{ "cells": [ { "cell_type": "code", "execution_count": 1, "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": 2, "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", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\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", "\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 " ] }, "execution_count": 2, "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()" ] }, { "cell_type": "code", "execution_count": 3, "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": 4, "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": 5, "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": 5, "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": 6, "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": 7, "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": 7, "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": 8, "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": 8, "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": 9, "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": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# print test labels (ground truth) that is compared to classifier\n", "y_test" ] }, { "cell_type": "code", "execution_count": 10, "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": 11, "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": 12, "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": 13, "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": 14, "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": 15, "id": "5404a42e", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\hp\\AppData\\Local\\Temp\\ipykernel_11644\\3758584095.py:11: FutureWarning: Series.ravel is deprecated. The underlying array is already 1D, so ravel is not necessary. Use `to_numpy()` for conversion to a numpy array instead.\n", " cv.fit(X_train, y_train.ravel())\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Best Parameters: {'C': 0.1, 'kernel': 'linear'}\n", "\n", "0.767 (+/-0.053) for {'C': 0.1, 'kernel': 'linear'}\n", "0.651 (+/-0.004) for {'C': 0.1, 'kernel': 'rbf'}\n", "0.765 (+/-0.056) for {'C': 1, 'kernel': 'linear'}\n", "0.752 (+/-0.053) for {'C': 1, 'kernel': 'rbf'}\n", "0.762 (+/-0.049) for {'C': 10, 'kernel': 'linear'}\n", "0.761 (+/-0.055) 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": 16, "id": "4bfb84c7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'C': 0.1,\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": 16, "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": "code", "execution_count": null, "id": "05d7456f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "33f56a89-cf7c-4697-9629-c04199149a09", "metadata": {}, "source": [ "# Decision Tree" ] }, { "cell_type": "markdown", "id": "472032f5-928c-49ab-8c8d-b2454195ea2a", "metadata": {}, "source": [ "from sklearn.tree import DecissionTreeClassifier" ] }, { "cell_type": "code", "execution_count": 17, "id": "9be2e2e6-cc3e-46e1-8ece-1d74db056ff4", "metadata": {}, "outputs": [], "source": [ "from sklearn.tree import DecisionTreeClassifier" ] }, { "cell_type": "code", "execution_count": 18, "id": "714cc906-b012-4f5e-973c-39b57e9aa903", "metadata": {}, "outputs": [], "source": [ "# Create Decision Tree classifer object\n", "clf = DecisionTreeClassifier()\n", "\n", "# Train Decision Tree Classifer\n", "clf = clf.fit(X_train,y_train)\n", "\n", "#Predict the response for test dataset\n", "y_pred = clf.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 19, "id": "7f34e620-79ef-4655-a898-5594adc55ecc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[78 21]\n", " [16 39]]\n", " precision recall f1-score support\n", "\n", " 0 0.830 0.788 0.808 99\n", " 1 0.650 0.709 0.678 55\n", "\n", " accuracy 0.760 154\n", " macro avg 0.740 0.748 0.743 154\n", "weighted avg 0.766 0.760 0.762 154\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_pred))\n", "\n", "\n", "print(metrics.classification_report(y_test, y_pred, digits=3))" ] }, { "cell_type": "code", "execution_count": 20, "id": "7d1f2281-ead6-4947-9a92-44525fe6bc9b", "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 1\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_pred}\n", "df = pd.DataFrame(data)\n", "print(df)" ] }, { "cell_type": "code", "execution_count": 21, "id": "1b5bd6e9-982f-49b4-99f7-decdf5a9ed3b", "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 0.830 0.788 0.808 99\n", " 1 0.650 0.709 0.678 55\n", "\n", " accuracy 0.760 154\n", " macro avg 0.740 0.748 0.743 154\n", "weighted avg 0.766 0.760 0.762 154\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_pred, digits=3))" ] }, { "cell_type": "markdown", "id": "b691d410-c1f7-419e-9c3f-24f0d55545db", "metadata": {}, "source": [ "# NaiveBayes " ] }, { "cell_type": "markdown", "id": "5cb737da-8ca9-43b7-8b39-c3f0b4f02d1b", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "id": "6881fb78-9b6d-441c-88ba-91ad3a30c9b9", "metadata": {}, "outputs": [], "source": [] }, { "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 [conda env:base] *", "language": "python", "name": "conda-base-py" }, "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 }