{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Explaining a classfier \n", "\n", "It's good to able to explain what an algorithm is doing (esp in public sector).\n", "\n", "It boosts confidence in the ML, good for transparency, and is useful in iterating the model. \n", "\n", "This uses the python package lime (Local Interpretable Model-Agnostic Explanations), an implementation by the authors of their paper - \n", "https://arxiv.org/abs/1602.04938" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: lime in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages\n", "Requirement already satisfied: scikit-image>=0.12 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from lime)\n", "Requirement already satisfied: numpy in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from lime)\n", "Requirement already satisfied: scikit-learn>=0.18 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from lime)\n", "Requirement already satisfied: scipy in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from lime)\n", "Requirement already satisfied: six>=1.7.3 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from scikit-image>=0.12->lime)\n", "Requirement already satisfied: networkx>=1.8 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from scikit-image>=0.12->lime)\n", "Requirement already satisfied: pillow>=2.1.0 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from scikit-image>=0.12->lime)\n", "Requirement already satisfied: dask[array]>=0.5.0 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from scikit-image>=0.12->lime)\n", "Requirement already satisfied: decorator>=3.4.0 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from networkx>=1.8->scikit-image>=0.12->lime)\n", "Requirement already satisfied: olefile in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from pillow>=2.1.0->scikit-image>=0.12->lime)\n", "Requirement already satisfied: toolz>=0.7.2 in c:\\users\\leungr\\appdata\\local\\continuum\\anaconda3\\lib\\site-packages (from dask[array]>=0.5.0->scikit-image>=0.12->lime)\n" ] } ], "source": [ "! pip install lime " ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import sklearn\n", "import sklearn.ensemble\n", "import numpy as np\n", "import lime\n", "import lime.lime_tabular\n", "from __future__ import print_function\n", "np.random.seed(2)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(5000, 2)\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", "
doctopic
0That this House notes the conviction in the Un...House of Lords
1That this House congratulates the US corporate...North America
2That this House is dismayed by the report in t...Speaker
3That this House notes that, according to a No....Members of the Lords
4That this House notes the appointment of a new...House of Lords
\n", "
" ], "text/plain": [ " doc topic\n", "0 That this House notes the conviction in the Un... House of Lords\n", "1 That this House congratulates the US corporate... North America\n", "2 That this House is dismayed by the report in t... Speaker\n", "3 That this House notes that, according to a No.... Members of the Lords\n", "4 That this House notes the appointment of a new... House of Lords" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "blob_account_name = \"parlpublic\"\n", "blob_account_key = \"xKEIV42ZsO8eL2IPjvbLarR2Xu1brxGucDauvVytPXD1uKhAfYUId7SwbGF82FslfkKebPB/ic6/RcPYnNBO6w==\" \n", "container = \"trainingdata\" \n", "blobname = \"5000_edms_justonetopic.csv\"\n", "datafile = \"output.txt\" \n", "import os\n", "import pandas as pd\n", "from azure.storage.blob import BlockBlobService\n", "\n", "dirname = os.getcwd()\n", "\n", "blob_service = BlockBlobService(account_name=blob_account_name,account_key=blob_account_key)\n", "blob_service.get_blob_to_path(container, blobname, datafile)\n", "\n", "edm = pd.read_csv(datafile, header = 0)\n", "os.remove(os.path.join(dirname, datafile))\n", "print(edm.shape)\n", "edm.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# load in tag hierarchy to extract top terms\n", "import json\n", "with open(\"tag_hierarchy.json\", 'r') as f:\n", " data = json.load(f) " ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "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", "
doctopic
0that this house notes the conviction in the un...Parliament, government and politics
1that this house congratulates the us corporate...International affairs
2that this house is dismayed by the report in t...Parliament, government and politics
3that this house notes that according to a no d...Parliament, government and politics
4that this house notes the appointment of a new...Parliament, government and politics
\n", "
" ], "text/plain": [ " doc \\\n", "0 that this house notes the conviction in the un... \n", "1 that this house congratulates the us corporate... \n", "2 that this house is dismayed by the report in t... \n", "3 that this house notes that according to a no d... \n", "4 that this house notes the appointment of a new... \n", "\n", " topic \n", "0 Parliament, government and politics \n", "1 International affairs \n", "2 Parliament, government and politics \n", "3 Parliament, government and politics \n", "4 Parliament, government and politics " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Cleaning\n", "import re\n", "\n", "def clean_text(string):\n", " string = re.sub(r\"\\d\", \"\", string) # remove numbers \n", " string = re.sub(r\"_+\", \"\", string) # remove consecutive underscores\n", " string = re.sub(r\"<[^>]*>\", \" \", string) #remove all html tags\n", " string = re.sub(r\"[^0-9a-zA-Z]+\", \" \", string) # remove speacial chars\n", " string = string.lower() # tranform to lower case \n", " \n", " return string.strip()\n", "\n", "edm[\"doc\"] = edm.doc.apply(clean_text)\n", "\n", "def get_parent(term):\n", " for i in data['children']:\n", " for k in i['children']:\n", " if term == k['name']:\n", " return i['name']\n", " if \"children\" in k:\n", " for j in k['children']:\n", " if term == j['name']:\n", " return get_parent(k['name'])\n", " \n", "# get_parent(\"Supported housing\")\n", "\n", "edm[\"topic\"] = edm.topic.apply(get_parent)\n", "\n", "edm.head()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "CountVectorizer(analyzer='word', binary=False, decode_error='strict',\n", " dtype=, encoding='utf-8', input='content',\n", " lowercase=True, max_df=0.95, max_features=1000, min_df=2,\n", " ngram_range=(1, 1), preprocessor=None, stop_words='english',\n", " strip_accents=None, token_pattern='(?u)\\\\b\\\\w\\\\w+\\\\b',\n", " tokenizer=None, vocabulary=None)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.feature_extraction.text import CountVectorizer\n", "tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2,max_features=1000,stop_words='english')\n", "tf_vectorizer" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "<5000x1000 sparse matrix of type ''\n", "\twith 150811 stored elements in Compressed Sparse Row format>" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X = tf_vectorizer.fit_transform(edm['doc'])\n", "X" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "array([[ 0., 0., 0., ..., 0., 0., 0.],\n", " [ 0., 0., 0., ..., 0., 0., 0.],\n", " [ 0., 0., 0., ..., 0., 0., 0.],\n", " ..., \n", " [ 0., 0., 0., ..., 0., 1., 0.],\n", " [ 0., 0., 0., ..., 0., 0., 0.],\n", " [ 0., 0., 0., ..., 0., 0., 0.]])" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "doc_array = X.toarray() \n", "doc_array.astype(float)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "['shall', 'fight', 'beaches']" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "analyze = tf_vectorizer.build_analyzer()\n", "analyze(\"we shall fight on the beaches\")" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [], "source": [ "feature_names = tf_vectorizer.get_feature_names()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n", " max_depth=None, max_features='auto', max_leaf_nodes=None,\n", " min_impurity_split=1e-07, min_samples_leaf=1,\n", " min_samples_split=2, min_weight_fraction_leaf=0.0,\n", " n_estimators=500, n_jobs=1, oob_score=False, random_state=None,\n", " verbose=0, warm_start=False)" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train, test, labels_train, labels_test = sklearn.model_selection.train_test_split(doc_array, edm.topic, train_size=0.80)\n", "rf = sklearn.ensemble.RandomForestClassifier(n_estimators=500)\n", "rf.fit(train, labels_train)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "0.57399999999999995" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "sklearn.metrics.accuracy_score(labels_test, rf.predict(test))" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": true }, "outputs": [], "source": [ "from sklearn import preprocessing\n", "le = preprocessing.LabelEncoder()\n", "le.fit(edm.topic)\n", "classes_names = le.classes_" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\leungr\\AppData\\Local\\Continuum\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:429: DataConversionWarning: Data with input dtype int64 was converted to float64 by StandardScaler.\n", " warnings.warn(msg, _DataConversionWarning)\n" ] } ], "source": [ "explainer = lime.lime_tabular.LimeTabularExplainer(train, feature_names=feature_names, class_names=classes_names, discretize_continuous=True)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "[array(['calls', 'chief', 'concern', 'court', 'engage', 'ensure',\n", " 'following', 'home', 'legislation', 'notes', 'officers', 'order',\n", " 'police', 'properly', 'public', 'recent', 'secretary', 'senior',\n", " 'settlement'], \n", " dtype='\n", " \n", " \n", "
\n", " \n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "exp = explainer.explain_instance(test[i], rf.predict_proba, num_features=10, top_labels=3)\n", "exp.show_in_notebook(show_table=True, show_all=False)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAABB8AAAKCCAYAAACZEHEPAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\ngItSPgAAAAAXpXwAAAAALqiq/g/PzviSOnGR8wAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Example that a piece of text that's classified as health services with .95 probability \n", "# You can tell for each class (here there are 3), which text features contributed to the prediction and to what degree\n", "from IPython.display import Image\n", "Image(filename='explainml.png') " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Notes\n", "\n", "This isn't the model that'd be used in production, just one sklearn random forests implementation. Though its possible to plug this python script into Azure ML studio (compatible with R and python) and inspect particular ones as requested. With human-in-the-loop retraining setups, may want to save historic models if you want audit trail.\n", "\n", "Besides transprency can check the predictions with low confidence to seek improvements. \n", "\n", "Also this relies on human readable text features. If use feature hashing, have to reverse hash if you want text labels\n", "\n", "To further investigate:\n", "- how this works with more classes, instead of just top 20\n", "- deep learning classifiers\n", "- integrating with Azure to store output into blob\n", "- what are good measures to track across retrained models?\n", "- ..." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 2 }