From 0a067f597078edee14bbeb41313a9e89c5a8c200 Mon Sep 17 00:00:00 2001
From: ashepley <ashepley@myune.edu.au>
Date: Tue, 4 Aug 2020 13:25:21 +1000
Subject: [PATCH] Upload New File
---
.../Non-linear_Support_Vector_Machinces.ipynb | 332 ++++++++++++++++++
1 file changed, 332 insertions(+)
create mode 100644 topic_28/Non-linear_Support_Vector_Machinces.ipynb
diff --git a/topic_28/Non-linear_Support_Vector_Machinces.ipynb b/topic_28/Non-linear_Support_Vector_Machinces.ipynb
new file mode 100644
index 0000000..e38af6e
--- /dev/null
+++ b/topic_28/Non-linear_Support_Vector_Machinces.ipynb
@@ -0,0 +1,332 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Non-linear Support Vector Machines\n",
+ "\n",
+ "You can obtain the dataset used in this lecture here: https://www.kaggle.com/rakeshrau/social-network-ads/data. It is a 'categorical dataset to determine whether a user purchased a particular product'."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#import\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "from matplotlib.colors import *\n",
+ "import pandas as pd\n",
+ "from sklearn.model_selection import *\n",
+ "from sklearn.linear_model import LinearRegression\n",
+ "from sklearn.metrics import *\n",
+ "from sklearn import metrics\n",
+ "from sklearn.svm import SVC\n",
+ "from sklearn.preprocessing import StandardScaler"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Here are the functions you used in the previous lectures"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def load_data(DATASET_PATH):\n",
+ " return pd.read_csv(DATASET_PATH)\n",
+ "\n",
+ "def check_NaN(dataframe):\n",
+ " print(\"Total NaN:\", dataframe.isnull().values.sum())\n",
+ " print(\"NaN by column:\\n\",dataframe.isnull().sum())\n",
+ " return\n",
+ "\n",
+ "def one_hot_encode(dataframe, col_name):\n",
+ " dataframe = pd.get_dummies(dataframe, columns=[col_name], prefix = [col_name])\n",
+ " return dataframe"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Load the dataset, and have a look at its contents"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DATASET_PATH = './datasets/Social_Network_Ads.csv'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#create pandas object\n",
+ "ads = load_data(DATASET_PATH)\n",
+ "ads.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We'll be training our SVM on the Age and Estimated Salary features, to predict whether the user purchased a product based on an ad or not. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "chosen_columns = ['Age','EstimatedSalary','Purchased']\n",
+ "subset = ads.filter(chosen_columns)\n",
+ "subset.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Always check whether your subset contains NaN values"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "check_NaN(subset)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Split the dataset into train and test sets"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "x_train, x_test, y_train, y_test = train_test_split(subset.drop(['Purchased'], axis=1),subset['Purchased'],test_size=0.2,random_state=42) \n",
+ "print(\"x train/test \",x_train.shape, x_test.shape)\n",
+ "print(\"y train/test \",y_train.shape, y_test.shape)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "x_dev = x_train.values\n",
+ "y_dev = y_train.values\n",
+ "x_t = x_test.values\n",
+ "y_t = y_test.values"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Normalisation of data is expected when using SVMs. Learn more here:\n",
+ "https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#feature scaling\n",
+ "sc = StandardScaler()\n",
+ "\n",
+ "x_dev = sc.fit_transform(x_dev)\n",
+ "x_t = sc.fit_transform(x_t)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### SVM Classifier\n",
+ "Create the SVM, and train it on the standardised data\n",
+ "\n",
+ "### Parameters for SVC: Gamma and C\n",
+ "A lower value of Gamma will loosely fit the training dataset, whereas a higher value of gamma will exactly fit the training dataset resulting in over-fitting.\n",
+ "\n",
+ "C parameter used is to maintain regularization. A smaller value of C creates a small-margin hyperplane and a larger value of C creates a larger-margin hyperplane."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "svm_classifier = SVC(kernel = 'rbf', random_state=0)#gamma=0.001, C=10\n",
+ "svm_classifier.fit(x_dev, y_dev)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Inference"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Pass in the test set, to see how well it performs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "predictions = svm_classifier.predict(x_t)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Confusion matrix shows you how many of each class were correctly and incorrectly classified"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "confusion_matrix(y_t, predictions, labels = [0,1])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Evaluation\n",
+ "Evaluation using mean squared error and accuracy, precision and recall"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#mean squared error\n",
+ "np.mean((predictions - y_t) ** 2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"Accuracy:\",str(metrics.accuracy_score(y_t, predictions)*100)+\"%\")\n",
+ "print(\"Precision:\",str(round(metrics.precision_score(y_t, predictions)*100))+\"%\")\n",
+ "print(\"Recall:\",str(round(metrics.recall_score(y_t, predictions)*100))+\"%\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Visualisation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "xs, ys = x_t, y_t\n",
+ "\n",
+ "X1, X2 = np.meshgrid(np.arange(start = xs[:,0].min() - 1,stop = xs[:,0].max() + 1,step = 0.01),\n",
+ " np.arange(start = xs[:,1].min() - 1,stop = xs[:,1].max() + 1,step = 0.01))\n",
+ "\n",
+ "plt.contourf(X1,X2, svm_classifier.predict(np.array([X1.ravel(),X2.ravel()]).T).reshape(X1.shape),\n",
+ " alpha = 0.75, cmap = ListedColormap(('orange','grey')))\n",
+ "\n",
+ "plt.xlim(X1.min(),X1.max())\n",
+ "plt.ylim(X2.min(),X2.max())\n",
+ "\n",
+ "for i, j in enumerate(np.unique(ys)):\n",
+ " plt.scatter(xs[ys==j,0],xs[ys==j,1],\n",
+ " c=ListedColormap(('orange','grey'))(i),label = j)\n",
+ "\n",
+ "plt.title('Test Set')\n",
+ "plt.xlabel('Age')\n",
+ "plt.ylabel('Estimated Salary')\n",
+ "plt.legend()\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Exercise\n",
+ "Add the feature 'Gender' to the training set, and see if the accuracy improves and the mean squared error drops!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "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": "3.7.1"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--
GitLab