" using the protodash explainer. " ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -2.0000e+04 4e+00 1e+00 1e+00\n", " 1: 1.3951e+01 -1.8757e+05 4e+01 1e+00 1e+00\n", " 2: -1.0452e+00 -2.4808e+06 5e+02 1e+00 1e+00\n", " 3: 9.9094e-01 -3.7820e+07 8e+03 1e+00 1e+00\n", " 4: 1.2044e+00 -5.7710e+09 1e+06 1e+00 1e+00\n", " 5: 1.6105e+08 -1.3427e+17 1e+17 7e-13 7e-04\n", " 6: 1.6105e+08 -1.3427e+15 1e+15 7e-15 2e-04\n", " 7: 1.6105e+08 -1.3427e+13 1e+13 2e-16 4e-06\n", " 8: 1.6104e+08 -1.3473e+11 1e+11 3e-17 2e-08\n", " 9: 1.6063e+08 -1.8053e+09 2e+09 3e-16 6e-10\n", "10: 1.2950e+08 -3.8084e+08 5e+08 2e-16 1e-09\n", "11: 6.9589e+06 -2.2750e+08 2e+08 5e-16 8e-12\n", "12: 2.4924e+06 -4.9489e+06 7e+06 1e-16 5e-13\n", "13: 3.7960e+05 -4.1688e+05 8e+05 3e-17 4e-13\n", "14: 5.4362e+04 -6.0989e+04 1e+05 6e-17 2e-13\n", "15: 7.7281e+03 -8.7442e+03 2e+04 3e-16 3e-14\n", "16: 1.0814e+03 -1.2777e+03 2e+03 3e-17 4e-15\n", "17: 1.4452e+02 -1.9320e+02 3e+02 3e-16 9e-15\n", "18: 1.6236e+01 -3.1901e+01 5e+01 2e-16 2e-15\n", "19: 7.9417e-02 -6.5709e+00 7e+00 4e-16 4e-16\n", "20: -1.5034e+00 -2.2383e+00 7e-01 3e-16 2e-16\n", "21: -1.6411e+00 -1.7669e+00 1e-01 9e-17 7e-17\n", "22: -1.6773e+00 -1.6963e+00 2e-02 1e-16 1e-16\n", "23: -1.6801e+00 -1.6816e+00 1e-03 5e-17 4e-17\n", "24: -1.6802e+00 -1.6802e+00 2e-05 2e-16 6e-17\n", "25: -1.6802e+00 -1.6802e+00 2e-07 2e-16 2e-16\n", "Optimal solution found.\n", " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -3.0000e+04 6e+00 1e+00 1e+00\n", " 1: 2.2652e+01 -3.4494e+05 7e+01 1e+00 1e+00\n", " 2: -9.7166e-01 -1.5165e+06 3e+02 1e+00 1e+00\n", " 3: 8.8732e-01 -6.4545e+06 1e+03 1e+00 1e+00\n", " 4: 4.0619e+00 -9.5492e+07 2e+04 1e+00 1e+00\n", " 5: 6.8342e+00 -3.0797e+10 7e+06 1e+00 1e+00\n", " 6: 1.4054e+08 -6.7268e+17 7e+17 4e-13 2e-03\n", " 7: 1.4054e+08 -6.7268e+15 7e+15 3e-15 7e-04\n", " 8: 1.4054e+08 -6.7269e+13 7e+13 3e-16 2e-05\n", " 9: 1.4054e+08 -6.7332e+11 7e+11 2e-16 2e-07\n", "10: 1.4040e+08 -7.3721e+09 8e+09 3e-16 3e-09\n", "11: 1.2803e+08 -6.5498e+08 8e+08 1e-16 3e-10\n", "12: 1.0414e+07 -2.6146e+08 3e+08 2e-16 3e-10\n", "13: 3.1711e+06 -6.3976e+06 1e+07 9e-17 7e-12\n", "14: 4.8148e+05 -5.3517e+05 1e+06 2e-16 5e-13\n", "15: 6.8958e+04 -7.7139e+04 1e+05 1e-16 2e-13\n", "16: 9.8128e+03 -1.1070e+04 2e+04 2e-16 4e-14\n", "17: 1.3771e+03 -1.6135e+03 3e+03 3e-16 2e-14\n", "18: 1.8573e+02 -2.4246e+02 4e+02 1e-16 5e-15\n", "19: 2.1713e+01 -3.9393e+01 6e+01 1e-16 4e-15\n", "20: 7.1800e-01 -7.7941e+00 9e+00 2e-16 5e-16\n", "21: -1.4375e+00 -2.4351e+00 1e+00 1e-16 2e-16\n", "22: -1.6114e+00 -1.8294e+00 2e-01 2e-16 1e-16\n", "23: -1.6765e+00 -1.7151e+00 4e-02 1e-16 9e-17\n", "24: -1.6822e+00 -1.6854e+00 3e-03 2e-16 2e-16\n", "25: -1.6824e+00 -1.6824e+00 6e-05 5e-16 1e-16\n", "26: -1.6824e+00 -1.6824e+00 6e-07 7e-17 4e-17\n", "Optimal solution found.\n", " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -4.0000e+04 8e+00 1e+00 1e+00\n", " 1: 3.1518e+01 -5.1960e+05 1e+02 1e+00 1e+00\n", " 2: -5.3941e-01 -2.2190e+06 5e+02 1e+00 1e+00\n", " 3: -5.5212e-01 -8.2651e+06 2e+03 1e+00 1e+00\n", " 4: 8.1060e-01 -7.5932e+07 2e+04 1e+00 1e+00\n", " 5: 2.5556e+00 -6.5290e+09 1e+06 1e+00 1e+00\n", " 6: 3.5093e+08 -1.5662e+17 2e+17 9e-13 3e-04\n", " 7: 3.5093e+08 -1.5662e+15 2e+15 9e-15 1e-04\n", " 8: 3.5093e+08 -1.5663e+13 2e+13 2e-16 2e-06\n", " 9: 3.5088e+08 -1.5782e+11 2e+11 2e-16 3e-08\n", "10: 3.4591e+08 -2.7463e+09 3e+09 2e-16 8e-10\n", "11: 1.5618e+08 -4.5360e+08 6e+08 1e-16 1e-08\n", "12: 2.5039e+07 -5.2066e+07 8e+07 2e-16 3e-12\n", "13: 3.9788e+06 -4.5353e+06 9e+06 2e-16 5e-13\n", "14: 5.7260e+05 -6.4450e+05 1e+06 1e-16 1e-13\n", "15: 8.1978e+04 -9.1397e+04 2e+05 1e-16 2e-13\n", "16: 1.1669e+04 -1.3145e+04 2e+04 9e-17 3e-14\n", "17: 1.6394e+03 -1.9143e+03 4e+03 4e-16 9e-15\n", "18: 2.2187e+02 -2.8701e+02 5e+02 2e-16 4e-15\n", "19: 2.6316e+01 -4.6341e+01 7e+01 1e-16 2e-15\n", "20: 1.1314e+00 -9.0235e+00 1e+01 2e-16 8e-16\n", "21: -1.4923e+00 -2.7146e+00 1e+00 2e-16 4e-16\n", "22: -1.6504e+00 -1.7666e+00 1e-01 2e-16 1e-16\n", "23: -1.6819e+00 -1.6990e+00 2e-02 1e-16 2e-16\n", "24: -1.6844e+00 -1.6860e+00 2e-03 3e-16 9e-17\n", "25: -1.6845e+00 -1.6845e+00 5e-05 1e-16 5e-17\n", "26: -1.6845e+00 -1.6845e+00 5e-07 6e-17 9e-17\n", "Optimal solution found.\n", " pcost dcost gap pres dres\n", " 0: 0.0000e+00 -5.0000e+04 1e+01 1e+00 1e+00\n", " 1: 4.2777e+01 -7.4034e+05 1e+02 1e+00 1e+00\n", " 2: -4.0907e-01 -3.0255e+06 6e+02 1e+00 1e+00\n", " 3: 3.2489e+00 -1.1962e+07 2e+03 1e+00 1e+00\n", " 4: 1.3141e+01 -1.5965e+08 3e+04 1e+00 1e+00\n", " 5: 2.0375e+01 -5.8520e+10 1e+07 1e+00 1e+00\n", " 6: 1.4807e+08 -1.2576e+18 1e+18 4e-13 3e-03\n", " 7: 1.4807e+08 -1.2576e+16 1e+16 4e-15 1e-03\n", " 8: 1.4807e+08 -1.2576e+14 1e+14 2e-16 2e-05\n", " 9: 1.4807e+08 -1.2588e+12 1e+12 2e-16 2e-07\n", "10: 1.4795e+08 -1.3762e+10 1e+10 2e-16 2e-09\n", "11: 1.3813e+08 -1.2350e+09 1e+09 1e-16 9e-10\n", "12: 1.4061e+07 -5.6498e+08 6e+08 3e-16 8e-11\n", "13: 3.8779e+06 -1.2907e+07 2e+07 2e-16 2e-12\n", "14: 5.8014e+05 -6.7599e+05 1e+06 2e-16 5e-13\n", "15: 8.2943e+04 -9.1922e+04 2e+05 2e-16 2e-13\n", "16: 1.1808e+04 -1.3283e+04 3e+04 2e-16 5e-14\n", "17: 1.6603e+03 -1.9330e+03 4e+03 8e-17 1e-14\n", "18: 2.2530e+02 -2.8932e+02 5e+02 1e-16 6e-15\n", "19: 2.7008e+01 -4.6485e+01 7e+01 2e-16 3e-15\n", "20: 1.3453e+00 -8.9445e+00 1e+01 1e-16 7e-16\n", "21: -1.3724e+00 -2.6264e+00 1e+00 1e-16 3e-16\n", "22: -1.5360e+00 -1.9467e+00 4e-01 5e-17 2e-16\n", "23: -1.6708e+00 -1.8638e+00 2e-01 2e-16 1e-16\n", "24: -1.6830e+00 -1.6970e+00 1e-02 3e-16 1e-16\n", "25: -1.6847e+00 -1.6856e+00 9e-04 2e-16 2e-16\n", "26: -1.6848e+00 -1.6848e+00 4e-05 1e-16 1e-16\n", "27: -1.6848e+00 -1.6848e+00 6e-07 3e-16 1e-16\n", "Optimal solution found.\n" ] } ], "source": [ "(W, S, setValues) = explainer.explain(X, z_train_bad, m=5) # Return weights W, Prototypes S and objective function values" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### c. Display similar applicant user profiles and the extent to which they are similar to the chosen applicant as indicated by the last row in the table below labelled as \"Weight\"." ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
01234
ExternalRiskEstimate736164550
MSinceOldestTradeOpen19112585194383
MSinceMostRecentTradeOpen177026383
AverageMInFile533213100383
NumSatisfactoryTrades1952181
NumTrades60Ever2DerogPubRec01001
NumTrades90Ever2DerogPubRec01001
PercentTradesNeverDelq10010010084100
MSinceMostRecentDelq00010
MaxDelq2PublicRecLast12M77746
MaxDelqEver88868
NumTotalTrades2069111
NumTradesOpeninLast12M03800
PercentInstallTrades25603342100
MSinceMostRecentInqexcl7days000230
NumInqLast6M016601
NumInqLast6Mexcl7days016601
NetFractionRevolvingBurden3123265840
NetFractionInstallBurden78830480
NumRevolvingTradesWBalance41250
NumInstallTradesWBalance33330
NumBank2NatlTradesWHighUtilization11130
PercentTradesWBalance54100711000
RiskPerformanceBadBadBadBadBad
Weight0.7817630.08225250.05739460.06428440.0143057
\n", "
" ], "text/plain": [ " 0 1 2 3 4\n", "ExternalRiskEstimate 73 61 64 55 0\n", "MSinceOldestTradeOpen 191 125 85 194 383\n", "MSinceMostRecentTradeOpen 17 7 0 26 383\n", "AverageMInFile 53 32 13 100 383\n", "NumSatisfactoryTrades 19 5 2 18 1\n", "NumTrades60Ever2DerogPubRec 0 1 0 0 1\n", "NumTrades90Ever2DerogPubRec 0 1 0 0 1\n", "PercentTradesNeverDelq 100 100 100 84 100\n", "MSinceMostRecentDelq 0 0 0 1 0\n", "MaxDelq2PublicRecLast12M 7 7 7 4 6\n", "MaxDelqEver 8 8 8 6 8\n", "NumTotalTrades 20 6 9 11 1\n", "NumTradesOpeninLast12M 0 3 8 0 0\n", "PercentInstallTrades 25 60 33 42 100\n", "MSinceMostRecentInqexcl7days 0 0 0 23 0\n", "NumInqLast6M 0 1 66 0 1\n", "NumInqLast6Mexcl7days 0 1 66 0 1\n", "NetFractionRevolvingBurden 31 232 65 84 0\n", "NetFractionInstallBurden 78 83 0 48 0\n", "NumRevolvingTradesWBalance 4 1 2 5 0\n", "NumInstallTradesWBalance 3 3 3 3 0\n", "NumBank2NatlTradesWHighUtilization 1 1 1 3 0\n", "PercentTradesWBalance 54 100 71 100 0\n", "RiskPerformance Bad Bad Bad Bad Bad\n", "Weight 0.781763 0.0822525 0.0573946 0.0642844 0.0143057" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# move samples to a dataframe to display\n", "dfs = pd.DataFrame.from_records(zun_train_bad[S, 0:-1].astype('double'))\n", "RP=[]\n", "for i in range(S.shape[0]):\n", " RP.append(class_names[z_train_bad[S[i], -1]]) # Append class names\n", "dfs[23] = RP\n", "dfs.columns = df.columns \n", "dfs[\"Weight\"] = np.around(W, 5)/np.sum(np.around(W, 5)) # Compute normalized importance weights for prototypes\n", "dfs.transpose()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### d. Compute how similar a feature of a prototypical user is to the chosen applicant.\n", "The more similar the feature of prototypical user is to the applicant, the closer its weight is to 1. We can see below that several features for prototypes are quite similar to the chosen applicant. Following this table we provide human friendly explanation based on this table." ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
01234
ExternalRiskEstimate0.730.860.960.680.08
MSinceOldestTradeOpen0.530.280.190.550.29
MSinceMostRecentTradeOpen0.990.950.900.930.08
AverageMInFile0.990.860.750.700.09
NumSatisfactoryTrades0.780.220.150.880.13
NumTrades60Ever2DerogPubRec1.000.131.001.000.13
NumTrades90Ever2DerogPubRec1.000.131.001.000.13
PercentTradesNeverDelq1.001.001.000.081.00
MSinceMostRecentDelq1.001.001.000.081.00
MaxDelq2PublicRecLast12M1.001.001.000.080.42
MaxDelqEver1.001.001.000.081.00
NumTotalTrades0.850.130.200.280.06
NumTradesOpeninLast12M1.000.380.081.001.00
PercentInstallTrades0.860.310.860.610.07
MSinceMostRecentInqexcl7days0.800.800.800.100.80
NumInqLast6M0.830.860.100.830.86
NumInqLast6Mexcl7days0.830.860.100.830.86
NetFractionRevolvingBurden0.720.110.910.710.49
NetFractionInstallBurden0.970.900.110.420.11
NumRevolvingTradesWBalance0.340.581.000.200.34
NumInstallTradesWBalance0.430.430.430.430.04
NumBank2NatlTradesWHighUtilization0.360.360.360.360.13
PercentTradesWBalance0.850.340.740.340.20
\n", "
" ], "text/plain": [ " 0 1 2 3 4\n", "ExternalRiskEstimate 0.73 0.86 0.96 0.68 0.08\n", "MSinceOldestTradeOpen 0.53 0.28 0.19 0.55 0.29\n", "MSinceMostRecentTradeOpen 0.99 0.95 0.90 0.93 0.08\n", "AverageMInFile 0.99 0.86 0.75 0.70 0.09\n", "NumSatisfactoryTrades 0.78 0.22 0.15 0.88 0.13\n", "NumTrades60Ever2DerogPubRec 1.00 0.13 1.00 1.00 0.13\n", "NumTrades90Ever2DerogPubRec 1.00 0.13 1.00 1.00 0.13\n", "PercentTradesNeverDelq 1.00 1.00 1.00 0.08 1.00\n", "MSinceMostRecentDelq 1.00 1.00 1.00 0.08 1.00\n", "MaxDelq2PublicRecLast12M 1.00 1.00 1.00 0.08 0.42\n", "MaxDelqEver 1.00 1.00 1.00 0.08 1.00\n", "NumTotalTrades 0.85 0.13 0.20 0.28 0.06\n", "NumTradesOpeninLast12M 1.00 0.38 0.08 1.00 1.00\n", "PercentInstallTrades 0.86 0.31 0.86 0.61 0.07\n", "MSinceMostRecentInqexcl7days 0.80 0.80 0.80 0.10 0.80\n", "NumInqLast6M 0.83 0.86 0.10 0.83 0.86\n", "NumInqLast6Mexcl7days 0.83 0.86 0.10 0.83 0.86\n", "NetFractionRevolvingBurden 0.72 0.11 0.91 0.71 0.49\n", "NetFractionInstallBurden 0.97 0.90 0.11 0.42 0.11\n", "NumRevolvingTradesWBalance 0.34 0.58 1.00 0.20 0.34\n", "NumInstallTradesWBalance 0.43 0.43 0.43 0.43 0.04\n", "NumBank2NatlTradesWHighUtilization 0.36 0.36 0.36 0.36 0.13\n", "PercentTradesWBalance 0.85 0.34 0.74 0.34 0.20" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "z = z_train_bad[S, 0:-1] # Store the prototypes\n", "eps = 1e-10 # Small constant to guard against divide by zero errors\n", "fwt = np.zeros(z.shape)\n", "for i in range (z.shape[0]): # Compute feature similarity for each prototype\n", " for j in range(z.shape[1]):\n", " fwt[i, j] = np.exp(-1 * abs(X[0, j] - z[i,j])/(np.std(z[:, j])+eps))\n", " \n", "# move wts to a dataframe to display\n", "dfw = pd.DataFrame.from_records(np.around(fwt.astype('double'), 2))\n", "dfw.columns = df.columns[:-1]\n", "dfw.transpose() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Explanation:\n", "Here again, the above table depicts the five closest user profiles to the chosen applicant. Based on importance weight outputted by the method we see that the prototype under column zero is the most representative user profile by far. This is (intuitively) confirmed from the feature similarity table above where 10 features out of 23 of this prototype are highly similar (>0.9) to that of the user we want to explain. Also the bank employee can see that the applicant belongs to a group of rejected applicants with similar deliquency behavior. Realizing that the user also poses similar risk as these other applicants whose loan was rejected, the employee takes the more conservative decision of rejecting the users application as well." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 4. Customer: Contrastive explanations for HELOC Use Case\n", "\n", "We now demonstrate how to compute contrastive explanations using AIX360 and how such explanations can help home owners understand the decisions made by AI models that approve or reject their HELOC applications. \n", "\n", "Typically, home owners would like to understand why they do not qualify for a line of credit and if so what changes in their application would qualify them. On the other hand, if they qualified, they might want to know what factors led to the approval of their application. \n", "\n", "In this context, contrastive explanations provide information to applicants about what minimal changes to their profile would have changed the decision of the AI model from reject to accept or vice-versa (_pertinent negatives_). For example, increasing the number of satisfactory trades to a certain value may have led to the acceptance of the application everything else being the same. \n", "\n", "The method presented here also highlights a minimal set of features and their values that would still maintain the original decision (_pertinent positives_). For example, for an applicant whose HELOC application was approved, the \n", "explanation may say that even if the number of satisfactory trades was reduced to a lower number, the loan would have still gotten through.\n", "\n", "Additionally, organizations (Banks, financial institutions, etc.) would like to understand trends in the behavior of their AI models in approving loan applications, which could be done by studying contrastive explanations for individuals whose loans were either accepted or rejected. Looking at the aggregate statistics of pertinent positives for approved applicants the organization can get insight into what minimal set of features and their values play an important role in acceptances. While studying the aggregate statistics of pertinent negatives the organization can get insight into features that could change the status of rejected applicants and potentially uncover ways that an applicant may game the system by changing potentially non-important features that could alter the models outcome. \n", "\n", "The contrastive explanations in AIX360 are implemented using the algorithm developed in the following work:\n", "###### [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://arxiv.org/abs/1802.07623)\n", "\n", "We now provide a brief overview of the method. As mentioned above the algorithm outputs a contrastive explanation which consists of two parts: a) pertinent negatives (PNs) and b) pertinent positives (PPs). PNs identify a minimal set of features which if altered would change the classification of the original input. For example, in the loan case if a person's credit score is increased their loan application status may change from reject to accept. The manner in which the method accomplishes this is by optimizing a change in the prediction probability loss while enforcing an elastic norm constraint that results in minimal change of features and their values. Optionally, an auto-encoder may also be used to force these minimal changes to produce realistic PNs. PPs on the other hand identify a minimal set of features and their values that are sufficient to yield the original input's classification. For example, an individual's loan may still be accepted if the salary was 50K as opposed to 100K. Here again we have an elastic norm term so that the amount of information needed is minimal, however, the first loss term in this case tries to make the original input's class to be the winning class. For a more in-depth discussion, please refer to the above work.\n", "\n", "\n", "The three main steps to obtain a contrastive explanation are shown below. The first two steps are more about processing the data and building an AI model while the third step computes the actual explanation. \n", "\n", " [Step 1. Process and Normalize HELOC dataset for training](#c1)
\n", " [Step 2. Define and train a NN classifier](#c2)
\n", " [Step 3. Compute contrastive explanations for a few applicants](#c3)
\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Load HELOC dataset and show sample applicants" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/envs/aix360/lib/python3.6/site-packages/aix360/datasets/heloc_dataset.py:31: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df[col][df[col].isin([-7, -8, -9])] = 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Size of HELOC dataset: (10459, 24)\n", "Number of \"Good\" applicants: 5000\n", "Number of \"Bad\" applicants: 5459\n", "Sample Applicants:\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0123456789
ExternalRiskEstimate55616766815954685961
MSinceOldestTradeOpen14458661693331378814832479
MSinceMostRecentTradeOpen4155127117724
AverageMInFile8441247313278376513836
NumSatisfactoryTrades202928123125172419
NumTrades60Ever2DerogPubRec3401000000
NumTrades90Ever2DerogPubRec0401000000
PercentTradesNeverDelq83100100931009192838595
MSinceMostRecentDelq2-7-776-7193155
MaxDelq2PublicRecLast12M3076744644
MaxDelqEver5886866666
NumTotalTrades237930123226182719
NumTradesOpeninLast12M1043013113
PercentInstallTrades43674457254758442626
MSinceMostRecentInqexcl7days0000000000
NumInqLast6M0045104016
NumInqLast6Mexcl7days0044104016
NetFractionRevolvingBurden3305372516289286831
NetFractionInstallBurden-8-8668389937648-886
NumRevolvingTradesWBalance80463127275
NumInstallTradesWBalance1-824147213
NumBank2NatlTradesWHighUtilization1-813032231
PercentTradesWBalance69086918094100409062
RiskPerformanceBadBadBadBadBadBadGoodGoodBadBad
\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 6 7 8 9\n", "ExternalRiskEstimate 55 61 67 66 81 59 54 68 59 61\n", "MSinceOldestTradeOpen 144 58 66 169 333 137 88 148 324 79\n", "MSinceMostRecentTradeOpen 4 15 5 1 27 11 7 7 2 4\n", "AverageMInFile 84 41 24 73 132 78 37 65 138 36\n", "NumSatisfactoryTrades 20 2 9 28 12 31 25 17 24 19\n", "NumTrades60Ever2DerogPubRec 3 4 0 1 0 0 0 0 0 0\n", "NumTrades90Ever2DerogPubRec 0 4 0 1 0 0 0 0 0 0\n", "PercentTradesNeverDelq 83 100 100 93 100 91 92 83 85 95\n", "MSinceMostRecentDelq 2 -7 -7 76 -7 1 9 31 5 5\n", "MaxDelq2PublicRecLast12M 3 0 7 6 7 4 4 6 4 4\n", "MaxDelqEver 5 8 8 6 8 6 6 6 6 6\n", "NumTotalTrades 23 7 9 30 12 32 26 18 27 19\n", "NumTradesOpeninLast12M 1 0 4 3 0 1 3 1 1 3\n", "PercentInstallTrades 43 67 44 57 25 47 58 44 26 26\n", "MSinceMostRecentInqexcl7days 0 0 0 0 0 0 0 0 0 0\n", "NumInqLast6M 0 0 4 5 1 0 4 0 1 6\n", "NumInqLast6Mexcl7days 0 0 4 4 1 0 4 0 1 6\n", "NetFractionRevolvingBurden 33 0 53 72 51 62 89 28 68 31\n", "NetFractionInstallBurden -8 -8 66 83 89 93 76 48 -8 86\n", "NumRevolvingTradesWBalance 8 0 4 6 3 12 7 2 7 5\n", "NumInstallTradesWBalance 1 -8 2 4 1 4 7 2 1 3\n", "NumBank2NatlTradesWHighUtilization 1 -8 1 3 0 3 2 2 3 1\n", "PercentTradesWBalance 69 0 86 91 80 94 100 40 90 62\n", "RiskPerformance Bad Bad Bad Bad Bad Bad Good Good Bad Bad" ] }, "execution_count": 69, "metadata": {}, "output_type": "execute_result" } ], "source": [ "heloc = HELOCDataset()\n", "df = heloc.dataframe()\n", "pd.set_option('display.max_rows', 500)\n", "pd.set_option('display.max_columns', 24)\n", "pd.set_option('display.width', 1000)\n", "print(\"Size of HELOC dataset:\", df.shape)\n", "print(\"Number of \\\"Good\\\" applicants:\", np.sum(df['RiskPerformance']=='Good'))\n", "print(\"Number of \\\"Bad\\\" applicants:\", np.sum(df['RiskPerformance']=='Bad'))\n", "print(\"Sample Applicants:\")\n", "df.head(10).transpose()" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Distribution of ExternalRiskEstimate and NumSatisfactoryTrades columns:\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Plot (example) distributions for two features\n", "print(\"Distribution of ExternalRiskEstimate and NumSatisfactoryTrades columns:\")\n", "hist = df.hist(column=['ExternalRiskEstimate', 'NumSatisfactoryTrades'], bins=10)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 1. Process and Normalize HELOC dataset for training\n", "\n", "We will first process the HELOC dataset before using it to train an NN model that can predict the\n", "target variable RiskPerformance. The HELOC dataset is a tabular dataset with numerical values. However, some of the values are negative and need to be filtered. The processed data is stored in the file heloc.npz for easy access. The dataset is also normalized for training.\n", "\n", "The data processing and model building is very similar to the Loan Officer persona above, where ProtoDash was the method of choice. We repeat these steps here so that both the use cases can be run independently." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### a. Process the dataset" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [], "source": [ "# Clean data and split dataset into train/test\n", "PROCESS_DATA = False\n", "\n", "if (PROCESS_DATA): \n", " (Data, x_train, x_test, y_train_b, y_test_b) = heloc.split()\n", " np.savez('heloc.npz', Data=Data, x_train=x_train, x_test=x_test, y_train_b=y_train_b, y_test_b=y_test_b)\n", "else:\n", " heloc = np.load('heloc.npz', allow_pickle = True)\n", " Data = heloc['Data']\n", " x_train = heloc['x_train']\n", " x_test = heloc['x_test']\n", " y_train_b = heloc['y_train_b']\n", " y_test_b = heloc['y_test_b']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "\n", "#### b. Normalize the dataset" ] }, { "cell_type": "code", "execution_count": 72, "metadata": {}, "outputs": [], "source": [ "Z = np.vstack((x_train, x_test))\n", "Zmax = np.max(Z, axis=0)\n", "Zmin = np.min(Z, axis=0)\n", "\n", "#normalize an array of samples to range [-0.5, 0.5]\n", "def normalize(V):\n", " VN = (V - Zmin)/(Zmax - Zmin)\n", " VN = VN - 0.5\n", " return(VN)\n", " \n", "# rescale a sample to recover original values for normalized values. \n", "def rescale(X):\n", " return(np.multiply ( X + 0.5, (Zmax - Zmin) ) + Zmin)\n", "\n", "N = normalize(Z)\n", "xn_train = N[0:x_train.shape[0], :]\n", "xn_test = N[x_train.shape[0]:, :]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 2. Define and train a NN classifier\n", "\n", "Let us now build a loan approval model based on the HELOC dataset.\n", "\n", "#### a. Define NN architecture\n", "We now define the architecture of a 2-layer neural network classifier whose predictions we will try to interpret. " ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [], "source": [ "# nn with no softmax\n", "def nn_small():\n", " model = Sequential()\n", " model.add(Dense(10, input_dim=23, kernel_initializer='normal', activation='relu'))\n", " model.add(Dense(2, kernel_initializer='normal')) \n", " return model " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### b. Train the NN" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "dense_9 (Dense) (None, 10) 240 \n", "_________________________________________________________________\n", "dense_10 (Dense) (None, 2) 22 \n", "=================================================================\n", "Total params: 262\n", "Trainable params: 262\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Train accuracy: 0.7387545589625827\n", "Test accuracy: 0.7224473257698542\n" ] } ], "source": [ "# Set random seeds for repeatability\n", "np.random.seed(1) \n", "tf.set_random_seed(2) \n", "\n", "class_names = ['Bad', 'Good']\n", "\n", "# loss function\n", "def fn(correct, predicted):\n", " return tf.nn.softmax_cross_entropy_with_logits(labels=correct, logits=predicted)\n", "\n", "# compile and print model summary\n", "nn = nn_small()\n", "nn.compile(loss=fn, optimizer='adam', metrics=['accuracy'])\n", "nn.summary()\n", "\n", "\n", "# train model or load a trained model\n", "TRAIN_MODEL = False\n", "\n", "if (TRAIN_MODEL): \n", " nn.fit(xn_train, y_train_b, batch_size=128, epochs=500, verbose=1, shuffle=False)\n", " nn.save_weights(\"heloc_nnsmall.h5\") \n", "else: \n", " nn.load_weights(\"heloc_nnsmall.h5\")\n", " \n", "\n", "# evaluate model accuracy \n", "score = nn.evaluate(xn_train, y_train_b, verbose=0) #Compute training set accuracy\n", "#print('Train loss:', score[0])\n", "print('Train accuracy:', score[1])\n", "\n", "score = nn.evaluate(xn_test, y_test_b, verbose=0) #Compute test set accuracy\n", "#print('Test loss:', score[0])\n", "print('Test accuracy:', score[1])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "### Step 3. Compute contrastive explanations for a few applicants\n", "\n", "Given the trained NN model to decide on loan approvals, let us first examine an applicant whose application was denied and what (minimal) changes to his/her application would lead to approval (i.e. finding pertinent negatives). We will then look at another applicant whose loan was approved and ascertain features that would minimally suffice in him/her still getting a positive outcome (i.e. finding pertinent positives).\n", "\n", "#### a. Compute Pertinent Negatives (PN): \n", "\n", "In order to compute pertinent negatives, the CEM explainer computes a user profile that is close to the original applicant but for whom the decision of HELOC application is different. The explainer alters a minimal set of features by a minimal (positive) amount. This will help the user whose loan application was initially rejected say, to ascertain how to get it accepted. " ] }, { "cell_type": "code", "execution_count": 75, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing PN for Sample: 1272\n", "Prediction made by the model: [[ 0.40682057 -0.391679 ]]\n", "Prediction probabilities: Bad\n", "\n", "iter:0 const:[10.]\n", "Loss_Overall:0.2935, Loss_Attack:0.0000\n", "Loss_L2Dist:0.2065, Loss_L1Dist:0.8703, AE_loss:0.0\n", "target_lab_score:-1.1559, max_nontarget_lab_score:1.3184\n", "\n", "iter:500 const:[10.]\n", "Loss_Overall:5.9870, Loss_Attack:5.9782\n", "Loss_L2Dist:0.0032, Loss_L1Dist:0.0563, AE_loss:0.0\n", "target_lab_score:0.2639, max_nontarget_lab_score:-0.2339\n", "\n", "iter:0 const:[5.]\n", "Loss_Overall:0.0668, Loss_Attack:0.0000\n", "Loss_L2Dist:0.0368, Loss_L1Dist:0.3000, AE_loss:0.0\n", "target_lab_score:-0.2295, max_nontarget_lab_score:0.3076\n", "\n", "iter:500 const:[5.]\n", "Loss_Overall:1.5487, Loss_Attack:1.5277\n", "Loss_L2Dist:0.0085, Loss_L1Dist:0.1243, AE_loss:0.0\n", "target_lab_score:0.1245, max_nontarget_lab_score:-0.0810\n", "\n", "iter:0 const:[2.5]\n", "Loss_Overall:1.8033, Loss_Attack:1.7989\n", "Loss_L2Dist:0.0011, Loss_L1Dist:0.0335, AE_loss:0.0\n", "target_lab_score:0.3218, max_nontarget_lab_score:-0.2978\n", "\n", "iter:500 const:[2.5]\n", "Loss_Overall:2.2462, Loss_Attack:2.2462\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[1.25]\n", "Loss_Overall:1.1231, Loss_Attack:1.1231\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:500 const:[1.25]\n", "Loss_Overall:1.1231, Loss_Attack:1.1231\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[1.875]\n", "Loss_Overall:1.6834, Loss_Attack:1.6834\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0001, AE_loss:0.0\n", "target_lab_score:0.4065, max_nontarget_lab_score:-0.3913\n", "\n", "iter:500 const:[1.875]\n", "Loss_Overall:1.6847, Loss_Attack:1.6847\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[2.1875]\n", "Loss_Overall:1.7709, Loss_Attack:1.7690\n", "Loss_L2Dist:0.0003, Loss_L1Dist:0.0168, AE_loss:0.0\n", "target_lab_score:0.3641, max_nontarget_lab_score:-0.3445\n", "\n", "iter:500 const:[2.1875]\n", "Loss_Overall:1.9655, Loss_Attack:1.9655\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[2.03125]\n", "Loss_Overall:1.7340, Loss_Attack:1.7331\n", "Loss_L2Dist:0.0001, Loss_L1Dist:0.0085, AE_loss:0.0\n", "target_lab_score:0.3853, max_nontarget_lab_score:-0.3679\n", "\n", "iter:500 const:[2.03125]\n", "Loss_Overall:1.8251, Loss_Attack:1.8251\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[1.953125]\n", "Loss_Overall:1.7104, Loss_Attack:1.7100\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0043, AE_loss:0.0\n", "target_lab_score:0.3959, max_nontarget_lab_score:-0.3796\n", "\n", "iter:500 const:[1.953125]\n", "Loss_Overall:1.7549, Loss_Attack:1.7549\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n", "iter:0 const:[1.9921875]\n", "Loss_Overall:1.7227, Loss_Attack:1.7220\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0064, AE_loss:0.0\n", "target_lab_score:0.3906, max_nontarget_lab_score:-0.3738\n", "\n", "iter:500 const:[1.9921875]\n", "Loss_Overall:1.7900, Loss_Attack:1.7900\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:0.4068, max_nontarget_lab_score:-0.3917\n", "\n" ] } ], "source": [ "# Some interesting user samples to try: 2344 449 1168 1272\n", "idx = 1272\n", "\n", "X = xn_test[idx].reshape((1,) + xn_test[idx].shape)\n", "print(\"Computing PN for Sample:\", idx)\n", "print(\"Prediction made by the model:\", nn.predict_proba(X))\n", "print(\"Prediction probabilities:\", class_names[np.argmax(nn.predict_proba(X))])\n", "print(\"\")\n", "\n", "mymodel = KerasClassifier(nn)\n", "explainer = CEMExplainer(mymodel)\n", "\n", "arg_mode = 'PN' # Find pertinent negatives\n", "arg_max_iter = 1000 # Maximum number of iterations to search for the optimal PN for given parameter settings\n", "arg_init_const = 10.0 # Initial coefficient value for main loss term that encourages class change\n", "arg_b = 9 # No. of updates to the coefficient of the main loss term\n", "arg_kappa = 0.1 # Minimum confidence gap between the PNs (changed) class probability and original class' probability\n", "arg_beta = 1e-1 # Controls sparsity of the solution (L1 loss)\n", "arg_gamma = 100 # Controls how much to adhere to a (optionally trained) auto-encoder\n", "my_AE_model = None # Pointer to an auto-encoder\n", "\n", "# Find PN for applicant 1272\n", "(adv_pn, delta_pn, info_pn) = explainer.explain_instance(X, arg_mode, my_AE_model, arg_kappa, arg_b,\n", " arg_max_iter, arg_init_const, arg_beta, arg_gamma)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us start by examining one particular loan application that was denied for applicant 1272. We showcase below how the decision could have been different through minimal changes to the profile conveyed by the pertinent negative. We also indicate the importance of different features to produce the change in the application status. The column delta in the table below indicates the necessary deviations for each of the features to produce this change. A human friendly explanation is then provided based on these deviations following the feature importance plot." ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sample: 1272\n", "prediction(X) [[ 0.40682057 -0.391679 ]] Bad\n", "prediction(Xpn) [[-0.02118406 0.07892033]] Good\n" ] }, { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
X X_PN (X_PN - X)
ExternalRiskEstimate6576.3711.37
MSinceOldestTradeOpen2562560
MSinceMostRecentTradeOpen15150
AverageMInFile5264.8112.81
NumSatisfactoryTrades1720.33.3
NumTrades60Ever2DerogPubRec000
NumTrades90Ever2DerogPubRec000
PercentTradesNeverDelq1001000
MSinceMostRecentDelq000
MaxDelq2PublicRecLast12M770
MaxDelqEver880
NumTotalTrades19190
NumTradesOpeninLast12M000
PercentInstallTrades29290
MSinceMostRecentInqexcl7days220
NumInqLast6M550
NumInqLast6Mexcl7days550
NetFractionRevolvingBurden57570
NetFractionInstallBurden79790
NumRevolvingTradesWBalance220
NumInstallTradesWBalance440
NumBank2NatlTradesWHighUtilization220
PercentTradesWBalance60600
RiskPerformanceBadGoodNIL
" ], "text/plain": [ "" ] }, "execution_count": 76, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Xpn = adv_pn\n", "classes = [ class_names[np.argmax(nn.predict_proba(X))], class_names[np.argmax(nn.predict_proba(Xpn))], 'NIL' ]\n", "\n", "print(\"Sample:\", idx)\n", "print(\"prediction(X)\", nn.predict_proba(X), class_names[np.argmax(nn.predict_proba(X))])\n", "print(\"prediction(Xpn)\", nn.predict_proba(Xpn), class_names[np.argmax(nn.predict_proba(Xpn))] )\n", "\n", "\n", "X_re = rescale(X) # Convert values back to original scale from normalized\n", "Xpn_re = rescale(Xpn)\n", "Xpn_re = np.around(Xpn_re.astype(np.double), 2)\n", "\n", "delta_re = Xpn_re - X_re\n", "delta_re = np.around(delta_re.astype(np.double), 2)\n", "delta_re[np.absolute(delta_re) < 1e-4] = 0\n", "\n", "X3 = np.vstack((X_re, Xpn_re, delta_re))\n", "\n", "dfre = pd.DataFrame.from_records(X3) # Create dataframe to display original point, PN and difference (delta)\n", "dfre[23] = classes\n", "\n", "dfre.columns = df.columns\n", "dfre.rename(index={0:'X',1:'X_PN', 2:'(X_PN - X)'}, inplace=True)\n", "dfret = dfre.transpose()\n", "\n", "\n", "def highlight_ce(s, col, ncols):\n", " if (type(s[col]) != str):\n", " if (s[col] > 0):\n", " return(['background-color: yellow']*ncols) \n", " return(['background-color: white']*ncols)\n", "\n", "dfret.style.apply(highlight_ce, col='(X_PN - X)', ncols=3, axis=1) " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let us compute the importance of different PN features that would be instrumental in 1272 receiving a favorable outcome and display below." ] }, { "cell_type": "code", "execution_count": 77, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.rcdefaults()\n", "fi = abs((X-Xpn).astype('double'))/np.std(xn_train.astype('double'), axis=0) # Compute PN feature importance\n", "objects = df.columns[-2::-1]\n", "y_pos = np.arange(len(objects))\n", "performance = fi[0, -1::-1]\n", "\n", "plt.barh(y_pos, performance, align='center', alpha=0.5) # bar chart\n", "plt.yticks(y_pos, objects) # Display features on y-axis\n", "plt.xlabel('weight') # x-label\n", "plt.title('PN (feature importance)') # Heading\n", "\n", "plt.show() # Display PN feature importance" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Explanation: \n", "We observe that the applicant 1272's loan application would have been accepted if the consolidated risk marker score (i.e. ExternalRiskEstimate) increased from 65 to 76, the loan application was on file (i.e. AverageMlnFile) for about 65 months and if the number of satisfactory trades (i.e. NumSatisfactoryTrades) increased to little over 20.\n", "\n", "_The above changes to the three suggested factors are also intuitively consistent in improving the chances of acceptance of an application, since all three are monotonic with probability of acceptance (refer HELOC description table). \n", "However, one must realize that the above explanation is for the particular applicant based on what the model would do and does not necessarily have to agree with their intuitive meaning. In fact, if the explanation is deemed unacceptable then its an indication that perhaps the model should be debugged/updated_." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Compute Pertinent Positives (PP):\n", "In order to compute pertinent positives, the CEM explainer identifies a minimal set of features along with their values (as close to 0) that would still maintain the predicted loan application status of the applicant." ] }, { "cell_type": "code", "execution_count": 78, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing PP for Sample: 8\n", "Prediction made by the model: Good\n", "Prediction probabilities: [[-0.1889221 0.29527372]]\n", "\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/envs/aix360/lib/python3.6/site-packages/keras/engine/sequential.py:247: UserWarning: Network returning invalid probability values. The last layer might not normalize predictions into probabilities (like softmax or sigmoid would).\n", " warnings.warn('Network returning invalid probability values. '\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "iter:0 const:[10.]\n", "Loss_Overall:8.1419, Loss_Attack:7.9649\n", "Loss_L2Dist:0.1243, Loss_L1Dist:0.5266, AE_loss:0.0\n", "target_lab_score:-0.3578, max_nontarget_lab_score:0.3387\n", "\n", "iter:500 const:[10.]\n", "Loss_Overall:0.3945, Loss_Attack:0.0000\n", "Loss_L2Dist:0.3318, Loss_L1Dist:0.6264, AE_loss:0.0\n", "target_lab_score:0.0991, max_nontarget_lab_score:-0.0737\n", "\n", "iter:0 const:[5.]\n", "Loss_Overall:8.4407, Loss_Attack:8.3992\n", "Loss_L2Dist:0.0216, Loss_L1Dist:0.1987, AE_loss:0.0\n", "target_lab_score:-0.8223, max_nontarget_lab_score:0.7575\n", "\n", "iter:500 const:[5.]\n", "Loss_Overall:4.1897, Loss_Attack:3.9453\n", "Loss_L2Dist:0.1997, Loss_L1Dist:0.4469, AE_loss:0.0\n", "target_lab_score:-0.3484, max_nontarget_lab_score:0.3406\n", "\n", "iter:0 const:[2.5]\n", "Loss_Overall:6.1030, Loss_Attack:6.1013\n", "Loss_L2Dist:0.0002, Loss_L1Dist:0.0149, AE_loss:0.0\n", "target_lab_score:-1.2149, max_nontarget_lab_score:1.1256\n", "\n", "iter:500 const:[2.5]\n", "Loss_Overall:6.2723, Loss_Attack:6.2723\n", "Loss_L2Dist:0.0000, Loss_L1Dist:0.0000, AE_loss:0.0\n", "target_lab_score:-1.2499, max_nontarget_lab_score:1.1590\n", "\n", "iter:0 const:[3.75]\n", "Loss_Overall:7.8400, Loss_Attack:7.8242\n", "Loss_L2Dist:0.0059, Loss_L1Dist:0.0990, AE_loss:0.0\n", "target_lab_score:-1.0324, max_nontarget_lab_score:0.9541\n", "\n", "iter:500 const:[3.75]\n", "Loss_Overall:5.8230, Loss_Attack:5.7570\n", "Loss_L2Dist:0.0449, Loss_L1Dist:0.2119, AE_loss:0.0\n", "target_lab_score:-0.7511, max_nontarget_lab_score:0.6841\n", "\n", "iter:0 const:[4.375]\n", "Loss_Overall:8.2661, Loss_Attack:8.2388\n", "Loss_L2Dist:0.0125, Loss_L1Dist:0.1488, AE_loss:0.0\n", "target_lab_score:-0.9274, max_nontarget_lab_score:0.8558\n", "\n", "iter:500 const:[4.375]\n", "Loss_Overall:6.5857, Loss_Attack:6.5105\n", "Loss_L2Dist:0.0523, Loss_L1Dist:0.2288, AE_loss:0.0\n", "target_lab_score:-0.7263, max_nontarget_lab_score:0.6618\n", "\n", "iter:0 const:[4.0625]\n", "Loss_Overall:8.0845, Loss_Attack:8.0632\n", "Loss_L2Dist:0.0089, Loss_L1Dist:0.1239, AE_loss:0.0\n", "target_lab_score:-0.9799, max_nontarget_lab_score:0.9049\n", "\n", "iter:500 const:[4.0625]\n", "Loss_Overall:6.6793, Loss_Attack:6.6236\n", "Loss_L2Dist:0.0365, Loss_L1Dist:0.1912, AE_loss:0.0\n", "target_lab_score:-0.7999, max_nontarget_lab_score:0.7306\n", "\n", "iter:0 const:[3.90625]\n", "Loss_Overall:7.9701, Loss_Attack:7.9516\n", "Loss_L2Dist:0.0073, Loss_L1Dist:0.1115, AE_loss:0.0\n", "target_lab_score:-1.0061, max_nontarget_lab_score:0.9295\n", "\n", "iter:500 const:[3.90625]\n", "Loss_Overall:6.2569, Loss_Attack:6.1965\n", "Loss_L2Dist:0.0403, Loss_L1Dist:0.2008, AE_loss:0.0\n", "target_lab_score:-0.7772, max_nontarget_lab_score:0.7091\n", "\n", "iter:0 const:[3.828125]\n", "Loss_Overall:7.9070, Loss_Attack:7.8899\n", "Loss_L2Dist:0.0066, Loss_L1Dist:0.1052, AE_loss:0.0\n", "target_lab_score:-1.0193, max_nontarget_lab_score:0.9418\n", "\n", "iter:500 const:[3.828125]\n", "Loss_Overall:6.3022, Loss_Attack:6.2467\n", "Loss_L2Dist:0.0364, Loss_L1Dist:0.1909, AE_loss:0.0\n", "target_lab_score:-0.8005, max_nontarget_lab_score:0.7312\n", "\n", "iter:0 const:[3.8671875]\n", "Loss_Overall:7.9391, Loss_Attack:7.9213\n", "Loss_L2Dist:0.0070, Loss_L1Dist:0.1083, AE_loss:0.0\n", "target_lab_score:-1.0127, max_nontarget_lab_score:0.9356\n", "\n", "iter:500 const:[3.8671875]\n", "Loss_Overall:6.0266, Loss_Attack:5.9612\n", "Loss_L2Dist:0.0443, Loss_L1Dist:0.2105, AE_loss:0.0\n", "target_lab_score:-0.7543, max_nontarget_lab_score:0.6872\n", "\n" ] } ], "source": [ "# Some interesting user samples to try: 8 9 11\n", "idx = 8\n", "\n", "X = xn_test[idx].reshape((1,) + xn_test[idx].shape)\n", "print(\"Computing PP for Sample:\", idx)\n", "print(\"Prediction made by the model:\", class_names[np.argmax(nn.predict_proba(X))])\n", "print(\"Prediction probabilities:\", nn.predict_proba(X))\n", "print(\"\")\n", "\n", "\n", "mymodel = KerasClassifier(nn)\n", "explainer = CEMExplainer(mymodel)\n", "\n", "arg_mode = 'PP' # Find pertinent positives\n", "arg_max_iter = 1000 # Maximum number of iterations to search for the optimal PN for given parameter settings\n", "arg_init_const = 10.0 # Initial coefficient value for main loss term that encourages class change\n", "arg_b = 9 # No. of updates to the coefficient of the main loss term\n", "arg_kappa = 0.1 # Minimum confidence gap between the PNs (changed) class probability and original class' probability\n", "arg_beta = 1e-1 # Controls sparsity of the solution (L1 loss)\n", "arg_gamma = 100 # Controls how much to adhere to a (optionally trained) auto-encoder\n", "my_AE_model = None # Pointer to an auto-encoder\n", "\n", "(adv_pp, delta_pp, info_pp) = explainer.explain_instance(X, arg_mode, my_AE_model, arg_kappa, arg_b,\n", " arg_max_iter, arg_init_const, arg_beta, arg_gamma)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For the pertinent positives, we look at a different applicant 8 whose loan application was approved. We want to ascertain here what minimal values for this profile would still have lead to acceptance. Below, we showcase the pertinent positive as well as the important features in maintaining the approved status. The 0s in the PP column indicate that those features were not important. The 0s in the PP column indicate that those features were not important. Here too, we provide a human friendly explanation following the feature importance plot." ] }, { "cell_type": "code", "execution_count": 79, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "PP for Sample: 8\n", "Prediction(Xpp) : Good\n", "Prediction probabilities for Xpp: [[-0.09004497 0.11049862]]\n", "\n" ] }, { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
X X_PP
ExternalRiskEstimate8237.65
MSinceOldestTradeOpen2800
MSinceMostRecentTradeOpen130
AverageMInFile10273.67
NumSatisfactoryTrades2211.49
NumTrades60Ever2DerogPubRec00
NumTrades90Ever2DerogPubRec00
PercentTradesNeverDelq910
MSinceMostRecentDelq260
MaxDelq2PublicRecLast12M60
MaxDelqEver60
NumTotalTrades230
NumTradesOpeninLast12M00
PercentInstallTrades90
MSinceMostRecentInqexcl7days00
NumInqLast6M00
NumInqLast6Mexcl7days00
NetFractionRevolvingBurden30
NetFractionInstallBurden00
NumRevolvingTradesWBalance40
NumInstallTradesWBalance10
NumBank2NatlTradesWHighUtilization10
PercentTradesWBalance420
RiskPerformanceGoodGood
" ], "text/plain": [ "" ] }, "execution_count": 79, "metadata": {}, "output_type": "execute_result" } ], "source": [ "Xpp = delta_pp\n", "classes = [ class_names[np.argmax(nn.predict_proba(X))], class_names[np.argmax(nn.predict_proba(Xpp))]]\n", "\n", "print(\"PP for Sample:\", idx)\n", "print(\"Prediction(Xpp) :\", class_names[np.argmax(nn.predict_proba(Xpp))])\n", "print(\"Prediction probabilities for Xpp:\", nn.predict_proba(Xpp))\n", "print(\"\")\n", "\n", "X_re = rescale(X) # Convert values back to original scale from normalized\n", "adv_pp_re = rescale(adv_pp)\n", "Xpp_re = X_re - adv_pp_re\n", "Xpp_re = np.around(Xpp_re.astype(np.double), 2)\n", "Xpp_re[Xpp_re < 1e-4] = 0\n", "\n", "X2 = np.vstack((X_re, Xpp_re))\n", "\n", "dfpp = pd.DataFrame.from_records(X2.astype('double')) # Showcase a dataframe for the original point and PP\n", "dfpp[23] = classes\n", "dfpp.columns = df.columns\n", "dfpp.rename(index={0:'X',1:'X_PP'}, inplace=True)\n", "dfppt = dfpp.transpose()\n", "\n", "dfppt.style.apply(highlight_ce, col='X_PP', ncols=2, axis=1) " ] }, { "cell_type": "code", "execution_count": 80, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.rcdefaults()\n", "fi = abs(Xpp_re.astype('double'))/np.std(x_train.astype('double'), axis=0) # Compute PP feature importance\n", " \n", "objects = df.columns[-2::-1]\n", "y_pos = np.arange(len(objects)) # Get input feature names\n", "performance = fi[0, -1::-1]\n", "\n", "plt.barh(y_pos, performance, align='center', alpha=0.5) # Bar chart\n", "plt.yticks(y_pos, objects) # Plot feature names on y-axis\n", "plt.xlabel('weight') #x-label\n", "plt.title('PP (feature importance)') # Figure heading\n", "\n", "plt.show() # Display the feature importance" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Explanation: \n", "We observe that the applicant 8's loan application would still have been accepted even if the consolidated risk marker score (i.e. ExternalRiskEstimate) reduced from 82 to around 40, application was on file (i.e. AverageMlnFile) for close to 70 months and number of satisfactory trades (i.e. NumSatisfactoryTrades) reduced from 22 to almost single digits.\n", "\n", "_Note that explanations may change a bit based on equivalent values in a local minima._" ] } ], "metadata": { "celltoolbar": "Edit Metadata", "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 2 }