{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "source": [ "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split, GridSearchCV\n", "from sklearn.preprocessing import StandardScaler, LabelEncoder\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n", "from sklearn.svm import SVC\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.metrics import accuracy_score, classification_report\n", "from sklearn.feature_selection import SelectKBest, f_classif\n", "from sklearn.ensemble import ExtraTreesClassifier\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns" ], "metadata": { "id": "kvKfKqiUQcpl" }, "execution_count": 14, "outputs": [] }, { "cell_type": "code", "source": [ "# 2. Upload and Read Data\n", "from google.colab import files\n", "uploaded = files.upload()\n", "\n", "# Assume the uploaded file is 'kidney_disease (1).csv'\n", "df = pd.read_csv('kidney_disease (1).csv')\n", "\n", "# Display dataset information\n", "print(\"Dataset Dimensions:\", df.shape)\n", "print(\"\\nDataset Preview:\")\n", "display(df.head())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 342 }, "id": "OPJK5IXCQgnh", "outputId": "2e1b467f-48c8-43aa-9bf4-e1e08de8257e" }, "execution_count": 15, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " \n", " Upload widget is only available when the cell has been executed in the\n", " current browser session. Please rerun this cell to enable.\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Saving kidney_disease (1).csv to kidney_disease (1) (1).csv\n", "Dataset Dimensions: (398, 25)\n", "\n", "Dataset Preview:\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ " age bp sg al su rbc pc pcc ba \\\n", "0 48.0 80.0 1.020 1.0 0.0 NaN normal notpresent notpresent \n", "1 7.0 50.0 1.020 4.0 0.0 NaN normal notpresent notpresent \n", "2 62.0 80.0 1.010 2.0 3.0 normal normal notpresent notpresent \n", "3 48.0 70.0 1.005 4.0 0.0 normal abnormal present notpresent \n", "4 51.0 80.0 1.010 2.0 0.0 normal normal notpresent notpresent \n", "\n", " bgr ... pcv wc rc htn dm cad appet pe ane classification \n", "0 121.0 ... 44 7800 5.2 yes yes no good no no ckd \n", "1 NaN ... 38 6000 NaN no no no good no no ckd \n", "2 423.0 ... 31 7500 NaN no yes no poor no yes ckd \n", "3 117.0 ... 32 6700 3.9 yes no no poor yes yes ckd \n", "4 106.0 ... 35 7300 4.6 no no no good no no ckd \n", "\n", "[5 rows x 25 columns]" ], "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agebpsgalsurbcpcpccbabgr...pcvwcrchtndmcadappetpeaneclassification
048.080.01.0201.00.0NaNnormalnotpresentnotpresent121.0...4478005.2yesyesnogoodnonockd
17.050.01.0204.00.0NaNnormalnotpresentnotpresentNaN...386000NaNnononogoodnonockd
262.080.01.0102.03.0normalnormalnotpresentnotpresent423.0...317500NaNnoyesnopoornoyesckd
348.070.01.0054.00.0normalabnormalpresentnotpresent117.0...3267003.9yesnonopooryesyesckd
451.080.01.0102.00.0normalnormalnotpresentnotpresent106.0...3573004.6nononogoodnonockd
\n", "

5 rows × 25 columns

\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "# Data Cleaning\n", "# Replace empty strings with NaN for proper handling\n", "data = pd.read_csv('kidney_disease (1).csv')\n", "data = data.replace('', np.nan)" ], "metadata": { "id": "mJk6_SmFQphh" }, "execution_count": 17, "outputs": [] }, { "cell_type": "code", "source": [ "# Impute missing values with mode for categorical columns and median for numerical\n", "for column in data.columns:\n", " if data[column].dtype == 'object':\n", " data[column] = data[column].fillna(data[column].mode()[0])\n", " else:\n", " data[column] = data[column].fillna(data[column].median())" ], "metadata": { "id": "aG0YAa0xQxDT" }, "execution_count": 18, "outputs": [] }, { "cell_type": "code", "source": [ "# Convert categorical features to numerical data.\n", "label_encoders = {}\n", "for column in data.select_dtypes(include=['object']).columns:\n", " le = LabelEncoder()\n", " data[column] = le.fit_transform(data[column])\n", " label_encoders[column] = le" ], "metadata": { "id": "SB_QvHEgQzt7" }, "execution_count": 19, "outputs": [] }, { "cell_type": "code", "source": [ "# Define features and target variable\n", "X = data.drop('classification', axis=1).values\n", "y = data['classification'].values\n", "\n", "# Splitting data\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)\n", "\n", "# Feature Scaling\n", "scaler = StandardScaler()\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)" ], "metadata": { "id": "RHAAmJZQQ17O" }, "execution_count": 21, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Function for Model Evaluation ---\n", "def evaluate_model(model, model_name, X_test, y_test):\n", " y_pred = model.predict(X_test)\n", " accuracy = accuracy_score(y_test, y_pred)\n", " report = classification_report(y_test, y_pred, zero_division=0)\n", " print(f\"--------------------{model_name}--------------------\")\n", " print(f\"Accuracy: {accuracy:.4f}\")\n", " print(\"Classification Report:\\n\", report)" ], "metadata": { "id": "ZvuIQhsRQ-7Q" }, "execution_count": 22, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Function for Grid Search ---\n", "def grid_search_model(model, param_grid, model_name, X_train, y_train, X_test, y_test):\n", " grid = GridSearchCV(model, param_grid, cv=3, scoring='accuracy', verbose=0)\n", " grid.fit(X_train, y_train)\n", " print(f\"Best parameters for {model_name}: {grid.best_params_}\")\n", " evaluate_model(grid.best_estimator_, model_name, X_test, y_test)\n", " return grid.best_estimator_" ], "metadata": { "id": "_c8zEkN9RB7Y" }, "execution_count": 23, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Function for Feature Selection (SelectKBest) ---\n", "def select_k_best_features(X, y, k=10):\n", " selector = SelectKBest(score_func=f_classif, k=k)\n", " X_new = selector.fit_transform(X, y)\n", " selected_features = X.columns[selector.get_support()]\n", " return X_new, selected_features" ], "metadata": { "id": "mprr5yOxREl_" }, "execution_count": 24, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Function for Feature Selection (Tree-based) ---\n", "def tree_based_feature_selection(X, y, k=10):\n", " model = ExtraTreesClassifier(n_estimators=100, random_state=42)\n", " model.fit(X, y)\n", " feature_importances = pd.Series(model.feature_importances_, index=X.columns)\n", " selected_features = feature_importances.nlargest(k).index\n", " X_new = X[selected_features]\n", " return X_new, selected_features" ], "metadata": { "id": "oVR84hsCRG_Y" }, "execution_count": 25, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Models and Parameter Grids ---\n", "models = {\n", " 'LogisticRegression': (LogisticRegression(max_iter=1000),\n", " {'C': [0.1, 1.0, 10.0], 'solver': ['liblinear', 'saga']}),\n", " 'DecisionTreeClassifier': (DecisionTreeClassifier(random_state=42),\n", " {'max_depth': [5, 10, 15], 'min_samples_leaf': [2, 5, 10]}),\n", " 'RandomForestClassifier': (RandomForestClassifier(random_state=42),\n", " {'n_estimators': [50, 100, 200], 'max_depth': [5, 10, 15], 'min_samples_leaf': [2, 5, 10]}),\n", " 'SVC': (SVC(random_state=42),\n", " {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf'], 'gamma': ['scale', 'auto']}),\n", " 'GaussianNB': (GaussianNB(), {}),\n", " 'KNeighborsClassifier': (KNeighborsClassifier(),\n", " {'n_neighbors': [3, 5, 7], 'weights': ['uniform', 'distance']}),\n", " 'GradientBoostingClassifier': (GradientBoostingClassifier(random_state=42),\n", " {'n_estimators': [50, 100, 200], 'learning_rate': [0.01, 0.1, 0.2], 'max_depth': [3, 5, 7]})\n", "}" ], "metadata": { "id": "2nkK2mfWRKGa" }, "execution_count": 26, "outputs": [] }, { "cell_type": "code", "source": [ "# --- Apply models with Grid Search ---\n", "print(\"-------------------Models with Grid Search-------------------\")\n", "for model_name, (model, param_grid) in models.items():\n", " best_model = grid_search_model(model, param_grid, model_name, X_train, y_train, X_test, y_test)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UzsmVeyZRNq4", "outputId": "e232bcf8-431d-45e0-a0a8-266b699a981f" }, "execution_count": 27, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "-------------------Models with Grid Search-------------------\n", "Best parameters for LogisticRegression: {'C': 0.1, 'solver': 'saga'}\n", "--------------------LogisticRegression--------------------\n", "Accuracy: 0.9833\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.97 0.99 76\n", " 1 0.96 1.00 0.98 44\n", "\n", " accuracy 0.98 120\n", " macro avg 0.98 0.99 0.98 120\n", "weighted avg 0.98 0.98 0.98 120\n", "\n", "Best parameters for DecisionTreeClassifier: {'max_depth': 5, 'min_samples_leaf': 2}\n", "--------------------DecisionTreeClassifier--------------------\n", "Accuracy: 0.9917\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.99 0.99 76\n", " 1 0.98 1.00 0.99 44\n", "\n", " accuracy 0.99 120\n", " macro avg 0.99 0.99 0.99 120\n", "weighted avg 0.99 0.99 0.99 120\n", "\n", "Best parameters for RandomForestClassifier: {'max_depth': 5, 'min_samples_leaf': 5, 'n_estimators': 50}\n", "--------------------RandomForestClassifier--------------------\n", "Accuracy: 1.0000\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 76\n", " 1 1.00 1.00 1.00 44\n", "\n", " accuracy 1.00 120\n", " macro avg 1.00 1.00 1.00 120\n", "weighted avg 1.00 1.00 1.00 120\n", "\n", "Best parameters for SVC: {'C': 1, 'gamma': 'scale', 'kernel': 'rbf'}\n", "--------------------SVC--------------------\n", "Accuracy: 0.9750\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.96 0.98 76\n", " 1 0.94 1.00 0.97 44\n", "\n", " accuracy 0.97 120\n", " macro avg 0.97 0.98 0.97 120\n", "weighted avg 0.98 0.97 0.98 120\n", "\n", "Best parameters for GaussianNB: {}\n", "--------------------GaussianNB--------------------\n", "Accuracy: 0.9500\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.92 0.96 76\n", " 1 0.88 1.00 0.94 44\n", "\n", " accuracy 0.95 120\n", " macro avg 0.94 0.96 0.95 120\n", "weighted avg 0.96 0.95 0.95 120\n", "\n", "Best parameters for KNeighborsClassifier: {'n_neighbors': 3, 'weights': 'uniform'}\n", "--------------------KNeighborsClassifier--------------------\n", "Accuracy: 0.9500\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.92 0.96 76\n", " 1 0.88 1.00 0.94 44\n", "\n", " accuracy 0.95 120\n", " macro avg 0.94 0.96 0.95 120\n", "weighted avg 0.96 0.95 0.95 120\n", "\n", "Best parameters for GradientBoostingClassifier: {'learning_rate': 0.01, 'max_depth': 7, 'n_estimators': 100}\n", "--------------------GradientBoostingClassifier--------------------\n", "Accuracy: 0.9500\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.92 0.96 76\n", " 1 0.88 1.00 0.94 44\n", "\n", " accuracy 0.95 120\n", " macro avg 0.94 0.96 0.95 120\n", "weighted avg 0.96 0.95 0.95 120\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "# --- Feature Selection (SelectKBest) ---\n", "print(\"\\n-------------------Feature Selection with SelectKBest-------------------\")\n", "X_df = pd.DataFrame(X, columns=data.drop('classification', axis=1).columns)\n", "X_new_kbest, selected_features_kbest = select_k_best_features(X_df, y)\n", "print(\"Selected features (SelectKBest):\", selected_features_kbest)\n", "\n", "X_train_kbest, X_test_kbest, y_train_kbest, y_test_kbest = train_test_split(X_new_kbest, y, test_size=0.30, random_state=42)\n", "X_train_kbest = scaler.fit_transform(X_train_kbest)\n", "X_test_kbest = scaler.transform(X_test_kbest)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "6BSv_pW-RRaf", "outputId": "ae032372-7125-4955-b63c-d69ed8d44827" }, "execution_count": 28, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "-------------------Feature Selection with SelectKBest-------------------\n", "Selected features (SelectKBest): Index(['sg', 'al', 'bgr', 'hemo', 'pcv', 'rc', 'htn', 'dm', 'appet', 'pe'], dtype='object')\n" ] } ] }, { "cell_type": "code", "source": [ "# --- Apply models to SelectKBest features ---\n", "print(\"\\n-------------------Models with SelectKBest Features-------------------\")\n", "for model_name, (model, param_grid) in models.items():\n", " if model_name == 'GaussianNB':\n", " model.fit(X_train_kbest, y_train_kbest)\n", " evaluate_model(model, model_name, X_test_kbest, y_test_kbest)\n", " else:\n", " best_model_kbest = grid_search_model(model, param_grid, model_name, X_train_kbest, y_train_kbest, X_test_kbest, y_test_kbest)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "GZXGfooXRe8F", "outputId": "9f63ce7e-8626-44e5-a44b-09f005b59cd0" }, "execution_count": 29, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "-------------------Models with SelectKBest Features-------------------\n", "Best parameters for LogisticRegression: {'C': 0.1, 'solver': 'saga'}\n", "--------------------LogisticRegression--------------------\n", "Accuracy: 0.9667\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.95 0.97 76\n", " 1 0.92 1.00 0.96 44\n", "\n", " accuracy 0.97 120\n", " macro avg 0.96 0.97 0.96 120\n", "weighted avg 0.97 0.97 0.97 120\n", "\n", "Best parameters for DecisionTreeClassifier: {'max_depth': 5, 'min_samples_leaf': 5}\n", "--------------------DecisionTreeClassifier--------------------\n", "Accuracy: 0.9917\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.99 0.99 76\n", " 1 0.98 1.00 0.99 44\n", "\n", " accuracy 0.99 120\n", " macro avg 0.99 0.99 0.99 120\n", "weighted avg 0.99 0.99 0.99 120\n", "\n", "Best parameters for RandomForestClassifier: {'max_depth': 5, 'min_samples_leaf': 2, 'n_estimators': 100}\n", "--------------------RandomForestClassifier--------------------\n", "Accuracy: 1.0000\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 76\n", " 1 1.00 1.00 1.00 44\n", "\n", " accuracy 1.00 120\n", " macro avg 1.00 1.00 1.00 120\n", "weighted avg 1.00 1.00 1.00 120\n", "\n", "Best parameters for SVC: {'C': 1, 'gamma': 'scale', 'kernel': 'rbf'}\n", "--------------------SVC--------------------\n", "Accuracy: 0.9833\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.97 0.99 76\n", " 1 0.96 1.00 0.98 44\n", "\n", " accuracy 0.98 120\n", " macro avg 0.98 0.99 0.98 120\n", "weighted avg 0.98 0.98 0.98 120\n", "\n", "--------------------GaussianNB--------------------\n", "Accuracy: 0.9250\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.88 0.94 76\n", " 1 0.83 1.00 0.91 44\n", "\n", " accuracy 0.93 120\n", " macro avg 0.92 0.94 0.92 120\n", "weighted avg 0.94 0.93 0.93 120\n", "\n", "Best parameters for KNeighborsClassifier: {'n_neighbors': 3, 'weights': 'uniform'}\n", "--------------------KNeighborsClassifier--------------------\n", "Accuracy: 0.9750\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.96 0.98 76\n", " 1 0.94 1.00 0.97 44\n", "\n", " accuracy 0.97 120\n", " macro avg 0.97 0.98 0.97 120\n", "weighted avg 0.98 0.97 0.98 120\n", "\n", "Best parameters for GradientBoostingClassifier: {'learning_rate': 0.1, 'max_depth': 3, 'n_estimators': 50}\n", "--------------------GradientBoostingClassifier--------------------\n", "Accuracy: 1.0000\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 76\n", " 1 1.00 1.00 1.00 44\n", "\n", " accuracy 1.00 120\n", " macro avg 1.00 1.00 1.00 120\n", "weighted avg 1.00 1.00 1.00 120\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "# --- Feature Selection (Tree-based) ---\n", "print(\"\\n-------------------Feature Selection with Tree-based method-------------------\")\n", "X_new_tree, selected_features_tree = tree_based_feature_selection(X_df, y)\n", "print(\"Selected features (Tree-based):\", selected_features_tree)\n", "\n", "X_train_tree, X_test_tree, y_train_tree, y_test_tree = train_test_split(X_new_tree, y, test_size=0.30, random_state=42)\n", "X_train_tree = scaler.fit_transform(X_train_tree)\n", "X_test_tree = scaler.transform(X_test_tree)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "lgtQfsVtRjkO", "outputId": "2399b9a7-e471-406e-a0e7-421224f4d34e" }, "execution_count": 30, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "-------------------Feature Selection with Tree-based method-------------------\n", "Selected features (Tree-based): Index(['sg', 'htn', 'hemo', 'al', 'pcv', 'dm', 'appet', 'rc', 'pe', 'pc'], dtype='object')\n" ] } ] }, { "cell_type": "code", "source": [ "# --- Apply models to Tree-based features ---\n", "print(\"\\n-------------------Models with Tree-based Features-------------------\")\n", "for model_name, (model, param_grid) in models.items():\n", " if model_name == 'GaussianNB':\n", " model.fit(X_train_tree, y_train_tree)\n", " evaluate_model(model, model_name, X_test_tree, y_test_tree)\n", " else:\n", " best_model_tree = grid_search_model(model, param_grid, model_name, X_train_tree, y_train_tree, X_test_tree, y_test_tree)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "GG5lJcNqRyYI", "outputId": "a8fcabf0-7363-4179-8dcb-300d18bff82b" }, "execution_count": 31, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "-------------------Models with Tree-based Features-------------------\n", "Best parameters for LogisticRegression: {'C': 0.1, 'solver': 'saga'}\n", "--------------------LogisticRegression--------------------\n", "Accuracy: 0.9750\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.96 0.98 76\n", " 1 0.94 1.00 0.97 44\n", "\n", " accuracy 0.97 120\n", " macro avg 0.97 0.98 0.97 120\n", "weighted avg 0.98 0.97 0.98 120\n", "\n", "Best parameters for DecisionTreeClassifier: {'max_depth': 10, 'min_samples_leaf': 2}\n", "--------------------DecisionTreeClassifier--------------------\n", "Accuracy: 0.9917\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.99 0.99 76\n", " 1 0.98 1.00 0.99 44\n", "\n", " accuracy 0.99 120\n", " macro avg 0.99 0.99 0.99 120\n", "weighted avg 0.99 0.99 0.99 120\n", "\n", "Best parameters for RandomForestClassifier: {'max_depth': 5, 'min_samples_leaf': 2, 'n_estimators': 50}\n", "--------------------RandomForestClassifier--------------------\n", "Accuracy: 1.0000\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 1.00 1.00 76\n", " 1 1.00 1.00 1.00 44\n", "\n", " accuracy 1.00 120\n", " macro avg 1.00 1.00 1.00 120\n", "weighted avg 1.00 1.00 1.00 120\n", "\n", "Best parameters for SVC: {'C': 1, 'gamma': 'scale', 'kernel': 'rbf'}\n", "--------------------SVC--------------------\n", "Accuracy: 0.9750\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.96 0.98 76\n", " 1 0.94 1.00 0.97 44\n", "\n", " accuracy 0.97 120\n", " macro avg 0.97 0.98 0.97 120\n", "weighted avg 0.98 0.97 0.98 120\n", "\n", "--------------------GaussianNB--------------------\n", "Accuracy: 0.9333\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.89 0.94 76\n", " 1 0.85 1.00 0.92 44\n", "\n", " accuracy 0.93 120\n", " macro avg 0.92 0.95 0.93 120\n", "weighted avg 0.94 0.93 0.93 120\n", "\n", "Best parameters for KNeighborsClassifier: {'n_neighbors': 7, 'weights': 'uniform'}\n", "--------------------KNeighborsClassifier--------------------\n", "Accuracy: 0.9417\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.91 0.95 76\n", " 1 0.86 1.00 0.93 44\n", "\n", " accuracy 0.94 120\n", " macro avg 0.93 0.95 0.94 120\n", "weighted avg 0.95 0.94 0.94 120\n", "\n", "Best parameters for GradientBoostingClassifier: {'learning_rate': 0.01, 'max_depth': 3, 'n_estimators': 50}\n", "--------------------GradientBoostingClassifier--------------------\n", "Accuracy: 0.9917\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 1.00 0.99 0.99 76\n", " 1 0.98 1.00 0.99 44\n", "\n", " accuracy 0.99 120\n", " macro avg 0.99 0.99 0.99 120\n", "weighted avg 0.99 0.99 0.99 120\n", "\n" ] } ] } ] }