Upload 5 files

app.py

@@ -0,0 +1,102 @@
+# app.py
+import gradio as gr
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import io
+from PIL import Image
+from src.prediction import predict_range
+
+def gradio_predict(start_month: str, end_month: str):
+    try:
+        df_pred = predict_range(start_month, end_month)
+        df_pred['input_month'] = pd.to_datetime(df_pred['input_month'])
+
+        # Label bulan dalam Bahasa Indonesia
+        bulan_indonesia = [
+            'Januari', 'Februari', 'Maret', 'April', 'Mei', 'Juni',
+            'Juli', 'Agustus', 'September', 'Oktober', 'November', 'Desember'
+        ]
+        df_pred['bulan_label'] = df_pred['input_month'].dt.month.apply(lambda x: bulan_indonesia[x-1]) + \
+                                 ' ' + df_pred['input_month'].dt.year.astype(str)
+
+        # Setup visualisasi
+        plt.figure(figsize=(15, 8))
+        sns.set_style("whitegrid")
+
+        # Warna berdasarkan nilai
+        cmap = plt.cm.Blues
+        norm = plt.Normalize(df_pred['prediksi_rr'].min(), df_pred['prediksi_rr'].max())
+        colors = cmap(norm(df_pred['prediksi_rr'].values))
+
+        # Garis utama
+        sns.lineplot(data=df_pred, x='bulan_label', y='prediksi_rr', color='darkcyan', linewidth=2, marker='o')
+
+        # Titik-titik & label nilai
+        for i, row in df_pred.iterrows():
+            plt.scatter(row['bulan_label'], row['prediksi_rr'], color=colors[i], s=120, edgecolor='black', zorder=5)
+            plt.text(
+                row['bulan_label'], row['prediksi_rr'] + 4,
+                f"{row['prediksi_rr']:.1f} mm", ha='center', va='bottom',
+                fontsize=9, color='black', bbox=dict(boxstyle="round,pad=0.2", fc="white", ec="gray", alpha=0.7)
+            )
+
+        # Titik ekstrem (max dan min)
+        max_idx = df_pred['prediksi_rr'].idxmax()
+        min_idx = df_pred['prediksi_rr'].idxmin()
+        plt.scatter(df_pred.loc[max_idx, 'bulan_label'], df_pred.loc[max_idx, 'prediksi_rr'],
+                    color='red', s=150, label='Tertinggi', zorder=6)
+        plt.scatter(df_pred.loc[min_idx, 'bulan_label'], df_pred.loc[min_idx, 'prediksi_rr'],
+                    color='blue', s=150, label='Terendah', zorder=6)
+
+        # Garis rata-rata
+        mean_val = df_pred['prediksi_rr'].mean()
+        plt.axhline(mean_val, color='orange', linestyle='--', linewidth=1.2, label=f'Rata-rata: {mean_val:.1f} mm')
+        plt.text(
+            x=len(df_pred) - 3, y=mean_val + 6,
+            s=f'{mean_val:.1f} mm', color='orange', fontsize=10, style='italic'
+        )
+
+        # Pengaturan plot
+        plt.title('Prediksi Curah Hujan Bulanan\nWilayah: Kota Bandung', fontsize=18, weight='bold')
+        plt.xlabel('Bulan', fontsize=12)
+        plt.ylabel('Curah Hujan (mm)', fontsize=12)
+        plt.xticks(rotation=45)
+        plt.legend()
+        plt.grid(True, linestyle='--', alpha=0.5)
+        plt.tight_layout()
+
+        # Simpan plot ke buffer
+        buf = io.BytesIO()
+        plt.savefig(buf, format='png', dpi=300)
+        plt.close()
+        buf.seek(0)
+        img = Image.open(buf)
+
+        # Format hasil tabel
+        df_pred['input_month'] = df_pred['input_month'].dt.strftime('%Y-%m')
+        result_str = df_pred[['input_month', 'prediksi_rr']].rename(
+            columns={'input_month': 'Bulan', 'prediksi_rr': 'Prediksi RR (mm)'}
+        ).to_string(index=False)
+
+        return result_str, img
+
+    except Exception as e:
+        return f"Terjadi kesalahan: {str(e)}", None
+
+# Gradio interface
+interface = gr.Interface(
+    fn=gradio_predict,
+    inputs=[
+        gr.Textbox(label="Bulan Awal (format: YYYY-MM)", placeholder="contoh: 2023-01"),
+        gr.Textbox(label="Bulan Akhir (format: YYYY-MM)", placeholder="contoh: 2023-12")
+    ],
+    outputs=[
+        gr.Textbox(label="Tabel Hasil Prediksi"),
+        gr.Image(label="Visualisasi Curah Hujan")
+    ],
+    title="Prediksi Curah Hujan Bulanan",
+    description="Masukkan rentang bulan untuk memprediksi curah hujan di Bandung menggunakan model Random Forest."
+)
+
+interface.launch(debug=True)

model/ModelFinal_random_forest_rainfall_.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d16fe864cfb4187597cfcfb153696db1c40b9eef42785af0d4e8b49cb4758f8
+size 3723425

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+matplotlib
+pandas
+seaborn
+scikit-learn
+joblib
+python-dateutil

src/model.py

@@ -0,0 +1,8 @@
+# src/model.py
+import joblib
+import os
+
+# Fungsi untuk memuat model
+def load_model():
+    model_path = os.path.join(os.path.dirname(__file__), '..', 'model', 'ModelFinal_random_forest_rainfall_.pkl')
+    return joblib.load(model_path)

src/prediction.py

@@ -0,0 +1,82 @@
+# src/prediction.py
+from datetime import datetime
+from dateutil.relativedelta import relativedelta
+import pandas as pd
+from src.model import load_model
+
+# Load model sekali di awal
+model = load_model()
+
+# PREDIKSI 1 BULAN
+def prediksi_curah_hujan(bulan_input: str):
+    """
+    Fungsi untuk memprediksi curah hujan berdasarkan bulan input.
+    Tidak ada preprocessing, asumsikan data sudah siap.
+    """
+    # Langsung pakai fitur yang diinginkan
+    features = [
+        'month_cos',
+        'RR_lag12',
+        'season_dry',
+        'season_rainy',
+        'RR_above_monthly_median',
+        'RR_monthly_median_loo',
+        'RR_monthly_std_loo',
+    ]
+    
+    # Anggap df_row sudah berisi data yang siap dipakai untuk prediksi
+    X = df_row[features]
+    prediksi = model.predict(X)
+    return prediksi[0]
+
+# PREDIKSI BANYAK BULAN
+def predict_range(start: str, end: str) -> pd.DataFrame:
+    """
+    Fungsi untuk melakukan prediksi curah hujan dalam rentang bulan.
+    Tanpa preprocessing, data langsung digunakan.
+    """
+    start_date = datetime.strptime(start, "%Y-%m")
+    end_date = datetime.strptime(end, "%Y-%m")
+    if start_date > end_date:
+        raise ValueError("Bulan awal tidak boleh lebih besar dari bulan akhir")
+
+    dates = []
+    current = start_date
+    while current <= end_date:
+        dates.append(current.strftime("%Y-%m"))
+        current += relativedelta(months=1)
+
+    # Di sini kita anggap data sudah siap tanpa perlu preprocessing
+    # Siapkan data secara langsung
+    processed_rows = []
+    for bulan_input in dates:
+        try:
+            row = prepare_data(bulan_input)  # Anggap kita sudah punya data yang siap dipakai
+            processed_rows.append(row)
+        except Exception as e:
+            print(f"[SKIP] {bulan_input} gagal diproses: {e}")
+
+    if not processed_rows:
+        raise ValueError("Tidak ada bulan yang berhasil diproses.")
+
+    df_all = pd.concat(processed_rows, ignore_index=True)
+
+    features = [
+        'month_cos',
+        'RR_lag12',
+        'season_dry',
+        'season_rainy',
+        'RR_above_monthly_median',
+        'RR_monthly_median_loo',
+        'RR_monthly_std_loo',
+    ]
+    
+    X = df_all[features]
+    y_pred = model.predict(X)
+
+    df_result = pd.DataFrame({
+        'input_month': df_all['YearMonth'].dt.strftime('%Y-%m'),
+        'prediksi_rr': y_pred
+    })
+
+    return df_result