Create app.py

app.py

@@ -0,0 +1,130 @@
+import streamlit as st
+import pandas as pd
+import plotly.graph_objs as go
+from statsmodels.tsa.arima.model import ARIMA
+from statsmodels.tsa.stattools import adfuller
+
+# Set Streamlit page configuration
+st.set_page_config(page_title="ARIMA Forecasting with Streamlit", layout="wide")
+
+# Title of the Streamlit app
+st.title("📈 Time Series Forecasting with ARIMA for Vegetable Prices")
+
+# Sidebar configuration for user inputs
+st.sidebar.header("User Configuration")
+file_path = st.sidebar.text_input("Enter the path to your CSV file", 'arima.csv')
+
+p = st.sidebar.number_input("ARIMA Parameter p (AR term)", min_value=0, max_value=5, value=1)
+d = st.sidebar.number_input("ARIMA Parameter d (Differencing)", min_value=0, max_value=2, value=1)
+q = st.sidebar.number_input("ARIMA Parameter q (MA term)", min_value=0, max_value=5, value=1)
+
+# Load and preprocess data
+try:
+    data = pd.read_csv(file_path)
+    data['Date'] = pd.to_datetime(data['Date'], format='%d-%m-%Y', errors='coerce')
+    data = data.dropna(subset=['Date', 'Average'])
+    commodities = data['Commodity'].unique()
+except FileNotFoundError:
+    st.error("Data file not found. Please check the file path and try again.")
+    st.stop()
+
+# Sidebar for user input to select a commodity
+selected_commodity = st.sidebar.selectbox("Select a Vegetable Commodity", commodities)
+
+# Filter data based on the selected commodity and sort by date
+commodity_data = data[data['Commodity'] == selected_commodity].sort_values('Date')
+
+# Display data and perform ADF Test
+st.subheader(f"Data Overview and Stationarity Check for '{selected_commodity}'")
+st.write(commodity_data.head())
+
+# Perform the Augmented Dickey-Fuller (ADF) test
+adf_result = adfuller(commodity_data['Average'])
+is_stationary = adf_result[1] < 0.05
+
+# Display ADF test results
+with st.expander(f"Augmented Dickey-Fuller Test Results for '{selected_commodity}'", expanded=False):
+    st.write(f"ADF Statistic: {adf_result[0]:.4f}")
+    st.write(f"p-value: {adf_result[1]:.4f}")
+    st.write("Critical Values:")
+    for key, value in adf_result[4].items():
+        st.write(f"   {key}: {value:.4f}")
+    st.success(f"The time series is {'stationary' if is_stationary else 'not stationary'} (p-value {'<' if is_stationary else '>='} 0.05).")
+
+# ARIMA model fitting with user-selected parameters
+st.subheader(f"ARIMA Model Fitting and Summary for '{selected_commodity}'")
+model = ARIMA(commodity_data['Average'], order=(p, d, q))
+model_fit = model.fit()
+
+# Display model summary
+with st.expander("ARIMA Model Summary", expanded=False):
+    st.write(model_fit.summary())
+
+# Forecast future values up to December 31, 2025
+last_date = commodity_data['Date'].max()
+forecast_end_date = pd.to_datetime('2025-12-31')
+forecast_periods = (forecast_end_date - last_date).days  # Calculate days until end of 2025
+
+# Make forecast
+forecast = model_fit.get_forecast(steps=forecast_periods)
+forecast_index = pd.date_range(start=last_date + pd.Timedelta(days=1), periods=forecast_periods)
+forecast_values = forecast.predicted_mean
+conf_int = forecast.conf_int()
+
+# Plotly graph for interactive visualization
+st.subheader(f"Forecast Visualization for '{selected_commodity}' until {forecast_end_date.date()}")
+fig = go.Figure()
+
+# Plot historical data
+fig.add_trace(go.Scatter(
+    x=commodity_data['Date'],
+    y=commodity_data['Average'],
+    mode='lines+markers',
+    name='Historical Data',
+    line=dict(color='royalblue', width=2)
+))
+
+# Plot forecasted data
+fig.add_trace(go.Scatter(
+    x=forecast_index,
+    y=forecast_values,
+    mode='lines+markers',
+    name='Forecast',
+    line=dict(color='red', width=2, dash='dash'),
+    hovertemplate='Date: %{x}<br>Price: %{y:.2f}<extra></extra>'
+))
+
+# Plot confidence intervals
+fig.add_trace(go.Scatter(
+    x=forecast_index.tolist() + forecast_index[::-1].tolist(),
+    y=conf_int.iloc[:, 0].tolist() + conf_int.iloc[:, 1][::-1].tolist(),
+    fill='toself',
+    fillcolor='rgba(173, 216, 230,0.2)',
+    line=dict(color='rgba(255,255,255,0)'),
+    name='Confidence Interval'
+))
+
+# Update layout for a better presentation
+fig.update_layout(
+    title=f"ARIMA Forecast for '{selected_commodity}' Prices until 2025",
+    xaxis_title='Date',
+    yaxis_title='Average Price (in Kg)',
+    legend=dict(x=0.01, y=0.99),
+    template='plotly_white',
+    hovermode='x unified'
+)
+
+# Display Plotly chart
+st.plotly_chart(fig, use_container_width=True)
+
+# Display forecasted values in a table format for better visibility
+st.subheader(f"Forecasted Prices for '{selected_commodity}' until 2025")
+forecast_table = pd.DataFrame({
+    'Date': forecast_index,
+    'Forecasted Price': forecast_values,
+    'Lower Confidence Interval': conf_int.iloc[:, 0],
+    'Upper Confidence Interval': conf_int.iloc[:, 1]
+})
+st.dataframe(forecast_table)
+
+st.info("Adjust the ARIMA parameters in the sidebar to see different results.")