{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "e4d6a756-7540-4741-8e3f-2b4da348783b", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from matplotlib.pyplot import subplots\n", "\n", "from sklearn.pipeline import Pipeline\n", "from sklearn.preprocessing import PolynomialFeatures\n", "from sklearn.metrics import r2_score, mean_squared_error\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.linear_model import LinearRegression" ] }, { "cell_type": "code", "execution_count": 2, "id": "9b9b6c7f-2584-4d16-ad2c-8b95a6fea9a4", "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
AgeBlood PressureBlood Glucose RandomWhite Blood Cell CountRed Blood Cell CountClass
0487011767003.91
1539070121003.71
2637038045003.81
36880157110002.61
4618017392003.21
.....................
153558014067004.90
15442707578006.20
155128010066005.40
156176011472005.90
157588013168006.10
\n", "

158 rows × 6 columns

\n", "
" ], "text/plain": [ " Age Blood Pressure Blood Glucose Random White Blood Cell Count \\\n", "0 48 70 117 6700 \n", "1 53 90 70 12100 \n", "2 63 70 380 4500 \n", "3 68 80 157 11000 \n", "4 61 80 173 9200 \n", ".. ... ... ... ... \n", "153 55 80 140 6700 \n", "154 42 70 75 7800 \n", "155 12 80 100 6600 \n", "156 17 60 114 7200 \n", "157 58 80 131 6800 \n", "\n", " Red Blood Cell Count Class \n", "0 3.9 1 \n", "1 3.7 1 \n", "2 3.8 1 \n", "3 2.6 1 \n", "4 3.2 1 \n", ".. ... ... \n", "153 4.9 0 \n", "154 6.2 0 \n", "155 5.4 0 \n", "156 5.9 0 \n", "157 6.1 0 \n", "\n", "[158 rows x 6 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ckd = pd.read_csv('ckd.csv')\n", "ckd = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count', 'Class']]\n", "ckd" ] }, { "cell_type": "code", "execution_count": 3, "id": "979258e3-0fd1-4d79-a700-17c792b7275a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Evaluation of Logistic Regression classification\n", "Accuracy: 0.9583333333333334\n", "\n", "Confusion Matrix:\n", "[[34 1]\n", " [ 1 12]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.97 0.97 0.97 35\n", " 1 0.92 0.92 0.92 13\n", "\n", " accuracy 0.96 48\n", " macro avg 0.95 0.95 0.95 48\n", "weighted avg 0.96 0.96 0.96 48\n", "\n" ] } ], "source": [ "# Logistic Regression\n", "\n", "X = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count']]\n", "y = ckd['Class']\n", "\n", "# Create a train:test split of the data \n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.30, random_state=42, stratify=y\n", ")\n", "\n", "# We shall use the StandardScaler to scale the training dataset\n", "scaler = StandardScaler()\n", "X_train_scaled = scaler.fit_transform(X_train)\n", "# The transform method is then used to scale the test data using parameters\n", "# obtained from the training data.\n", "X_test_scaled = scaler.transform(X_test)\n", "\n", "from sklearn.linear_model import LogisticRegression\n", "logreg = LogisticRegression(max_iter=1000)\n", "\n", "logreg.fit(X_train, y_train)\n", "y_pred = logreg.predict(X_test)\n", "\n", "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n", "# Evaluate\n", "print('Evaluation of Logistic Regression classification')\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_pred))\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "code", "execution_count": 4, "id": "33be67d0-3e6c-4eb4-be24-9c558612bd9f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Evaluation of KNN classification\n", "Accuracy: 0.8541666666666666\n", "\n", "Confusion Matrix:\n", "[[35 0]\n", " [ 7 6]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.83 1.00 0.91 35\n", " 1 1.00 0.46 0.63 13\n", "\n", " accuracy 0.85 48\n", " macro avg 0.92 0.73 0.77 48\n", "weighted avg 0.88 0.85 0.83 48\n", "\n" ] } ], "source": [ "from sklearn.neighbors import KNeighborsClassifier\n", "knn = KNeighborsClassifier(n_neighbors=9)\n", "knn.fit(X_train, y_train)\n", "y_pred = knn.predict(X_test)\n", "\n", "# Evaluate\n", "print('Evaluation of KNN classification')\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_pred))\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "code", "execution_count": 5, "id": "c6e2c252-32aa-40ff-aac3-d2a051d876cf", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.9791666666666666\n", "\n", "Confusion Matrix:\n", "[[35 0]\n", " [ 1 12]]\n", "\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.97 1.00 0.99 35\n", " 1 1.00 0.92 0.96 13\n", "\n", " accuracy 0.98 48\n", " macro avg 0.99 0.96 0.97 48\n", "weighted avg 0.98 0.98 0.98 48\n", "\n" ] } ], "source": [ "X = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count']]\n", "y = ckd['Class']\n", "\n", "# Create a train:test split of the data \n", "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.30, random_state=42, stratify=y\n", ")\n", "\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n", "\n", "# Create and train the classifier\n", "gnb_model = GaussianNB()\n", "gnb_model.fit(X_train, y_train)\n", "\n", "# Make predictions\n", "y_pred = gnb_model.predict(X_test)\n", "\n", "# Evaluate\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"\\nConfusion Matrix:\")\n", "print(confusion_matrix(y_test, y_pred))\n", "print(\"\\nClassification Report:\")\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "code", "execution_count": null, "id": "4b4565f0-c297-4b40-8897-03237941ff78", "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": "3.9.6" } }, "nbformat": 4, "nbformat_minor": 5 }