Upload 13 files

README.md

@@ -1,8 +1,8 @@
 ---
-title: Saham Bbca Multivariate
-emoji: 🏆
-colorFrom: purple
-colorTo: gray
+title: Cardano Forecasting
+emoji: 📊
+colorFrom: green
+colorTo: pink
 sdk: docker
 pinned: false
 ---

app.py

@@ -1,100 +1,151 @@
-from flask import Flask, render_template
+from flask import Flask, render_template, request, redirect, url_for
 import pandas as pd
+import numpy as np
+import seaborn as sns
 import matplotlib.pyplot as plt
-import datetime
+import joblib 
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.neighbors import LocalOutlierFactor
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error, r2_score, mean_absolute_error
-from sklearn.linear_model import LinearRegression
+from sklearn.ensemble import RandomForestRegressor
 import os
+from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error, r2_score, mean_absolute_error
 
 app = Flask(__name__)
 
-def create_lagged_features(data, lags):
-    features = pd.DataFrame()
-    for lag in range(1, lags + 1):
-        features[f'Lag_{lag}'] = data.shift(lag)
-    return features
-
-df = pd.read_csv('./dataset/BBCA-History.csv')
-df = df = df.reindex(index=df.index[::-1])
+history_data = pd.read_csv('./datasets/HistoricalCardano.csv')
+history_data = history_data.reindex(index=history_data.index[::-1])
+history_data = history_data.reset_index(drop=True)
 
-df_display = df
+history_data['Tanggal'] = pd.to_datetime(history_data['Tanggal'], dayfirst=True)
+history_data['Perubahan%'] = history_data['Perubahan%'].str.replace('%', '').str.replace(',', '.').astype(float)
+history_data['Perubahan%'] = history_data['Perubahan%'].astype(float)
+history_data['Vol.'] = history_data['Vol.'].str.replace('M', 'e6').str.replace('B', 'e9').str.replace(',', '.').astype(float)
+history_data['Terakhir'] = history_data['Terakhir'].str.replace(',', '.').astype(float)
+history_data['Pembukaan'] = history_data['Pembukaan'].str.replace(',', '.').astype(float)
+history_data['Tertinggi'] = history_data['Tertinggi'].str.replace(',', '.').astype(float)
+history_data['Terendah'] = history_data['Terendah'].str.replace(',', '.').astype(float)
 
-df['Tanggal'] = pd.to_datetime(df['Tanggal'], dayfirst=True)
-df['Perubahan%'] = df['Perubahan%'].str.replace('%', '').str.replace(',', '.').astype(float)
-df['Perubahan%'] = df['Perubahan%'].astype(float)
-df['Vol.'] = df['Vol.'].str.replace('M', 'e6').str.replace('B', 'e9').str.replace(',', '.').astype(float)
+history_data = history_data.set_index('Tanggal')
 
 # Calculate 30-day moving average
-df['MA30'] = df['Terakhir'].rolling(window=30).mean()
+history_data['MA30'] = history_data['Terakhir'].rolling(window=30).mean()
 
-# Generate the plot
 plt.figure(figsize=(10, 6))
-plt.plot(df['Tanggal'], df['Pembukaan'], label='Harga Pembukaan')
-plt.plot(df['Tanggal'], df['Terakhir'], label='Harga Terakhir')
-plt.plot(df['Tanggal'], df['MA30'], label='MA 30', linestyle='--', color='red')
+plt.plot(history_data['Pembukaan'], label='Harga Pembukaan')
+plt.plot(history_data['Terakhir'], label='Harga Terakhir')
+plt.plot(history_data['MA30'], label='MA 30', linestyle='--', color='red')
 plt.xlabel('Tanggal')
 plt.ylabel('Harga')
 plt.title('Pergerakan Harga Pembukaan dan Terakhir dengan MA 30')
 plt.legend()
 
-# Save the plot to a static file
-plot_path = os.path.join('static', 'plot.png')
-plt.savefig(plot_path)
+plot_ma_a = os.path.join('static', 'ma_a.png')
+plt.savefig(plot_ma_a)
 plt.close()
 
-selected_features = ['Tanggal', 'Pembukaan']
-df = df[selected_features]
-
-df.set_index('Tanggal', inplace=True)
-
-lags = 90
-lagged_features = create_lagged_features(df['Pembukaan'], lags)
-df_with_lags = pd.concat([df, lagged_features], axis=1).dropna()
-
-X = df_with_lags[[f'Lag_{i}' for i in range(1, lags + 1)]]
-y = df_with_lags['Pembukaan']
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=False)
-
-model = LinearRegression()
-model.fit(X_train, y_train)
-
-y_pred = model.predict(X_test)
+# Calculate 30-day moving average
+history_data['MA30'] = history_data['Terakhir'].rolling(window=30).mean()
 
 plt.figure(figsize=(10, 6))
-plt.plot(y_test.index, y_test, label='Actual Values')
-plt.plot(y_test.index, y_pred, label='Predicted Values', linestyle='--')
+plt.plot(history_data['Tertinggi'], label='Harga Tertinggi')
+plt.plot(history_data['Terendah'], label='Harga Terendah')
+plt.plot(history_data['MA30'], label='MA 30', linestyle='--', color='red')
 plt.xlabel('Tanggal')
-plt.ylabel('Harga Pembukaan')
-plt.title('Actual vs Predicted Values')
+plt.ylabel('Harga')
+plt.title('Pergerakan Harga Tertinggi dan Terendah dengan MA 30')
 plt.legend()
 
-# Save the plot to a static file
-plot_training_path = os.path.join('static', 'plot_training.png')
-plt.savefig(plot_training_path)
+plot_ma_b = os.path.join('static', 'ma_b.png')
+plt.savefig(plot_ma_b)
 plt.close()
 
-mse = mean_squared_error(y_test, y_pred)
-mae = mean_absolute_error(y_test, y_pred)
-mape = mean_absolute_percentage_error(y_test, y_pred)
-r2 = r2_score(y_test, y_pred)
+history_data = history_data.drop(columns=['MA30'])
 
-last_date = y_test.index[-1]
-next_date = last_date + datetime.timedelta(days=1)
-
-latest_lags = X.iloc[-1].values.reshape(1, -1)
-next_value = model.predict(latest_lags)
+def create_lagged_features(data, lags=3):
+    lagged_data = data.copy()
+    for lag in range(1, lags + 1):
+        lagged_data[[f"{col}_lag{lag}" for col in data.columns]] = data.shift(lag)
+    lagged_data.dropna(inplace=True)
+    return lagged_data
+
+lags = 30 * 24
+
+# Load the model
+model = joblib.load('./models/random_forest_model.pkl')
+lagged_data = create_lagged_features(history_data.drop(['Vol.', 'Perubahan%'], axis=1), lags)
+
+X = lagged_data.drop(columns=['Pembukaan', 'Terakhir', 'Tertinggi', 'Terendah'])
+y = lagged_data["Pembukaan"]
+
+def multistep_forecast(model, data, n_steps):
+  forecast = []
+  last_observation = data.iloc[-1].values.reshape(1, -1)
+  
+  for _ in range(n_steps):
+    next_step = model.predict(last_observation)
+    forecast.append(next_step[0])
+    
+    # Update the last observation with the new prediction
+    last_observation = np.roll(last_observation, -1)
+    last_observation[0, -1] = next_step[0]
+  
+  return forecast
 
 @app.route('/')
 def index():
-    table_html = df_display.to_html(classes='table table-striped', index=False)
+    table_html = history_data.to_html(classes='table table-striped', index=True)
 
-    return render_template('index.html', table=table_html, plot_url=plot_path)
+    return render_template('index.html', table_html=table_html, plot_ma_a=plot_ma_a, plot_ma_b=plot_ma_b)
 
-@app.route('/predict')
+@app.route('/predict', methods=['GET', 'POST'])
 def predict():
-
-    return render_template('predict.html', plot_training_url=plot_training_path, next_date=next_date.date(), next_value=next_value[0], mse=mse, mae=mae, mape=mape, r2=r2)
+  n_steps = 0
+  
+  if request.method == 'POST':
+    if request.form['waktu'] == '1 bulan':
+      n_steps = 30
+    elif request.form['waktu'] == '3 bulan':
+      n_steps = 30 * 3
+    elif request.form['waktu'] == '6 bulan':
+      n_steps = 30 * 6
+    elif request.form['waktu'] == '1 tahun':
+      n_steps = 30 * 12
+    elif request.form['waktu'] == '2 tahun':
+      n_steps = 30 * 24
+
+    # Perform the forecast
+    forecasted_values = multistep_forecast(model, X, n_steps)
+
+    # Combine past and forecasted values
+    combined_values = np.concatenate([y.values, forecasted_values])
+
+    # Create a time index for the combined values
+    time_index = pd.date_range(start=y.index[0], periods=len(combined_values), freq='D')
+
+    plt.figure(figsize=(12, 6))
+    plt.plot(history_data.index, history_data['Pembukaan'], label="Past Data", linestyle="-", color="blue")
+    plt.plot(time_index[len(y):], forecasted_values, label="Forecasted Values", linestyle="-", color="green")
+    plt.title("All Past Data and Forecasted Future Values")
+    plt.xlabel("Date")
+    plt.ylabel("Values")
+    plt.legend()
+    plt.grid()
+
+    result_img = os.path.join('static', 'result.png')
+    plt.savefig(result_img)
+    plt.close()
+
+    forecasted_df = pd.DataFrame({
+      'Tanggal': time_index[len(y):],
+      'Forecasted_Pembukaan': forecasted_values
+    })
+
+    forecasted_df.to_csv('./datasets/forecasted_values.csv', index=False)
+
+    return render_template('predict.html', result_img=result_img, forecasted_table=forecasted_df.to_html(classes='table table-striped', index=False))
+  else:
+    return redirect(url_for('index'))
 
 if __name__ == '__main__':
     app.run(debug=True)

datasets/forecasted_values.csv

@@ -0,0 +1,181 @@
+Tanggal,Forecasted_Pembukaan
+2024-10-01,0.40139400000000003
+2024-10-02,0.40513499999999975
+2024-10-03,0.40849299999999994
+2024-10-04,0.3959179999999998
+2024-10-05,0.4050889999999998
+2024-10-06,0.40602899999999986
+2024-10-07,0.409478
+2024-10-08,0.39236799999999983
+2024-10-09,0.40253599999999984
+2024-10-10,0.4060509999999999
+2024-10-11,0.41532900000000017
+2024-10-12,0.3997899999999997
+2024-10-13,0.40253299999999986
+2024-10-14,0.3848709999999999
+2024-10-15,0.40508199999999994
+2024-10-16,0.3784180000000001
+2024-10-17,0.3812949999999999
+2024-10-18,0.3871420000000002
+2024-10-19,0.3940159999999998
+2024-10-20,0.3786769999999999
+2024-10-21,0.38716600000000023
+2024-10-22,0.3640600000000001
+2024-10-23,0.39207000000000003
+2024-10-24,0.35764399999999996
+2024-10-25,0.36391700000000016
+2024-10-26,0.3508319999999998
+2024-10-27,0.36564900000000017
+2024-10-28,0.3439839999999998
+2024-10-29,0.3509899999999998
+2024-10-30,0.3574809999999999
+2024-10-31,0.35876999999999987
+2024-11-01,0.34257199999999977
+2024-11-02,0.35742999999999986
+2024-11-03,0.3511939999999998
+2024-11-04,0.3592849999999999
+2024-11-05,0.3504139999999997
+2024-11-06,0.35118699999999975
+2024-11-07,0.3508149999999997
+2024-11-08,0.3614750000000001
+2024-11-09,0.3497109999999997
+2024-11-10,0.3508309999999997
+2024-11-11,0.34209599999999973
+2024-11-12,0.3565669999999998
+2024-11-13,0.3420869999999997
+2024-11-14,0.34203599999999973
+2024-11-15,0.3328820000000001
+2024-11-16,0.3420559999999997
+2024-11-17,0.328207
+2024-11-18,0.3329300000000001
+2024-11-19,0.3309120000000001
+2024-11-20,0.34207299999999974
+2024-11-21,0.32930400000000004
+2024-11-22,0.3309290000000001
+2024-11-23,0.33784
+2024-11-24,0.33777799999999997
+2024-11-25,0.326565
+2024-11-26,0.33798599999999995
+2024-11-27,0.35257399999999983
+2024-11-28,0.3567239999999999
+2024-11-29,0.338039
+2024-11-30,0.3525539999999998
+2024-12-01,0.35975
+2024-12-02,0.36219400000000024
+2024-12-03,0.3508389999999998
+2024-12-04,0.35955
+2024-12-05,0.35667999999999983
+2024-12-06,0.3644960000000001
+2024-12-07,0.3502509999999998
+2024-12-08,0.3566579999999998
+2024-12-09,0.3515269999999998
+2024-12-10,0.3618360000000002
+2024-12-11,0.3512779999999998
+2024-12-12,0.35152299999999975
+2024-12-13,0.3421029999999998
+2024-12-14,0.35684299999999985
+2024-12-15,0.3301010000000001
+2024-12-16,0.3419449999999998
+2024-12-17,0.3420459999999998
+2024-12-18,0.34366299999999983
+2024-12-19,0.33738200000000007
+2024-12-20,0.34254999999999974
+2024-12-21,0.33768099999999995
+2024-12-22,0.34967799999999977
+2024-12-23,0.336995
+2024-12-24,0.3376249999999999
+2024-12-25,0.325614
+2024-12-26,0.33918699999999996
+2024-12-27,0.3237450000000001
+2024-12-28,0.32553699999999997
+2024-12-29,0.314538
+2024-12-30,0.3280120000000001
+2024-12-31,0.31443099999999996
+2025-01-01,0.314547
+2025-01-02,0.324797
+2025-01-03,0.33197000000000015
+2025-01-04,0.3033240000000001
+2025-01-05,0.32517199999999996
+2025-01-06,0.32286200000000015
+2025-01-07,0.338189
+2025-01-08,0.31902100000000017
+2025-01-09,0.32284400000000013
+2025-01-10,0.3181350000000002
+2025-01-11,0.33011100000000015
+2025-01-12,0.3062210000000002
+2025-01-13,0.3184950000000002
+2025-01-14,0.337531
+2025-01-15,0.33829099999999995
+2025-01-16,0.31744400000000017
+2025-01-17,0.3375540000000001
+2025-01-18,0.3311330000000002
+2025-01-19,0.3376440000000001
+2025-01-20,0.32550500000000004
+2025-01-21,0.3311570000000001
+2025-01-22,0.34338799999999986
+2025-01-23,0.3436099999999998
+2025-01-24,0.3284850000000001
+2025-01-25,0.3435919999999998
+2025-01-26,0.34386499999999987
+2025-01-27,0.35016699999999984
+2025-01-28,0.3437179999999998
+2025-01-29,0.3440629999999998
+2025-01-30,0.3573969999999999
+2025-01-31,0.36219500000000016
+2025-02-01,0.33840900000000007
+2025-02-02,0.3573489999999999
+2025-02-03,0.3503319999999998
+2025-02-04,0.3672670000000003
+2025-02-05,0.3498339999999998
+2025-02-06,0.3503299999999998
+2025-02-07,0.35019399999999984
+2025-02-08,0.35975199999999996
+2025-02-09,0.3401849999999999
+2025-02-10,0.35039999999999977
+2025-02-11,0.3665330000000003
+2025-02-12,0.3721180000000001
+2025-02-13,0.34273199999999965
+2025-02-14,0.36656800000000034
+2025-02-15,0.385209
+2025-02-16,0.3876800000000001
+2025-02-17,0.36603400000000014
+2025-02-18,0.385187
+2025-02-19,0.394805
+2025-02-20,0.39513099999999995
+2025-02-21,0.3783980000000001
+2025-02-22,0.39494899999999994
+2025-02-23,0.3911699999999999
+2025-02-24,0.40316499999999983
+2025-02-25,0.38761500000000004
+2025-02-26,0.3913419999999999
+2025-02-27,0.375906
+2025-02-28,0.392419
+2025-03-01,0.3737660000000001
+2025-03-02,0.375916
+2025-03-03,0.36828300000000025
+2025-03-04,0.377441
+2025-03-05,0.36438400000000015
+2025-03-06,0.36833200000000027
+2025-03-07,0.34198099999999976
+2025-03-08,0.37735
+2025-03-09,0.34196799999999966
+2025-03-10,0.3423249999999997
+2025-03-11,0.33730600000000005
+2025-03-12,0.34972899999999973
+2025-03-13,0.33726200000000006
+2025-03-14,0.337171
+2025-03-15,0.3361630000000001
+2025-03-16,0.33749
+2025-03-17,0.3286930000000001
+2025-03-18,0.3334970000000002
+2025-03-19,0.33757200000000004
+2025-03-20,0.3380929999999999
+2025-03-21,0.3319840000000002
+2025-03-22,0.33760599999999996
+2025-03-23,0.33095700000000017
+2025-03-24,0.337658
+2025-03-25,0.32849800000000007
+2025-03-26,0.3306860000000001
+2025-03-27,0.32460100000000014
+2025-03-28,0.3438399999999998
+2025-03-29,0.3192120000000002

models/random_forest_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67e32d591256bd4fc76920b9dcf245c1685e629d9fd2532d2e886d0194516b7
+size 7116481

templates/index.html

@@ -32,24 +32,35 @@
   </style>
 </head>
 <body>
-  <h1>Forecasting Harga Pembukaan Saham BCA (BBCA) dengan Linear Regression Multivariate</h1>
-  <p>Data terakhir diambil tanggal : 2024-11-29</p>
-  <a href="/predict">Lihat prediksi tanggal berikutnya</a>
+  <h1>Forecasting Harga Pembukaan Mata Uang Kripto Cardano (ADA) dengan Random Forest</h1>
+  <p>Data terakhir diambil tanggal : 2024-09-30</p>
+
+  <form action="{{ url_for('predict') }}" method="post">
+    <label for="timeframe">Pilih rentang waktu:</label>
+    <select name="waktu" id="timeframe">
+      <option value="1 bulan">1 Bulan</option>
+      <option value="3 bulan">3 Bulan</option>
+      <option value="6 bulan">6 Bulan</option>
+      <option value="1 tahun">1 Tahun</option>
+    </select>
+    <button type="submit">Submit</button>
+  </form>
+
   <div class="container my-5">
     <h2>DataFrame Display</h2>
     <div class="table-container">
-        {{ table|safe }}
+        {{ table_html|safe }}
     </div>
+  </div>
 
-    <div class="container my-5">
-      <h2>Pergerakan Harga Pembukaan dan Terakhir MA 30</h2>
-      <img src="{{ plot_pembukaan_terakhir_url }}" alt="Plot">
-    </div>
+  <div class="container my-5">
+    <h2>Pergerakan Harga Pembukaan dan Terakhir MA 30</h2>
+    <img src="{{ plot_ma_a }}" alt="Plot">
+  </div>
 
-    <div class="container my-5">
-      <h2>Pergerakan Harga Tertinggi dan Terendah MA 30</h2>
-      <img src="{{ plot_tertinggi_terendah_url }}" alt="Plot">
-    </div>
+  <div class="container my-5">
+    <h2>Pergerakan Harga Tertinggi dan Terendah MA 30</h2>
+    <img src="{{ plot_ma_b }}" alt="Plot">
   </div>
 </body>
 </html>

templates/predict.html

@@ -3,38 +3,46 @@
 <head>
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>IMPHNEN</title>
+  <title>Document</title>
+  <style>
+    table {
+      border-collapse: collapse;
+      width: 100%;
+      border: 1px solid black; /* Add this line */
+    }
+
+    th, td {
+      border: 1px solid black;
+      padding: 8px;
+      text-align: left;
+    }
+
+    th {
+      background-color: #f2f2f2;
+    }
+
+    tr:nth-child(even) {
+      background-color: #f2f2f2;
+    }
+
+    .table-container {
+      max-height: 400px;
+      overflow-y: auto;
+    }
+  </style>
 </head>
 <body>
-  <h1>Hasil Forecasting Harga Pembukaan Saham BCA (BBCA) dengan Linear Regression Multivariate</h1>
-  <a href="/">Kembali halaman utama</a>
+  <h1>Hasil Prediksi</h1>
+
+  <a href="/">Kembali </a>
+
   <div class="container my-5">
-    <h2>Hasil Prediksi</h2>
-    <p>Harga Pembukaan Saham BCA (BBCA) pada tanggal {{ next_date }} adalah sebesar Rp {{ next_value }}</p>
-  </div>
-  <div class="container my-5">
-    <h2>Grafik Training Data</h2>
-    <img src="{{ plot_training_url }}" alt="">
-  </div>
-  <div class="container my-5">
-    <h2>Score Evaluasi</h2>
-    <ul>
-      <li>
-        <strong>Mean Absolute Error (MAE):</strong> {{ mae }}
-      </li>
-      <li>
-        <strong>Mean Squared Error (MSE):</strong> {{ mse }}
-      </li>
-      <li>
-        <strong>Root Mean Squared Error (RMSE):</strong> {{ rmse }}
-      </li>
-      <li>
-        <strong>Coefficient of Determination (R^2):</strong> {{ r2 }}
-      </li>
-      <li>
-        <strong>Mean Absolute Percentage Error (MAPE):</strong> {{ mape }}
-      </li>
-    </ul>
+    <h2>DataFrame Display</h2>
+    <div class="table-container">
+        {{ forecasted_table|safe }}
+    </div>
   </div>
+
+  <img src="{{ result_img }}" alt="" srcset="">
 </body>
 </html>