{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"1j1yObtD_a49L7dT7grndQLARBD2vzee_","authorship_tag":"ABX9TyMX98kjm6Oo4c++pRYU4gfp"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"id":"kOq8P8tFoAy7"},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","from sklearn.model_selection import train_test_split\n","from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n","from sklearn.tree import DecisionTreeClassifier\n","from sklearn.ensemble import RandomForestClassifier\n","from sklearn.naive_bayes import GaussianNB\n","from sklearn.svm import SVC"]},{"cell_type":"code","source":["df = pd.read_csv('/content/drive/MyDrive/Application of Machine Learning/diabetes.csv')\n","df.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":206},"id":"5kx2-A4foaUS","executionInfo":{"status":"ok","timestamp":1770141307041,"user_tz":0,"elapsed":43,"user":{"displayName":"Vishvaraj Rana","userId":"10986470577049836064"}},"outputId":"86b5beda-da0f-4d92-895f-67cc6c1ec47a"},"execution_count":4,"outputs":[{"output_type":"execute_result","data":{"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 "],"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","
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\n","
\n","
\n","\n","
\n"," \n","\n"," \n","\n"," \n","
\n","\n","\n","
\n","
\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"df","summary":"{\n \"name\": \"df\",\n \"rows\": 768,\n \"fields\": [\n {\n \"column\": \"PatientId\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 221,\n \"min\": 1,\n \"max\": 768,\n \"num_unique_values\": 768,\n \"samples\": [\n 669,\n 325,\n 625\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Pregnancies\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3,\n \"min\": 0,\n \"max\": 17,\n \"num_unique_values\": 17,\n \"samples\": [\n 6,\n 1,\n 3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Glucose\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 31,\n \"min\": 0,\n \"max\": 199,\n \"num_unique_values\": 136,\n \"samples\": [\n 151,\n 101,\n 112\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"BloodPressure\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 19,\n \"min\": 0,\n \"max\": 122,\n \"num_unique_values\": 47,\n \"samples\": [\n 86,\n 46,\n 85\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"SkinThickness\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 15,\n \"min\": 0,\n \"max\": 99,\n \"num_unique_values\": 51,\n \"samples\": [\n 7,\n 12,\n 48\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Insulin\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 115,\n \"min\": 0,\n \"max\": 846,\n \"num_unique_values\": 186,\n \"samples\": [\n 52,\n 41,\n 183\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"BMI\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 7.8841603203754405,\n \"min\": 0.0,\n \"max\": 67.1,\n \"num_unique_values\": 248,\n \"samples\": [\n 19.9,\n 31.0,\n 38.1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"DiabetesPedigreeFunction\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.33132859501277484,\n \"min\": 0.078,\n \"max\": 2.42,\n \"num_unique_values\": 517,\n \"samples\": [\n 1.731,\n 0.426,\n 0.138\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11,\n \"min\": 21,\n \"max\": 81,\n \"num_unique_values\": 52,\n \"samples\": [\n 60,\n 47,\n 72\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Outcome\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"}},"metadata":{},"execution_count":4}]},{"cell_type":"code","source":["# Features and target\n","X = df.drop('Outcome', axis=1)\n","y = df['Outcome']\n","\n","# 80/20 split\n","X_train, X_test, y_train, y_test = train_test_split(\n"," X, y, test_size=0.2, random_state=42\n",")\n","\n","# Features and target\n","X = df.drop('Outcome', axis=1)\n","y = df['Outcome']\n","\n","# 80/20 Train-Test Split\n","X_train, X_test, y_train, y_test = train_test_split(\n"," X, y, test_size=0.2, random_state=42\n",")\n","\n","# ===============================\n","# Function to Train & Evaluate\n","# ===============================\n","def evaluate_model(model, model_name):\n"," model.fit(X_train, y_train)\n","\n"," y_train_pred = model.predict(X_train)\n"," y_test_pred = model.predict(X_test)\n","\n"," print(\"=\"*50)\n"," print(f\"{model_name}\")\n"," print(\"=\"*50)\n","\n"," print(\"Training Accuracy:\", accuracy_score(y_train, y_train_pred))\n"," print(\"Test Accuracy:\", accuracy_score(y_test, y_test_pred))\n","\n"," print(\"\\nClassification Report:\")\n"," print(classification_report(y_test, y_test_pred))\n","\n"," print(\"Confusion Matrix:\")\n"," print(confusion_matrix(y_test, y_test_pred))\n"," print(\"\\n\")\n","\n"," return accuracy_score(y_train, y_train_pred), accuracy_score(y_test, y_test_pred)\n","\n","# ===============================\n","# Step 3: Train Models\n","# ===============================\n","\n","results = []\n","\n","# 1. Decision Tree\n","dt = DecisionTreeClassifier()\n","dt_train_acc, dt_test_acc = evaluate_model(dt, \"Decision Tree\")\n","results.append([\"Decision Tree\", dt_train_acc, dt_test_acc])\n","\n","# 2. Random Forest\n","rf = RandomForestClassifier(n_estimators=100, random_state=42)\n","rf_train_acc, rf_test_acc = evaluate_model(rf, \"Random Forest\")\n","results.append([\"Random Forest\", rf_train_acc, rf_test_acc])\n","\n","# 3. Naïve Bayes\n","nb = GaussianNB()\n","nb_train_acc, nb_test_acc = evaluate_model(nb, \"Naïve Bayes\")\n","results.append([\"Naïve Bayes\", nb_train_acc, nb_test_acc])\n","\n","# 4. SVM - Linear Kernel\n","svm_linear = SVC(kernel='linear')\n","svm_l_train_acc, svm_l_test_acc = evaluate_model(svm_linear, \"SVM (Linear)\")\n","results.append([\"SVM (Linear)\", svm_l_train_acc, svm_l_test_acc])\n","\n","# 5. SVM - RBF Kernel\n","svm_rbf = SVC(kernel='rbf')\n","svm_r_train_acc, svm_r_test_acc = evaluate_model(svm_rbf, \"SVM (RBF)\")\n","results.append([\"SVM (RBF)\", svm_r_train_acc, svm_r_test_acc])\n","\n","# ===============================\n","# Step 4: Summary Table\n","# ===============================\n","summary = pd.DataFrame(\n"," results,\n"," columns=[\"Model\", \"Training Accuracy\", \"Test Accuracy\"]\n",")\n","\n","print(\"FINAL MODEL COMPARISON\")\n","print(summary)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0q9rGtQ1pIWW","executionInfo":{"status":"ok","timestamp":1770141974541,"user_tz":0,"elapsed":22533,"user":{"displayName":"Vishvaraj Rana","userId":"10986470577049836064"}},"outputId":"be03c73d-8639-426f-b2f7-7166893f449a"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["==================================================\n","Decision Tree\n","==================================================\n","Training Accuracy: 1.0\n","Test Accuracy: 0.7727272727272727\n","\n","Classification Report:\n"," precision recall f1-score support\n","\n"," 0 0.82 0.83 0.82 99\n"," 1 0.69 0.67 0.68 55\n","\n"," accuracy 0.77 154\n"," macro avg 0.75 0.75 0.75 154\n","weighted avg 0.77 0.77 0.77 154\n","\n","Confusion Matrix:\n","[[82 17]\n"," [18 37]]\n","\n","\n","==================================================\n","Random Forest\n","==================================================\n","Training Accuracy: 1.0\n","Test Accuracy: 0.7532467532467533\n","\n","Classification Report:\n"," precision recall f1-score support\n","\n"," 0 0.82 0.79 0.80 99\n"," 1 0.64 0.69 0.67 55\n","\n"," accuracy 0.75 154\n"," macro avg 0.73 0.74 0.74 154\n","weighted avg 0.76 0.75 0.76 154\n","\n","Confusion Matrix:\n","[[78 21]\n"," [17 38]]\n","\n","\n","==================================================\n","Naïve Bayes\n","==================================================\n","Training Accuracy: 0.752442996742671\n","Test Accuracy: 0.7597402597402597\n","\n","Classification Report:\n"," precision recall f1-score support\n","\n"," 0 0.83 0.79 0.81 99\n"," 1 0.65 0.71 0.68 55\n","\n"," accuracy 0.76 154\n"," macro avg 0.74 0.75 0.74 154\n","weighted avg 0.77 0.76 0.76 154\n","\n","Confusion Matrix:\n","[[78 21]\n"," [16 39]]\n","\n","\n","==================================================\n","SVM (Linear)\n","==================================================\n","Training Accuracy: 0.7736156351791531\n","Test Accuracy: 0.7662337662337663\n","\n","Classification Report:\n"," precision recall f1-score support\n","\n"," 0 0.82 0.82 0.82 99\n"," 1 0.67 0.67 0.67 55\n","\n"," accuracy 0.77 154\n"," macro avg 0.75 0.75 0.75 154\n","weighted avg 0.77 0.77 0.77 154\n","\n","Confusion Matrix:\n","[[81 18]\n"," [18 37]]\n","\n","\n","==================================================\n","SVM (RBF)\n","==================================================\n","Training Accuracy: 0.744299674267101\n","Test Accuracy: 0.7467532467532467\n","\n","Classification Report:\n"," precision recall f1-score support\n","\n"," 0 0.75 0.92 0.82 99\n"," 1 0.75 0.44 0.55 55\n","\n"," accuracy 0.75 154\n"," macro avg 0.75 0.68 0.69 154\n","weighted avg 0.75 0.75 0.73 154\n","\n","Confusion Matrix:\n","[[91 8]\n"," [31 24]]\n","\n","\n","FINAL MODEL COMPARISON\n"," Model Training Accuracy Test Accuracy\n","0 Decision Tree 1.000000 0.772727\n","1 Random Forest 1.000000 0.753247\n","2 Naïve Bayes 0.752443 0.759740\n","3 SVM (Linear) 0.773616 0.766234\n","4 SVM (RBF) 0.744300 0.746753\n"]}]}]}