From ad4fdf25cb2369bfa03bc3d0590d5d380317f6bd Mon Sep 17 00:00:00 2001
From: ashepley <ashepley@myune.edu.au>
Date: Tue, 4 Aug 2020 13:21:19 +1000
Subject: [PATCH] Upload New File
---
...Linear_Support_Vector_Machines-Final.ipynb | 404 ++++++++++++++++++
1 file changed, 404 insertions(+)
create mode 100644 topic_27/Linear_Support_Vector_Machines-Final.ipynb
diff --git a/topic_27/Linear_Support_Vector_Machines-Final.ipynb b/topic_27/Linear_Support_Vector_Machines-Final.ipynb
new file mode 100644
index 0000000..1c95764
--- /dev/null
+++ b/topic_27/Linear_Support_Vector_Machines-Final.ipynb
@@ -0,0 +1,404 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Linear Support Vector Machines\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "from matplotlib import pyplot as plt\n",
+ "from sklearn import svm\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "from sklearn.svm import SVC\n",
+ "from sklearn.metrics import *\n",
+ "from sklearn import metrics\n",
+ "import matplotlib.pyplot as plt\n",
+ "from matplotlib.colors import *"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "xBlue = np.array([0.3,0.5,1,1.4,1.7,2])\n",
+ "yBlue = np.array([1,4.5,2.3,1.9,8.9,4.1])\n",
+ "xRed = np.array([3.3,3.5,4,4.4,5.7,6])\n",
+ "yRed = np.array([7,1.5,6.3,1.9,2.9,7.1])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X = np.array([[0.3,1],[0.5,4.5],[1,2.3],[1.4,1.9],[1.7,8.9],[2,4.1],[3.3,7],[3.5,1.5],[4,6.3],[4.4,1.9],[5.7,2.9],[6,7.1]])\n",
+ "y = np.array([0,0,0,0,0,0,1,1,1,1,1,1]) # 0: blue class, 1: red class"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.plot(xBlue, yBlue, 'ro', color='blue')\n",
+ "plt.plot(xRed, yRed, 'ro', color='red')\n",
+ "plt.plot(4.5,4.5,'ro',color='green')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "classifier = svm.SVC()\n",
+ "classifier.fit(X,y)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "coord = [4.5,4.5]\n",
+ "blue_red = classifier.predict([coord])\n",
+ "\n",
+ "if blue_red == 1:\n",
+ " print(coord,\" is red\")\n",
+ "else:\n",
+ " print(coord, \" is blue\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Let's apply this to 'real' data!\n",
+ "\n",
+ "We'll be using a Support Vector Machine to predict whether a country is developed or not based its World Health Organisation life expectancy and GDP. You can access the dataset in this lecture here: https://www.kaggle.com/augustus0498/life-expectancy-who"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "from sklearn.model_selection import *\n",
+ "from sklearn.linear_model import LinearRegression\n",
+ "import numpy as np\n",
+ "from sklearn.metrics import mean_squared_error\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "\n",
+ "def load_data(DATASET_PATH):\n",
+ " return pd.read_csv(DATASET_PATH)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DATASET_PATH = './datasets/2015.csv'\n",
+ "dataset = load_data(DATASET_PATH)\n",
+ "dataset.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#functions\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 fillNaN_median(dataframe, key):\n",
+ " median = dataframe[key].median()\n",
+ " dataframe[key].fillna(median, inplace = True)\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\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "dataset.columns"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "dataset.loc[dataset['Happiness Score'] < 5, 'Happiness Score'] = 0\n",
+ "dataset.loc[dataset['Happiness Score'] >= 5, 'Happiness Score'] = 1\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "dataset.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Choose your features: We'll be choosing Happiness Score','Trust (Government Corruption)','Economy (GDP per Capita)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#chosen_columns = ['Happiness Score','Economy (GDP per Capita)','Family']\n",
+ "chosen_columns = ['Happiness Score','Trust (Government Corruption)','Economy (GDP per Capita)']\n",
+ "#You can experiment with others, such as;'Measles','AdultMortality','infantdeaths','Alcohol','HepatitisB','Measles','Polio','Population','thinness5-9years','HIV/AIDS','BMI','Diphtheria','GDP']\n",
+ "life_expectancy = dataset.filter(chosen_columns)\n",
+ "life_expectancy.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Check the feature columns for NaN values and correct any missing data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "check_NaN(life_expectancy)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Create the train and test splits"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "x_train, x_test, y_train, y_test = train_test_split(life_expectancy.drop(['Happiness Score'], axis=1),life_expectancy['Happiness Score'],test_size=0.2,random_state=12) \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. \n",
+ "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": [
+ "#### Train the linear SVM"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 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.\n",
+ "\t\t\t\t\t\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "svm_classifier = SVC(kernel = 'linear')#gamma=0.001,C=100\n",
+ "svm_classifier.fit(x_dev, y_dev)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Inference\n",
+ "Pass in the test set..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "predictions = svm_classifier.predict(x_t)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Evaluation\n",
+ "Check out the mean squared error and accuracy"
+ ]
+ },
+ {
+ "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(round(metrics.accuracy_score(y_t, predictions)*100))+\"%\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Visualise Linearly Seperable Data"
+ ]
+ },
+ {
+ "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('Trust')\n",
+ "plt.ylabel('GDP')\n",
+ "plt.legend()\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Exercise\n",
+ "Train an SVM using Family and Life Expectancy to predict whether a country is happy or not. Is this data linearly seperable?"
+ ]
+ },
+ {
+ "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