Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,292 @@
-import altair as alt
-import numpy as np
+# Import libraries
 import pandas as pd
-import streamlit as st
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import warnings
+warnings.filterwarnings('ignore')
 
-"""
-# Welcome to Streamlit!
+# Machine Learning Libraries
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import (classification_report, confusion_matrix,
+                           accuracy_score, precision_score, recall_score, f1_score)
+
+# Visualization
+import matplotlib.pyplot as plt
+import seaborn as sns
+plt.style.use('seaborn-v0_8')
 
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+print("Library berhasil diimpor!")
+
+"""## 2. Data Loading & Exploration
 
-In the meantime, below is an example of what you can do with just a few lines of code:
 """
 
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+# Load dataset
+print("Memuat dataset diabetes...")
+try:
+    df = pd.read_csv("datasets.csv")
+    print(f"Dataset berhasil dimuat: {df.shape[0]:,} baris, {df.shape[1]} kolom")
+except FileNotFoundError:
+    print("File 'datasets.csv' tidak ditemukan!")
+    print("Silakan upload file dataset ke Google Colab terlebih dahulu.")
+
+# Basic dataset information
+print(f"\nInformasi Dataset:")
+print(f"   • Ukuran: {df.shape}")
+print(f"   • Penggunaan memori: {df.memory_usage(deep=True).sum() / 1024**2:.2f} MB")
+print(f"   • Nilai kosong: {df.isnull().sum().sum()}")
+
+# Display first few rows
+print(f"\n5 Baris Pertama:")
+display(df.head())
+
+# Dataset statistics
+print(f"\nStatistik Dataset:")
+display(df.describe())
 
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
+"""## 3. Target Variable Analysis
 
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
+"""
+
+# Target variable distribution
+target_column = 'Diabetes_012'
+print(f"Variabel target: {target_column}")
 
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
+target_counts = df[target_column].value_counts().sort_index()
+target_percentages = df[target_column].value_counts(normalize=True).sort_index() * 100
+
+# Create target analysis dataframe
+target_analysis = pd.DataFrame({
+    'Kelas': ['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2'],
+    'Jumlah': target_counts.values,
+    'Persentase': target_percentages.values
 })
 
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+print("Distribusi:")
+display(target_analysis)
+
+# Visualization of target distribution
+fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 6))
+
+# Pie chart
+colors = ['#2E8B57', '#DC143C', '#FF8C00']
+ax1.pie(target_counts.values, labels=target_analysis['Kelas'],
+        autopct='%1.1f%%', colors=colors, startangle=90)
+ax1.set_title('Distribusi Variabel Target', fontsize=14, fontweight='bold')
+
+# Bar chart
+bars = ax2.bar(target_analysis['Kelas'], target_analysis['Jumlah'], color=colors)
+ax2.set_title('Jumlah Sampel per Kelas', fontsize=14, fontweight='bold')
+ax2.set_ylabel('Jumlah Sampel')
+ax2.set_xlabel('Kelas Diabetes')
+
+# Add value labels on bars
+for bar, count in zip(bars, target_analysis['Jumlah']):
+    ax2.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 1000,
+             f'{count:,}', ha='center', va='bottom', fontweight='bold')
+
+plt.tight_layout()
+plt.show()
+
+"""## 4. Data Preprocessing & Model Training
+
+"""
+
+# Prepare data
+feature_columns = [col for col in df.columns if col != target_column]
+X = df[feature_columns]
+y = df[target_column]
+
+print(f"Ukuran data:")
+print(f"   • Fitur (X): {X.shape}")
+print(f"   • Target (y): {y.shape}")
+
+# Feature scaling
+print(f"\nMenerapkan StandardScaler...")
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+X_scaled = pd.DataFrame(X_scaled, columns=feature_columns)
+
+print(f"Fitur berhasil dinormalisasi!")
+
+# Split data
+X_train, X_test, y_train, y_test = train_test_split(
+    X_scaled, y, test_size=0.2, random_state=42, stratify=y
+)
+
+print(f"\nHasil Pembagian Data:")
+print(f"   • Data latih: {X_train.shape[0]:,} sampel")
+print(f"   • Data uji: {X_test.shape[0]:,} sampel")
+
+# Train Random Forest
+print(f"\nMelatih Random Forest Classifier...")
+rf_classifier = RandomForestClassifier(
+    n_estimators=100,
+    random_state=42,
+    max_depth=10,
+    min_samples_split=5,
+    min_samples_leaf=2,
+    n_jobs=-1
+)
+
+rf_classifier.fit(X_train, y_train)
+print("Pelatihan model selesai!")
+
+# Make predictions
+y_pred = rf_classifier.predict(X_test)
+y_pred_proba = rf_classifier.predict_proba(X_test)
+
+print(f"\nPrediksi selesai!")
+print(f"   • Ukuran prediksi: {y_pred.shape}")
+print(f"   • Ukuran probabilitas: {y_pred_proba.shape}")
+
+"""## 5. Model Evaluation & Visualization
+
+"""
+
+# Calculate metrics
+accuracy = accuracy_score(y_test, y_pred)
+precision = precision_score(y_test, y_pred, average='weighted')
+recall = recall_score(y_test, y_pred, average='weighted')
+f1 = f1_score(y_test, y_pred, average='weighted')
+
+print(f"Metrik Performa:")
+print(f"   • Akurasi: {accuracy:.4f} ({accuracy*100:.2f}%)")
+print(f"   • Presisi (terbobot): {precision:.4f}")
+print(f"   • Recall (terbobot): {recall:.4f}")
+print(f"   • F1-Score (terbobot): {f1:.4f}")
+
+# Detailed classification report
+print(f"\nLaporan Klasifikasi Detail:")
+print(classification_report(y_test, y_pred,
+                          target_names=['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2']))
+
+# Confusion Matrix
+cm = confusion_matrix(y_test, y_pred)
+print(f"\nMatriks Konfusi:")
+print(cm)
+
+# Visualization
+fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 6))
+
+# Confusion Matrix Heatmap
+sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', ax=ax1,
+            xticklabels=['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2'],
+            yticklabels=['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2'])
+ax1.set_title('Matriks Konfusi', fontsize=14, fontweight='bold')
+ax1.set_xlabel('Prediksi')
+ax1.set_ylabel('Aktual')
+
+# Feature Importance
+feature_importance = pd.DataFrame({
+    'feature': feature_columns,
+    'importance': rf_classifier.feature_importances_
+}).sort_values('importance', ascending=False)
+
+# Top 10 features
+top_features = feature_importance.head(10)
+ax2.barh(top_features['feature'], top_features['importance'], color='skyblue')
+ax2.set_title('10 Fitur Terpenting', fontsize=14, fontweight='bold')
+ax2.set_xlabel('Tingkat Kepentingan')
+
+plt.tight_layout()
+plt.show()
+
+# Display feature importance table
+print(f"\nTingkat Kepentingan Fitur (10 Teratas):")
+display(feature_importance.head(10))
+
+"""## 6. Model Inference Example
+
+"""
+
+# Example prediction
+print("Contoh: Memprediksi diabetes untuk pasien baru...")
+
+# Sample patient data
+sample_patient = {
+    'HighBP': 1.0,           # Tekanan darah tinggi: Ya
+    'HighChol': 0.0,         # Kolesterol tinggi: Tidak
+    'CholCheck': 1.0,        # Pengecekan kolesterol: Ya
+    'BMI': 28.5,             # BMI: 28.5 (kelebihan berat badan)
+    'Smoker': 0.0,           # Perokok: Tidak
+    'Stroke': 0.0,           # Riwayat stroke: Tidak
+    'HeartDiseaseorAttack': 0.0,  # Penyakit jantung: Tidak
+    'PhysActivity': 1.0,     # Aktivitas fisik: Ya
+    'Fruits': 1.0,           # Konsumsi buah: Ya
+    'Veggies': 1.0,          # Konsumsi sayuran: Ya
+    'HvyAlcoholConsump': 0.0, # Konsumsi alkohol berat: Tidak
+    'AnyHealthcare': 1.0,    # Akses layanan kesehatan: Ya
+    'NoDocbcCost': 0.0,      # Tidak ke dokter karena biaya: Tidak
+    'GenHlth': 3.0,          # Kesehatan umum: 3 (cukup)
+    'MentHlth': 5.0,         # Hari kesehatan mental buruk: 5
+    'PhysHlth': 5.0,         # Hari kesehatan fisik buruk: 5
+    'DiffWalk': 0.0,         # Kesulitan berjalan: Tidak
+    'Sex': 0.0,              # Jenis kelamin: Perempuan
+    'Age': 9.0,              # Kategori usia: 9 (45-49)
+    'Education': 4.0,        # Pendidikan: 4 (kuliah sebagian)
+    'Income': 3.0            # Pendapatan: 3 ($15k-$20k)
+}
+
+print(f"Data pasien contoh:")
+for key, value in sample_patient.items():
+    print(f"   • {key}: {value}")
+
+# Create DataFrame for prediction
+patient_df = pd.DataFrame([sample_patient])
+patient_scaled = scaler.transform(patient_df)
+patient_scaled_df = pd.DataFrame(patient_scaled, columns=feature_columns)
+
+# Make prediction
+prediction = rf_classifier.predict(patient_scaled_df)[0]
+prediction_proba = rf_classifier.predict_proba(patient_scaled_df)[0]
+
+print(f"\nHasil Prediksi:")
+print(f"   • Kelas yang diprediksi: {prediction}")
+print(f"   • Nama kelas: {['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2'][int(prediction)]}")
+
+print(f"\nProbabilitas Prediksi:")
+for i, prob in enumerate(prediction_proba):
+    class_name = ['Tidak Diabetes', 'Diabetes Tipe 1', 'Diabetes Tipe 2'][i]
+    print(f"   • {class_name}: {prob:.4f} ({prob*100:.2f}%)")
+
+"""## 7. Save Model & Summary
+
+"""
+
+# Save model and scaler
+import joblib
+
+print("💾 Menyimpan model dan scaler...")
+
+# Save the trained model
+model_filename = 'diabetes_rf_model.joblib'
+joblib.dump(rf_classifier, model_filename)
+print(f" Model disimpan sebagai: {model_filename}")
+
+# Save the scaler
+scaler_filename = 'diabetes_scaler.joblib'
+joblib.dump(scaler, scaler_filename)
+print(f"Scaler disimpan sebagai: {scaler_filename}")
+
+print(f"\n🎉 Pelatihan dan evaluasi model berhasil diselesaikan!")
+print(f" File yang dibuat:")
+print(f"   • {model_filename}")
+print(f"   • {scaler_filename}")
+
+# Summary
+print(f"\n Ringkasan Performa Model:")
+print(f"   • Dataset: {df.shape[0]:,} sampel, {df.shape[1]} fitur")
+print(f"   • Model: Random Forest Classifier")
+print(f"   • Akurasi: {accuracy:.4f} ({accuracy*100:.2f}%)")
+print(f"   • F1-Score: {f1:.4f}")
+print(f"   • Kelas: 3 (Tidak Diabetes, Diabetes Tipe 1, Diabetes Tipe 2)")
+
+print(f"\n 5 Fitur Terpenting:")
+for i, (_, row) in enumerate(feature_importance.head(5).iterrows()):
+    print(f"   {i+1}. {row['feature']}: {row['importance']:.4f}")
+
+print(f"\n Model siap untuk deployment!")