Update index.py

index.py

@@ -99,7 +99,13 @@ app.layout = dbc.Container([
     dbc.Row([ # row 7 but needs to be updated
         dbc.Col(dcc.Graph(id="bar-graph-1"))
     ]),
-
+    
+    # html.Div(id='pie-container-1'),
+    dbc.Row([ # row 9
+             dbc.Col(dcc.Graph(id='pie-graph-1'),
+                )
+    ]),
+    
     dbc.Row([ # row 7
             dbc.Label("Escolha um site de notícias:", className="fw-bold")
     ]),
@@ -117,24 +123,54 @@ app.layout = dbc.Container([
 
         )
     ]),
-
+    
+     dbc.Row([ # row 9
+             dbc.Col(dcc.Graph(id='line-graph-2'),
+                     )
+     ]),
+    
+    # dbc.Row([ # row 9
+    #         dbc.Col(dcc.Graph(id='line-graph-2'),
+    #                 )
+    # ]),
+
+    # dbc.Row([ # row 10
+    #         dbc.Col(dcc.Graph(id='line-graph-3'),
+    #                 )
+    # ]),
+    
+    # dbc.Row([ # row 11
+    #         dbc.Col(dcc.Graph(id='line-graph-4'),
+    #                 )
+    # ]),
+
+    # html.Div(id='pie-container-2'),
+     dbc.Row([ # row 9
+             dbc.Col(dcc.Graph(id='pie-graph-2'),
+                )
+     ]),
+    
     dbc.Row([ # row 9
-            dbc.Col(dcc.Graph(id='line-graph-2'),
-                    )
-    ]),
-
-    dbc.Row([ # row 10
-            dbc.Col(dcc.Graph(id='line-graph-3'),
-                    )
-    ]),
+            dbc.Col(
+                dash_table.DataTable(
+                    id='headlines-table',
+                    columns=[
+                        {"name": "Headline", "id": "Headline"},
+                        {"name": "URL", "id": "url"},
+                        {"name": "Date", "id": "date"},
+                        {"name": "Sentiment Label", "id": "FinBERT_label"}
+                    ],
+                    style_table={'overflowX': 'auto'},
+                    style_cell={
+                        'textAlign': 'left',
+                        'whiteSpace': 'normal',
+                        'height': 'auto',
+                        'minWidth': '180px', 'width': '180px', 'maxWidth': '180px',
+                    },
+                )
+            )
+        ])
     
-    dbc.Row([ # row 11
-            dbc.Col(dcc.Graph(id='line-graph-4'),
-                    )
-    ]),
-
-    html.Div(id='pie-container-1')
-
 ])
 
 # # Create a function to generate pie charts
@@ -154,10 +190,9 @@ app.layout = dbc.Container([
 @app.callback(
     Output('line-graph-1', 'figure'),
     Output('bar-graph-1','figure'),
+    Output('pie-container-1', 'figure'),
     Output('line-graph-2', 'figure'),
-    Output('line-graph-3', 'figure'),
-    Output('line-graph-4', 'figure'),
-    Output('pie-container-1', 'children'),
+    Output('pie-container-2', 'figure'),
     Input("topic-selector", "value"),
     Input ("domain-selector", "value"),
     Input('date-range', 'start_date'),
@@ -210,44 +245,40 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
         # Bar Graph ends
                            
         # filter dataframes based on updated data range
-        mask_2 = ((df_pos["Topic"] == selected_topic) & (df_pos["domain_folder_name"] == selected_domain) & (df_pos['date'] >= start_date) & (df_pos['date'] <= end_date))
-        mask_3 = ((df_neu["Topic"] == selected_topic) & (df_neu["domain_folder_name"] == selected_domain) & (df_neu['date'] >= start_date) & (df_neu['date'] <= end_date))
-        mask_4 = ((df_neg["Topic"] == selected_topic) & (df_neg["domain_folder_name"] == selected_domain) & (df_neg['date'] >= start_date) & (df_neg['date'] <= end_date))
-        df2_filtered = df_pos.loc[mask_2]
-        df3_filtered = df_neu.loc[mask_3]
-        df4_filtered = df_neg.loc[mask_4]
+        # Filtering data...
+        df_filtered = counts[(counts['Topic'] == selected_topic) &
+                             (counts['domain_folder_name'] == selected_domain) &
+                             (counts['date'] >= start_date) &
+                             (counts['date'] <= end_date)]
     
-        #create line graphs based on filtered dataframes
-        line_fig_2 = px.line(df2_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
-                         title="Positive")
-        line_fig_3 = px.line(df3_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
-                         title="Neutral")
-        line_fig_4 = px.line(df4_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
-                         title="Negative")
+        # Create a date range for the selected period
+        date_range = pd.date_range(start=start_date, end=end_date)
     
-        #set x-axis title and y-axis title in line graphs
-        line_fig_2.update_layout(
-                       xaxis_title='Data',
-                       yaxis_title='Número de notícias com sentimento positivo')
-        line_fig_3.update_layout(
-                       xaxis_title='Data',
-                       yaxis_title='Número de notícias com sentimento neutro')
-        line_fig_4.update_layout(
-                       xaxis_title='Data',
-                       yaxis_title='Número de notícias com sentimento negativo')
+        # Create a DataFrame with all possible combinations of classes, topics, and dates
+        all_combinations = pd.MultiIndex.from_product([['positive', 'neutral', 'negative'],
+                                                       [selected_topic],
+                                                       [selected_domain],
+                                                       date_range],
+                                                      names=['FinBERT_label', 'Topic', 'domain_folder_name', 'date'])
+        df_all_combinations = pd.DataFrame(index=all_combinations).reset_index()
     
-        #set label format on y-axis in line graphs
-        line_fig_2.update_xaxes(tickformat="%b %d<br>%Y")
-        line_fig_3.update_xaxes(tickformat="%b %d<br>%Y")
-        line_fig_4.update_xaxes(tickformat="%b %d<br>%Y")
+        # Merge filtered DataFrame with DataFrame of all combinations
+        merged_df = pd.merge(df_all_combinations, df_filtered, on=['FinBERT_label', 'Topic', 'domain_folder_name', 'date'], how='left')
     
-        #set label format on y-axis in line graphs
-        line_fig_2.update_traces(line_color='#1E88E5')
-        line_fig_3.update_traces(line_color='#004D40')
-        line_fig_4.update_traces(line_color='#D81B60')
-
-        #
-        # pie_container_1 = generate_pie_chart(category)
+        # Fill missing values with zeros
+        merged_df['count'].fillna(0, inplace=True)
+        merged_df['rolling_mean_counts'].fillna(0, inplace=True)
+    
+        # Create line graph...
+        line_fig_2 = px.line(merged_df, x="date", y="count", color="FinBERT_label",
+                       line_group="FinBERT_label", title="Sentiment Over Time",
+                       labels={"count": "Number of News Articles", "date": "Date"})
+    
+    
+        # Update layout...
+        line_fig_2.update_layout(xaxis_title='Date', yaxis_title='Number of News Articles',
+                               xaxis=dict(tickformat="%b %d<br>%Y"))
+        
         # 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)
@@ -259,49 +290,41 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
         label_percentages_all = (label_counts_all / label_counts_all.sum()) * 100
         
         # Plot general pie chart
-        fig_general = px.pie(
+        pie_chart_1 = px.pie(
             values=label_percentages_all,
             names=label_percentages_all.index,
             title='Distribuição Geral',
             color_discrete_sequence=['#039a4d', '#3c03f4', '#ca3919']
         )
         
-        
         # Get unique media categories
         media_categories = df_filtered['Veículos de notícias'].unique()
         
         # Define colors for each label
         label_colors = {'positivo': '#039a4d', 'neutro': '#3c03f4', 'negativo': '#ca3919'}
-        
                          
-        pie_container_1 = []
-        # Loop through each media category
-        row_content = []
-        for media in media_categories:
-            # Filter DataFrame for current media category
-            media_df = df_filtered[df_filtered['Veículos de notícias'] == media]
-        
-            # Group by FinBERT_label and count occurrences
-            label_counts = media_df['FinBERT_label_transformed'].value_counts()
-        
-            # Calculate percentage of each label
-            label_percentages = (label_counts / label_counts.sum()) * 100
-        
-            # Plot pie chart
-            fig = px.pie(
-                values=label_percentages,
-                names=label_percentages.index,
-                title=f'Distribuição para {media}',
-                color_discrete_sequence=[label_colors[label] for label in label_percentages.index]
-            )
-            fig = dcc.Graph(figure=fig)
-            pie_chart = html.Div(fig,className='four columns')
-            row_content.append(pie_chart)
-        pie_container_1.append(html.Div(row_content, className='row'))
+        # Filter DataFrame for current media category
+        media_df = df_filtered[df_filtered['Veículos de notícias'] == media]
+    
+        # Group by FinBERT_label and count occurrences
+        label_counts = media_df['FinBERT_label_transformed'].value_counts()
+    
+        # Calculate percentage of each label
+        label_percentages = (label_counts / label_counts.sum()) * 100
+    
+        # Plot pie chart
+        pie_chart_2 = px.pie(
+            values=label_percentages,
+            names=label_percentages.index,
+            title=f'Distribuição para {media}',
+            color_discrete_sequence=[label_colors[label] for label in label_percentages.index]
+        )
+        # pie_chart_2 = dcc.Graph(figure=fig)
+        # pie_chart_2 = html.Div(fig,className='four columns')
             
-        return line_fig_1, bar_fig_1, line_fig_2, line_fig_3, line_fig_4, pie_container_1
+        return line_fig_1, bar_fig_1, pie_chart_1, line_fig_2, pie_chart_2
     else:
-        return {'data': []},{'data': []} ,{'data': []} ,{'data': []} , {'data': []}, {'data':[]} 
+        return {'data': []},{'data': []} ,{'data': []} ,{'data': []} , {'data': []}
     
     # return line_fig_1
     
@@ -325,6 +348,30 @@ def update_output(selected_topic, selected_domain, start_date, end_date):
 #     dff = df[df.country==value]
 #     return px.line(dff, x='year', y='pop')
 
-
+# Define callback function for updating the headlines table
+@app.callback(
+    Output('headlines-table', 'data'),
+    Input("topic-selector", "value"),
+    Input ("domain-selector", "value"),
+    Input('date-range', 'start_date'),
+    Input('date-range', 'end_date')
+)
+def update_headlines_table(selected_topic, selected_domain, start_date, end_date):
+    # Filtering data...
+    df_filtered = df[(df['Topic'] == selected_topic) &
+                    (df['domain_folder_name'] == selected_domain) &
+                    (df['date'] >= start_date) &
+                    (df['date'] <= end_date)]
+
+    # Convert FinBERT_label to categorical for better sorting
+    df_filtered['FinBERT_label'] = pd.Categorical(df_filtered['FinBERT_label'],
+                                                  categories=['positive', 'neutral', 'negative'],
+                                                  ordered=True)
+
+    # Sort DataFrame by sentiment label and date
+    df_filtered = df_filtered.sort_values(by=['FinBERT_label', 'date'])
+
+    return df_filtered.to_dict('records')
+    
 if __name__ == '__main__':
     app.run_server(debug=True)