Update index.py

index.py

@@ -40,9 +40,13 @@ df["Veículos de notícias"] = df["domain_folder_name"]
 
 df['FinBERT_label'] = df['FinBERT_label'].astype(str)
 df['FinBERT_label'].replace({
-    '3.0': 'positive',
-    '2.0': 'neutral',
-    '1.0': 'negative'
+    # '3.0': 'positive',
+    # '2.0': 'neutral',
+    # '1.0': 'negative'
+    '3.0': 'positivo',
+    '2.0': 'neutro',
+    '1.0': 'negativo'
+    
 }, inplace=True)
 
 
@@ -51,9 +55,9 @@ counts = df.groupby(['date', 'Topic', 'domain_folder_name', 'FinBERT_label']).si
 counts['count'] = counts['count'].astype('float64')
 counts['rolling_mean_counts'] = counts['count'].rolling(window=30, min_periods=2).mean()
 
-df_pos = counts[[x in ['positive'] for x in counts.FinBERT_label]]
-df_neu = counts[[x in ['neutral'] for x in counts.FinBERT_label]]
-df_neg = counts[[x in ['negative'] for x in counts.FinBERT_label]]
+df_pos = counts[[x in ['positivo'] for x in counts.FinBERT_label]]
+df_neu = counts[[x in ['neutro'] for x in counts.FinBERT_label]]
+df_neg = counts[[x in ['negativo'] for x in counts.FinBERT_label]]
 
 
 # app.layout 
@@ -261,7 +265,7 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
         date_range = pd.date_range(start=start_date, end=end_date)
     
         # Create a DataFrame with all possible combinations of classes, topics, and dates
-        all_combinations = pd.MultiIndex.from_product([['positive', 'neutral', 'negative'],
+        all_combinations = pd.MultiIndex.from_product([['positivo', 'neutro', 'negativo'],
                                                        [selected_topic],
                                                        [selected_domain],
                                                        date_range],
@@ -270,7 +274,12 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
     
         # Merge filtered DataFrame with DataFrame of all combinations
         merged_df = pd.merge(df_all_combinations, df_filtered_2, on=['FinBERT_label', 'Topic', 'domain_folder_name', 'date'], how='left')
-    
+        
+        # Map original labels to their translated versions
+        label_translation = {'positive': 'positivo', 'neutral': 'neutro', 'negative': 'negativo'}
+        
+        # merged_df['FinBERT_label_transformed'] = merged_df['FinBERT_label'].map(label_translation)
+
         # Fill missing values with zeros
         merged_df['count'].fillna(0, inplace=True)
         merged_df['rolling_mean_counts'].fillna(0, inplace=True)
@@ -286,12 +295,10 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
                                xaxis=dict(tickformat="%b %d<br>%Y"))
         # line-fig 2 ends
         
-        # Map original labels to their translated versions
-        label_translation = {'positive': 'positivo', 'neutral': 'neutro', 'negative': 'negativo'}
-        df_filtered['FinBERT_label_transformed'] = df_filtered['FinBERT_label'].map(label_translation)
+        # df_filtered['FinBERT_label_transformed'] = df_filtered['FinBERT_label'].map(label_translation)
         
         # Group by FinBERT_label and count occurrences
-        label_counts_all = df_filtered['FinBERT_label_transformed'].value_counts()
+        label_counts_all = df_filtered['FinBERT_label'].value_counts()
         
         # Calculate percentage of each label
         label_percentages_all = (label_counts_all / label_counts_all.sum()) * 100
@@ -315,7 +322,7 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
         media_df = df_filtered[df_filtered['Veículos de notícias'] == selected_domain]
     
         # Group by FinBERT_label and count occurrences
-        label_counts = media_df['FinBERT_label_transformed'].value_counts()
+        label_counts = media_df['FinBERT_label'].value_counts()
     
         # Calculate percentage of each label
         label_percentages = (label_counts / label_counts.sum()) * 100
@@ -331,12 +338,12 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
         # pie_chart_2 = html.Div(fig,className='four columns')
        
         # Convert FinBERT_label to categorical for better sorting
-        media_df['FinBERT_label_transformed'] = pd.Categorical(media_df['FinBERT_label_transformed'],
+        media_df['FinBERT_label'] = pd.Categorical(media_df['FinBERT_label'],
                                                       categories=['positivo', 'neutro', 'negativo'],
                                                       ordered=True)
 
         # Sort DataFrame by sentiment label and date
-        data_table_1 = media_df.sort_values(by=['date', "FinBERT_label_transformed"])
+        data_table_1 = media_df.sort_values(by=['date', "FinBERT_label"])
     
         return line_fig_1, bar_fig_1, pie_chart_1, line_fig_2, pie_chart_2, data_table_1.to_dict('records')
     else: