{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"17B2O19Go1DK4co0UH8rm9YKOiEWgj6w8","authorship_tag":"ABX9TyOWGtp2Pz8wjUtSuTwegPLK"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":9,"metadata":{"id":"IWG_M1NlWHFO","executionInfo":{"status":"ok","timestamp":1770740552539,"user_tz":0,"elapsed":9,"user":{"displayName":"Vishvaraj Rana","userId":"10986470577049836064"}}},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","from sklearn.model_selection import train_test_split\n","from sklearn.ensemble import RandomForestClassifier\n","from sklearn.linear_model import LogisticRegression\n","from sklearn.naive_bayes import GaussianNB\n","from sklearn.decomposition import PCA\n","from sklearn.metrics import classification_report, accuracy_score"]},{"cell_type":"code","source":["# 1. Load data\n","df = pd.read_csv('/content/drive/MyDrive/Application of Machine Learning/diabetes.csv')\n","\n","# 2. Check for missing values (usually represented as 0 in this dataset)\n","# Optional: Replace 0s with the median for columns where 0 doesn't make sense (like Glucose or BMI)\n","cols_to_fix = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']\n","df[cols_to_fix] = df[cols_to_fix].replace(0, np.nan)\n","df.fillna(df.median(), inplace=True)\n","\n","# 3. Split into X (features) and y (target - 'Outcome')\n","X = df.drop('Outcome', axis=1)\n","y = df['Outcome']\n","\n","X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"],"metadata":{"id":"xIvReGbAWjQG","executionInfo":{"status":"ok","timestamp":1770740585456,"user_tz":0,"elapsed":233,"user":{"displayName":"Vishvaraj Rana","userId":"10986470577049836064"}}},"execution_count":10,"outputs":[]},{"cell_type":"code","source":["# Train the model\n","rf = RandomForestClassifier(random_state=42)\n","rf.fit(X_train, y_train)\n","\n","# View results\n","y_pred = rf.predict(X_test)\n","print(\"Full Model Accuracy:\", accuracy_score(y_test, y_pred))\n","print(classification_report(y_test, y_pred))\n","\n","# Get Feature Importance\n","importances = pd.Series(rf.feature_importances_, index=X.columns).sort_values(ascending=False)\n","print(\"\\nFeature Importances:\\n\", importances)\n","\n","# Plotting the features\n","importances.plot(kind='barh')\n","plt.title('Feature Importance Scores')\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":834},"id":"-sHLNg9yWkx6","executionInfo":{"status":"ok","timestamp":1770740601687,"user_tz":0,"elapsed":1765,"user":{"displayName":"Vishvaraj Rana","userId":"10986470577049836064"}},"outputId":"ec8d8c9c-c481-425e-cb63-111ffbffc3eb"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["Full Model Accuracy: 0.7467532467532467\n","              precision    recall  f1-score   support\n","\n","           0       0.80      0.81      0.80        99\n","           1       0.65      0.64      0.64        55\n","\n","    accuracy                           0.75       154\n","   macro avg       0.72      0.72      0.72       154\n","weighted avg       0.75      0.75      0.75       154\n","\n","\n","Feature Importances:\n"," Glucose                     0.267096\n","BMI                         0.144299\n","Age                         0.131702\n","DiabetesPedigreeFunction    0.102785\n","PatientId                   0.087289\n","Insulin                     0.076877\n","BloodPressure               0.069971\n","SkinThickness               0.062592\n","Pregnancies                 0.057390\n","dtype: float64\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]}]}