Update index.py

index.py

@@ -21,13 +21,29 @@ url='https://drive.google.com/uc?id=' + url.split('/')[-2]
 
 # reading of file
 df = pd.read_csv(url)
-df['FinBERT_label'] = df['FinBERT_label'].astype(str)
+
 df['date'] = pd.to_datetime(df['date'])
+
 df = df.rename(columns={df.columns[4]: "Veículos de notícias"})
 
+df['FinBERT_label'] = df['FinBERT_label'].astype(str)
+df['FinBERT_label'].replace({
+    '3.0': 'positive',
+    '2.0': 'neutral',
+    '1.0': 'negative'
+}, inplace=True)
+
 unique_topics = df['Topic'].unique()
 print(unique_topics)
 
+counts = df.groupby(['date', 'Topic', 'domain_folder_name', 'FinBERT_label']).size().reset_index(name='count')
+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]]
+
+
 
 app.layout = dbc.Container(
 [   dbc.Row([ # row 1
@@ -73,17 +89,52 @@ dbc.Row([ # row 6
                 )
 ]),
 
+ dbc.Row([ # row 7
+        dbc.Label("Escolha um site de notícias:", className="fw-bold")
+]),
+
+dbc.Row([ # row 8
+        dbc.Col(
+            dcc.Dropdown(
+                id="domain-selector",
+                options=[
+                    {"label": domain, "value": domain} for domain in unique_domains
+                ],
+                value="expresso-pt",  # Set the initial value
+                style={"width": "50%"})
+
+
+        )
+]),
+
+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'),
+                )
+])
 
 ])
 
 # callback decorator
 @app.callback(
     Output('line-graph-1', 'figure'),
+    Output('line-graph-2', 'figure'),
+    Output('line-graph-3', 'figure'),
+    Output('line-graph-4', 'figure'),
     Input("topic-selector", "value"),
+    Input ("domain-selector", "value"),
     Input('date-range', 'start_date'),
     Input('date-range', 'end_date')
 )
-
 # callback function
 def update_output(selected_topic, start_date, end_date):
     # filter dataframes based on updated data range
@@ -106,11 +157,6 @@ def update_output(selected_topic, start_date, end_date):
     return line_fig_1
     
 
-# df['FinBERT_label'].replace({
-#     '3.0': 'positive',
-#     '2.0': 'neutral',
-#     '1.0': 'negative'
-# }, inplace=True)
 
 # df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/gapminder_unfiltered.csv')