{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "28511a89", "metadata": {}, "outputs": [], "source": [ "# Import dependencies and packages needed\n", "from sklearn import neighbors, datasets\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\n", "from sklearn import datasets" ] }, { "cell_type": "code", "execution_count": 2, "id": "6492ec18", "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": "987e1130", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Int64Index: 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": "fea7a65c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Int64Index: 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": "48a3730a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'algorithm': 'auto',\n", " 'leaf_size': 30,\n", " 'metric': 'minkowski',\n", " 'metric_params': None,\n", " 'n_jobs': None,\n", " 'n_neighbors': 5,\n", " 'p': 2,\n", " 'weights': 'uniform'}" ] }, "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", "neighbors.KNeighborsClassifier().get_params()" ] }, { "cell_type": "code", "execution_count": 6, "id": "5cd6e3bf", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['__abstractmethods__',\n", " '__class__',\n", " '__delattr__',\n", " '__dict__',\n", " '__dir__',\n", " '__doc__',\n", " '__eq__',\n", " '__format__',\n", " '__ge__',\n", " '__getattribute__',\n", " '__getstate__',\n", " '__gt__',\n", " '__hash__',\n", " '__init__',\n", " '__init_subclass__',\n", " '__le__',\n", " '__lt__',\n", " '__module__',\n", " '__ne__',\n", " '__new__',\n", " '__reduce__',\n", " '__reduce_ex__',\n", " '__repr__',\n", " '__setattr__',\n", " '__setstate__',\n", " '__sizeof__',\n", " '__str__',\n", " '__subclasshook__',\n", " '__weakref__',\n", " '_abc_impl',\n", " '_check_algorithm_metric',\n", " '_check_feature_names',\n", " '_check_n_features',\n", " '_estimator_type',\n", " '_fit',\n", " '_get_param_names',\n", " '_get_tags',\n", " '_kneighbors_reduce_func',\n", " '_more_tags',\n", " '_pairwise',\n", " '_repr_html_',\n", " '_repr_html_inner',\n", " '_repr_mimebundle_',\n", " '_validate_data',\n", " 'fit',\n", " 'get_params',\n", " 'kneighbors',\n", " 'kneighbors_graph',\n", " 'predict',\n", " 'predict_proba',\n", " 'score',\n", " 'set_params']" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# this step is just to demonstrate the api methods and not a necessary step\n", "dir(neighbors.KNeighborsClassifier)" ] }, { "cell_type": "code", "execution_count": 7, "id": "edaa2532", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "KNeighborsClassifier(n_neighbors=3)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Create a model for K-Nearest Neighbours and include parameters\n", "model = neighbors.KNeighborsClassifier(n_neighbors=3)\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": "9c479ce4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0,\n", " 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1,\n", " 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1,\n", " 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0,\n", " 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1,\n", " 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0,\n", " 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 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": "c3a45ab5", "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": "93c59e31", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[65 34]\n", " [20 35]]\n", " precision recall f1-score support\n", "\n", " 0 0.765 0.657 0.707 99\n", " 1 0.507 0.636 0.565 55\n", "\n", " accuracy 0.649 154\n", " macro avg 0.636 0.646 0.636 154\n", "weighted avg 0.673 0.649 0.656 154\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": "40459779", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Actual Predicted\n", "668 0 0\n", "324 0 1\n", "624 0 0\n", "690 0 1\n", "473 0 1\n", ".. ... ...\n", "355 1 1\n", "534 0 0\n", "344 0 0\n", "296 1 1\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": "4ad19c10", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.765 0.657 0.707 99\n", " 1 0.507 0.636 0.565 55\n", "\n", " accuracy 0.649 154\n", " macro avg 0.636 0.646 0.636 154\n", "weighted avg 0.673 0.649 0.656 154\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": "code", "execution_count": 13, "id": "11fe93ff", "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": "deafc454", "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": 16, "id": "30e640b6", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Best Parameters: {'n_neighbors': 11}\n", "\n", "0.708 (+/-0.027) for {'n_neighbors': 3}\n", "0.718 (+/-0.027) for {'n_neighbors': 5}\n", "0.728 (+/-0.056) for {'n_neighbors': 7}\n", "0.736 (+/-0.047) for {'n_neighbors': 9}\n", "0.743 (+/-0.069) for {'n_neighbors': 11}\n" ] } ], "source": [ "# Create a model using the KNN algorithm\n", "knn = neighbors.KNeighborsClassifier()\n", "# Set the parameters to be tuned\n", "parameters = {\n", " 'n_neighbors' : [3, 5, 7, 9, 11]\n", "}\n", "# instantiate the grid search\n", "cv = GridSearchCV(knn, 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 values (K value)\n", "print_results(cv)" ] }, { "cell_type": "code", "execution_count": 17, "id": "9ef91a8e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'algorithm': 'auto',\n", " 'leaf_size': 30,\n", " 'metric': 'minkowski',\n", " 'metric_params': None,\n", " 'n_jobs': None,\n", " 'n_neighbors': 11,\n", " 'p': 2,\n", " 'weights': 'uniform'}" ] }, "execution_count": 17, "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": "5a903f22", "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": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 5 }