fix missing YYYYQ data in the chart

app.py

@@ -4,7 +4,6 @@ import pickle
 from tensorflow.keras.models import load_model
 from sklearn.preprocessing import MinMaxScaler
 import matplotlib.pyplot as plt
-import matplotlib.ticker as ticker
 from io import BytesIO
 from PIL import Image
 import json
@@ -17,9 +16,10 @@ with open('data/2024_11_7_total_return_sample.pkl', 'rb') as f:
     data = pickle.load(f)
 
 columns_to_drop = ['Date', 'CBSA_Name', 'Id', 'iname', 'type', 'Cluster', 'region', 'division', 'state', 'msa', 'tret',
-                   'treturn', 'tot_index', 'inc_index', 'app_index', 'count', 'emv', 'bmv', 'income', 'psales',
-                   'capimp', 'ireturn', 'areturn', 'Latitude_x', 'Longitude_x', 'Latitude_y', 'Longitude_y', 'tmin',
-                   'tmean', 'tmax', 'tdmean', 'ppt', 'vpdmin', 'vpdmax', 'tmin_low', 'tmax_high']
+                   'iret', 'aret', 'treturn', 'tot_index', 'inc_index', 'app_index', 'count', 'emv', 'bmv', 'income',
+                   'psales', 'capimp', 'ireturn', 'areturn', 'Latitude_x', 'Longitude_x', 'Latitude_y', 'Longitude_y',
+                   'tmin', 'tmean', 'tmax', 'tdmean', 'ppt', 'vpdmin', 'vpdmax', 'tmin_low', 'tmax_high',
+                   'num_of_positive_headlines', 'num_of_negative_headlines', 'remote_work_shift']
 
 features = data.drop(columns=columns_to_drop)
 scaler.fit(features)
@@ -34,21 +34,17 @@ def create_sequences(data_param, target_param, input_steps=12, forecast_steps=4)
 
 
 def predict_and_plot(cbsa_name):
-    print(f"Processing predictions for CBSA: {cbsa_name}")
-
     cbsa_data = data[data['CBSA_Name'] == cbsa_name]
 
+    print(cbsa_data['YYYYQ'].sort_values())
+
     cbsa_features = cbsa_data.drop(columns=columns_to_drop)
     cbsa_features = cbsa_features[features.columns]
 
     cbsa_target = cbsa_data['tret']
 
-    print(f"Feature shape for {cbsa_name} before scaling: {cbsa_features.shape}")
-
     cbsa_scaled_features = scaler.transform(cbsa_features)
 
-    print(f"Feature shape for {cbsa_name} after scaling: {cbsa_scaled_features.shape}")
-
     X_cbsa, y_cbsa = create_sequences(cbsa_scaled_features, cbsa_target)
 
     predictions = model.predict(X_cbsa)
@@ -58,6 +54,7 @@ def predict_and_plot(cbsa_name):
     predictions = np.roll(predictions, -shift_steps)
 
     future_quarters = [f"{year}-Q{quarter}" for year in range(2024, 2026) for quarter in range(1, 5)]
+
     num_future_steps = len(future_quarters)
 
     future_predictions = []
@@ -65,25 +62,27 @@ def predict_and_plot(cbsa_name):
 
     for _ in range(num_future_steps):
         next_prediction = model.predict(current_input.reshape(1, -1, X_cbsa.shape[2]))
+
         future_predictions.append(next_prediction.squeeze())
+
         current_input = np.roll(current_input, -1, axis=0)
+
         current_input[-1] = next_prediction.squeeze()
 
     predictions = np.concatenate((predictions, np.array(future_predictions)))
 
     time_index = (
-        cbsa_data['YYYYQ'].iloc[-len(y_cbsa):]
+        cbsa_data['YYYYQ'].iloc[:len(y_cbsa)]
         .apply(lambda x: f"{str(x)[:4]}-Q{str(x)[4]}")
         .sort_values()
     )
+
     future_time_index = pd.Series(future_quarters)
     full_time_index = pd.concat([time_index, future_time_index]).reset_index(drop=True)
 
     actual_index = full_time_index[:len(y_cbsa)]
     predicted_index = full_time_index[:len(predictions)]
 
-    print("time_index", predicted_index)
-
     predicted_json = [
         {
             "year": int(year_quarter.split("-")[0]),