{ "cells": [ { "cell_type": "code", "execution_count": 4, "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": 5, "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": 5, "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": 6, "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": 7, "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": 8, "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": 8, "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": 9, "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": 10, "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": 10, "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": 11, "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": 11, "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": 12, "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": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# print test labels (ground truth) that is compared to classifier\n", "y_test" ] }, { "cell_type": "code", "execution_count": 13, "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": 14, "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": 15, "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": 16, "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": 17, "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": 18, "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": 19, "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": 19, "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": "code", "execution_count": 20, "id": "ae91e95b-eab1-4cf4-8273-c3f309680712", "metadata": {}, "outputs": [], "source": [ "from sklearn.tree import DecisionTreeClassifier" ] }, { "cell_type": "markdown", "id": "472032f5-928c-49ab-8c8d-b2454195ea2a", "metadata": {}, "source": [ "from sklearn.tree import DecissionTreeClassifier" ] }, { "cell_type": "code", "execution_count": 24, "id": "435da210-fd53-4ab3-8ecf-a2b5007599f4", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
DecisionTreeClassifier()
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": [ "DecisionTreeClassifier()" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Create a model for DecissionTree classifier using default parameters\n", "DTmodel = DecisionTreeClassifier()\n", "\n", "# fit the data to the model, both features and labels to train it\n", "DTmodel.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 29, "id": "aca60fec-b2ba-4374-9814-d772f049e2c8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1,\n", " 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n", " 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1,\n", " 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,\n", " 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", " 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0])" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# use the model to classify the data within the test set\n", "DTy_pred=DTmodel.predict(X_test)\n", "# print predicted classifications\n", "DTy_pred" ] }, { "cell_type": "code", "execution_count": 30, "id": "7227801f-2e80-4ec3-ac98-987232c16385", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[79 20]\n", " [18 37]]\n", " precision recall f1-score support\n", "\n", " 0 0.814 0.798 0.806 99\n", " 1 0.649 0.673 0.661 55\n", "\n", " accuracy 0.753 154\n", " macro avg 0.732 0.735 0.733 154\n", "weighted avg 0.755 0.753 0.754 154\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, DTy_pred))\n", "\n", "\n", "print(metrics.classification_report(y_test, DTy_pred, digits=3))" ] }, { "cell_type": "code", "execution_count": 33, "id": "49d7f222-a00e-4890-838c-b2daaf7dce9e", "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 0.814 0.798 0.806 99\n", " 1 0.649 0.673 0.661 55\n", "\n", " accuracy 0.753 154\n", " macro avg 0.732 0.735 0.733 154\n", "weighted avg 0.755 0.753 0.754 154\n", "\n" ] } ], "source": [ "# Use Seaborn to create a confusion matrix heatmap and MatPlotLib to display\n", "confusion_matrix = pd.crosstab(df['Actual'], DTy_pred, rownames=['Actual'], colnames=['Predicted'])\n", "sn.heatmap(confusion_matrix, annot=True)\n", "plt.show()\n", "print(metrics.classification_report(y_test, DTy_pred, digits=3))" ] }, { "cell_type": "code", "execution_count": 27, "id": "5234f77f-19a1-4cdb-aeaa-18f1e44e607c", "metadata": {}, "outputs": [], "source": [ "from sklearn.datasets import load_iris\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import accuracy_score\n" ] }, { "cell_type": "code", "execution_count": null, "id": "ca69f501-4cc5-451a-8b40-48bc473ed59c", "metadata": {}, "outputs": [], "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": "code", "execution_count": null, "id": "14033631-63b3-4cfe-b53b-4ed1373ae15f", "metadata": {}, "outputs": [], "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": "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 }