From 9f30627e47197e1d85e582b929342da778ae7614 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Montan=CC=83ana?= Date: Sun, 17 May 2020 18:06:03 +0200 Subject: [PATCH] Fix main and small issues in notebook test --- README.md | 6 +-- main.py | 43 ++++++++++--------- test.ipynb | 110 ++++++++++++------------------------------------- trees/Stree.py | 7 +--- 4 files changed, 52 insertions(+), 114 deletions(-) diff --git a/README.md b/README.md index d13e1e7..b32bfd9 100644 --- a/README.md +++ b/README.md @@ -6,11 +6,11 @@ Oblique Tree classifier based on SVM nodes ## Example -## Jupyter +### Jupyter -[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?filepath=test.ipynb) +[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/test.ipynb) -## Command line +### Command line ```python python main.py diff --git a/main.py b/main.py index 0982a02..36ed38d 100644 --- a/main.py +++ b/main.py @@ -1,11 +1,8 @@ -from sklearn.datasets import make_classification - +import time +from sklearn.model_selection import train_test_split from trees.Stree import Stree -random_state = 1 -X, y = make_classification(n_samples=1500, n_features=3, n_informative=3, - n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2, - class_sep=1.5, flip_y=0, weights=[0.5, 0.5], random_state=random_state) +random_state=1 def load_creditcard(n_examples=0): import pandas as pd @@ -16,8 +13,6 @@ def load_creditcard(n_examples=0): print("Valid: {0:.3f}% {1}".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count())) y = np.expand_dims(df.Class.values, axis=1) X = df.drop(['Class', 'Time', 'Amount'], axis=1).values - #Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y) - #return Xtrain, Xtest, ytrain, ytest if n_examples > 0: # Take first n_examples samples X = X[:n_examples, :] @@ -32,19 +27,23 @@ def load_creditcard(n_examples=0): y = np.append(yt, y[indices], axis=0) print("X.shape", X.shape, " y.shape", y.shape) print("Fraud: {0:.3f}% {1}".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1]))) - print("Valid: {0:.3f}% {1}".format(len(y[y == 0])*100/X.shape[0], len(y[y == 0]))) - return X, y -#X, y = load_creditcard(-5000) -#X, y = load_creditcard() -#X, y = load_creditcard() + print("Valid: {0:.3f}% {1}".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0]))) + Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y) + return Xtrain, Xtest, ytrain, ytest -clf = Stree(C=.01, max_iter=100, random_state=random_state) -clf.fit(X, y) +# data = load_creditcard(-5000) # Take all true samples + 5000 of the others +# data = load_creditcard(5000) # Take the first 5000 samples +data = load_creditcard() # Take all the samples + +Xtrain = data[0] +Xtest = data[1] +ytrain = data[2] +ytest = data[3] + +now = time.time() +clf = Stree(C=.01, random_state=random_state) +clf.fit(Xtrain, ytrain) +print(f"Took {time.time() - now:.2f} seconds to train") print(clf) -#clf.show_tree() -#clf.save_sub_datasets() -yp = clf.predict_proba(X[0, :].reshape(-1, X.shape[1])) -print(f"Predicting {y[0]} we have {yp[0, 0]} with {yp[0, 1]} of belief") -print(f"Classifier's accuracy: {clf.score(X, y, print_out=False):.4f}") -clf.show_tree(only_leaves=True) -print(clf.predict_proba(X)) +print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}") +print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}") \ No newline at end of file diff --git a/test.ipynb b/test.ipynb index 4080ef6..b43acf6 100644 --- a/test.ipynb +++ b/test.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -18,7 +18,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -30,22 +30,16 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "2020-05-17 16:15:24\n" - } - ], + "outputs": [], "source": [ "print(datetime.date.today(), time.strftime(\"%H:%M:%S\"))" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -57,15 +51,9 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "Fraud: 0.173% 492\nValid: 99.827% 284,315\n" - } - ], + "outputs": [], "source": [ "print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n", "print(\"Valid: {0:.3f}% {1:,}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))" @@ -73,7 +61,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -85,15 +73,9 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "X shape: (284807, 29)\ny shape: (284807,)\n" - } - ], + "outputs": [], "source": [ "# Remove unneeded features\n", "y = df.Class.values\n", @@ -103,7 +85,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -114,7 +96,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -124,17 +106,17 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Random Forest\n", - "random_forest = RandomForestClassifier(random_state=random_state, n_jobs=-1, n_estimators=100)" + "random_forest = RandomForestClassifier(random_state=random_state)" ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -144,7 +126,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -154,7 +136,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -164,7 +146,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -189,34 +171,9 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "************************** Linear Tree **********************\nTrain Model Linear Tree took: 14.13 seconds\n=========== Linear Tree - Train 199,364 samples =============\n precision recall f1-score support\n\n 0 1.000000 1.000000 1.000000 199020\n 1 1.000000 1.000000 1.000000 344\n\n accuracy 1.000000 199364\n macro avg 1.000000 1.000000 1.000000 199364\nweighted avg 1.000000 1.000000 1.000000 199364\n\n=========== Linear Tree - Test 85,443 samples =============\n precision recall f1-score support\n\n 0 0.999578 0.999613 0.999596 85295\n 1 0.772414 0.756757 0.764505 148\n\n accuracy 0.999192 85443\n macro avg 0.885996 0.878185 0.882050 85443\nweighted avg 0.999184 0.999192 0.999188 85443\n\nConfusion Matrix in Train\n[[199020 0]\n [ 0 344]]\nConfusion Matrix in Test\n[[85262 33]\n [ 36 112]]\n************************** Random Forest **********************\n" - }, - { - "output_type": "error", - "ename": "KeyboardInterrupt", - "evalue": "", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0moutcomes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmodels\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 10\u001b[0;31m \u001b[0mf1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtime_spent\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtry_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 11\u001b[0m \u001b[0moutcomes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtime_spent\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mf1\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0mbest_f1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m\u001b[0m in \u001b[0;36mtry_model\u001b[0;34m(name, model)\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"************************** {name} **********************\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mnow\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mXtrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mytrain\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0mspent\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mnow\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Train Model {name} took: {spent:.4} seconds\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Code/pyblique/venv/lib/python3.7/site-packages/sklearn/ensemble/_forest.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m 381\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mverbose\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mclass_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclass_weight\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 382\u001b[0m n_samples_bootstrap=n_samples_bootstrap)\n\u001b[0;32m--> 383\u001b[0;31m for i, t in enumerate(trees))\n\u001b[0m\u001b[1;32m 384\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 385\u001b[0m \u001b[0;31m# Collect newly grown trees\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Code/pyblique/venv/lib/python3.7/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m 1015\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1016\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieval_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1017\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieve\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1018\u001b[0m \u001b[0;31m# Make sure that we get a last message telling us we are done\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1019\u001b[0m \u001b[0melapsed_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_start_time\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Code/pyblique/venv/lib/python3.7/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36mretrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 907\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 908\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'supports_timeout'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 909\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 910\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 911\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/Cellar/python/3.7.6_1/Frameworks/Python.framework/Versions/3.7/lib/python3.7/multiprocessing/pool.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 649\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 650\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 651\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 652\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mready\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 653\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTimeoutError\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/Cellar/python/3.7.6_1/Frameworks/Python.framework/Versions/3.7/lib/python3.7/multiprocessing/pool.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 646\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 647\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 648\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_event\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 649\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 650\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/Cellar/python/3.7.6_1/Frameworks/Python.framework/Versions/3.7/lib/python3.7/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 550\u001b[0m \u001b[0msignaled\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_flag\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 551\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0msignaled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 552\u001b[0;31m \u001b[0msignaled\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_cond\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 553\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0msignaled\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 554\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/Cellar/python/3.7.6_1/Frameworks/Python.framework/Versions/3.7/lib/python3.7/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 294\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 295\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 296\u001b[0;31m \u001b[0mwaiter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 297\u001b[0m \u001b[0mgotit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 298\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mKeyboardInterrupt\u001b[0m: " - ] - } - ], + "outputs": [], "source": [ "# Train & Test models\n", "models = {\n", @@ -237,26 +194,9 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "************************************************************************************************************************************\n" - }, - { - "output_type": "error", - "ename": "NameError", - "evalue": "name 'best_model' is not defined", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"*\"\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m132\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"*The best f1 model is {best_model}, with a f1 score: {best_f1:.4} in {best_time:.6} seconds with {train_size:,} samples in train dataset\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"*\"\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m132\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtime_spent\u001b[0m \u001b[0;32min\u001b[0m \u001b[0moutcomes\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Model: {name}\\t Time: {time_spent:6.2f} seconds\\t f1: {f1:.4}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mNameError\u001b[0m: name 'best_model' is not defined" - ] - } - ], + "outputs": [], "source": [ "print(\"*\"*132)\n", "print(f\"*The best f1 model is {best_model}, with a f1 score: {best_f1:.4} in {best_time:.6} seconds with {train_size:,} samples in train dataset\")\n", @@ -269,15 +209,17 @@ "cell_type": "markdown", "metadata": {}, "source": [ + "```\n", "************************************************************************************************************************************\n", "*The best f1 model is Random Forest, with a f1 score: 0.8815 in 218.966 seconds with 0.7 samples in train dataset\n", "************************************************************************************************************************************\n", - "Model: Linear Tree\t Time: 23.05 seconds\t f1: 0.7645\n", + "Model: Linear Tree Time: 23.05 seconds\t f1: 0.7645\n", "Model: Random Forest\t Time: 218.97 seconds\t f1: 0.8815\n", "Model: Stree (SVM Tree)\t Time: 49.45 seconds\t f1: 0.8467\n", "Model: AdaBoost model\t Time: 73.83 seconds\t f1: 0.7509\n", "Model: Gradient Boost.\t Time: 388.69 seconds\t f1: 0.5259\n", - "Model: Neural Network\t Time: 25.47 seconds\t f1: 0.8328" + "Model: Neural Network\t Time: 25.47 seconds\t f1: 0.8328\n", + "```" ] }, { diff --git a/trees/Stree.py b/trees/Stree.py index d0c9573..1f93df6 100644 --- a/trees/Stree.py +++ b/trees/Stree.py @@ -144,15 +144,12 @@ class Stree(BaseEstimator, ClassifierMixin): #result[:, 1] = 1 / (1 + np.exp(-result[:, 1])) return self._reorder_results(result, indices) - def score(self, X: np.array, y: np.array, print_out=True) -> float: + def score(self, X: np.array, y: np.array) -> float: if not self.__trained: self.fit(X, y) yp = self.predict(X).reshape(y.shape) right = (yp == y).astype(int) - accuracy = np.sum(right) / len(y) - if print_out: - print(f"Accuracy: {accuracy:.6f}") - return accuracy + return np.sum(right) / len(y) def __print_tree(self, tree: Snode, only_leaves=False) -> str: if not only_leaves: