added app.py, models and requirements

README.md

@@ -10,3 +10,13 @@ pinned: false
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+-------------------------------------------------------------------------------------------------------------
+
+This Repository contain following models with app root file app.py
+* ARIMA Daily prediction
+* Prophet Daily Prediction
+* Prophet Seasonal
+
+User interface lets user select a specific model and days ahead for prediction. Results shows in the form of an image, Model Prediction.

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import pandas as pd
+import yfinance as yf
+import matplotlib.pyplot as plt
+import pickle
+import io
+
+# Load pickled models
+with open("arima_model.pkl", "rb") as f:
+    arima_model = pickle.load(f)
+
+with open("prophet_daily.pkl", "rb") as f:
+    prophet_daily_model = pickle.load(f)
+
+with open("prophet_seasonal.pkl", "rb") as f:
+    prophet_seasonal_model = pickle.load(f)
+
+def forecast_stock(ticker, model_type, days=1):
+    # Fetch recent data for plotting
+    df = yf.download(ticker, start="2010-01-01", interval="1d")
+    df.columns = df.columns.get_level_values(0)
+    df = df[['Close']].sort_index()
+    df = df.asfreq('B').ffill()
+    
+    # Forecast
+    if model_type == "ARIMA":
+        forecast = arima_model.forecast(steps=days)
+    elif model_type == "Prophet Daily":
+        future = prophet_daily_model.make_future_dataframe(periods=days, freq='B')
+        forecast_df = prophet_daily_model.predict(future)
+        forecast = forecast_df['yhat'].iloc[-days:].values
+    else:  # Prophet Seasonal
+        future = prophet_seasonal_model.make_future_dataframe(periods=days, freq='B')
+        forecast_df = prophet_seasonal_model.predict(future)
+        forecast = forecast_df['yhat'].iloc[-days:].values
+    
+    # Plot
+    plt.figure(figsize=(10,5))
+    plt.plot(df.index[-50:], df['Close'].values[-50:], label='Recent Actual')
+    plt.plot(pd.date_range(df.index[-1]+pd.Timedelta(days=1), periods=days, freq='B'),
+             forecast, label='Forecast', marker='o')
+    plt.legend()
+    plt.title(f"{ticker} Stock Forecast ({model_type})")
+    plot_path = "temp_plot.png"  # temporary file
+    plt.savefig(plot_path)
+    plt.close()
+    return plot_path
+# Gradio interface
+ticker_input = gr.Textbox(label="Ticker Symbol", value="AAPL")
+model_input = gr.Radio(["ARIMA", "Prophet Daily", "Prophet Seasonal"], label="Model")
+days_input = gr.Slider(1, 30, step=1, label="Days Ahead")
+
+gr.Interface(
+    forecast_stock,
+    inputs=[ticker_input, model_input, days_input],
+    outputs=gr.Image(type="pil"),
+    live=True,
+    title="Stock Price Forecasting",
+    description="Forecast next n days stock prices using ARIMA or Prophet"
+).launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,8 @@
+pandas
+numpy
+matplotlib
+prophet
+statsmodels
+gradio
+yfinance
+pmdarima