Update app.py

app.py

@@ -14,31 +14,33 @@ df['real'] = df['real'].apply(lambda x: f"{x:.2f}")
 # Fill NaN values and convert all columns to strings
 df = df.fillna('').astype(str)
 
-# Function to filter the DataFrame using RapidFuzz for dates
-def filter_dataframe_by_date(df, date_str, threshold=80):
-    # Apply fuzzy matching on the 'ds' (date) column
-    matches = process.extract(date_str, df['ds'], scorer=fuzz.token_sort_ratio, limit=None)
-    filtered_rows = [match[2] for match in matches if match[1] >= threshold]
-    return df.iloc[filtered_rows]
-
-# Function to filter the DataFrame using RapidFuzz for groups
-def filter_dataframe_by_group(df, group_keyword, threshold=80):
-    # Apply fuzzy matching on the 'Group' column
-    matches = process.extract(group_keyword, df['Group'], scorer=fuzz.token_sort_ratio, limit=None)
-    filtered_rows = [match[2] for match in matches if match[1] >= threshold]
-    return df.iloc[filtered_rows]
+# Function to filter the DataFrame using RapidFuzz
+def filter_dataframe(df, date_str, group_keyword, threshold=80):
+    # Apply fuzzy matching on the 'ds' (date) and 'Group' columns
+    date_matches = process.extract(date_str, df['ds'], scorer=fuzz.token_sort_ratio, limit=None)
+    group_matches = process.extract(group_keyword, df['Group'], scorer=fuzz.token_sort_ratio, limit=None)
+
+    # Get the indices that match both criteria
+    date_indices = {match[2] for match in date_matches if match[1] >= threshold}
+    group_indices = {match[2] for match in group_matches if match[1] >= threshold}
+    common_indices = list(date_indices & group_indices)
+
+    return df.iloc[common_indices]
 
 # Function to generate a response using the TAPAS model
 def response(user_question, df):
     a = datetime.datetime.now()
 
     # Extract date and group keywords from the user question
-    date_str = "December 2022"  # Example; you'd extract this from the user question
+    date_str = "December 2022"  # Example; you'd extract this from the user question dynamically
     group_keyword = "IPVA"
 
     # Filter the DataFrame by date and group
-    subset_df = filter_dataframe_by_date(df, date_str)
-    subset_df = filter_dataframe_by_group(subset_df, group_keyword)
+    subset_df = filter_dataframe(df, date_str, group_keyword)
+
+    # Check if the DataFrame is empty
+    if subset_df.empty:
+        return {"Resposta": "Desculpe, não há dados disponíveis para responder à sua pergunta."}
 
     # Initialize the TAPAS model
     tqa = pipeline(task="table-question-answering", model="google/tapas-large-finetuned-wtq", 
@@ -52,10 +54,10 @@ def response(user_question, df):
     # Query the TAPAS model
     try:
         answer = tqa(table=subset_df, query=user_question)['answer']
-    except IndexError as e:
+    except ValueError as e:
         print(f"Error: {e}")
-        answer = "Error occurred: " + str(e)
-    
+        answer = "Desculpe, ocorreu um erro ao processar sua pergunta."
+
     query_result = {
         "Resposta": answer
     }