Neurolab-rep

{"nbformat_minor": 0, "cells": [{"execution_count": 1, "cell_type": "code", "source": "import numpy as np\nimport pandas as pd\nimport matplotlib.pylab as plt\n%matplotlib inline", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 2, "cell_type": "code", "source": "from rep.utils import train_test_split\nfrom sklearn.metrics import roc_auc_score\n\nsig_data = pd.read_csv('../toy_datasets/toyMC_sig_mass.csv', sep='\\t')\nbck_data = pd.read_csv('../toy_datasets/toyMC_bck_mass.csv', sep='\\t')\n\nlabels = np.array([1] * len(sig_data) + [0] * len(bck_data))\ndata = pd.concat([sig_data, bck_data])\nvariables = [\"FlightDistance\", \"FlightDistanceError\", \"IP\", \"VertexChi2\", \"pt\", \"p0_pt\", \"p1_pt\", \"p2_pt\", 'LifeTime','dira']", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 3, "cell_type": "code", "source": "X_train, X_test, y_train, y_test = train_test_split(data, labels, train_size=0.5)", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 4, "cell_type": "code", "source": "X_train.shape", "outputs": [{"execution_count": 4, "output_type": "execute_result", "data": {"text/plain": "(72449, 40)"}, "metadata": {}}], "metadata": {"collapsed": false, "trusted": true}}, {"source": "#Neurolab", "cell_type": "markdown", "metadata": {}}, {"source": "\u0422\u0438\u043f \u0441\u0435\u0442\u0438 \u0437\u0430\u0434\u0430\u0451\u0442\u0441\u044f \u043e\u043f\u0446\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u044b\u043c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u043c net_type. fit \u0438 predict \u0440\u0430\u0431\u043e\u0442\u0430\u044e\u0442 \u0432 \u043f\u043e\u043b\u043d\u043e\u043c \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0438\u0438 \u0441 sklearn'\u043e\u0432\u0441\u043a\u043e\u0439 \u0441\u043f\u0435\u0446\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0435\u0439, \u043d\u0438\u043a\u0430\u043a\u0438\u0445 \u043f\u0440\u0435\u0434\u0432\u0430\u0440\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u043f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u043d\u0438\u0439 \u0432\u0445\u043e\u0434\u043d\u044b\u0445 \u0434\u0430\u043d\u043d\u044b\u0445 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u044c \u043d\u0435 \u043d\u0443\u0436\u043d\u043e. \u0422\u0430\u043a\u0436\u0435, \u0432 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0438\u0438 \u0441 \u0438\u0434\u0435\u043e\u043b\u043e\u0433\u0438\u0435\u0439 REP, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0430\u0440\u0433\u0443\u043c\u0435\u043d\u0442 features, \u043e\u0442\u0432\u0435\u0447\u0430\u044e\u0449\u0438\u0439 \u0437\u0430 \u0442\u043e, \u043f\u043e \u043a\u0430\u043a\u0438\u043c \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u0430\u043c \u0438\u0434\u0451\u0442 \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435 \u043c\u043e\u0434\u0435\u043b\u0438.", "cell_type": "markdown", "metadata": {}}, {"execution_count": 12, "cell_type": "code", "source": "import neurolab as nl\nf2 = nl.trans.SoftMax()\nf = nl.trans.LogSig()\nfrom rep.estimators import NeurolabClassifier\nclf = NeurolabClassifier(features=variables, show=1, transf=[f, f, f])", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 19, "cell_type": "code", "source": "%time clf.fit(X_train, y_train)", "outputs": [{"output_type": "stream", "name": "stdout", "text": "Epoch: 1; Error: 18112.25;\nEpoch: 2; Error: 10252.4735735;\nEpoch: 3; Error: 9965.43621617;\nEpoch: 4; Error: 26737.2827356;\nEpoch: 5; Error: 12012.6412675;\nEpoch: 6; Error: 9006.56659507;\nEpoch: 7; Error: 9025.80858723;\nEpoch: 8; Error: 8748.69865159;\nEpoch: 9; Error: 8790.338461;\nEpoch: 10; Error: 8730.6051094;\nThe maximum number of train epochs is reached\nCPU times: user 2min 21s, sys: 208 ms, total: 2min 21s\nWall time: 2min 21s\n"}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 16, "cell_type": "code", "source": "predict_labels = clf.predict(X_test)\npredict_proba = clf.predict_proba(X_test)", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 17, "cell_type": "code", "source": "print predict_labels\nprint predict_proba", "outputs": [{"output_type": "stream", "name": "stdout", "text": "[1 1 1 ..., 1 1 1]\n[[ 0.14969219  0.85030781]\n [ 0.16340585  0.83659415]\n [ 0.14998982  0.85001018]\n ..., \n [ 0.14882971  0.85117029]\n [ 0.14423919  0.85576081]\n [ 0.14883047  0.85116953]]\n"}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 18, "cell_type": "code", "source": "from sklearn.metrics import roc_auc_score\nroc_auc_score(y_test, predict_proba[:, 1])", "outputs": [{"execution_count": 18, "output_type": "execute_result", "data": {"text/plain": "0.71249081962693095"}, "metadata": {}}], "metadata": {"collapsed": false, "trusted": true}}, {"source": "\u041f\u0440\u043e\u0432\u0435\u0440\u0438\u043c, \u0447\u0442\u043e set_params \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442", "cell_type": "markdown", "metadata": {}}, {"execution_count": 31, "cell_type": "code", "source": "clf.set_params(epochs=50, show=0)\n%time clf.fit(X_train, y_train)", "outputs": [{"output_type": "stream", "name": "stdout", "text": "CPU times: user 12min, sys: 933 ms, total: 12min 1s\nWall time: 12min 1s\n"}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 23, "cell_type": "code", "source": "predict_proba = clf.predict_proba(X_test)", "outputs": [], "metadata": {"collapsed": true, "trusted": true}}, {"execution_count": 24, "cell_type": "code", "source": "roc_auc_score(y_test, predict_proba[:, 1])", "outputs": [{"execution_count": 24, "output_type": "execute_result", "data": {"text/plain": "0.82945868098368991"}, "metadata": {}}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 30, "cell_type": "code", "source": "from sklearn.metrics import classification_report\nfrom sklearn.metrics import zero_one_loss\n\nprint \"Accuracy:\", zero_one_loss(y_test, predict_labels)\nprint \"Classification report:\"\nprint classification_report(y_test, predict_labels)", "outputs": [{"output_type": "stream", "name": "stdout", "text": "Accuracy: 0.138881987578\nClassification report:\n             precision    recall  f1-score   support\n\n          0       0.88      0.02      0.03     10208\n          1       0.86      1.00      0.93     62242\n\navg / total       0.86      0.86      0.80     72450\n\n"}], "metadata": {"collapsed": false, "trusted": true}}, {"source": "\u041f\u0440\u043e\u0432\u0435\u0440\u0438\u043c, \u0447\u0442\u043e \u0441\u0435\u0442\u044c \u043d\u043e\u0440\u043c\u0430\u043b\u044c\u043d\u043e (\u0434\u0435-)\u0441\u0435\u0440\u0438\u0430\u043b\u0438\u0437\u0443\u0435\u0442\u0441\u044f \u043d\u0430 \u0434\u0438\u0441\u043a", "cell_type": "markdown", "metadata": {}}, {"execution_count": 27, "cell_type": "code", "source": "import pickle\n\npickle.dump(clf, open(\"dump.p\", \"wb\"))\nclf_loaded = pickle.load(open(\"dump.p\", \"rb\"))", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 29, "cell_type": "code", "source": "predict_proba = clf_loaded.predict_proba(X_test)\nroc_auc_score(y_test, predict_proba[:, 1])", "outputs": [{"execution_count": 29, "output_type": "execute_result", "data": {"text/plain": "0.82945868098368991"}, "metadata": {}}], "metadata": {"collapsed": false, "trusted": true}}], "nbformat": 4, "metadata": {"kernelspec": {"display_name": "Python 2", "name": "python2", "language": "python"}, "language_info": {"mimetype": "text/x-python", "nbconvert_exporter": "python", "version": "2.7.6", "name": "python", "file_extension": ".py", "pygments_lexer": "ipython2", "codemirror_mode": {"version": 2, "name": "ipython"}}}}