Update app.py

app.py

@@ -8,8 +8,6 @@ from neuralforecast.losses.pytorch import HuberMQLoss
 from neuralforecast.utils import AirPassengersDF
 import time
 
-
-
 @st.cache_resource
 def load_model(path, freq):
     nf = NeuralForecast.load(path=path)
@@ -17,7 +15,6 @@ def load_model(path, freq):
 
 @st.cache_resource
 def load_all_models():
-        # Paths for saving models
     nhits_paths = {
         'D': './M4/NHITS/daily',
         'M': './M4/NHITS/monthly',
@@ -161,16 +158,17 @@ def select_model(horizon, model_type, max_steps=200):
 def model_train(df,model):
     model.fit(df)
     return model
+
 def forecast_time_series(df, model_type, horizon, max_steps=200):
     start_time = time.time()  # Start timing
     freq = determine_frequency(df)
-    st.write(f"Determined frequency: {freq}")
+    st.sidebar.write(f"Determined frequency: {freq}")
     
     selected_model = select_model(horizon, model_type, max_steps)
-    model = model_train(df,selected_model)
+    model = model_train(df, selected_model)
     
     forecast_results = {}
-    st.write(f"Generating forecast using {model_type} model...")
+    st.sidebar.write(f"Generating forecast using {model_type} model...")
     forecast_results[model_type] = generate_forecast(model, df)
 
     for model_name, forecast_df in forecast_results.items():
@@ -178,7 +176,7 @@ def forecast_time_series(df, model_type, horizon, max_steps=200):
         
     end_time = time.time()  # End timing
     time_taken = end_time - start_time
-    st.success(f"Time taken for {model_type} forecast: {time_taken:.2f} seconds")
+    st.sidebar.success(f"Time taken for {model_type} forecast: {time_taken:.2f} seconds")
 
 @st.cache_data
 def load_default():
@@ -189,7 +187,7 @@ def transfer_learning_forecasting():
     st.title("Transfer Learning Forecasting")
 
     # Upload dataset
-    uploaded_file = st.file_uploader("Upload your time series data (CSV)", type=["csv"])
+    uploaded_file = st.sidebar.file_uploader("Upload your time series data (CSV)", type=["csv"])
     if uploaded_file:
         df = pd.read_csv(uploaded_file)
     else:
@@ -198,13 +196,13 @@ def transfer_learning_forecasting():
     nhits_models, timesnet_models, lstm_models, tft_models = load_all_models()
     
     # Model selection and forecasting
-    st.subheader("Model Selection and Forecasting")
-    model_choice = st.selectbox("Select model", ["NHITS", "TimesNet", "LSTM", "TFT"])
-    horizon = st.number_input("Forecast horizon", value=18)
+    st.sidebar.subheader("Model Selection and Forecasting")
+    model_choice = st.sidebar.selectbox("Select model", ["NHITS", "TimesNet", "LSTM", "TFT"])
+    horizon = st.sidebar.number_input("Forecast horizon", value=18)
 
     # Determine frequency of data
     frequency = determine_frequency(df)
-    st.write(f"Detected frequency: {frequency}")
+    st.sidebar.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)
@@ -225,27 +223,26 @@ def transfer_learning_forecasting():
 
     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")
+    st.sidebar.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"])
+    uploaded_file = st.sidebar.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.number_input("Forecast horizon", value=18)
-    dynamic_max_steps = st.number_input('Max steps', value=200)
+    st.sidebar.subheader("Dynamic Model Selection and Forecasting")
+    dynamic_model_choice = st.sidebar.selectbox("Select model for dynamic forecasting", ["NHITS", "TimesNet", "LSTM", "TFT"], key="dynamic_model_choice")
+    dynamic_horizon = st.sidebar.number_input("Forecast horizon", value=18)
+    dynamic_max_steps = st.sidebar.number_input('Max steps', value=200)
 
-    
     forecast_time_series(df, dynamic_model_choice, dynamic_horizon, dynamic_max_steps)
-    
+
 pg = st.navigation({
     "Overview": [
         # Load pages from functions
@@ -257,4 +254,4 @@ pg = st.navigation({
 try:
     pg.run()
 except Exception as e:
-    st.error(f"Something went wrong: {str(e)}", icon=":material/error:")
+    st.sidebar.error(f"Something went wrong: {e}", icon=":material/error:")