Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
+import pytorch_lightning as pl
 from neuralforecast.core import NeuralForecast
 from neuralforecast.models import NHITS, TimesNet, LSTM, TFT
 from neuralforecast.losses.pytorch import HuberMQLoss
@@ -9,35 +10,35 @@ import time
 
 # Paths for saving models
 nhits_paths = {
-    'D': './M4/NHITS/daily',
-    'M': './M4/NHITS/monthly',
-    'H': './M4/NHITS/hourly',
-    'W': './M4/NHITS/weekly',
-    'Y': './M4/NHITS/yearly'
+    'D': './results/M4/NHITS/daily',
+    'M': './results/M4/NHITS/monthly',
+    'H': './results/M4/NHITS/hourly',
+    'W': './results/M4/NHITS/weekly',
+    'Y': './results/M4/NHITS/yearly'
 }
 
 timesnet_paths = {
-    'D': './M4/TimesNet/daily',
-    'M': './M4/TimesNet/monthly',
-    'H': './M4/TimesNet/hourly',
-    'W': './M4/TimesNet/weekly',
-    'Y': './M4/TimesNet/yearly'
+    'D': './results/M4/TimesNet/daily',
+    'M': './results/M4/TimesNet/monthly',
+    'H': './results/M4/TimesNet/hourly',
+    'W': './results/M4/TimesNet/weekly',
+    'Y': './results/M4/TimesNet/yearly'
 }
 
 lstm_paths = {
-    'D': './M4/LSTM/daily',
-    'M': './M4/LSTM/monthly',
-    'H': './M4/LSTM/hourly',
-    'W': './M4/LSTM/weekly',
-    'Y': './M4/LSTM/yearly'
+    'D': './results/M4/LSTM/daily',
+    'M': './results/M4/LSTM/monthly',
+    'H': './results/M4/LSTM/hourly',
+    'W': './results/M4/LSTM/weekly',
+    'Y': './results/M4/LSTM/yearly'
 }
 
 tft_paths = {
-    'D': './M4/TFT/daily',
-    'M': './M4/TFT/monthly',
-    'H': './M4/TFT/hourly',
-    'W': './M4/TFT/weekly',
-    'Y': './M4/TFT/yearly'
+    'D': './results/M4/TFT/daily',
+    'M': './results/M4/TFT/monthly',
+    'H': './results/M4/TFT/hourly',
+    'W': './results/M4/TFT/weekly',
+    'Y': './results/M4/TFT/yearly'
 }
 
 @st.cache_resource
@@ -164,7 +165,7 @@ def forecast_time_series(df, model_type, freq, horizon, max_steps=200):
     model = select_model(horizon, model_type, max_steps)
     forecast_results = {}
     st.write(f"Generating forecast using {model_type} model...")
-    forecast_results[model_type] = generate_forecast(model, df, freq)
+    forecast_results[model_type] = generate_forecast(model, df)
 
     for model_name, forecast_df in forecast_results.items():
         plot_forecasts(forecast_df, df, f'{model_name} Forecast Comparison')
@@ -173,49 +174,82 @@ def forecast_time_series(df, model_type, freq, horizon, max_steps=200):
     time_taken = end_time - start_time
     st.success(f"Time taken for {model_type} forecast: {time_taken:.2f} seconds")
 
-# Streamlit App
-st.title("Dynamic and Automatic Time Series Forecasting")
-
-# Upload dataset
-uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
-if uploaded_file:
-    df = pd.read_csv(uploaded_file)
-else:
-    st.warning("Using default data")
-    df = AirPassengersDF.copy()
-
-# Model selection and forecasting
-st.subheader("Transfer Learning Forecasting")
-model_choice = st.selectbox("Select model", ["NHITS", "TimesNet", "LSTM", "TFT"])
-horizon = st.slider("Forecast horizon", 1, 100, 10)
-
-# Determine frequency of data
-frequency = determine_frequency(df)
-st.write(f"Detected frequency: {frequency}")
-
-# Load pre-trained models
-nhits_model, timesnet_model, lstm_model, tft_model = select_model_based_on_frequency(frequency, nhits_models, timesnet_models, lstm_models, tft_models)
-forecast_results = {}
-
-start_time = time.time()  # Start timing
-if model_choice == "NHITS":
-    forecast_results['NHITS'] = generate_forecast(nhits_model, df)
-elif model_choice == "TimesNet":
-    forecast_results['TimesNet'] = generate_forecast(timesnet_model, df)
-elif model_choice == "LSTM":
-    forecast_results['LSTM'] = generate_forecast(lstm_model, df)
-elif model_choice == "TFT":
-    forecast_results['TFT'] = generate_forecast(tft_model, df)
-
-for model_name, forecast_df in forecast_results.items():
-    plot_forecasts(forecast_df, df, f'{model_name} Forecast')
+@st.cache_data
+def load_default():
+    df = AirPassengersDf.copy()
+    return df
     
-end_time = time.time()  # End timing
-time_taken = end_time - start_time
-st.success(f"Time taken for {model_choice} forecast: {time_taken:.2f} seconds")
-
-# Dynamic forecasting
-st.subheader("Dynamic Forecasting")
-dynamic_model_choice = st.selectbox("Select model for dynamic forecasting", ["NHITS", "TimesNet", "LSTM", "TFT"], key="dynamic_model_choice")
-dynamic_horizon = st.slider("Forecast horizon for dynamic forecasting", 1, 100, 10, key="dynamic_horizon")
-forecast_time_series(df, dynamic_model_choice, frequency, dynamic_horizon)
+def transfer_learning_forecasting():
+    st.title("Transfer Learning Forecasting")
+
+    # Upload dataset
+    uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
+    if uploaded_file:
+        df = pd.read_csv(uploaded_file)
+    else:
+        df = load_default()  
+
+    # Model selection and forecasting
+    st.subheader("Model Selection and Forecasting")
+    model_choice = st.selectbox("Select model", ["NHITS", "TimesNet", "LSTM", "TFT"])
+    horizon = st.slider("Forecast horizon", 1, 100, 10)
+
+    # Determine frequency of data
+    frequency = determine_frequency(df)
+    st.write(f"Detected frequency: {frequency}")
+
+    # Load pre-trained models
+    nhits_model, timesnet_model, lstm_model, tft_model = select_model_based_on_frequency(frequency, nhits_models, timesnet_models, lstm_models, tft_models)
+    forecast_results = {}
+
+    start_time = time.time()  # Start timing
+    if model_choice == "NHITS":
+        forecast_results['NHITS'] = generate_forecast(nhits_model, df)
+    elif model_choice == "TimesNet":
+        forecast_results['TimesNet'] = generate_forecast(timesnet_model, df)
+    elif model_choice == "LSTM":
+        forecast_results['LSTM'] = generate_forecast(lstm_model, df)
+    elif model_choice == "TFT":
+        forecast_results['TFT'] = generate_forecast(tft_model, df)
+
+    for model_name, forecast_df in forecast_results.items():
+        plot_forecasts(forecast_df, df, f'{model_name} Forecast')
+
+    end_time = time.time()  # End timing
+    time_taken = end_time - start_time
+    st.success(f"Time taken for {model_choice} forecast: {time_taken:.2f} seconds")
+
+ def dynamic_forecasting():
+    st.title("Dynamic Forecasting")
+
+    # Upload dataset
+    uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
+    if uploaded_file:
+        df = pd.read_csv(uploaded_file)
+    else:
+        df = load_default()
+
+    # Dynamic forecasting
+    st.subheader("Dynamic Model Selection and Forecasting")
+    dynamic_model_choice = st.selectbox("Select model for dynamic forecasting", ["NHITS", "TimesNet", "LSTM", "TFT"], key="dynamic_model_choice")
+    dynamic_horizon = st.slider("Forecast horizon for dynamic forecasting", 1, 100, 10, key="dynamic_horizon")
+
+    # Determine frequency of data
+    frequency = determine_frequency(df)
+    st.write(f"Detected frequency: {frequency}")
+
+    forecast_time_series(df, dynamic_model_choice, frequency, dynamic_horizon
+                         
+# Define the main navigation
+pg = st.navigation({
+    "Overview": [
+        # Load pages from functions
+        st.Page(transfer_learning_forecasting, title="Transfer Learning Forecasting", default=True, icon=":material/library_books:"),
+        st.Page(dynamic_forecasting, title="Dynamic Forecasting", icon=":material/person:"),
+    ]
+})
+
+try:
+    pg.run()
+except Exception as e:
+    st.error(f"Something went wrong: {str(e)}", icon=":material/error:")