Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| from statsmodels.tsa.statespace.sarimax import SARIMAX | |
| from sklearn.metrics import mean_absolute_percentage_error | |
| # Streamlit app layout | |
| st.set_page_config(layout="wide") | |
| st.title("Air Passenger Data Analysis and Forecasting") | |
| st.write("Time Series Analysis and Forecasting with SARIMAX") | |
| # Load data | |
| data_path = "AirPassengers.csv" # Ensure this file is in the correct directory | |
| data = pd.read_csv(data_path, parse_dates=['Month'], index_col='Month') | |
| data.index.freq = 'MS' # Set the frequency to Month Start to avoid warnings | |
| st.write("Data Preview", data.head()) | |
| # Sidebar for SARIMAX parameters | |
| st.sidebar.header("SARIMAX Model Parameters") | |
| p = st.sidebar.slider("AR order (p)", 0, 5, 1) | |
| d = st.sidebar.slider("Difference order (d)", 0, 2, 1) | |
| q = st.sidebar.slider("MA order (q)", 0, 5, 1) | |
| P = st.sidebar.slider("Seasonal AR order (P)", 0, 5, 1) | |
| D = st.sidebar.slider("Seasonal Difference order (D)", 0, 2, 1) | |
| Q = st.sidebar.slider("Seasonal MA order (Q)", 0, 5, 1) | |
| s = st.sidebar.selectbox("Seasonal period (s)", [12]) # Monthly seasonality | |
| forecast_steps = st.sidebar.slider("Forecast Steps (Months)", min_value=1, max_value=36, value=12) | |
| # Display data preview and time series plot | |
| st.subheader("Air Passenger Traffic Over Time") | |
| fig, ax = plt.subplots() | |
| ax.plot(data.index, data['#Passengers'], color='blue', label="Observed") | |
| ax.set_xlabel("Date") | |
| ax.set_ylabel("Number of Passengers") | |
| ax.set_title("Monthly Air Passenger Data") | |
| ax.legend() | |
| st.pyplot(fig) | |
| # Train the model and forecast | |
| if st.button("Train Model and Forecast"): | |
| try: | |
| # Split data into training and test sets | |
| train_data = data[:-forecast_steps] # Use all data except the last 'forecast_steps' for training | |
| test_data = data[-forecast_steps:] # Use the last 'forecast_steps' data points for testing | |
| # Fit the SARIMAX model on the training data | |
| model = SARIMAX(train_data['#Passengers'], | |
| order=(p, d, q), | |
| seasonal_order=(P, D, Q, s), | |
| enforce_stationarity=False, | |
| enforce_invertibility=False) | |
| sarimax_model = model.fit(disp=False) | |
| st.success("Model training completed successfully.") | |
| # Display Model Summary | |
| st.subheader("Model Summary") | |
| st.text(sarimax_model.summary()) | |
| # Generate forecast for the test period to evaluate accuracy | |
| forecast = sarimax_model.get_forecast(steps=forecast_steps) | |
| forecast_df = forecast.summary_frame(alpha=0.05) # 95% confidence intervals | |
| # Calculate accuracy (MAPE) | |
| forecasted_values = forecast_df['mean'] | |
| actual_values = test_data['#Passengers'] | |
| mape = mean_absolute_percentage_error(actual_values, forecasted_values) * 100 # MAPE in percentage | |
| # Display the accuracy | |
| st.subheader("Forecast Accuracy") | |
| st.write(f"Mean Absolute Percentage Error (MAPE): {mape:.2f}%") | |
| st.write(f"Accuracy: {100 - mape:.2f}%") | |
| # Display forecast data | |
| st.subheader("Forecast Data") | |
| st.write(forecasted_values) | |
| # Display confidence intervals | |
| lower_conf_int = forecast_df['mean_ci_lower'].rename('lower #Passengers') | |
| upper_conf_int = forecast_df['mean_ci_upper'].rename('upper #Passengers') | |
| forecast_confidence_df = pd.concat([lower_conf_int, upper_conf_int], axis=1) | |
| st.subheader("Forecast Confidence Interval") | |
| st.write(forecast_confidence_df) | |
| # Plot forecasted values with confidence intervals | |
| fig, ax = plt.subplots() | |
| ax.plot(data.index, data['#Passengers'], label='Observed', color='blue') | |
| ax.plot(forecasted_values.index, forecasted_values, label='Forecast', color='red') | |
| ax.fill_between(forecasted_values.index, lower_conf_int, upper_conf_int, color='pink', alpha=0.3) | |
| ax.set_xlabel("Date") | |
| ax.set_ylabel("Number of Passengers") | |
| ax.set_title("Air Passenger Forecast with Accuracy") | |
| ax.legend() | |
| st.pyplot(fig) | |
| except Exception as e: | |
| st.error(f"An error occurred during model training or forecasting: {e}") | |