Upload 4 files

app.py

@@ -0,0 +1,253 @@
+# app.py
+import pandas as pd
+import numpy as np
+import joblib
+import os
+from datetime import datetime
+from dateutil.relativedelta import relativedelta
+import gradio as gr
+import matplotlib.pyplot as plt
+import seaborn as sns
+from PIL import Image
+import io
+
+# Load Dataset (path relatif)
+dataset_path = os.path.join(os.path.dirname(__file__), 'dataset', 'data_bulanan.csv')
+df_historis = pd.read_csv(dataset_path)
+df_historis['YearMonth'] = pd.to_datetime(df_historis['YearMonth'], format='%Y-%m')
+df_historis['month'] = df_historis['YearMonth'].dt.month
+df_historis['year'] = df_historis['YearMonth'].dt.year
+
+# Tambahkan fitur yang dibutuhkan di awal
+df_historis['month_sin'] = np.sin(2 * np.pi * df_historis['month'] / 12)
+df_historis['month_cos'] = np.cos(2 * np.pi * df_historis['month'] / 12)
+
+def season(month):
+    return 'rainy' if month in [11, 12, 1, 2, 3, 4] else 'dry'
+
+df_historis['season'] = df_historis['month'].apply(season)
+df_historis = pd.concat([df_historis, pd.get_dummies(df_historis['season'], prefix='season')], axis=1)
+
+# Hitung RR bulanan historis
+monthly_medians = df_historis.groupby('month')['RR'].median()
+monthly_stats = df_historis.groupby('month')['RR'].agg(['median', 'std']).rename(columns={'median': 'monthly_median', 'std': 'monthly_std'})
+
+# Tambahkan RR lag12 ke data historis
+df_historis = df_historis.sort_values('YearMonth')
+df_historis['RR_lag12'] = df_historis['RR'].shift(12)
+df_historis = df_historis.reset_index(drop=True)
+
+# Fungsi preprocessing
+def preprocess_single_row_from_date(input_date: str) -> pd.DataFrame:
+    """Preprocess input tanggal (YYYY-MM-DD) jadi 1-row DataFrame dengan fitur lengkap"""
+    target_date = pd.to_datetime(input_date).replace(day=1)  # Pastikan awal bulan
+    df_all = df_historis.copy()
+
+    # Ambil 12 bulan sebelumnya
+    past_12_months = target_date - pd.DateOffset(months=12)
+    df_up_to = df_all[df_all['YearMonth'] <= past_12_months]
+
+    # Cek apakah data cukup panjang
+    if df_up_to.empty:
+        raise ValueError(f"Tanggal {input_date} tidak punya data historis 12 bulan ke belakang.")
+
+    month = target_date.month
+    season_str = season(month)
+
+    # Buat 1 baris data
+    row = {
+        'YearMonth': target_date,
+        'month': month,
+        'month_cos': np.cos(2 * np.pi * month / 12),
+        'season_dry': 1 if season_str == 'dry' else 0,
+        'season_rainy': 1 if season_str == 'rainy' else 0,
+    }
+
+    # Ambil RR_lag12
+    rr_lag12_date = target_date - pd.DateOffset(months=12)
+    rr_lag12 = df_all.loc[df_all['YearMonth'] == rr_lag12_date, 'RR']
+    row['RR_lag12'] = rr_lag12.values[0] if not rr_lag12.empty else np.nan
+
+    # Fitur statistik LOO bulan target
+    rr_values_bulan_ini = df_all[df_all['month'] == month]['RR'].values
+    if len(rr_values_bulan_ini) < 2:
+        row['RR_monthly_median_loo'] = np.nan
+        row['RR_monthly_std_loo'] = np.nan
+    else:
+        rr_loo = rr_values_bulan_ini[:-1]  # anggap data terakhir belum tersedia
+        row['RR_monthly_median_loo'] = np.median(rr_loo)
+        row['RR_monthly_std_loo'] = np.std(rr_loo, ddof=1)
+
+    # RR_above_monthly_median: bandingkan dengan median historis bulan tsb
+    row['RR_above_monthly_median'] = (
+        1 if row['RR_monthly_median_loo'] > monthly_medians[month] else 0
+    )
+
+    # Return sebagai DataFrame
+    return pd.DataFrame([row])
+
+# Fungsi untuk load model
+def load_model():
+    model_path = os.path.join(os.path.dirname(__file__), 'model', 'ModelFinalSVR_rainfallpkl.pkl')
+    model = joblib.load(model_path)
+    return model
+
+# Load model
+model = load_model()
+
+# PREDIKSI 1 BULAN
+def prediksi_curah_hujan(bulan_input: str):
+    """Fungsi untuk memprediksi curah hujan berdasarkan bulan input."""
+    df_row = preprocess_single_row_from_date(bulan_input)
+    features = [
+        'month_cos',
+        'RR_lag12',
+        'season_dry',
+        'season_rainy',
+        'RR_above_monthly_median',
+        'RR_monthly_median_loo',
+        'RR_monthly_std_loo',
+    ]
+    X = df_row[features]
+    prediksi = model.predict(X)
+    return prediksi[0]
+
+# PREDIKSI BANYAK BULAN
+def predict_range(start: str, end: str) -> pd.DataFrame:
+    """Melakukan prediksi curah hujan untuk rentang bulan tertentu."""
+    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)
+
+    processed_rows = []
+    for bulan_input in dates:
+        try:
+            row = preprocess_single_row_from_date(bulan_input)
+            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
+
+# Gradio interface untuk visualisasi
+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
+
+# Setup Gradio 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="Aplikasi Prediksi Curah Hujan",
+    description="Masukkan rentang bulan untuk memprediksi curah hujan bulanan."
+).launch()

dataset/data_bulanan.csv

@@ -0,0 +1,389 @@
+YearMonth,RR
+1993-01,251.08135025656145
+1993-02,150.37262839504174
+1993-03,390.7
+1993-04,197.0075286170563
+1993-05,122.56188768000386
+1993-06,118.69999999999999
+1993-07,14.566219567258194
+1993-08,96.1
+1993-09,80.4
+1993-10,134.3
+1993-11,240.12527981766715
+1993-12,344.4766996714088
+1994-01,366.77182912490593
+1994-02,225.6
+1994-03,363.2
+1994-04,432.5660649351236
+1994-05,85.4
+1994-06,65.5
+1994-07,0.0
+1994-08,11.7
+1994-09,57.5351072686592
+1994-10,51.6
+1994-11,243.98012230099923
+1994-12,216.66464940636305
+1995-01,199.1891677897583
+1995-02,127.13280608084733
+1995-03,278.1180329428387
+1995-04,182.04822301879344
+1995-05,202.53895422814801
+1995-06,129.6
+1995-07,50.5
+1995-08,0.0
+1995-09,81.49468997686888
+1995-10,229.9
+1995-11,397.03326111728165
+1995-12,129.9028443439577
+1996-01,292.4
+1996-02,166.29999999999998
+1996-03,229.70000000000002
+1996-04,342.6994459381333
+1996-05,101.85526951873305
+1996-06,69.29116051763859
+1996-07,90.7
+1996-08,108.30816330151055
+1996-09,172.0
+1996-10,292.3
+1996-11,610.2
+1996-12,242.51779630088916
+1997-01,156.19956676540858
+1997-02,125.0796972537279
+1997-03,188.7
+1997-04,241.19844826637615
+1997-05,206.41137921233945
+1997-06,7.616059180328022
+1997-07,15.53677889077752
+1997-08,16.557572497186086
+1997-09,1.4
+1997-10,37.0
+1997-11,116.47118852757926
+1997-12,331.7959182704611
+1998-01,183.6
+1998-02,414.5295496360607
+1998-03,507.172770065446
+1998-04,314.92894396846464
+1998-05,181.52427268445223
+1998-06,244.5758154519582
+1998-07,135.77302400218824
+1998-08,74.6
+1998-09,134.3
+1998-10,211.4639977605679
+1998-11,229.42735335397427
+1998-12,97.6
+1999-01,199.58415299855494
+1999-02,118.87401572211743
+1999-03,240.673351922766
+1999-04,133.3942558576711
+1999-05,248.3
+1999-06,74.07277449141301
+1999-07,77.18755196634574
+1999-08,25.363982480635606
+1999-09,18.7
+1999-10,265.7
+1999-11,295.1514942143291
+1999-12,244.96981379033673
+2000-01,279.38441758682706
+2000-02,142.57330537170455
+2000-03,138.05966091042984
+2000-04,262.6149202763099
+2000-05,240.1
+2000-06,49.712135218936865
+2000-07,80.2
+2000-08,20.922727915835882
+2000-09,51.67500379888218
+2000-10,158.05452928517144
+2000-11,337.67202002399347
+2000-12,80.58619478377489
+2001-01,223.32430779195107
+2001-02,253.31578383391732
+2001-03,217.0204668177401
+2001-04,259.1920090553131
+2001-05,93.03265954761467
+2001-06,87.5
+2001-07,193.86357214461242
+2001-08,52.3
+2001-09,108.79184391497556
+2001-10,415.82291931200433
+2001-11,526.4
+2001-12,75.5
+2002-01,374.8903931276039
+2002-02,112.27804616775673
+2002-03,344.1
+2002-04,183.5
+2002-05,55.0
+2002-06,54.1
+2002-07,133.72269337818736
+2002-08,37.8
+2002-09,10.3
+2002-10,20.8
+2002-11,211.5421684180434
+2002-12,465.37348277161055
+2003-01,70.10004662530501
+2003-02,271.2144064775262
+2003-03,359.05275430266335
+2003-04,136.7594288099275
+2003-05,116.91849302846519
+2003-06,37.593951646601816
+2003-07,40.5
+2003-08,78.69715959751016
+2003-09,79.56816330299387
+2003-10,320.2
+2003-11,185.6
+2003-12,203.97199722009177
+2004-01,209.14869058580464
+2004-02,232.77658162240834
+2004-03,249.74186884319855
+2004-04,303.6981899422686
+2004-05,286.5
+2004-06,88.35156126272939
+2004-07,40.18089163282056
+2004-08,11.4
+2004-09,86.05290014705008
+2004-10,86.9985807167679
+2004-11,190.63494526593695
+2004-12,255.86157928520208
+2005-01,170.86775735669755
+2005-02,440.88667294204924
+2005-03,310.97987800600606
+2005-04,257.5511957678716
+2005-05,209.84899495802273
+2005-06,212.20178506431148
+2005-07,98.946595329573
+2005-08,66.68359438387021
+2005-09,158.3680740956845
+2005-10,156.42384803930068
+2005-11,237.80625912916258
+2005-12,205.7000281469098
+2006-01,326.95405226015663
+2006-02,282.3
+2006-03,74.73169255551863
+2006-04,241.7572058518405
+2006-05,112.83292031444998
+2006-06,51.36871787119322
+2006-07,58.776975287238486
+2006-08,0.0
+2006-09,1.7243913136799156
+2006-10,58.200007910300585
+2006-11,129.18779806716452
+2006-12,512.9060308617175
+2007-01,133.67910950905053
+2007-02,409.0949626599001
+2007-03,132.95584296984413
+2007-04,505.43323039858274
+2007-05,126.36308591260254
+2007-06,187.05782736876162
+2007-07,11.0
+2007-08,88.91379184788718
+2007-09,182.39012278636278
+2007-10,179.20518873492944
+2007-11,361.63393565709316
+2007-12,382.5317880490638
+2008-01,259.42332246135635
+2008-02,135.0279473718514
+2008-03,242.4
+2008-04,322.4216281192347
+2008-05,181.21353666767806
+2008-06,79.20694948920988
+2008-07,3.6
+2008-08,77.78154170139875
+2008-09,56.21896326501911
+2008-10,140.53869295256138
+2008-11,289.15698476922597
+2008-12,366.93714169165577
+2009-01,210.5175561599849
+2009-02,236.238456637764
+2009-03,393.82480475116427
+2009-04,176.1962427810293
+2009-05,189.91508002729583
+2009-06,108.37496339673358
+2009-07,33.16611481118132
+2009-08,0.8107843564343054
+2009-09,28.73432976910153
+2009-10,261.977011414297
+2009-11,376.02317802750304
+2009-12,279.0434776062234
+2010-01,365.5868947485269
+2010-02,557.1
+2010-03,559.6204706837364
+2010-04,96.07836702312055
+2010-05,372.59388433043284
+2010-06,170.39615551647037
+2010-07,241.5526951691408
+2010-08,120.99924674320692
+2010-09,428.7780825562002
+2010-10,256.16272504824616
+2010-11,439.3425717528467
+2010-12,246.03237363945593
+2011-01,122.3216474413144
+2011-02,90.20470946764267
+2011-03,120.39939211185718
+2011-04,382.63329712253
+2011-05,194.6848614812256
+2011-06,132.9504670566075
+2011-07,95.46910412640837
+2011-08,3.1
+2011-09,107.88865878793106
+2011-10,108.97120779210906
+2011-11,336.5365683828699
+2011-12,293.08774118583204
+2012-01,123.4341690333577
+2012-02,304.9602420483437
+2012-03,163.02809044787992
+2012-04,297.9517169383213
+2012-05,265.4726136905434
+2012-06,89.10649705767621
+2012-07,37.58064647205457
+2012-08,0.0
+2012-09,33.143910586239556
+2012-10,127.11403073964557
+2012-11,564.7500572457384
+2012-12,636.9
+2013-01,216.9
+2013-02,263.4380887675806
+2013-03,316.2171989666979
+2013-04,297.55764098933577
+2013-05,177.8605237239985
+2013-06,255.84827812249927
+2013-07,174.51388936268847
+2013-08,75.40921745179475
+2013-09,194.2366861979934
+2013-10,205.29695015015193
+2013-11,182.0503861612477
+2013-12,390.23534052627275
+2014-01,323.44980090226267
+2014-02,174.9602071533784
+2014-03,345.8792037963495
+2014-04,319.15228565699755
+2014-05,218.86862871420595
+2014-06,220.22329943366452
+2014-07,222.00963423847557
+2014-08,162.48290652468685
+2014-09,30.697103757073187
+2014-10,150.77532707802038
+2014-11,280.5327621963137
+2014-12,311.22660915720354
+2015-01,268.44597478139076
+2015-02,261.9220380209493
+2015-03,347.5202104325999
+2015-04,317.2672873718662
+2015-05,264.29672356457803
+2015-06,94.79472625847774
+2015-07,28.48681767396458
+2015-08,26.418829633355696
+2015-09,61.70861829094549
+2015-10,65.51097262740697
+2015-11,505.50977741742184
+2015-12,334.62812309356366
+2016-01,451.05832137686497
+2016-02,208.42041817018406
+2016-03,447.45806563130395
+2016-04,469.7255801955244
+2016-05,378.0961339270254
+2016-06,180.76857229278173
+2016-07,206.20425159965515
+2016-08,177.78658334208833
+2016-09,309.94783792135735
+2016-10,385.38446987853877
+2016-11,472.54993120938644
+2016-12,89.58773722976137
+2017-01,91.59854510058943
+2017-02,203.94350300763767
+2017-03,427.7059284805644
+2017-04,231.50285036316524
+2017-05,252.61527270669504
+2017-06,163.97346571055053
+2017-07,215.8306004618938
+2017-08,63.98220588075185
+2017-09,92.5756682215938
+2017-10,346.8
+2017-11,457.9926554140231
+2017-12,168.42776093948407
+2018-01,209.70965888869222
+2018-02,239.91616485384893
+2018-03,292.097431011106
+2018-04,313.4874464952281
+2018-05,141.3978006017689
+2018-06,33.4
+2018-07,15.664818099662051
+2018-08,40.21016547118674
+2018-09,54.08733528243221
+2018-10,141.58974882140342
+2018-11,498.56752131042197
+2018-12,325.52770785091076
+2019-01,231.4
+2019-02,275.269297009915
+2019-03,237.81367790969256
+2019-04,314.4744094372529
+2019-05,262.36848518322546
+2019-06,26.5
+2019-07,17.248187844876682
+2019-08,2.6167495556427434
+2019-09,57.339936906043654
+2019-10,91.76411978893357
+2019-11,278.9860029033337
+2019-12,367.74898035024984
+2020-01,293.20641769857497
+2020-02,372.5957914042957
+2020-03,346.55076947047854
+2020-04,343.9137634262813
+2020-05,260.8945506303953
+2020-06,112.09918095252984
+2020-07,157.40915303926636
+2020-08,80.4529869918556
+2020-09,144.657204262832
+2020-10,338.4963294135904
+2020-11,241.16637931037678
+2020-12,148.6836525618784
+2021-01,265.42343836962976
+2021-02,191.2224652264138
+2021-03,385.578105212618
+2021-04,311.25680902408845
+2021-05,295.5328755958329
+2021-06,138.95568449582794
+2021-07,155.20393442994296
+2021-08,166.97661914699515
+2021-09,216.3185847615164
+2021-10,302.5802034466951
+2021-11,472.991881394166
+2021-12,230.0184447192437
+2022-01,125.8100259311639
+2022-02,153.30683845792902
+2022-03,238.45949809096317
+2022-04,420.65234252780795
+2022-05,280.3307643523407
+2022-06,242.72385238238581
+2022-07,178.0948265160396
+2022-08,118.98603546767782
+2022-09,294.62060502656965
+2022-10,335.92
+2022-11,309.00269772787976
+2022-12,343.4114186277845
+2023-01,211.13494915526633
+2023-02,120.40668991499172
+2023-03,343.1042983486973
+2023-04,399.7114552397399
+2023-05,317.588290958841
+2023-06,245.32943432669816
+2023-07,92.57339297952734
+2023-08,73.86438118727291
+2023-09,76.36124630750058
+2023-10,156.7884226357093
+2023-11,368.0072365245131
+2023-12,418.74159053603546
+2024-01,360.83871763682805
+2024-02,335.6914371466504
+2024-03,307.9739595430766
+2024-04,228.31447305647336
+2024-05,170.3470991761926
+2024-06,239.8851788966072
+2024-07,40.932802665391954
+2024-08,22.900000000000002
+2024-09,179.85871676743912
+2024-10,136.4342202266847
+2024-11,549.6916845822988
+2024-12,265.5119508617036
+2025-01,161.2660874675449
+2025-02,193.27965381794792
+2025-03,364.7579048790125
+2025-04,233.1

model/ModelFinalSVR_rainfallpkl.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99dea464402def4ac1ac9d99999e214ed213e1572a4510491bbc1266447fbb7
+size 22334

requirements.txt

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