Upload 2 files

app.py

@@ -0,0 +1,149 @@
+# -*- coding: utf-8 -*-
+"""Huggingface_Prototype.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1i--A21QuJPKdv-HM2kUrFSwj89Qfv4cb
+"""
+
+#! mkdir ~/.kaggle
+#! cp kaggle.json ~/.kaggle/
+#! chmod 600 ~/.kaggle/kaggle.json
+
+#!kaggle datasets download -d sercandikici/merged-dataset-electricty-weather-for-modelling
+#! unzip merged-dataset-electricty-weather-for-modelling.zip
+
+pip install gradio
+
+from google.colab import files
+uploaded = files.upload()
+
+#df = pd.read_csv("merged_data.csv")
+#df.drop('is_holiday', axis=1, inplace=True)
+#df.to_csv('merged_data_huggingface.csv', index=False)
+#from google.colab import files
+#files.download('merged_data_huggingface.csv')
+
+from prophet import Prophet
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import gradio as gr
+
+def forecast_plot(forecast_days,test_days, days):
+
+  fig, ax = plt.subplots(figsize=(14, 4))
+  ax.plot(forecast_days['ds'], forecast_days['yhat'], label='Forecast', color='green')
+  ax.scatter(test_days['ds'], test_days['y'], label='Actual', color='orange')
+  ax.set_xlabel('Date')
+  ax.set_ylabel('MGW')
+  plt.title(f'Prophet Forecast - Model 3 - {days} days horizon')
+  plt.legend()
+
+  return fig
+
+def mean_absolute_percentage_error(y_true, y_pred):
+    y_true, y_pred = np.array(y_true), np.array(y_pred)
+    mape = np.mean(np.abs((y_true - y_pred) / y_true))
+    return mape
+
+def root_mean_squared_error(y_true, y_pred):
+    y_true, y_pred = np.array(y_true), np.array(y_pred)
+    mse = np.mean((y_true - y_pred) ** 2)
+    rmse = np.sqrt(mse)
+    return rmse
+
+def r_squared(y_true, y_pred):
+    y_true, y_pred = np.array(y_true), np.array(y_pred)
+    mean_y_true = np.mean(y_true)
+    ss_total = np.sum((y_true - mean_y_true) ** 2)
+    ss_residual = np.sum((y_true - y_pred) ** 2)
+    r2 = 1 - (ss_residual / ss_total)
+    return r2
+
+def predict_and_evaluate(csv_file, days_to_predict,freq, country_name):
+
+    df_model = pd.read_csv(csv_file)
+    df_model.columns = ["ds", "y", "temp"]
+    df_model['ds'] = pd.to_datetime(df_model['ds'])
+
+
+    split_from = 90 * 12
+    train_data = df_model[:-split_from]
+    test_data = df_model[-split_from:]
+    freq = freq
+    seasonality_prior_scale = 0.01
+    changepoint_prior_scale = 0.05
+    mcmc_samples = 50
+    periods = days_to_predict * 12
+
+    m = Prophet(mcmc_samples=mcmc_samples, changepoint_prior_scale=changepoint_prior_scale,
+                seasonality_prior_scale=seasonality_prior_scale)
+    m.add_country_holidays(country_name=country_name)
+    m.add_regressor("temp", mode="additive")
+    m.fit(train_data)
+
+    future = m.make_future_dataframe(periods=periods, freq=freq)
+    train_idx = future["ds"].isin(train_data.ds)
+    test_idx = ~train_idx
+
+    reg = ["temp"]
+    for r in reg:
+        future.loc[train_idx, r] = train_data[r].to_list()
+    for r in reg:
+        future.loc[test_idx, r] = test_data.iloc[:periods][r].to_list()
+
+    forecast = m.predict(future)
+    forecast_days = forecast[forecast["ds"] >= test_data["ds"].iloc[0]]
+    test_days = test_data[(test_data["ds"] >= test_data["ds"].iloc[0]) & (
+                test_data["ds"] <= forecast_days["ds"].iloc[-1])]
+
+    plot = forecast_plot(forecast_days, test_days, days_to_predict)
+
+    mape = mean_absolute_percentage_error(test_days["y"], forecast_days["yhat"])
+    rmse = root_mean_squared_error(test_days["y"], forecast_days["yhat"])
+    rsqr = r_squared(test_days["y"], forecast_days["yhat"])
+
+    metrics = {
+        "MAPE": round(mape,3),
+        "RMSE": round(rmse,1),
+        "R-squared": round(rsqr,3)
+    }
+
+    return metrics,plot
+
+csv_name = "merged_data_huggingface.csv"
+#df_merged['settlement_date'] = pd.to_datetime(df_merged['settlement_date'])
+#df_model = df_merged[["tsd", "settlement_date", "temp"]]
+#df_model.columns = ["y", "ds", "temp"]
+
+days_to_predict = 15  # Set the default value for days to predict
+country_name = "UK" # Set the default value for country to predict
+freq = "2H" # Set the default value for country to predict
+
+predict_and_evaluate(csv_name, days_to_predict, freq, country_name)
+
+iface = gr.Interface(
+    fn=predict_and_evaluate,
+    inputs=[
+        gr.File(label="CSV File"),
+        gr.Slider(1, 90, value=30, step=1, label="Days to Predict"),
+        gr.Textbox(label="Data Frequency", placeholder="Enter frequency (e.g., 2H for 2 hourly)"),
+        gr.Textbox(label="Country Code", placeholder="Enter country code (e.g., UK)")
+    ],
+    outputs=[
+        gr.Textbox(label=" Evaluation Metrics"),
+        "plot"
+
+    ],
+    title="Prophet Electricty Load Forecasting Model",
+    description="Upload a CSV file of time series data to generate electricty demand forecasts using Prophet. Update country code(eg UK or DE) for holidays and data frequency",
+
+
+    examples=[
+        ["merged_data_huggingface.csv", 30, "2H", "UK"]
+        ]
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+prophet
+numpy
+pandas
+matplotlib