{
"cells": [
{
"cell_type": "markdown",
"id": "italic-seafood",
"metadata": {},
"source": [
"# <center> Welcome to PyExplainer Quickstart Guide </center>"
]
},
{
"cell_type": "markdown",
"id": "northern-birmingham",
"metadata": {},
"source": [
"# Top Note - MUST READ !!\n",
"#### 1. When initialising the PyExplainer object, you should prepare 5 necessary parameters and follow the data type \n",
"(1) X_train (pd.core.frame.DataFrame) - feature columns from training data <br><br> \n",
"(2) y_train (pd.core.series.Series) - label column from training data <br><br>\n",
"(3) indep (pd.core.indexes.base.Index) - names of feature columns > most of the time, you can get it by 'X_explain.columns' <br><br>\n",
"(4) dep (str) - name of label column<br><br>\n",
"(5) blackbox_model (any supervised classification model trained from sklearn lib) - model trained from sklearn lib<br><br>\n",
"\n",
"#### 2. When using the explain() function under PyExplainer object, you should prepare 2 parameters and follow the data type\n",
"(1) X_explain (pd.core.frame.DataFrame) - one row of feature data <br><br> \n",
"(2) y_explain (pd.core.series.Series) - one row of predicted data \n",
"\n",
"#### 3. Be careful when using the custom pandas index for Series and DataFrame \n",
"In our Full Tutorial (PART B) example, the FileName column was used as the custom index.<br> \n",
"However, it is fine if you don't have custom index, pandas will generate default row index starting from 0.<br><br>\n",
"If you do want to make use of custom index, make sure to use it consistently, whenever you do the data processing.<br><br>\n",
"Otherwise, some of your data may have pandas default index while the others have your custom index, <br><br>\n",
"which will trigger errors whenever you try to combine your DataFrame and Series. "
]
},
{
"cell_type": "markdown",
"id": "conscious-roommate",
"metadata": {},
"source": [
"---"
]
},
{
"cell_type": "markdown",
"id": "employed-intensity",
"metadata": {},
"source": [
"# PART A - Quick Start"
]
},
{
"cell_type": "markdown",
"id": "deadly-immigration",
"metadata": {},
"source": [
"## 1. Prepare data and model\n",
"\n",
"Note. We use the default data and model here for an example"
]
},
{
"cell_type": "markdown",
"id": "higher-cooling",
"metadata": {},
"source": [
"### 1.1 Import required library"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "harmful-morocco",
"metadata": {},
"outputs": [],
"source": [
"from pyexplainer import pyexplainer_pyexplainer"
]
},
{
"cell_type": "markdown",
"id": "practical-jenny",
"metadata": {},
"source": [
"### 1.2 Obtain default dataset and global model (Random Forest)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "employed-adobe",
"metadata": {},
"outputs": [],
"source": [
"default_data_and_model = pyexplainer_pyexplainer.get_dflt()\n",
"py_explainer = pyexplainer_pyexplainer.PyExplainer(X_train = default_data_and_model['X_train'],\n",
" y_train = default_data_and_model['y_train'],\n",
" indep = default_data_and_model['indep'],\n",
" dep = default_data_and_model['dep'],\n",
" blackbox_model = default_data_and_model['blackbox_model'])"
]
},
{
"cell_type": "markdown",
"id": "informational-disclosure",
"metadata": {},
"source": [
"## 🔧2. Create PyExplainer object "
]
},
{
"cell_type": "markdown",
"id": "anticipated-tourism",
"metadata": {},
"source": [
"### 2.1 Prepare data for creating PyExplainer"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "abstract-disposal",
"metadata": {},
"outputs": [],
"source": [
"X_explain = default_data_and_model['X_explain']\n",
"y_explain = default_data_and_model['y_explain']"
]
},
{
"cell_type": "markdown",
"id": "inside-republic",
"metadata": {},
"source": [
"### 2.2 Create rules"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "spatial-wrong",
"metadata": {},
"outputs": [],
"source": [
"created_rules = py_explainer.explain(X_explain=X_explain,\n",
" y_explain=y_explain,\n",
" search_function='crossoverinterpolation')"
]
},
{
"cell_type": "markdown",
"id": "engaging-ridge",
"metadata": {},
"source": [
"## 3. Create interactive visualization\n",
"\n",
"You can change feature values at the slider bar to observe change of risk score."
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "second-trout",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9feefd892e174452bc28777e0ad4dfba",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(Label(value='Risk Score: '), FloatProgress(value=0.0, bar_style='info', layout=Layout(width='40…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "07d0fafe28994776bc5666a43c492587",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Output(layout=Layout(border='3px solid black'), outputs=({'output_type': 'display_data', 'data': {'text/plain'…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7f0ae3bba93d4ffbb4a944874bfcbe74",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"FloatSlider(value=0.0, continuous_update=False, description='#1 The value of CountDeclInstanceVariable is more…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "012c0a572d1e440b8bc3d847bed27af6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"FloatSlider(value=90.0, continuous_update=False, description='#2 The value of PercentLackOfCohesion is more th…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fc2862721c44469c90a106c385682435",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"FloatSlider(value=7.0, continuous_update=False, description='#3 The value of CountDeclMethodPublic is more tha…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"py_explainer.visualise(created_rules)"
]
},
{
"cell_type": "markdown",
"id": "894f3a9a",
"metadata": {},
"source": [
"##### *** If the widget is not displayed, please run the code cell below, restart the notebook, and rerun from the top"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9db21a4d",
"metadata": {},
"outputs": [],
"source": [
"import os \n",
"os.system(\"jupyter nbextension enable --py widgetsnbextension\")"
]
},
{
"cell_type": "markdown",
"id": "a15de81b",
"metadata": {},
"source": [
"# PART B - Full Tutorial"
]
},
{
"cell_type": "markdown",
"id": "italic-services",
"metadata": {},
"source": [
"## 1. Prepare sample data and model"
]
},
{
"cell_type": "markdown",
"id": "front-programmer",
"metadata": {},
"source": [
"### 1.1 For the simplicity, we load the sample DataFrame that is included in the package already"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "removable-problem",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>File</th>\n",
" <th>CountDeclMethodPrivate</th>\n",
" <th>AvgLineCode</th>\n",
" <th>CountLine</th>\n",
" <th>MaxCyclomatic</th>\n",
" <th>CountDeclMethodDefault</th>\n",
" <th>AvgEssential</th>\n",
" <th>CountDeclClassVariable</th>\n",
" <th>SumCyclomaticStrict</th>\n",
" <th>AvgCyclomatic</th>\n",
" <th>...</th>\n",
" <th>OWN_LINE</th>\n",
" <th>OWN_COMMIT</th>\n",
" <th>MINOR_COMMIT</th>\n",
" <th>MINOR_LINE</th>\n",
" <th>MAJOR_COMMIT</th>\n",
" <th>MAJOR_LINE</th>\n",
" <th>RealBug</th>\n",
" <th>HeuBug</th>\n",
" <th>HeuBugCount</th>\n",
" <th>RealBugCount</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>activemq-console/src/main/java/org/apache/acti...</td>\n",
" <td>0</td>\n",
" <td>10</td>\n",
" <td>171</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>18</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>1.00000</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>activemq-console/src/main/java/org/apache/acti...</td>\n",
" <td>0</td>\n",
" <td>8</td>\n",
" <td>123</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>15</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>0.98374</td>\n",
" <td>0.5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>activemq-console/src/main/java/org/apache/acti...</td>\n",
" <td>0</td>\n",
" <td>7</td>\n",
" <td>136</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>16</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>1.00000</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 70 columns</p>\n",
"</div>"
],
"text/plain": [
" File CountDeclMethodPrivate \\\n",
"0 activemq-console/src/main/java/org/apache/acti... 0 \n",
"1 activemq-console/src/main/java/org/apache/acti... 0 \n",
"2 activemq-console/src/main/java/org/apache/acti... 0 \n",
"\n",
" AvgLineCode CountLine MaxCyclomatic CountDeclMethodDefault \\\n",
"0 10 171 5 0 \n",
"1 8 123 5 0 \n",
"2 7 136 5 0 \n",
"\n",
" AvgEssential CountDeclClassVariable SumCyclomaticStrict AvgCyclomatic \\\n",
"0 2 0 18 2 \n",
"1 1 1 15 3 \n",
"2 1 1 16 2 \n",
"\n",
" ... OWN_LINE OWN_COMMIT MINOR_COMMIT MINOR_LINE MAJOR_COMMIT \\\n",
"0 ... 1.00000 1.0 0 1 1 \n",
"1 ... 0.98374 0.5 0 1 2 \n",
"2 ... 1.00000 1.0 0 1 1 \n",
"\n",
" MAJOR_LINE RealBug HeuBug HeuBugCount RealBugCount \n",
"0 0 False False 0 0 \n",
"1 1 False False 0 0 \n",
"2 0 False False 0 0 \n",
"\n",
"[3 rows x 70 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from pyexplainer import pyexplainer_pyexplainer\n",
"\n",
"df = pyexplainer_pyexplainer.load_sample_data()\n",
"df.head(3)"
]
},
{
"cell_type": "markdown",
"id": "connected-occurrence",
"metadata": {},
"source": [
"### 1.2 Define index column (OPTIONAL) and drop unwanted columns\n",
"##### First, we set 'File' col as index col since it is the file that we wanna inspect, and it has nothing to do with features or label\n",
"##### We use 'RealBug' as the label col, and the cols before 'RealBug' as feature cols\n",
"##### Then we drop unnecessary cols (e.g. File, HeuBug, HeuBugCount, RealBugCount)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "median-moisture",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>CountDeclMethodPrivate</th>\n",
" <th>AvgLineCode</th>\n",
" <th>CountLine</th>\n",
" <th>MaxCyclomatic</th>\n",
" <th>CountDeclMethodDefault</th>\n",
" <th>AvgEssential</th>\n",
" <th>CountDeclClassVariable</th>\n",
" <th>SumCyclomaticStrict</th>\n",
" <th>AvgCyclomatic</th>\n",
" <th>AvgLine</th>\n",
" <th>...</th>\n",
" <th>DDEV</th>\n",
" <th>Added_lines</th>\n",
" <th>Del_lines</th>\n",
" <th>OWN_LINE</th>\n",
" <th>OWN_COMMIT</th>\n",
" <th>MINOR_COMMIT</th>\n",
" <th>MINOR_LINE</th>\n",
" <th>MAJOR_COMMIT</th>\n",
" <th>MAJOR_LINE</th>\n",
" <th>RealBug</th>\n",
" </tr>\n",
" <tr>\n",
" <th>File</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>activemq-console/src/main/java/org/apache/activemq/console/command/AbstractAmqCommand.java</th>\n",
" <td>0</td>\n",
" <td>10</td>\n",
" <td>171</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>18</td>\n",
" <td>2</td>\n",
" <td>18</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>32</td>\n",
" <td>18</td>\n",
" <td>1.00000</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-console/src/main/java/org/apache/activemq/console/command/AbstractCommand.java</th>\n",
" <td>0</td>\n",
" <td>8</td>\n",
" <td>123</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>15</td>\n",
" <td>3</td>\n",
" <td>17</td>\n",
" <td>...</td>\n",
" <td>2</td>\n",
" <td>30</td>\n",
" <td>28</td>\n",
" <td>0.98374</td>\n",
" <td>0.5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-console/src/main/java/org/apache/activemq/console/command/AbstractJmxCommand.java</th>\n",
" <td>0</td>\n",
" <td>7</td>\n",
" <td>136</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>16</td>\n",
" <td>2</td>\n",
" <td>13</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>8</td>\n",
" <td>8</td>\n",
" <td>1.00000</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 66 columns</p>\n",
"</div>"
],
"text/plain": [
" CountDeclMethodPrivate \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" AvgLineCode CountLine \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 10 171 \n",
"activemq-console/src/main/java/org/apache/activ... 8 123 \n",
"activemq-console/src/main/java/org/apache/activ... 7 136 \n",
"\n",
" MaxCyclomatic \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 5 \n",
"activemq-console/src/main/java/org/apache/activ... 5 \n",
"activemq-console/src/main/java/org/apache/activ... 5 \n",
"\n",
" CountDeclMethodDefault \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" AvgEssential \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 2 \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"\n",
" CountDeclClassVariable \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"\n",
" SumCyclomaticStrict \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 18 \n",
"activemq-console/src/main/java/org/apache/activ... 15 \n",
"activemq-console/src/main/java/org/apache/activ... 16 \n",
"\n",
" AvgCyclomatic AvgLine \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 2 18 \n",
"activemq-console/src/main/java/org/apache/activ... 3 17 \n",
"activemq-console/src/main/java/org/apache/activ... 2 13 \n",
"\n",
" ... DDEV Added_lines \\\n",
"File ... \n",
"activemq-console/src/main/java/org/apache/activ... ... 1 32 \n",
"activemq-console/src/main/java/org/apache/activ... ... 2 30 \n",
"activemq-console/src/main/java/org/apache/activ... ... 1 8 \n",
"\n",
" Del_lines OWN_LINE \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 18 1.00000 \n",
"activemq-console/src/main/java/org/apache/activ... 28 0.98374 \n",
"activemq-console/src/main/java/org/apache/activ... 8 1.00000 \n",
"\n",
" OWN_COMMIT MINOR_COMMIT \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1.0 0 \n",
"activemq-console/src/main/java/org/apache/activ... 0.5 0 \n",
"activemq-console/src/main/java/org/apache/activ... 1.0 0 \n",
"\n",
" MINOR_LINE MAJOR_COMMIT \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1 1 \n",
"activemq-console/src/main/java/org/apache/activ... 1 2 \n",
"activemq-console/src/main/java/org/apache/activ... 1 1 \n",
"\n",
" MAJOR_LINE RealBug \n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 False \n",
"activemq-console/src/main/java/org/apache/activ... 1 False \n",
"activemq-console/src/main/java/org/apache/activ... 0 False \n",
"\n",
"[3 rows x 66 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = df.set_index(df['File'])\n",
"df = df.drop(['File', 'HeuBug', 'HeuBugCount', 'RealBugCount'], axis=1)\n",
"df.head(3)"
]
},
{
"cell_type": "markdown",
"id": "advance-wilderness",
"metadata": {},
"source": [
"### 1.3 Define feature cols (X), and label col (y)\n",
"##### the function AutoSpearman is used as a feature selection method to reduce number of features\n",
"##### for more information about the algorithm please refer to [this paper](https://ieeexplore.ieee.org/document/8530020)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "growing-scale",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(Part 1) Automatically select non-correlated metrics based on a Spearman rank correlation test\n",
"> Step 1 comparing between CountDeclMethod and CountDeclFunction\n",
">> CountDeclMethod has the average correlation of 0.433 with other metrics\n",
">> CountDeclFunction has the average correlation of 0.433 with other metrics\n",
">> Exclude CountDeclMethod\n",
"> Step 2 comparing between MAJOR_COMMIT and DDEV\n",
">> MAJOR_COMMIT has the average correlation of 0.274 with other metrics\n",
">> DDEV has the average correlation of 0.274 with other metrics\n",
">> Exclude DDEV\n",
"> Step 3 comparing between SumCyclomatic and SumCyclomaticModified\n",
">> SumCyclomatic has the average correlation of 0.501 with other metrics\n",
">> SumCyclomaticModified has the average correlation of 0.501 with other metrics\n",
">> Exclude SumCyclomatic\n",
"> Step 4 comparing between AvgCyclomatic and AvgCyclomaticModified\n",
">> AvgCyclomatic has the average correlation of 0.387 with other metrics\n",
">> AvgCyclomaticModified has the average correlation of 0.387 with other metrics\n",
">> Exclude AvgCyclomatic\n",
"> Step 5 comparing between MaxCyclomatic and MaxCyclomaticModified\n",
">> MaxCyclomatic has the average correlation of 0.476 with other metrics\n",
">> MaxCyclomaticModified has the average correlation of 0.476 with other metrics\n",
">> Exclude MaxCyclomatic\n",
"> Step 6 comparing between SumCyclomaticModified and SumCyclomaticStrict\n",
">> SumCyclomaticModified has the average correlation of 0.488 with other metrics\n",
">> SumCyclomaticStrict has the average correlation of 0.489 with other metrics\n",
">> Exclude SumCyclomaticStrict\n",
"> Step 7 comparing between CountStmtDecl and CountLineCodeDecl\n",
">> CountStmtDecl has the average correlation of 0.49 with other metrics\n",
">> CountLineCodeDecl has the average correlation of 0.487 with other metrics\n",
">> Exclude CountStmtDecl\n",
"> Step 8 comparing between CountLineCode and CountStmt\n",
">> CountLineCode has the average correlation of 0.504 with other metrics\n",
">> CountStmt has the average correlation of 0.501 with other metrics\n",
">> Exclude CountLineCode\n",
"> Step 9 comparing between CountSemicolon and CountStmt\n",
">> CountSemicolon has the average correlation of 0.484 with other metrics\n",
">> CountStmt has the average correlation of 0.492 with other metrics\n",
">> Exclude CountStmt\n",
"> Step 10 comparing between OWN_COMMIT and MAJOR_COMMIT\n",
">> OWN_COMMIT has the average correlation of 0.238 with other metrics\n",
">> MAJOR_COMMIT has the average correlation of 0.249 with other metrics\n",
">> Exclude MAJOR_COMMIT\n",
"> Step 11 comparing between CountPath_Max and MaxCyclomaticModified\n",
">> CountPath_Max has the average correlation of 0.447 with other metrics\n",
">> MaxCyclomaticModified has the average correlation of 0.448 with other metrics\n",
">> Exclude MaxCyclomaticModified\n",
"> Step 12 comparing between CountStmtExe and CountLineCodeExe\n",
">> CountStmtExe has the average correlation of 0.473 with other metrics\n",
">> CountLineCodeExe has the average correlation of 0.475 with other metrics\n",
">> Exclude CountLineCodeExe\n",
"> Step 13 comparing between SumEssential and CountDeclFunction\n",
">> SumEssential has the average correlation of 0.397 with other metrics\n",
">> CountDeclFunction has the average correlation of 0.379 with other metrics\n",
">> Exclude SumEssential\n",
"> Step 14 comparing between CountPath_Max and MaxCyclomaticStrict\n",
">> CountPath_Max has the average correlation of 0.427 with other metrics\n",
">> MaxCyclomaticStrict has the average correlation of 0.428 with other metrics\n",
">> Exclude MaxCyclomaticStrict\n",
"> Step 15 comparing between CountPath_Max and CountPath_Mean\n",
">> CountPath_Max has the average correlation of 0.416 with other metrics\n",
">> CountPath_Mean has the average correlation of 0.399 with other metrics\n",
">> Exclude CountPath_Max\n",
"> Step 16 comparing between AvgCyclomaticStrict and AvgCyclomaticModified\n",
">> AvgCyclomaticStrict has the average correlation of 0.337 with other metrics\n",
">> AvgCyclomaticModified has the average correlation of 0.33 with other metrics\n",
">> Exclude AvgCyclomaticStrict\n",
"> Step 17 comparing between CountDeclFunction and CountDeclInstanceMethod\n",
">> CountDeclFunction has the average correlation of 0.364 with other metrics\n",
">> CountDeclInstanceMethod has the average correlation of 0.342 with other metrics\n",
">> Exclude CountDeclFunction\n",
"> Step 18 comparing between CountSemicolon and CountLineCodeDecl\n",
">> CountSemicolon has the average correlation of 0.436 with other metrics\n",
">> CountLineCodeDecl has the average correlation of 0.421 with other metrics\n",
">> Exclude CountSemicolon\n",
"> Step 19 comparing between CountLine and CountLineBlank\n",
">> CountLine has the average correlation of 0.413 with other metrics\n",
">> CountLineBlank has the average correlation of 0.372 with other metrics\n",
">> Exclude CountLine\n",
"> Step 20 comparing between MaxNesting_Mean and CountPath_Mean\n",
">> MaxNesting_Mean has the average correlation of 0.33 with other metrics\n",
">> CountPath_Mean has the average correlation of 0.365 with other metrics\n",
">> Exclude CountPath_Mean\n",
"> Step 21 comparing between MaxNesting_Max and MaxNesting_Mean\n",
">> MaxNesting_Max has the average correlation of 0.337 with other metrics\n",
">> MaxNesting_Mean has the average correlation of 0.316 with other metrics\n",
">> Exclude MaxNesting_Max\n",
"> Step 22 comparing between CountOutput_Mean and AvgLineCode\n",
">> CountOutput_Mean has the average correlation of 0.284 with other metrics\n",
">> AvgLineCode has the average correlation of 0.317 with other metrics\n",
">> Exclude AvgLineCode\n",
"> Step 23 comparing between CountLineCodeDecl and SumCyclomaticModified\n",
">> CountLineCodeDecl has the average correlation of 0.385 with other metrics\n",
">> SumCyclomaticModified has the average correlation of 0.375 with other metrics\n",
">> Exclude CountLineCodeDecl\n",
"> Step 24 comparing between CountPath_Min and MaxNesting_Min\n",
">> CountPath_Min has the average correlation of 0.083 with other metrics\n",
">> MaxNesting_Min has the average correlation of 0.077 with other metrics\n",
">> Exclude CountPath_Min\n",
"> Step 25 comparing between CountDeclInstanceMethod and SumCyclomaticModified\n",
">> CountDeclInstanceMethod has the average correlation of 0.304 with other metrics\n",
">> SumCyclomaticModified has the average correlation of 0.371 with other metrics\n",
">> Exclude SumCyclomaticModified\n",
"> Step 26 comparing between RatioCommentToCode and CountStmtExe\n",
">> RatioCommentToCode has the average correlation of 0.341 with other metrics\n",
">> CountStmtExe has the average correlation of 0.379 with other metrics\n",
">> Exclude CountStmtExe\n",
"> Step 27 comparing between CountInput_Max and CountInput_Mean\n",
">> CountInput_Max has the average correlation of 0.293 with other metrics\n",
">> CountInput_Mean has the average correlation of 0.232 with other metrics\n",
">> Exclude CountInput_Max\n",
"> Step 28 comparing between CountOutput_Max and CountOutput_Mean\n",
">> CountOutput_Max has the average correlation of 0.329 with other metrics\n",
">> CountOutput_Mean has the average correlation of 0.259 with other metrics\n",
">> Exclude CountOutput_Max\n",
"> Step 29 comparing between MaxNesting_Mean and AvgCyclomaticModified\n",
">> MaxNesting_Mean has the average correlation of 0.257 with other metrics\n",
">> AvgCyclomaticModified has the average correlation of 0.247 with other metrics\n",
">> Exclude MaxNesting_Mean\n",
"> Step 30 comparing between Added_lines and Del_lines\n",
">> Added_lines has the average correlation of 0.294 with other metrics\n",
">> Del_lines has the average correlation of 0.291 with other metrics\n",
">> Exclude Added_lines\n",
"> Step 31 comparing between CountLineBlank and CountDeclInstanceMethod\n",
">> CountLineBlank has the average correlation of 0.299 with other metrics\n",
">> CountDeclInstanceMethod has the average correlation of 0.258 with other metrics\n",
">> Exclude CountLineBlank\n",
"> Step 32 comparing between MINOR_LINE and OWN_LINE\n",
">> MINOR_LINE has the average correlation of 0.08 with other metrics\n",
">> OWN_LINE has the average correlation of 0.078 with other metrics\n",
">> Exclude MINOR_LINE\n",
"> Step 33 comparing between CountDeclInstanceMethod and CountDeclMethodPublic\n",
">> CountDeclInstanceMethod has the average correlation of 0.246 with other metrics\n",
">> CountDeclMethodPublic has the average correlation of 0.232 with other metrics\n",
">> Exclude CountDeclInstanceMethod\n",
"> Step 34 comparing between AvgLine and CountOutput_Mean\n",
">> AvgLine has the average correlation of 0.234 with other metrics\n",
">> CountOutput_Mean has the average correlation of 0.239 with other metrics\n",
">> Exclude CountOutput_Mean\n",
"> Step 35 comparing between CountLineComment and AvgLineComment\n",
">> CountLineComment has the average correlation of 0.149 with other metrics\n",
">> AvgLineComment has the average correlation of 0.112 with other metrics\n",
">> Exclude CountLineComment\n",
"> Step 36 comparing between Del_lines and ADEV\n",
">> Del_lines has the average correlation of 0.265 with other metrics\n",
">> ADEV has the average correlation of 0.233 with other metrics\n",
">> Exclude Del_lines\n",
"According to Part 1 of AutoSpearman, ['ADEV', 'CountClassCoupled', 'AvgLine', 'OWN_LINE', 'CountDeclMethodProtected', 'CountDeclInstanceVariable', 'PercentLackOfCohesion', 'CountDeclClass', 'MAJOR_LINE', 'AvgLineBlank', 'CountDeclMethodPublic', 'CountInput_Mean', 'MaxNesting_Min', 'CountOutput_Min', 'CountDeclMethodDefault', 'AvgCyclomaticModified', 'CountInput_Min', 'CountDeclClassMethod', 'CountClassDerived', 'AvgLineComment', 'CountDeclClassVariable', 'CountClassBase', 'OWN_COMMIT', 'MaxInheritanceTree', 'CountDeclMethodPrivate', 'MINOR_COMMIT', 'AvgEssential', 'COMM', 'RatioCommentToCode'] are selected.\n",
"(Part 2) Automatically select non-correlated metrics based on a Variance Inflation Factor analysis\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\micha\\miniconda3\\lib\\site-packages\\statsmodels\\tsa\\tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only\n",
" x = pd.concat(x[::order], 1)\n",
"C:\\Users\\micha\\miniconda3\\lib\\site-packages\\statsmodels\\stats\\outliers_influence.py:193: RuntimeWarning: divide by zero encountered in double_scalars\n",
" vif = 1. / (1. - r_squared_i)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"> Step 1 - exclude ADEV\n",
"> Step 2 - exclude AvgLine\n",
"Finally, according to Part 2 of AutoSpearman, Index(['CountClassCoupled', 'OWN_LINE', 'CountDeclMethodProtected',\n",
" 'CountDeclInstanceVariable', 'PercentLackOfCohesion', 'CountDeclClass',\n",
" 'MAJOR_LINE', 'AvgLineBlank', 'CountDeclMethodPublic',\n",
" 'CountInput_Mean', 'MaxNesting_Min', 'CountOutput_Min',\n",
" 'CountDeclMethodDefault', 'AvgCyclomaticModified', 'CountInput_Min',\n",
" 'const', 'CountDeclClassMethod', 'CountClassDerived', 'AvgLineComment',\n",
" 'CountDeclClassVariable', 'CountClassBase', 'OWN_COMMIT',\n",
" 'MaxInheritanceTree', 'CountDeclMethodPrivate', 'MINOR_COMMIT',\n",
" 'AvgEssential', 'COMM', 'RatioCommentToCode'],\n",
" dtype='object') are selected.\n",
"27 out of 65 were selected via AutoSpearman feature selection process\n",
"feature cols: \n",
"\n",
" CountClassCoupled \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 2 \n",
"\n",
" OWN_LINE \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1.0 \n",
"\n",
" CountDeclMethodProtected \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 7 \n",
"\n",
" CountDeclInstanceVariable \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 3 \n",
"\n",
" PercentLackOfCohesion \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 61 \n",
"\n",
" CountDeclClass \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"\n",
" MAJOR_LINE AvgLineBlank \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 1 \n",
"\n",
" CountDeclMethodPublic \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" CountInput_Mean ... \\\n",
"File ... \n",
"activemq-console/src/main/java/org/apache/activ... 2.714286 ... \n",
"\n",
" AvgLineComment \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 6 \n",
"\n",
" CountDeclClassVariable \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" CountClassBase \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1 \n",
"\n",
" OWN_COMMIT \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 1.0 \n",
"\n",
" MaxInheritanceTree \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 2 \n",
"\n",
" CountDeclMethodPrivate \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" MINOR_COMMIT \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0 \n",
"\n",
" AvgEssential COMM \\\n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 2 1 \n",
"\n",
" RatioCommentToCode \n",
"File \n",
"activemq-console/src/main/java/org/apache/activ... 0.7 \n",
"\n",
"[1 rows x 27 columns] \n",
"\n",
"\n",
"label col: \n",
"\n",
" File\n",
"activemq-console/src/main/java/org/apache/activemq/console/command/AbstractAmqCommand.java False\n",
"Name: RealBug, dtype: bool\n"
]
}
],
"source": [
"from pyexplainer.pyexplainer_pyexplainer import AutoSpearman\n",
"# select all rows, and all feature cols\n",
"# the last col, which is label col, is not selected\n",
"X = df.iloc[:, :-1]\n",
"total_features = len(X.columns)\n",
"\n",
"# apply feature selection function to our feature DataFrame\n",
"X = AutoSpearman(X)\n",
"selected = len(X.columns)\n",
"\n",
"# select all rows, and the last label col\n",
"y = df.iloc[:, -1]\n",
"\n",
"print(selected, \" out of \", total_features, \" were selected via AutoSpearman feature selection process\")\n",
"print('feature cols:', '\\n\\n', X.head(1), '\\n\\n')\n",
"print('label col:', '\\n\\n', y.head(1))"
]
},
{
"cell_type": "markdown",
"id": "offshore-cattle",
"metadata": {},
"source": [
"### 1.4 Split data into training and testing set"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "absolute-diversity",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"# 70% training and 30% test\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)"
]
},
{
"cell_type": "markdown",
"id": "fewer-webmaster",
"metadata": {},
"source": [
"## 2. Training and Predicting"
]
},
{
"cell_type": "markdown",
"id": "increased-queensland",
"metadata": {},
"source": [
"### 2.1 Train a RandomForest model using sklearn"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "lesser-coupon",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RandomForestClassifier(random_state=0)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.ensemble import RandomForestClassifier\n",
"\n",
"rf_model = RandomForestClassifier(n_estimators=100, max_depth=None, min_samples_split=2, random_state=0)\n",
"rf_model.fit(X_train, y_train)"
]
},
{
"cell_type": "markdown",
"id": "early-admission",
"metadata": {},
"source": [
"### 2.2 Generate predictions"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "detailed-isaac",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PredictedBug</th>\n",
" </tr>\n",
" <tr>\n",
" <th>File</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>activemq-core/src/main/java/org/apache/activemq/kaha/MapContainer.java</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-core/src/main/java/org/apache/activemq/openwire/v3/MessageAckMarshaller.java</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-core/src/main/java/org/apache/activemq/ConnectionFailedException.java</th>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PredictedBug\n",
"File \n",
"activemq-core/src/main/java/org/apache/activemq... False\n",
"activemq-core/src/main/java/org/apache/activemq... False\n",
"activemq-core/src/main/java/org/apache/activemq... False"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# generate prediction from the model, which will return a list of predicted labels\n",
"y_preds = rf_model.predict(X_test) \n",
"# create a DataFrame which only has predicted label column\n",
"y_preds = pd.DataFrame(data={'PredictedBug': y_preds}, index=y_test.index) \n",
"y_preds.head(3)"
]
},
{
"cell_type": "markdown",
"id": "inappropriate-decline",
"metadata": {},
"source": [
"## 3. Prediction post processing"
]
},
{
"cell_type": "markdown",
"id": "weekly-homeless",
"metadata": {},
"source": [
"### 3.1 Combine feature cols, label col, and the predicted col in testing set"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "steady-comparison",
"metadata": {},
"outputs": [],
"source": [
"combined_testing_data = X_test.join(y_test.to_frame())\n",
"combined_testing_data = combined_testing_data.join(y_preds)\n",
"combined_testing_data.head(3)\n",
"# total num of rows\n",
"total_rows = len(combined_testing_data)"
]
},
{
"cell_type": "markdown",
"id": "viral-limit",
"metadata": {},
"source": [
"### 3.2 Filter out wronly predicted rows "
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "median-element",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The model correctly predicted 90.60000000000001 % of testing data\n"
]
}
],
"source": [
"correctly_predicted_data = combined_testing_data[combined_testing_data['RealBug']==combined_testing_data['PredictedBug']]\n",
"correctly_predicted_rows = len(correctly_predicted_data)\n",
"print('The model correctly predicted ', round((correctly_predicted_rows / total_rows), 3) * 100, '% of testing data')"
]
},
{
"cell_type": "markdown",
"id": "single-compression",
"metadata": {},
"source": [
"### 3.3 We focus on the bug file, therefore, filter out the non-buggy file"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "welsh-aspect",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>CountClassCoupled</th>\n",
" <th>OWN_LINE</th>\n",
" <th>CountDeclMethodProtected</th>\n",
" <th>CountDeclInstanceVariable</th>\n",
" <th>PercentLackOfCohesion</th>\n",
" <th>CountDeclClass</th>\n",
" <th>MAJOR_LINE</th>\n",
" <th>AvgLineBlank</th>\n",
" <th>CountDeclMethodPublic</th>\n",
" <th>CountInput_Mean</th>\n",
" <th>...</th>\n",
" <th>CountClassBase</th>\n",
" <th>OWN_COMMIT</th>\n",
" <th>MaxInheritanceTree</th>\n",
" <th>CountDeclMethodPrivate</th>\n",
" <th>MINOR_COMMIT</th>\n",
" <th>AvgEssential</th>\n",
" <th>COMM</th>\n",
" <th>RatioCommentToCode</th>\n",
" <th>RealBug</th>\n",
" <th>PredictedBug</th>\n",
" </tr>\n",
" <tr>\n",
" <th>File</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>activemq-core/src/test/java/org/apache/activemq/transport/fanout/FanoutTransportBrokerTest.java</th>\n",
" <td>12</td>\n",
" <td>0.738916</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>77</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8</td>\n",
" <td>2.181818</td>\n",
" <td>...</td>\n",
" <td>2</td>\n",
" <td>0.800000</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0.27</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-core/src/main/java/org/apache/activemq/ActiveMQMessageConsumer.java</th>\n",
" <td>27</td>\n",
" <td>0.569082</td>\n",
" <td>10</td>\n",
" <td>21</td>\n",
" <td>89</td>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>35</td>\n",
" <td>4.807692</td>\n",
" <td>...</td>\n",
" <td>4</td>\n",
" <td>0.500000</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" <td>0.42</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>activemq-openwire-generator/src/main/java/org/apache/activemq/openwire/tool/SingleSourceGenerator.java</th>\n",
" <td>0</td>\n",
" <td>0.995781</td>\n",
" <td>8</td>\n",
" <td>8</td>\n",
" <td>88</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>20</td>\n",
" <td>1.428571</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0.666667</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>0.15</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 29 columns</p>\n",
"</div>"
],
"text/plain": [
" CountClassCoupled \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 12 \n",
"activemq-core/src/main/java/org/apache/activemq... 27 \n",
"activemq-openwire-generator/src/main/java/org/a... 0 \n",
"\n",
" OWN_LINE \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.738916 \n",
"activemq-core/src/main/java/org/apache/activemq... 0.569082 \n",
"activemq-openwire-generator/src/main/java/org/a... 0.995781 \n",
"\n",
" CountDeclMethodProtected \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"activemq-core/src/main/java/org/apache/activemq... 10 \n",
"activemq-openwire-generator/src/main/java/org/a... 8 \n",
"\n",
" CountDeclInstanceVariable \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"activemq-core/src/main/java/org/apache/activemq... 21 \n",
"activemq-openwire-generator/src/main/java/org/a... 8 \n",
"\n",
" PercentLackOfCohesion \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 77 \n",
"activemq-core/src/main/java/org/apache/activemq... 89 \n",
"activemq-openwire-generator/src/main/java/org/a... 88 \n",
"\n",
" CountDeclClass \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"activemq-core/src/main/java/org/apache/activemq... 5 \n",
"activemq-openwire-generator/src/main/java/org/a... 1 \n",
"\n",
" MAJOR_LINE AvgLineBlank \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 1 \n",
"activemq-core/src/main/java/org/apache/activemq... 2 0 \n",
"activemq-openwire-generator/src/main/java/org/a... 1 0 \n",
"\n",
" CountDeclMethodPublic \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 8 \n",
"activemq-core/src/main/java/org/apache/activemq... 35 \n",
"activemq-openwire-generator/src/main/java/org/a... 20 \n",
"\n",
" CountInput_Mean ... \\\n",
"File ... \n",
"activemq-core/src/test/java/org/apache/activemq... 2.181818 ... \n",
"activemq-core/src/main/java/org/apache/activemq... 4.807692 ... \n",
"activemq-openwire-generator/src/main/java/org/a... 1.428571 ... \n",
"\n",
" CountClassBase \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"activemq-core/src/main/java/org/apache/activemq... 4 \n",
"activemq-openwire-generator/src/main/java/org/a... 1 \n",
"\n",
" OWN_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.800000 \n",
"activemq-core/src/main/java/org/apache/activemq... 0.500000 \n",
"activemq-openwire-generator/src/main/java/org/a... 0.666667 \n",
"\n",
" MaxInheritanceTree \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 6 \n",
"activemq-core/src/main/java/org/apache/activemq... 1 \n",
"activemq-openwire-generator/src/main/java/org/a... 2 \n",
"\n",
" CountDeclMethodPrivate \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"activemq-core/src/main/java/org/apache/activemq... 5 \n",
"activemq-openwire-generator/src/main/java/org/a... 0 \n",
"\n",
" MINOR_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"activemq-core/src/main/java/org/apache/activemq... 0 \n",
"activemq-openwire-generator/src/main/java/org/a... 0 \n",
"\n",
" AvgEssential COMM \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 5 \n",
"activemq-core/src/main/java/org/apache/activemq... 1 10 \n",
"activemq-openwire-generator/src/main/java/org/a... 1 3 \n",
"\n",
" RatioCommentToCode \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.27 \n",
"activemq-core/src/main/java/org/apache/activemq... 0.42 \n",
"activemq-openwire-generator/src/main/java/org/a... 0.15 \n",
"\n",
" RealBug PredictedBug \n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... True True \n",
"activemq-core/src/main/java/org/apache/activemq... True True \n",
"activemq-openwire-generator/src/main/java/org/a... True True \n",
"\n",
"[3 rows x 29 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"correctly_predicted_bug = correctly_predicted_data[correctly_predicted_data['RealBug']==True]\n",
"correctly_predicted_bug.head(3)"
]
},
{
"cell_type": "markdown",
"id": "systematic-equipment",
"metadata": {},
"source": [
"### 3.4 Define feature cols and label col using correctly predicted testing data"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "shaped-confirmation",
"metadata": {},
"outputs": [],
"source": [
"# select all rows and feature cols\n",
"feature_cols = correctly_predicted_bug.iloc[:, :-2]\n",
"# selected all rows and one label col (either RealBug or PredictedBug is fine since they are the same)\n",
"label_col = correctly_predicted_bug.iloc[:, -2]"
]
},
{
"cell_type": "markdown",
"id": "vocational-spending",
"metadata": {},
"source": [
"### 3.5 Select one row of correctly predicted bug to be explained"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "cross-rhythm",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"one row of feature: \n",
"\n",
" CountClassCoupled \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 12 \n",
"\n",
" OWN_LINE \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.738916 \n",
"\n",
" CountDeclMethodProtected \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"\n",
" CountDeclInstanceVariable \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" PercentLackOfCohesion \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 77 \n",
"\n",
" CountDeclClass \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"\n",
" MAJOR_LINE AvgLineBlank \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 1 \n",
"\n",
" CountDeclMethodPublic \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 8 \n",
"\n",
" CountInput_Mean ... \\\n",
"File ... \n",
"activemq-core/src/test/java/org/apache/activemq... 2.181818 ... \n",
"\n",
" AvgLineComment \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" CountDeclClassVariable \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 \n",
"\n",
" CountClassBase \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" OWN_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.8 \n",
"\n",
" MaxInheritanceTree \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 6 \n",
"\n",
" CountDeclMethodPrivate \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"\n",
" MINOR_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"\n",
" AvgEssential COMM \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 5 \n",
"\n",
" RatioCommentToCode \n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.27 \n",
"\n",
"[1 rows x 27 columns] \n",
"\n",
"one row of label: \n",
"\n",
" File\n",
"activemq-core/src/test/java/org/apache/activemq/transport/fanout/FanoutTransportBrokerTest.java True\n",
"Name: RealBug, dtype: bool\n"
]
}
],
"source": [
"# decide which row to be selected\n",
"selected_row = 0\n",
"# select the row in X_test which contains all of the feature values\n",
"X_explain = feature_cols.iloc[[selected_row]]\n",
"# select the corresponding label from the DataFrame that we just created above\n",
"y_explain = label_col.iloc[[selected_row]]\n",
"print('one row of feature:', '\\n\\n', X_explain, '\\n')\n",
"print('one row of label:', '\\n\\n', y_explain)"
]
},
{
"cell_type": "markdown",
"id": "second-overhead",
"metadata": {},
"source": [
"## 4. Create rules (explanations) and visualise it !"
]
},
{
"cell_type": "markdown",
"id": "private-symbol",
"metadata": {},
"source": [
"### 4.1 Initialise a PyExplainer object"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "coastal-assist",
"metadata": {},
"outputs": [],
"source": [
"from pyexplainer import pyexplainer_pyexplainer\n",
"\n",
"py_explainer = pyexplainer_pyexplainer.PyExplainer(X_train = X_train,\n",
" y_train = y_train,\n",
" indep = X_train.columns,\n",
" dep = 'RealBug',\n",
" blackbox_model = rf_model)"
]
},
{
"cell_type": "markdown",
"id": "fatal-leather",
"metadata": {},
"source": [
"### 4.2 Create rules by triggering explain function under PyExplainer object\n",
"##### Attention: This step can be time-consuming"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "floating-milwaukee",
"metadata": {},
"outputs": [],
"source": [
"rules = py_explainer.explain(X_explain=X_explain,\n",
" y_explain=y_explain,\n",
" search_function='crossoverinterpolation')"
]
},
{
"cell_type": "markdown",
"id": "interim-banner",
"metadata": {},
"source": [
"##### Those created rules are stored in a dictionary, for more information about what is contained in each key, please refer to 'Appendix' part"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "short-atlanta",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"dict_keys(['synthetic_data', 'synthetic_predictions', 'X_explain', 'y_explain', 'indep', 'dep', 'top_k_positive_rules', 'top_k_negative_rules', 'local_rulefit_model'])"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rules.keys()"
]
},
{
"cell_type": "markdown",
"id": "desperate-profit",
"metadata": {},
"source": [
"### 4.3 Simply trigger visualise function under PyExplainer object to visualise the created rules "
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "fourth-queensland",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a2baa847c99441bd982b8792e092f003",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(Label(value='Risk Score: '), FloatProgress(value=0.0, bar_style='info', layout=Layout(width='40…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "07d0fafe28994776bc5666a43c492587",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Output(layout=Layout(border='3px solid black'))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f6f9d182fd2949dbbcc534fd2bfd17d9",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"FloatSlider(value=1.0, continuous_update=False, description='#1 The value of CountDeclClassVariable is more th…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "25fbbd2765cc4afba015f97b46dfdfc8",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"FloatSlider(value=0.0, continuous_update=False, description='#2 The value of CountDeclMethodPrivate is more th…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"py_explainer.visualise(rules)"
]
},
{
"cell_type": "markdown",
"id": "olive-filename",
"metadata": {},
"source": [
"# Appendix"
]
},
{
"cell_type": "markdown",
"id": "closed-draft",
"metadata": {},
"source": [
"## The detail of variables used to to create PyExplainer"
]
},
{
"cell_type": "markdown",
"id": "sufficient-vault",
"metadata": {},
"source": [
"### Synthetic_data\n",
"\n",
"Synthetic_data is data that are generated by PyExplainer using one of the following approaches.\n",
"\n",
"1. Crossover and Interpolation\n",
"2. Random Perturbation.\n",
"\n",
"After Synthetic_data is generated, it is stored as a pandas DataFrame object. "
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "vital-dynamics",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['synthetic_data'] - <class 'pandas.core.frame.DataFrame'> \n",
"\n",
"Example\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>CountClassCoupled</th>\n",
" <th>OWN_LINE</th>\n",
" <th>CountDeclMethodProtected</th>\n",
" <th>CountDeclInstanceVariable</th>\n",
" <th>PercentLackOfCohesion</th>\n",
" <th>CountDeclClass</th>\n",
" <th>MAJOR_LINE</th>\n",
" <th>AvgLineBlank</th>\n",
" <th>CountDeclMethodPublic</th>\n",
" <th>CountInput_Mean</th>\n",
" <th>...</th>\n",
" <th>AvgLineComment</th>\n",
" <th>CountDeclClassVariable</th>\n",
" <th>CountClassBase</th>\n",
" <th>OWN_COMMIT</th>\n",
" <th>MaxInheritanceTree</th>\n",
" <th>CountDeclMethodPrivate</th>\n",
" <th>MINOR_COMMIT</th>\n",
" <th>AvgEssential</th>\n",
" <th>COMM</th>\n",
" <th>RatioCommentToCode</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>0.75</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>42.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>6.0</td>\n",
" <td>3.57</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.8</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>0.27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>1.00</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>68.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>2.60</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" CountClassCoupled OWN_LINE CountDeclMethodProtected \\\n",
"0 1.0 0.75 1.0 \n",
"1 1.0 1.00 0.0 \n",
"\n",
" CountDeclInstanceVariable PercentLackOfCohesion CountDeclClass \\\n",
"0 2.0 42.0 1.0 \n",
"1 2.0 68.0 1.0 \n",
"\n",
" MAJOR_LINE AvgLineBlank CountDeclMethodPublic CountInput_Mean ... \\\n",
"0 0.0 3.0 6.0 3.57 ... \n",
"1 0.0 0.0 5.0 2.60 ... \n",
"\n",
" AvgLineComment CountDeclClassVariable CountClassBase OWN_COMMIT \\\n",
"0 3.0 1.0 1.0 0.8 \n",
"1 0.0 3.0 1.0 1.0 \n",
"\n",
" MaxInheritanceTree CountDeclMethodPrivate MINOR_COMMIT AvgEssential \\\n",
"0 3.0 0.0 0.0 1.0 \n",
"1 6.0 0.0 0.0 1.0 \n",
"\n",
" COMM RatioCommentToCode \n",
"0 5.0 0.27 \n",
"1 2.0 0.64 \n",
"\n",
"[2 rows x 27 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"Type of pyExp_rule_obj['synthetic_data'] - \", type(rules['synthetic_data']), \"\\n\")\n",
"\n",
"print('Example')\n",
"display(rules['synthetic_data'].head(2))"
]
},
{
"cell_type": "markdown",
"id": "quality-examination",
"metadata": {},
"source": [
"### Synthetic_predictions\n",
"\n",
"Synthetic_predictions is the prediction of Synthetic_data, which is obtained from the global model inside PyExplainer."
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "funny-ranch",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['synthetic_predictions'] - <class 'numpy.ndarray'> \n",
"\n",
"Example \n",
"\n",
" [ True False False ... False False False]\n"
]
}
],
"source": [
"print(\"Type of pyExp_rule_obj['synthetic_predictions'] - \", type(rules['synthetic_predictions']), \"\\n\")\n",
"print(\"Example\", \"\\n\\n\", rules['synthetic_predictions'])"
]
},
{
"cell_type": "markdown",
"id": "removable-behalf",
"metadata": {},
"source": [
"### X_explain\n",
"\n",
"X_explain is an instance to be explained (which is a defective commit in this context)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "compound-jewel",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['X_explain'] - <class 'pandas.core.frame.DataFrame'> \n",
"\n",
"Example\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>CountClassCoupled</th>\n",
" <th>OWN_LINE</th>\n",
" <th>CountDeclMethodProtected</th>\n",
" <th>CountDeclInstanceVariable</th>\n",
" <th>PercentLackOfCohesion</th>\n",
" <th>CountDeclClass</th>\n",
" <th>MAJOR_LINE</th>\n",
" <th>AvgLineBlank</th>\n",
" <th>CountDeclMethodPublic</th>\n",
" <th>CountInput_Mean</th>\n",
" <th>...</th>\n",
" <th>AvgLineComment</th>\n",
" <th>CountDeclClassVariable</th>\n",
" <th>CountClassBase</th>\n",
" <th>OWN_COMMIT</th>\n",
" <th>MaxInheritanceTree</th>\n",
" <th>CountDeclMethodPrivate</th>\n",
" <th>MINOR_COMMIT</th>\n",
" <th>AvgEssential</th>\n",
" <th>COMM</th>\n",
" <th>RatioCommentToCode</th>\n",
" </tr>\n",
" <tr>\n",
" <th>File</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>activemq-core/src/test/java/org/apache/activemq/transport/fanout/FanoutTransportBrokerTest.java</th>\n",
" <td>12</td>\n",
" <td>0.738916</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>77</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8</td>\n",
" <td>2.181818</td>\n",
" <td>...</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>0.27</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 27 columns</p>\n",
"</div>"
],
"text/plain": [
" CountClassCoupled \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 12 \n",
"\n",
" OWN_LINE \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.738916 \n",
"\n",
" CountDeclMethodProtected \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"\n",
" CountDeclInstanceVariable \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" PercentLackOfCohesion \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 77 \n",
"\n",
" CountDeclClass \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 3 \n",
"\n",
" MAJOR_LINE AvgLineBlank \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 1 \n",
"\n",
" CountDeclMethodPublic \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 8 \n",
"\n",
" CountInput_Mean ... \\\n",
"File ... \n",
"activemq-core/src/test/java/org/apache/activemq... 2.181818 ... \n",
"\n",
" AvgLineComment \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" CountDeclClassVariable \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 \n",
"\n",
" CountClassBase \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 2 \n",
"\n",
" OWN_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.8 \n",
"\n",
" MaxInheritanceTree \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 6 \n",
"\n",
" CountDeclMethodPrivate \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"\n",
" MINOR_COMMIT \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0 \n",
"\n",
" AvgEssential COMM \\\n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 1 5 \n",
"\n",
" RatioCommentToCode \n",
"File \n",
"activemq-core/src/test/java/org/apache/activemq... 0.27 \n",
"\n",
"[1 rows x 27 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"Type of pyExp_rule_obj['X_explain'] - \", type(rules['X_explain']), \"\\n\")\n",
"\n",
"print('Example')\n",
"display(rules['X_explain'])"
]
},
{
"cell_type": "markdown",
"id": "ongoing-drilling",
"metadata": {},
"source": [
"### y_explain\n",
"\n",
"y_explain is a label of X_explain "
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "antique-straight",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['y_explain'] - <class 'pandas.core.series.Series'> \n",
"\n",
"Example \n",
"\n",
" File\n",
"activemq-core/src/test/java/org/apache/activemq/transport/fanout/FanoutTransportBrokerTest.java True\n",
"Name: RealBug, dtype: bool\n"
]
}
],
"source": [
"print(\"Type of pyExp_rule_obj['y_explain'] - \", type(rules['y_explain']), \"\\n\")\n",
"print(\"Example\", \"\\n\\n\", rules['y_explain'])"
]
},
{
"cell_type": "markdown",
"id": "narrative-senator",
"metadata": {},
"source": [
"### indep\n",
"#### indep is feature names of X_explain"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "sized-valuable",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['indep'] - <class 'pandas.core.indexes.base.Index'> \n",
"\n",
"Example \n",
"\n",
" Index(['CountClassCoupled', 'OWN_LINE', 'CountDeclMethodProtected',\n",
" 'CountDeclInstanceVariable', 'PercentLackOfCohesion', 'CountDeclClass',\n",
" 'MAJOR_LINE', 'AvgLineBlank', 'CountDeclMethodPublic',\n",
" 'CountInput_Mean', 'MaxNesting_Min', 'CountOutput_Min',\n",
" 'CountDeclMethodDefault', 'AvgCyclomaticModified', 'CountInput_Min',\n",
" 'CountDeclClassMethod', 'CountClassDerived', 'AvgLineComment',\n",
" 'CountDeclClassVariable', 'CountClassBase', 'OWN_COMMIT',\n",
" 'MaxInheritanceTree', 'CountDeclMethodPrivate', 'MINOR_COMMIT',\n",
" 'AvgEssential', 'COMM', 'RatioCommentToCode'],\n",
" dtype='object')\n"
]
}
],
"source": [
"print(\"Type of pyExp_rule_obj['indep'] - \", type(rules['indep']), \"\\n\")\n",
"print(\"Example\", \"\\n\\n\", rules['indep'])"
]
},
{
"cell_type": "markdown",
"id": "atlantic-charles",
"metadata": {},
"source": [
"### dep\n",
"#### dep is a label name"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "moral-collectible",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['dep'] - <class 'str'> \n",
"\n",
"Example \n",
"\n",
" RealBug\n"
]
}
],
"source": [
"print(\"Type of pyExp_rule_obj['dep'] - \", type(rules['dep']), \"\\n\")\n",
"print(\"Example\", \"\\n\\n\", rules['dep'])"
]
},
{
"cell_type": "markdown",
"id": "compact-willow",
"metadata": {},
"source": [
"### top_k_positive_rules\n",
"\n",
"top_k_positive_rules is top-k rules that are genereated by PyExplainer to explain why a commit is predicted as defective.\n",
"\n",
"Here we show top-3 rules that lead to defective commits="
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "measured-miller",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['top_k_positive_rules'] - <class 'pandas.core.frame.DataFrame'> \n",
"\n",
"Example\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>index</th>\n",
" <th>rule</th>\n",
" <th>type</th>\n",
" <th>coef</th>\n",
" <th>support</th>\n",
" <th>importance</th>\n",
" <th>is_satisfy_instance</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>161</td>\n",
" <td>AvgLineComment > -3.6149998903274536 & CountCl...</td>\n",
" <td>rule</td>\n",
" <td>3.490109e-23</td>\n",
" <td>0.271540</td>\n",
" <td>1.552240e-23</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>562</td>\n",
" <td>OWN_COMMIT <= 0.8349999785423279 & COMM > 2.98...</td>\n",
" <td>rule</td>\n",
" <td>3.639777e-23</td>\n",
" <td>0.208877</td>\n",
" <td>1.479593e-23</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>820</td>\n",
" <td>CountClassBase <= 2.9850000143051147 & OWN_COM...</td>\n",
" <td>rule</td>\n",
" <td>3.484802e-23</td>\n",
" <td>0.232376</td>\n",
" <td>1.471797e-23</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" index rule type \\\n",
"0 161 AvgLineComment > -3.6149998903274536 & CountCl... rule \n",
"1 562 OWN_COMMIT <= 0.8349999785423279 & COMM > 2.98... rule \n",
"2 820 CountClassBase <= 2.9850000143051147 & OWN_COM... rule \n",
"\n",
" coef support importance is_satisfy_instance \n",
"0 3.490109e-23 0.271540 1.552240e-23 True \n",
"1 3.639777e-23 0.208877 1.479593e-23 True \n",
"2 3.484802e-23 0.232376 1.471797e-23 True "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"Type of pyExp_rule_obj['top_k_positive_rules'] - \", type(rules['top_k_positive_rules']), \"\\n\")\n",
"print('Example')\n",
"display(rules['top_k_positive_rules'].head(3))"
]
},
{
"cell_type": "markdown",
"id": "employed-choir",
"metadata": {},
"source": [
"### top_k_negative_rules\n",
"\n",
"top_k_negative_rules is top-k negative rules that are genereated by PyExplainer to explain why a commit is predicted as clean.\n",
"\n",
"The default number of generated rules is 3.\n"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "opposite-ownership",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Type of pyExp_rule_obj['top_k_negative_rules'] - <class 'pandas.core.frame.DataFrame'> \n",
"\n",
"Example\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>rule</th>\n",
" <th>type</th>\n",
" <th>coef</th>\n",
" <th>support</th>\n",
" <th>importance</th>\n",
" <th>Class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>918</th>\n",
" <td>OWN_COMMIT > 0.8550000190734863 & CountDeclCla...</td>\n",
" <td>rule</td>\n",
" <td>-4.819474e-23</td>\n",
" <td>0.678851</td>\n",
" <td>2.250298e-23</td>\n",
" <td>Clean</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1652</th>\n",
" <td>OWN_COMMIT > 0.8650000095367432</td>\n",
" <td>rule</td>\n",
" <td>-4.748976e-23</td>\n",
" <td>0.689295</td>\n",
" <td>2.197742e-23</td>\n",
" <td>Clean</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1107</th>\n",
" <td>CountDeclMethodPrivate <= 1.8399999737739563 &...</td>\n",
" <td>rule</td>\n",
" <td>-4.863102e-23</td>\n",
" <td>0.725849</td>\n",
" <td>2.169360e-23</td>\n",
" <td>Clean</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" rule type coef \\\n",
"918 OWN_COMMIT > 0.8550000190734863 & CountDeclCla... rule -4.819474e-23 \n",
"1652 OWN_COMMIT > 0.8650000095367432 rule -4.748976e-23 \n",
"1107 CountDeclMethodPrivate <= 1.8399999737739563 &... rule -4.863102e-23 \n",
"\n",
" support importance Class \n",
"918 0.678851 2.250298e-23 Clean \n",
"1652 0.689295 2.197742e-23 Clean \n",
"1107 0.725849 2.169360e-23 Clean "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(\"Type of pyExp_rule_obj['top_k_negative_rules'] - \", type(rules['top_k_negative_rules']), \"\\n\")\n",
"print('Example')\n",
"display(rules['top_k_negative_rules'])"
]
},
{
"cell_type": "markdown",
"id": "written-insertion",
"metadata": {},
"source": [
"# Bug Report Channel\n",
"#### Please report <a href=\"https://github.com/awsm-research/pyExplainer/issues\">here</a>\n",
"#### 📧 or email your report to michaelfu1998@gmail.com"
]
}
],
"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": "3.9.5"
},
"varInspector": {
"cols": {
"lenName": 16,
"lenType": 16,
"lenVar": 40
},
"kernels_config": {
"python": {
"delete_cmd_postfix": "",
"delete_cmd_prefix": "del ",
"library": "var_list.py",
"varRefreshCmd": "print(var_dic_list())"
},
"r": {
"delete_cmd_postfix": ") ",
"delete_cmd_prefix": "rm(",
"library": "var_list.r",
"varRefreshCmd": "cat(var_dic_list()) "
}
},
"types_to_exclude": [
"module",
"function",
"builtin_function_or_method",
"instance",
"_Feature"
],
"window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 5
}