change default date

model.py

@@ -32,7 +32,7 @@ def split(predictors, target):
     predictors_train, predictors_test, target_train, target_test = train_test_split(predictors,
                                                                                     target,
                                                                                     test_size=0.2,
-                                                                                    random_state=42)
+                                                                                    random_state=50)
     return predictors_train, predictors_test, target_train, target_test
 
 
@@ -50,7 +50,7 @@ def run_cv_training(predictors_train, target_train):
             'subsample': 0.8,
             'objective': 'reg:squarederror'}
         cv_results = cv(dtrain=data_train, params=params, nfold=2,
-                        num_boost_round=1000, early_stopping_rounds=3, metrics="rmse", as_pandas=True, seed=123)
+                        num_boost_round=1000, early_stopping_rounds=3, metrics="rmse", as_pandas=True, seed=50)
         best_value = cv_results['test-rmse-mean'].values[-1]
         best_round = cv_results.index[-1]
         xgb_csv.append(

stream_app.py

@@ -44,7 +44,7 @@ else:
     select_auth = authorities.name.sort_values()
 
 authority = st.sidebar.selectbox('Authority', ['All', *select_auth])
-min_year, max_year = st.sidebar.slider('Decisions year', min_value=2001, max_value=2021, value=(2001, 2021))
+min_year, max_year = st.sidebar.slider('Decisions year', min_value=2001, max_value=2021, value=(2008, 2021))
 
 # apply filters
 authority_filter = True
@@ -184,14 +184,15 @@ if st.button('Run training'):
         st.metric(label="Training size", value=predictors_train.shape[0])
         st.metric(label="Test size", value=predictors_test.shape[0])
 
-        #run cross validation
+        # run cross validation
         st.subheader("Cross validation error")
         xgb_cv, best_params = run_cv_training(predictors_train, target_train)
-        print(best_params)
-        st.json(best_params)
-        xgb_cv.to_csv('cv_results.csv')
+
         st.line_chart(xgb_cv[[col for col in xgb_cv.columns if "mean" in col]])
+        st.subheader("Selected variables")
+        st.json(best_params)
 
+        # train final model
         xgb_model = run_training(predictors_train, target_train, best_params[1], best_params[2])
 
         # evaluate model error