{ "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", "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": "9c236d8a", "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": "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": 1, "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/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": 12, "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": 14, "id": "e5d198fa", "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWgAAAEGCAYAAABIGw//AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAW0klEQVR4nO3deZRV1ZXH8e+PAnGOIIMFGoeIGmMiKtoOiRoR5wRNgq0mkaSJpUnUaCYx3Stq2u42KzFpkybRUjRlggOiBNR2wHJAO4GIihNoUEQcSnCKOCBY9Xb/8S6mIlS9V/Deu6fK38d1Vr07vHM3rlqbw77nnquIwMzM0tMr7wDMzGzNnKDNzBLlBG1mlignaDOzRDlBm5klqnfeAXTkvVcWenqJrWaDIZ/JOwRLUOvKF7SufXQl5/QZsN06X68cySZoM7OaKrTlHcFqnKDNzACikHcEq3GCNjMDKDhBm5klKTyCNjNLVFtr3hGsxgnazAx8k9DMLFkucZiZJco3Cc3M0uSbhGZmqfII2swsUW3v5R3BapygzczANwnNzJLlEoeZWaI8gjYzS5RH0GZmaYpCejcJ/UYVMzMojqDLbSVIOlPS45Iek3S1pPUl9Zc0Q9KC7Ge/Uv04QZuZQbEGXW7rhKShwOnAiIjYBagDjgPGA80RMQxozrY75QRtZgbFxZLKbaX1BjaQ1BvYEHgRGA00ZcebgKNLdeIEbWYGFRtBR8QLwM+BxUAL8EZE3A4MjoiW7JwWYFCpkJygzcygSzVoSQ2S5rRrDau6yWrLo4FtgSHARpK+sjYheRaHmRl0acH+iGgEGjs4fDDwTES8DCDpBmBfYImk+ohokVQPLC11HY+gzcygkrM4FgN7S9pQkoCRwHxgOjA2O2csMK1URx5Bm5kBEZV5o0pEzJY0BXgQaAUeojja3hiYLGkcxSQ+plRfTtBmZlDRJwkj4hzgnA/sXkFxNF02J2gzM/BaHGZmyfJaHGZmierCLI5acYI2MwOXOMzMkuUSh5lZopygzcwS5RKHmVmifJPQzCxRLnGYmSXKJQ4zs0R5BG1mlignaDOzREXkHcFqnKDNzABaPYvDzCxNvkloZpYo16DNzBLlGrSZWaI8gjYzS5QTtJlZmqKtMi+NraReeQdgZpaEQqH81glJO0qa264tk3SGpP6SZkhakP3sVyokJ2gzMyhOsyu3ddZNxJMRMTwihgN7AO8AU4HxQHNEDAOas+1OOUGbmQEUovxWvpHA0xHxLDAaaMr2NwFHl/qya9BmZlCtm4THAVdnnwdHRAtARLRIGlTqyx5Bm5kBtLWV3SQ1SJrTrjV8sDtJ6wGfB65b25A8gk7MlddM5fobb0USwz62Def/6Lv86PwLWbT4eQDefOstNtl4Y65vmpBzpFZLlzZeyJFHHMzSl19h+G4jAfjpf/0bRx41ipUrV7Jw4bOM+8Z3eeONZTlH2o11YQQdEY1AY4nTDgcejIgl2fYSSfXZ6LkeWFrqOh5BJ2TJy68waco0rr38V/zxDxdTKBS45Y57uPDfz+b6pglc3zSBUQd+moMP2DfvUK3GrrxyMkce9eV/2HdH80x2HX4Qu+8xigULFjL+rFNziq6HqHwN+nj+Xt4AmA6MzT6PBaaV6sAJOjGtbW2sWLGS1tY2lr+7goED+r9/LCK49c6ZHDHqwPwCtFzce99sXnv9b/+wb8YdM2nL5u7Omv0gQ4fW5xBZD1KhWRwAkjYERgE3tNt9ATBK0oLs2AWl+qlaiUPSThTvWg4FAngRmB4R86t1ze5u8MABfO34L3LwF05k/b7rse+eu7PfP+3x/vEHHn6Mzfv1Y+uthuYYpaXo6187jsnXTc87jO6ta7MzOhUR7wCbf2DfqxRndZStKiNoSWcB1wAC/gLcn32+WlKHc//aF94vu/Lqjk7rsd5Y9iZ33TuL2667gjunTWL5uyu48bY73z/+vzPu5ohRB+QYoaXo7PGn09raylVX3VD6ZOtQFAplt1qp1gh6HPCJiHiv/U5JvwAep4OhffvC+3uvLExvaakqmzVnLkOHDKZ/v80AGHnAvsx9dB6fO/QgWlvbuOOePzH58l/lG6Ql5atfHcORRxzMqEOPzTuU7u9D9Kh3ARiyhv312TFbg/rBA3nksSdY/u67RASz58xlu623AmDWnIfYbust2WLQwJyjtFQcesiB/OD73+LoL3yN5cvfzTuc7q86D6qsk2qNoM8AmrNi+HPZvo8C2wO+1dyBT31iJ0Z99tMc+/XTqKurY6cdPsaY0YcDcMsd93D4wQfmG6Dl5g+/n8AB++/DgAH9WbRwDuf95Oec9cNT6du3L7fecg0As2c/yLdPLfn0sHUkwdXsFFVapFpSL2AvijcJBTwP3B8RZf074sNY4rDSNhjymbxDsAS1rnxB69rH2z8+ruycs9FPrlnn65WjarM4IqIAzKpW/2ZmFeV3EpqZJaqGteVyOUGbmQHRmt4sDidoMzPwCNrMLFmuQZuZJcojaDOzNIUTtJlZonyT0MwsUR5Bm5klygnazCxN1Vr2Yl04QZuZgUfQZmbJcoI2M0tTtPpBFTOzNKWXn/1WbzMzKD6oUm4rRdJmkqZIekLSfEn7SOovaYakBdnPfqX6cYI2M4NKv/LqIuDWiNgJ2BWYD4wHmiNiGNCcbXfKCdrMDIoljnJbJyRtCuwPTASIiJUR8TdgNNCUndYEHF0qJCdoMzMqWuLYDngZuELSQ5Iuk7QRMDgiWgCyn4NKdeQEbWYGRGuU3SQ1SJrTrjW066o3sDvw24jYDXibMsoZa+JZHGZm0KVZHBHRCDR2cPh54PmImJ1tT6GYoJdIqo+IFkn1wNJS1/EI2syM4nr95bZO+4l4CXhO0o7ZrpHAPGA6MDbbNxaYViomj6DNzKDS86BPAyZJWg9YCHyd4oB4sqRxwGJgTKlOnKDNzKjsG68iYi4wYg2HRnalHydoMzMgWvOOYHVO0GZmJPnOWCdoMzNwgjYzS1co7whW4wRtZoZH0GZmyYqCR9BmZkkqtDlBm5klySUOM7NEucRhZpaoSO+dsU7QZmbgEbSZWbJ8k9DMLFHdagQt6ddAh1WZiDi9KhGZmeUgutmThHNqFoWZWc661TS7iGjq6JiZWU9T6GYjaAAkDQTOAnYG1l+1PyIOqmJcZmY1lWKJo5x3Ek4C5gPbAucBi4D7qxiTmVnNFdpUdquVchL05hExEXgvIu6JiH8B9q5yXGZmNRUFld1qpZxpdu9lP1skHQm8CGxZvZDMzGqvW9aggfMlfQT4HvBrYFPgzKpGZWZWY5WsQUtaBLwJtAGtETFCUn/gWmAbiqXiYyPi9c76KZmgI+Km7OMbwGfXPmQzs3RVYS2Oz0bEK+22xwPNEXGBpPHZ9lmddVDOLI4rWMMDK1kt2sysR6hBiWM0cGD2uQm4m3VN0MBN7T6vDxxDsQ5tZtZjFCp78y+A2yUFcElENAKDI6IFICJaJA0q1Uk5JY7r229Luhq4Y+1iNjNLU1dG0JIagIZ2uxqzJLzKfhHxYpaEZ0h6Ym1iWpvFkoYBH12bi3XFQbueVO1LWDd04pB98g7Beqiu3CTMknFjJ8dfzH4ulTQV2AtYIqk+Gz3XA0tLXafkPGhJb0patqoBN1KibmJm1t0UQmW3zkjaSNImqz4DhwCPAdOBsdlpY4FppWIqp8SxSalzzMy6uwpO4hgMTJUExRx7VUTcKul+YLKkccBiYEypjsqZxdEcESNL7TMz687aCuU8WF1aRCwEdl3D/leBLuXNztaDXh/YEBggqR+waly/KTCkKxcxM0tdgquNdjqCPhk4g2IyfoC/J+hlwITqhmVmVltBN3rUOyIuAi6SdFpE/LqGMZmZ1Vwhwbd6l1N0KUjabNWGpH6SvlW9kMzMaq+Aym61Uk6CPiki/rZqI1vcw5OUzaxHCVR2q5VyHlTpJUkRxaVEJNUB61U3LDOz2mrrTjXodm6jOHfvYopTBU8BbqlqVGZmNdbdZnGschbFZ86/SXEmx0NAfTWDMjOrtRQTdMkadEQUgFnAQmAExYnW86scl5lZTXWrGrSkHYDjgOOBVym+CYCI8KL9Ztbj1PBVg2XrrMTxBHAv8LmIeApAkl91ZWY9Ui2nz5WrsxLHF4GXgLskXSppJCT4JzAzq4C2LrRa6TBBR8TUiPhnYCeKr2Y5Exgs6beSDqlRfGZmNVGQym61Us5NwrcjYlJEHAVsCcyl+LJDM7MeI7rQaqVL6+tFxGsRcUlEHFStgMzM8lDoQquVtXnllZlZj9PdZnGYmX1odNdHvc3MejyPoM3MEpXio95O0GZm1HZ2Rrkq85ZEM7NurqDyWzkk1Ul6SNJN2XZ/STMkLch+9ivVhxO0mRlVmWb3Hf5xYbnxQHNEDAOaKeN5EidoMzOgTeW3UiRtCRwJXNZu92igKfvcBBxdqh/XoM3MqPhNwv8Gfghs0m7f4IhoAYiIFkmDSnXiEbSZGV0rcUhqkDSnXWtY1Y+ko4ClEfHAusbkEbSZGV2bxRERjUBjB4f3Az4v6QhgfWBTSX8Alkiqz0bP9cDSUtfxCNrMjMrN4oiIsyNiy4jYhuJLT+6MiK8A04Gx2WljgWmlYvII2syMmjyocgHFF3CPAxYDY0p9wQnazIzqLMQfEXdTXE+fiHiV4jtdy+YEbWaG1+IwM0uW1+IwM0tUimtxOEGbmQGFBFO0E7SZGbV9W3e5nKDNzHAN2swsWZ7FYWaWKNegzcwSlV56doI2MwNcgzYzS1ZbgmNoJ2gzMzyCNjNLlm8SmpklKr307ARtZga4xGFmlizfJDQzS5Rr0FbSoCED+deLxtN/YD+iEEyfdDNTJt7w/vHjTh7Dt398CkftcgxvvL4sx0itVnr37cP4a39Cn7596FVXx5xb/sy0X05mxBH7MPqMY6nffijnjz6bRY8+nXeo3Vp66dkJOjltrW1MOO9i/vrYAjbYaAMm3noxc2Y+wKIFzzJoyED23H8PXnp+Sd5hWg21rniPn51wHiveeZe63nWcPeV8Hr37IV54cjETTvkZJ/7nyXmH2COkOIL2W70T8+rS1/jrYwsAWP72chYteJYBWwwA4LRzv8Vv/qORiPR+kay6VrzzLgB1veuo610HAS1Pv8BLC1/MObKeo9CFViseQSdsiy0Hs8Mu2zPvofnsN2ofXm55hafnLcw7LMuBevXinJt+yqCtt+DO39/GwrkL8g6px4kKjaAlrQ/MBPpSzLFTIuIcSf2Ba4FtgEXAsRHxemd91XwELenrnRxrkDRH0pyX3n6hlmElZ4MN1+f8S8/lV+f8hrbWNk48/ctM/Pnv8g7LchKFAuce8QO+t8/JbLvr9gzdYau8Q+px2oiyWwkrgIMiYldgOHCYpL2B8UBzRAwDmrPtTuVR4jivowMR0RgRIyJixBYbDa1lTEmp613H+Zeey4ypzcy85T6GbjOE+o9uwRUzGpk8axID6wcy8baL6T+wX96hWo0tX/YOT856nF0O2C3vUHqcSpU4ouitbLNP1gIYDTRl+5uAo0vFVJUSh6RHOjoEDK7GNXuS8Rd+n0VPLebaxikALHziGT6/65fePz551iROOvybnsXxIbFJ/01pbW1l+bJ36NN3PXbe71PccvEf8w6rxylU8N6OpDrgAWB7YEJEzJY0OCJaACKiRdKgUv1UqwY9GDgU+GB9RcCfqnTNHuGTe+7CYV86hKfnLeTy2y8BoPGCicy68y85R2Z5+cigfoy78FR69eqFeon7b/4TD9/5ALsfuhcnnDuOTfpvyncuP5vn5i/iFyeen3e43VZX0rOkBqCh3a7GiGh8v6+INmC4pM2AqZJ2WZuYVI0ZAZImAldExH1rOHZVRJxQqo/PDB3pqQq2mmF9XNax1V2+aMo6v7DqhK2PKTvnXPXs1LKvJ+kc4G3gJODAbPRcD9wdETt29t2q1KAjYtyaknN2rGRyNjOrtejCf52RNDAbOSNpA+Bg4AlgOjA2O20sMK1UTJ5mZ2YGtFbuQZV6oCmrQ/cCJkfETZL+DEyWNA5YDIwp1ZETtJkZlZsHHRGPAKtNs4mIV4GRXenLCdrMDC83amaWrBSXUHCCNjMjzcWSnKDNzPCC/WZmyfII2swsUa5Bm5klyrM4zMwSVal50JXkBG1mhmvQZmbJaov0ihxO0GZmuMRhZpasSi7YXylO0GZmdG3B/lpxgjYzwzcJzcyS5QRtZpYoz+IwM0uUZ3GYmSXKa3GYmSXKNWgzs0SlOILulXcAZmYpaKNQduuMpK0k3SVpvqTHJX0n299f0gxJC7Kf/UrF5ARtZkbxScJyWwmtwPci4uPA3sC3Je0MjAeaI2IY0Jxtd8oJ2syM4iyOcv/rtJ+Iloh4MPv8JjAfGAqMBpqy05qAo0vF5Bq0mRnVWYtD0jbAbsBsYHBEtEAxiUsaVOr7HkGbmdG1EbSkBklz2rWGD/YnaWPgeuCMiFi2NjF5BG1mRtdG0BHRCDR2dFxSH4rJeVJE3JDtXiKpPhs91wNLS13HI2gzM4qPepfbOiNJwERgfkT8ot2h6cDY7PNYYFqpmDyCNjOjoo967wd8FXhU0txs34+AC4DJksYBi4ExpTpygjYzA6JCiyVFxH2AOjg8sit9OUGbmeFHvc3MkpXio95O0GZmeARtZpastoIX7DczS5IX7DczS5Rr0GZmiXIN2swsUR5Bm5klyjcJzcwS5RKHmVmiXOIwM0tUNRbsX1dO0GZmeB60mVmyPII2M0tUoULLjVaSE7SZGb5JaGaWLCdoM7NEpZeeQSn+rWH/SFJD9hZhs/f596Ln81u9u4eGvAOwJPn3oodzgjYzS5QTtJlZopyguwfXGW1N/HvRw/kmoZlZojyCNjNLlBO0mVminKATJ+kwSU9KekrS+LzjsfxJulzSUkmP5R2LVZcTdMIk1QETgMOBnYHjJe2cb1SWgN8Bh+UdhFWfE3Ta9gKeioiFEbESuAYYnXNMlrOImAm8lnccVn1O0GkbCjzXbvv5bJ+ZfQg4QadNa9jneZFmHxJO0Gl7Htiq3faWwIs5xWJmNeYEnbb7gWGStpW0HnAcMD3nmMysRpygExYRrcCpwG3AfGByRDyeb1SWN0lXA38GdpT0vKRxecdk1eFHvc3MEuURtJlZopygzcwS5QRtZpYoJ2gzs0Q5QZuZJcoJ2qpCUpukuZIek3SdpA3Xoa/fSfpS9vmyzhaMknSgpH3X4hqLJA1Y2xjNqsEJ2qpleUQMj4hdgJXAKe0PZiv1dVlEfCMi5nVyyoFAlxO0WYqcoK0W7gW2z0a3d0m6CnhUUp2kn0m6X9Ijkk4GUNH/SJon6WZg0KqOJN0taUT2+TBJD0p6WFKzpG0o/kVwZjZ6/4ykgZKuz65xv6T9su9uLul2SQ9JuoQ1r3tilqveeQdgPZuk3hTXs74127UXsEtEPCOpAXgjIvaU1Bf4P0m3A7sBOwKfBAYD84DLP9DvQOBSYP+sr/4R8Zqki4G3IuLn2XlXAb+MiPskfZTiU5kfB84B7ouIn0g6Emio6v8Is7XgBG3VsoGkudnne4GJFEsPf4mIZ7L9hwCfWlVfBj4CDAP2B66OiDbgRUl3rqH/vYGZq/qKiI7WRz4Y2Fl6f4C8qaRNsmt8IfvuzZJeX7s/pln1OEFbtSyPiOHtd2RJ8u32u4DTIuK2D5x3BKWXVVUZ50CxjLdPRCxfQyxe58CS5hq05ek24JuS+gBI2kHSRsBM4LisRl0PfHYN3/0zcICkbbPv9s/2vwls0u682ykuOEV23vDs40zgy9m+w4F+lfpDmVWKE7Tl6TKK9eUHsxegXkLxX3VTgQXAo8BvgXs++MWIeJli3fgGSQ8D12aHbgSOWXWTEDgdGJHdhJzH32eTnAfsL+lBiqWWxVX6M5qtNa9mZ2aWKI+gzcwS5QRtZpYoJ2gzs0Q5QZuZJcoJ2swsUU7QZmaJcoI2M0vU/wNBEEYHX5cTMAAAAABJRU5ErkJggg==\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 0.784 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": 15, "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": 16, "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": "markdown", "id": "472032f5-928c-49ab-8c8d-b2454195ea2a", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "id": "9be2e2e6-cc3e-46e1-8ece-1d74db056ff4", "metadata": {}, "outputs": [], "source": [] }, { "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 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": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 5 }