Update app.py

app.py

@@ -81,10 +81,10 @@ os.makedirs(app.config['MODEL_FOLDER'], exist_ok=True)
 # Prediction analysis models loaded from Hugging Face.
 src_path = hf_hub_download(
     repo_id="WebashalarForML/Diamond_model_",
-    filename="models_list/mkble/DecisionTree_best_pipeline_mkble_0_to_2.pkl",
+    filename="models_list/mkble/DecisionTree_best_pipeline_mkble_1_to_1.49.pkl",
     cache_dir=MODEL_FOLDER
 )
-dst_path = os.path.join(MODEL_FOLDER, "DecisionTree_best_pipeline_mkble_0_to_2.pkl")
+dst_path = os.path.join(MODEL_FOLDER, "DecisionTree_best_pipeline_mkble_1_to_1.49.pkl")
 shutil.copy(src_path, dst_path)
 makable_model = load(dst_path)
 
@@ -265,7 +265,7 @@ def process_dataframe(df):
         
         # Create two DataFrames: one for prediction and one for classification.
         df_pred = df[required_columns].copy()
-        df_pred = df_pred[(df_pred[['EngCts']] > 0.00).all(axis=1) & (df_pred[['EngCts']] <= 2.00).all(axis=1)] 
+        df_pred = df_pred[(df_pred[['EngCts']] > 1.00).all(axis=1) & (df_pred[['EngCts']] <= 1.49).all(axis=1)] 
         df_pred[['EngBlk', 'EngWht', 'EngOpen', 'EngPav']]=df_pred[['EngBlk', 'EngWht', 'EngOpen', 'EngPav']].fillna("NA")
         df_class = df[required_columns_2].fillna("NA").copy()