{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "35b66458-54be-479e-82f2-27de1c4e617f", "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
iddiagnosisradius_meantexture_meanperimeter_meanarea_meansmoothness_meancompactness_meanconcavity_meanconcave points_mean...texture_worstperimeter_worstarea_worstsmoothness_worstcompactness_worstconcavity_worstconcave points_worstsymmetry_worstfractal_dimension_worstUnnamed: 32
0842302M17.9910.38122.801001.00.118400.277600.30010.14710...17.33184.602019.00.16220.66560.71190.26540.46010.11890NaN
1842517M20.5717.77132.901326.00.084740.078640.08690.07017...23.41158.801956.00.12380.18660.24160.18600.27500.08902NaN
284300903M19.6921.25130.001203.00.109600.159900.19740.12790...25.53152.501709.00.14440.42450.45040.24300.36130.08758NaN
384348301M11.4220.3877.58386.10.142500.283900.24140.10520...26.5098.87567.70.20980.86630.68690.25750.66380.17300NaN
484358402M20.2914.34135.101297.00.100300.132800.19800.10430...16.67152.201575.00.13740.20500.40000.16250.23640.07678NaN
\n", "

5 rows × 33 columns

\n", "
" ], "text/plain": [ " id diagnosis radius_mean texture_mean perimeter_mean area_mean \\\n", "0 842302 M 17.99 10.38 122.80 1001.0 \n", "1 842517 M 20.57 17.77 132.90 1326.0 \n", "2 84300903 M 19.69 21.25 130.00 1203.0 \n", "3 84348301 M 11.42 20.38 77.58 386.1 \n", "4 84358402 M 20.29 14.34 135.10 1297.0 \n", "\n", " smoothness_mean compactness_mean concavity_mean concave points_mean \\\n", "0 0.11840 0.27760 0.3001 0.14710 \n", "1 0.08474 0.07864 0.0869 0.07017 \n", "2 0.10960 0.15990 0.1974 0.12790 \n", "3 0.14250 0.28390 0.2414 0.10520 \n", "4 0.10030 0.13280 0.1980 0.10430 \n", "\n", " ... texture_worst perimeter_worst area_worst smoothness_worst \\\n", "0 ... 17.33 184.60 2019.0 0.1622 \n", "1 ... 23.41 158.80 1956.0 0.1238 \n", "2 ... 25.53 152.50 1709.0 0.1444 \n", "3 ... 26.50 98.87 567.7 0.2098 \n", "4 ... 16.67 152.20 1575.0 0.1374 \n", "\n", " compactness_worst concavity_worst concave points_worst symmetry_worst \\\n", "0 0.6656 0.7119 0.2654 0.4601 \n", "1 0.1866 0.2416 0.1860 0.2750 \n", "2 0.4245 0.4504 0.2430 0.3613 \n", "3 0.8663 0.6869 0.2575 0.6638 \n", "4 0.2050 0.4000 0.1625 0.2364 \n", "\n", " fractal_dimension_worst Unnamed: 32 \n", "0 0.11890 NaN \n", "1 0.08902 NaN \n", "2 0.08758 NaN \n", "3 0.17300 NaN \n", "4 0.07678 NaN \n", "\n", "[5 rows x 33 columns]" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.model_selection import train_test_split, GridSearchCV\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.impute import SimpleImputer\n", "from sklearn.feature_selection import SelectKBest, f_classif, RFE\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.svm import SVC\n", "from sklearn.metrics import classification_report, accuracy_score\n", "\n", "\n", "import pandas as pd\n", "import numpy as np\n", "import seaborn as sns\n", "from matplotlib import pyplot as plt\n", "\n", "df = pd.read_csv('data.csv')\n", "df.head()\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "66dff97c-e50a-4aad-b5ef-685a4671b1be", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "id int64\n", "diagnosis object\n", "radius_mean float64\n", "texture_mean float64\n", "perimeter_mean float64\n", "area_mean float64\n", "smoothness_mean float64\n", "compactness_mean float64\n", "concavity_mean float64\n", "concave points_mean float64\n", "symmetry_mean float64\n", "fractal_dimension_mean float64\n", "radius_se float64\n", "texture_se float64\n", "perimeter_se float64\n", "area_se float64\n", "smoothness_se float64\n", "compactness_se float64\n", "concavity_se float64\n", "concave points_se float64\n", "symmetry_se float64\n", "fractal_dimension_se float64\n", "radius_worst float64\n", "texture_worst float64\n", "perimeter_worst float64\n", "area_worst float64\n", "smoothness_worst float64\n", "compactness_worst float64\n", "concavity_worst float64\n", "concave points_worst float64\n", "symmetry_worst float64\n", "fractal_dimension_worst float64\n", "Unnamed: 32 float64\n", "dtype: object" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.dtypes" ] }, { "cell_type": "code", "execution_count": 3, "id": "62493a38-7b99-46c3-bdd6-411ae774ec84", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "diagnosis 0\n", "radius_mean 0\n", "texture_mean 0\n", "perimeter_mean 0\n", "area_mean 0\n", "smoothness_mean 0\n", "compactness_mean 0\n", "concavity_mean 0\n", "concave points_mean 0\n", "symmetry_mean 0\n", "fractal_dimension_mean 0\n", "radius_se 0\n", "texture_se 0\n", "perimeter_se 0\n", "area_se 0\n", "smoothness_se 0\n", "compactness_se 0\n", "concavity_se 0\n", "concave points_se 0\n", "symmetry_se 0\n", "fractal_dimension_se 0\n", "radius_worst 0\n", "texture_worst 0\n", "perimeter_worst 0\n", "area_worst 0\n", "smoothness_worst 0\n", "compactness_worst 0\n", "concavity_worst 0\n", "concave points_worst 0\n", "symmetry_worst 0\n", "fractal_dimension_worst 0\n", "dtype: int64\n" ] } ], "source": [ "df = df.drop(['id', 'Unnamed: 32'], axis=1)\n", "\n", "df['diagnosis'] = df['diagnosis'].map({'B': 0, 'M': 1})\n", "print(df.isnull().sum())\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "407fe468-430a-4cc6-b55e-517f5ab3c8bf", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Best parameters: {'C': 1, 'kernel': 'rbf'}\n", " precision recall f1-score support\n", "\n", " 0 0.97 1.00 0.99 71\n", " 1 1.00 0.95 0.98 43\n", "\n", " accuracy 0.98 114\n", " macro avg 0.99 0.98 0.98 114\n", "weighted avg 0.98 0.98 0.98 114\n", "\n" ] } ], "source": [ "X = df.drop('diagnosis', axis=1)\n", "y = df['diagnosis']\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "scaler = StandardScaler()\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)\n", "\n", "param_grid = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}\n", "grid = GridSearchCV(SVC(), param_grid, cv=5)\n", "grid.fit(X_train, y_train)\n", "\n", "print(\"Best parameters:\", grid.best_params_)\n", "y_pred = grid.predict(X_test)\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "code", "execution_count": 5, "id": "faae582a-f3ef-4117-8bef-b77490424bfc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "SelectKBest features: ['radius_mean', 'perimeter_mean', 'area_mean', 'concavity_mean', 'concave points_mean', 'radius_worst', 'perimeter_worst', 'area_worst', 'concavity_worst', 'concave points_worst']\n", "RFE features: ['radius_mean', 'compactness_mean', 'concavity_mean', 'texture_se', 'radius_worst', 'smoothness_worst', 'compactness_worst', 'concavity_worst', 'concave points_worst', 'symmetry_worst']\n" ] } ], "source": [ "selector = SelectKBest(score_func=f_classif, k=10)\n", "X_kbest = selector.fit_transform(X, y)\n", "selected_kbest = X.columns[selector.get_support()]\n", "print(\"SelectKBest features:\", selected_kbest.tolist())\n", "\n", "model = LogisticRegression(max_iter=5000)\n", "rfe = RFE(model, n_features_to_select=10)\n", "rfe.fit(X, y)\n", "selected_rfe = X.columns[rfe.support_]\n", "print(\"RFE features:\", selected_rfe.tolist())\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "c84ea9ec-5f30-4d8b-a952-2f0669b99db2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Performance with selected features (SelectKBest):\n", " precision recall f1-score support\n", "\n", " 0 0.96 0.97 0.97 71\n", " 1 0.95 0.93 0.94 43\n", "\n", " accuracy 0.96 114\n", " macro avg 0.96 0.95 0.95 114\n", "weighted avg 0.96 0.96 0.96 114\n", "\n" ] } ], "source": [ "X_selected = df[selected_kbest]\n", "X_train, X_test, y_train, y_test = train_test_split(X_selected, y, test_size=0.2, random_state=42)\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)\n", "\n", "clf = RandomForestClassifier()\n", "clf.fit(X_train, y_train)\n", "y_pred = clf.predict(X_test)\n", "print(\"Performance with selected features (SelectKBest):\")\n", "print(classification_report(y_test, y_pred))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "de8908d8-c942-40de-a689-e0f4e59bdc2e", "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": "3.12.9" } }, "nbformat": 4, "nbformat_minor": 5 }