{ "cells": [ { "cell_type": "code", "execution_count": 5, "id": "36ac21fc", "metadata": {}, "outputs": [], "source": [ "# Import dependencies and packages neededfrom sklearn import datasets\n", "from sklearn.svm import SVC\n", "from sklearn.model_selection import train_test_split\n", "import numpy as np\n", "import pandas as pd\n", "import seaborn as sn\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 6, "id": "3c07c748", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
565116740025.60.201300
6737850328831.00.248261
781011500035.30.134290
892197704554330.50.158531
910812596000.00.232541
10114110920037.60.191300
111210168740038.00.537341
121310139800027.11.441570
13141189602384630.10.398591
14155166721917525.80.587511
1516710000030.00.484321
16170118844723045.80.551311
17187107740029.60.254311
1819110330388343.30.183330
1920111570309634.60.529321
\n", "
" ], "text/plain": [ " PatientId Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n", "0 1 6 148 72 35 0 \n", "1 2 1 85 66 29 0 \n", "2 3 8 183 64 0 0 \n", "3 4 1 89 66 23 94 \n", "4 5 0 137 40 35 168 \n", "5 6 5 116 74 0 0 \n", "6 7 3 78 50 32 88 \n", "7 8 10 115 0 0 0 \n", "8 9 2 197 70 45 543 \n", "9 10 8 125 96 0 0 \n", "10 11 4 110 92 0 0 \n", "11 12 10 168 74 0 0 \n", "12 13 10 139 80 0 0 \n", "13 14 1 189 60 23 846 \n", "14 15 5 166 72 19 175 \n", "15 16 7 100 0 0 0 \n", "16 17 0 118 84 47 230 \n", "17 18 7 107 74 0 0 \n", "18 19 1 103 30 38 83 \n", "19 20 1 115 70 30 96 \n", "\n", " BMI DiabetesPedigreeFunction Age Outcome \n", "0 33.6 0.627 50 1 \n", "1 26.6 0.351 31 0 \n", "2 23.3 0.672 32 1 \n", "3 28.1 0.167 21 0 \n", "4 43.1 2.288 33 1 \n", "5 25.6 0.201 30 0 \n", "6 31.0 0.248 26 1 \n", "7 35.3 0.134 29 0 \n", "8 30.5 0.158 53 1 \n", "9 0.0 0.232 54 1 \n", "10 37.6 0.191 30 0 \n", "11 38.0 0.537 34 1 \n", "12 27.1 1.441 57 0 \n", "13 30.1 0.398 59 1 \n", "14 25.8 0.587 51 1 \n", "15 30.0 0.484 32 1 \n", "16 45.8 0.551 31 1 \n", "17 29.6 0.254 31 1 \n", "18 43.3 0.183 33 0 \n", "19 34.6 0.529 32 1 " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# import the dataset (stored in a variable)\n", "diabetes = pd.read_csv(\"diabetes.csv\")\n", "# Inspect the data(first five rows, or this can be changed by including how many rows within the brackets)\n", "diabetes.head(20)" ] }, { "cell_type": "code", "execution_count": 7, "id": "f5ce7fbc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 614 entries, 60 to 102\n", "Data columns (total 10 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 PatientId 614 non-null int64 \n", " 1 Pregnancies 614 non-null int64 \n", " 2 Glucose 614 non-null int64 \n", " 3 BloodPressure 614 non-null int64 \n", " 4 SkinThickness 614 non-null int64 \n", " 5 Insulin 614 non-null int64 \n", " 6 BMI 614 non-null float64\n", " 7 DiabetesPedigreeFunction 614 non-null float64\n", " 8 Age 614 non-null int64 \n", " 9 Outcome 614 non-null int64 \n", "dtypes: float64(2), int64(8)\n", "memory usage: 52.8 KB\n" ] } ], "source": [ "# split the data into train and test using the SciKitLearn package\n", "from sklearn.model_selection import train_test_split\n", "train,test=train_test_split(diabetes,test_size=0.2,random_state=42)\n", "# view the information\n", "train.info()" ] }, { "cell_type": "code", "execution_count": 8, "id": "9c236d8a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 154 entries, 668 to 462\n", "Data columns (total 8 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 Pregnancies 154 non-null int64 \n", " 1 Glucose 154 non-null int64 \n", " 2 BloodPressure 154 non-null int64 \n", " 3 SkinThickness 154 non-null int64 \n", " 4 Insulin 154 non-null int64 \n", " 5 BMI 154 non-null float64\n", " 6 DiabetesPedigreeFunction 154 non-null float64\n", " 7 Age 154 non-null int64 \n", "dtypes: float64(2), int64(6)\n", "memory usage: 10.8 KB\n" ] } ], "source": [ "# Ensure only labels are saved in y variables\n", "y_train=train['Outcome']\n", "y_test=test['Outcome']\n", "#drop the unwanted / irrelevant columns, features are stored in X variables\n", "X_train=train.drop(['PatientId','Outcome'],axis=1)\n", "X_test=test.drop(['PatientId','Outcome'],axis=1)\n", "# view the information\n", "X_test.info()" ] }, { "cell_type": "code", "execution_count": 9, "id": "cf217602", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'C': 1.0,\n", " 'break_ties': False,\n", " 'cache_size': 200,\n", " 'class_weight': None,\n", " 'coef0': 0.0,\n", " 'decision_function_shape': 'ovr',\n", " 'degree': 3,\n", " 'gamma': 'scale',\n", " 'kernel': 'rbf',\n", " 'max_iter': -1,\n", " 'probability': False,\n", " 'random_state': None,\n", " 'shrinking': True,\n", " 'tol': 0.001,\n", " 'verbose': False}" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# this step is just to demonstrate the adjustable parameters within the algorithm and not a necessary step\n", "SVC().get_params()" ] }, { "cell_type": "code", "execution_count": 10, "id": "3f4c8504", "metadata": {}, "outputs": [], "source": [ "# # this step is just to demonstrate the api methods and not a necessary step\n", "# dir(SVC)" ] }, { "cell_type": "code", "execution_count": 11, "id": "25ec0839", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
SVC()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "SVC()" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Create a model for Support Vector (Machine) Classifier using default parameters\n", "model = SVC()\n", "# fit the data to the model, both features and labels to train it\n", "model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 12, "id": "59cf09a6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0,\n", " 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0,\n", " 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n", " 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0],\n", " dtype=int64)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# use the model to classify the datapoints within the test set\n", "y_pred2=model.predict(X_test)\n", "# print predicted classifications\n", "y_pred2" ] }, { "cell_type": "code", "execution_count": 13, "id": "606707f8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "668 0\n", "324 0\n", "624 0\n", "690 0\n", "473 0\n", " ..\n", "355 1\n", "534 0\n", "344 0\n", "296 1\n", "462 0\n", "Name: Outcome, Length: 154, dtype: int64" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# print test labels (ground truth) that is compared to classifier\n", "y_test" ] }, { "cell_type": "code", "execution_count": 14, "id": "fb8d51eb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[87 12]\n", " [24 31]]\n", " precision recall f1-score support\n", "\n", " 0 0.784 0.879 0.829 99\n", " 1 0.721 0.564 0.633 55\n", "\n", " accuracy 0.766 154\n", " macro avg 0.752 0.721 0.731 154\n", "weighted avg 0.761 0.766 0.759 154\n", "\n" ] } ], "source": [ "# display the metrics of the model's classification through confusion matrix and classification report\n", "# (accuracy / precision / recall / f1)\n", "from sklearn import metrics\n", "print(metrics.confusion_matrix(y_test, y_pred2))\n", "\n", "\n", "print(metrics.classification_report(y_test, y_pred2, digits=3))" ] }, { "cell_type": "code", "execution_count": 15, "id": "a1096778", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Actual Predicted\n", "668 0 0\n", "324 0 0\n", "624 0 0\n", "690 0 0\n", "473 0 0\n", ".. ... ...\n", "355 1 1\n", "534 0 0\n", "344 0 0\n", "296 1 0\n", "462 0 0\n", "\n", "[154 rows x 2 columns]\n" ] } ], "source": [ "# use Pandas to create a dataframe to view the ground truth and classifications side by side\n", "data = {'Actual': y_test,\n", " 'Predicted': y_pred2}\n", "df = pd.DataFrame(data)\n", "print(df)" ] }, { "cell_type": "code", "execution_count": 16, "id": "e5d198fa", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.784 0.879 0.829 99\n", " 1 0.721 0.564 0.633 55\n", "\n", " accuracy 0.766 154\n", " macro avg 0.752 0.721 0.731 154\n", "weighted avg 0.761 0.766 0.759 154\n", "\n" ] } ], "source": [ "# Use Seaborn to create a confusion matrix heatmap and MatPlotLib to display\n", "confusion_matrix = pd.crosstab(df['Actual'], df['Predicted'], rownames=['Actual'], colnames=['Predicted'])\n", "sn.heatmap(confusion_matrix, annot=True)\n", "plt.show()\n", "print(metrics.classification_report(y_test, y_pred2, digits=3))" ] }, { "cell_type": "markdown", "id": "ef72442e-63bb-4a75-a2ab-dd2aa8df1840", "metadata": {}, "source": [ "## Searching for the Best Hyperparameters with GridSearchCV" ] }, { "cell_type": "code", "execution_count": 17, "id": "fa40302a", "metadata": {}, "outputs": [], "source": [ "# Create an iterative grid search to tune the parameters\n", "import joblib\n", "from sklearn.model_selection import GridSearchCV" ] }, { "cell_type": "code", "execution_count": 18, "id": "06a71bed", "metadata": {}, "outputs": [], "source": [ "# Create a function to show the results of the classifier under different parameter values\n", "def print_results(results):\n", " print('Best Parameters: {}\\n'.format(results.best_params_))\n", " \n", " means = results.cv_results_['mean_test_score']\n", " stds = results.cv_results_['std_test_score']\n", " for mean, std, params in zip(means, stds, results.cv_results_['params']):\n", " print('{} (+/-{}) for {}'.format(round(mean, 3), round(std * 2, 3), params))" ] }, { "cell_type": "code", "execution_count": 26, "id": "5404a42e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Best Parameters: {'C': 1, 'kernel': 'linear'}\n", "\n", "0.942 (+/-0.125) for {'C': 0.1, 'kernel': 'linear'}\n", "0.892 (+/-0.155) for {'C': 0.1, 'kernel': 'rbf'}\n", "0.958 (+/-0.091) for {'C': 1, 'kernel': 'linear'}\n", "0.95 (+/-0.122) for {'C': 1, 'kernel': 'rbf'}\n", "0.95 (+/-0.122) for {'C': 10, 'kernel': 'linear'}\n", "0.95 (+/-0.122) for {'C': 10, 'kernel': 'rbf'}\n" ] } ], "source": [ "# Create a model using the Support Vector Classifier / Machine algorithm\n", "svm = SVC()\n", "# Set the parameters to be tuned\n", "parameters = {\n", " 'kernel' : ['linear', 'rbf'],\n", " 'C' : [0.1, 1, 10]\n", "}\n", "# instantiate the grid search\n", "cv = GridSearchCV(svm, parameters, cv=5)\n", "# fit the training data to the model\n", "cv.fit(X_train, y_train.ravel())\n", "# display the model evaluation with the different paramter combination values (C value and kernel)\n", "print_results(cv)" ] }, { "cell_type": "code", "execution_count": 27, "id": "4bfb84c7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'C': 1,\n", " 'break_ties': False,\n", " 'cache_size': 200,\n", " 'class_weight': None,\n", " 'coef0': 0.0,\n", " 'decision_function_shape': 'ovr',\n", " 'degree': 3,\n", " 'gamma': 'scale',\n", " 'kernel': 'linear',\n", " 'max_iter': -1,\n", " 'probability': False,\n", " 'random_state': None,\n", " 'shrinking': True,\n", " 'tol': 0.001,\n", " 'verbose': False}" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# show the best paramters for classification (not a necesary step unless you are saving best parameter models to compare)\n", "cv.best_estimator_.get_params()" ] }, { "cell_type": "markdown", "id": "33f56a89-cf7c-4697-9629-c04199149a09", "metadata": {}, "source": [ "# Decision Tree" ] }, { "cell_type": "code", "execution_count": 28, "id": "9be2e2e6-cc3e-46e1-8ece-1d74db056ff4", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Feature importances: [0.01667014 0.01667014 0.88947325 0.07718647]\n" ] } ], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.datasets import load_iris\n", "\n", "data = load_iris()\n", "X, y = data.data, data.target\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "dtree = DecisionTreeClassifier()\n", "dtree.fit(X_train, y_train)\n", "\n", "y_pred = dtree.predict(X_test)\n", "\n", "print(\"Feature importances:\", dtree.feature_importances_)\n" ] }, { "cell_type": "markdown", "id": "b691d410-c1f7-419e-9c3f-24f0d55545db", "metadata": {}, "source": [ "# NaiveBayes " ] }, { "cell_type": "code", "execution_count": 29, "id": "6881fb78-9b6d-441c-88ba-91ad3a30c9b9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Class probabilities: [[5.97327448e-090 9.95635767e-001 4.36423302e-003]\n", " [1.00000000e+000 4.96158126e-014 6.54922363e-021]\n", " [7.31890302e-290 4.92947614e-012 1.00000000e+000]\n", " [2.81842533e-094 9.77593559e-001 2.24064412e-002]\n", " [1.13877801e-105 8.70022596e-001 1.29977404e-001]\n", " [1.00000000e+000 1.73180181e-013 3.66170159e-021]\n", " [5.90437185e-053 9.99955645e-001 4.43550046e-005]\n", " [5.98735064e-177 1.18219872e-006 9.99998818e-001]\n", " [4.01752535e-096 9.92158276e-001 7.84172366e-003]\n", " [3.15071776e-059 9.99938983e-001 6.10171853e-005]\n", " [4.44911663e-152 5.88867020e-004 9.99411133e-001]\n", " [1.00000000e+000 2.04863718e-017 4.73585098e-025]\n", " [1.00000000e+000 4.22431128e-017 1.86022566e-024]\n", " [1.00000000e+000 5.31248651e-017 1.85939976e-024]\n", " [1.00000000e+000 8.92960033e-017 4.55408899e-024]\n", " [1.04918592e-107 6.02930476e-001 3.97069524e-001]\n", " [6.78610052e-204 5.05656256e-007 9.99999494e-001]\n", " [3.07256674e-055 9.99982769e-001 1.72305837e-005]\n", " [1.46366429e-084 9.98040608e-001 1.95939244e-003]\n", " [1.68882019e-192 2.94971181e-006 9.99997050e-001]\n", " [1.00000000e+000 5.98122647e-016 1.63332320e-023]\n", " [8.42966853e-128 9.89169319e-002 9.01083068e-001]\n", " [1.00000000e+000 1.43755981e-013 2.80756525e-021]\n", " [4.85851497e-185 1.83103291e-005 9.99981690e-001]\n", " [9.62966511e-234 1.64396056e-009 9.99999998e-001]\n", " [8.19796396e-181 1.37161759e-006 9.99998628e-001]\n", " [9.32787870e-178 6.28437300e-004 9.99371563e-001]\n", " [7.90472310e-219 1.36528257e-008 9.99999986e-001]\n", " [1.00000000e+000 2.08539921e-015 1.67773682e-023]\n", " [1.00000000e+000 1.31930917e-015 3.02915134e-023]]\n" ] } ], "source": [ "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.datasets import load_iris\n", "\n", "data = load_iris()\n", "X, y = data.data, data.target\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "nb_model = GaussianNB()\n", "nb_model.fit(X_train, y_train)\n", "\n", "y_pred = nb_model.predict(X_test)\n", "\n", "print(\"Class probabilities:\", nb_model.predict_proba(X_test))\n" ] }, { "cell_type": "markdown", "id": "d105e676-f417-4b03-b21d-74d1b52d474b", "metadata": {}, "source": [ "# Summary and Conclusion" ] }, { "cell_type": "markdown", "id": "433777c4-445e-451c-b2de-bdc858dae981", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "id": "f1a9fe59-25f8-4528-93b1-bea00ffc9f52", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }