{ "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])" ] }, "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": "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": [ "[[77 22]\n", " [16 39]]\n", " precision recall f1-score support\n", "\n", " 0 0.828 0.778 0.802 99\n", " 1 0.639 0.709 0.672 55\n", "\n", " accuracy 0.753 154\n", " macro avg 0.734 0.743 0.737 154\n", "weighted avg 0.761 0.753 0.756 154\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": 22, "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 0.828 0.778 0.802 99\n", " 1 0.639 0.709 0.672 55\n", "\n", " accuracy 0.753 154\n", " macro avg 0.734 0.743 0.737 154\n", "weighted avg 0.761 0.753 0.756 154\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": "code", "execution_count": null, "id": "4052ebb5-e7d8-4559-a4c9-5c67db402883", "metadata": {}, "outputs": [], "source": [ "# Import necessary libraries\n", "import pandas as pd\n", "import seaborn as sn\n", "import matplotlib.pyplot as plt\n", "from sklearn import metrics\n", "\n", "# 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() # Fixed typo: changed pltl to plt\n", "print(metrics.classification_report(y_test, y_pred, digits=3))" ] }, { "cell_type": "code", "execution_count": null, "id": "cc0723c0-b231-4ef4-870e-934e52be8aeb", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "c6060471-f0c9-40cf-a0fc-f293b727829e", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "anaconda-panel-2023.05-py310", "language": "python", "name": "conda-env-anaconda-panel-2023.05-py310-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": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 5 }