{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "---\n", "\n", "_You are currently looking at **version 1.0** of this notebook. To download notebooks and datafiles, as well as get help on Jupyter notebooks in the Coursera platform, visit the [Jupyter Notebook FAQ](https://www.coursera.org/learn/python-machine-learning/resources/bANLa) course resource._\n", "\n", "---" ] }, { "cell_type": "markdown", "metadata": { "deletable": true, "editable": true }, "source": [ "# Classifier Visualization Playground\n", "\n", "The purpose of this notebook is to let you visualize various classsifiers' decision boundaries.\n", "\n", "The data used in this notebook is based on the [UCI Mushroom Data Set](http://archive.ics.uci.edu/ml/datasets/Mushroom?ref=datanews.io) stored in `mushrooms.csv`. \n", "\n", "In order to better vizualize the decision boundaries, we'll perform Principal Component Analysis (PCA) on the data to reduce the dimensionality to 2 dimensions. Dimensionality reduction will be covered in a later module of this course.\n", "\n", "Play around with different models and parameters to see how they affect the classifier's decision boundary and accuracy!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "%matplotlib notebook\n", "\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from sklearn.decomposition import PCA\n", "from sklearn.model_selection import train_test_split\n", "\n", "df = pd.read_csv('readonly/mushrooms.csv')\n", "df2 = pd.get_dummies(df)\n", "\n", "df3 = df2.sample(frac=0.08)\n", "\n", "X = df3.iloc[:,2:]\n", "y = df3.iloc[:,1]\n", "\n", "\n", "pca = PCA(n_components=2).fit_transform(X)\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(pca, y, random_state=0)\n", "\n", "\n", "plt.figure(dpi=120)\n", "plt.scatter(pca[y.values==0,0], pca[y.values==0,1], alpha=0.5, label='Edible', s=2)\n", "plt.scatter(pca[y.values==1,0], pca[y.values==1,1], alpha=0.5, label='Poisonous', s=2)\n", "plt.legend()\n", "plt.title('Mushroom Data Set\\nFirst Two Principal Components')\n", "plt.xlabel('PC1')\n", "plt.ylabel('PC2')\n", "plt.gca().set_aspect('equal')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "def plot_mushroom_boundary(X, y, fitted_model):\n", "\n", " plt.figure(figsize=(9.8,5), dpi=100)\n", " \n", " for i, plot_type in enumerate(['Decision Boundary', 'Decision Probabilities']):\n", " plt.subplot(1,2,i+1)\n", "\n", " mesh_step_size = 0.01 # step size in the mesh\n", " x_min, x_max = X[:, 0].min() - .1, X[:, 0].max() + .1\n", " y_min, y_max = X[:, 1].min() - .1, X[:, 1].max() + .1\n", " xx, yy = np.meshgrid(np.arange(x_min, x_max, mesh_step_size), np.arange(y_min, y_max, mesh_step_size))\n", " if i == 0:\n", " Z = fitted_model.predict(np.c_[xx.ravel(), yy.ravel()])\n", " else:\n", " try:\n", " Z = fitted_model.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:,1]\n", " except:\n", " plt.text(0.4, 0.5, 'Probabilities Unavailable', horizontalalignment='center',\n", " verticalalignment='center', transform = plt.gca().transAxes, fontsize=12)\n", " plt.axis('off')\n", " break\n", " Z = Z.reshape(xx.shape)\n", " plt.scatter(X[y.values==0,0], X[y.values==0,1], alpha=0.4, label='Edible', s=5)\n", " plt.scatter(X[y.values==1,0], X[y.values==1,1], alpha=0.4, label='Posionous', s=5)\n", " plt.imshow(Z, interpolation='nearest', cmap='RdYlBu_r', alpha=0.15, \n", " extent=(x_min, x_max, y_min, y_max), origin='lower')\n", " plt.title(plot_type + '\\n' + \n", " str(fitted_model).split('(')[0]+ ' Test Accuracy: ' + str(np.round(fitted_model.score(X, y), 5)))\n", " plt.gca().set_aspect('equal');\n", " \n", " plt.tight_layout()\n", " plt.subplots_adjust(top=0.9, bottom=0.08, wspace=0.02)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true, "scrolled": false }, "outputs": [], "source": [ "from sklearn.linear_model import LogisticRegression\n", "\n", "model = LogisticRegression()\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.neighbors import KNeighborsClassifier\n", "\n", "model = KNeighborsClassifier(n_neighbors=20)\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "\n", "model = DecisionTreeClassifier(max_depth=3)\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "\n", "model = DecisionTreeClassifier()\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "\n", "model = RandomForestClassifier()\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.svm import SVC\n", "\n", "model = SVC(kernel='linear')\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.svm import SVC\n", "\n", "model = SVC(kernel='rbf', C=1)\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.svm import SVC\n", "\n", "model = SVC(kernel='rbf', C=10)\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.naive_bayes import GaussianNB\n", "\n", "model = GaussianNB()\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "deletable": true, "editable": true }, "outputs": [], "source": [ "from sklearn.neural_network import MLPClassifier\n", "\n", "model = MLPClassifier()\n", "model.fit(X_train,y_train)\n", "\n", "plot_mushroom_boundary(X_test, y_test, model)" ] }, { "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": "3.6.2" } }, "nbformat": 4, "nbformat_minor": 2 }