Update app.py

app.py

@@ -322,10 +322,10 @@ with news_analysis:
     figure = go.Figure(data=[line_stock], layout=layout)
     figure.add_scatter(x=plot_sub_pos['Date'], y=plot_sub_pos['Price'], mode='markers', 
         marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Positive Impact', 
-        customdata=plot_sub_pos['Feature'], hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>')  
+        customdata=set(plot_sub_pos['Feature']), hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>')  
     figure.add_scatter(x=plot_sub_neg['Date'], y=plot_sub_neg['Price'], mode='markers', 
         marker=dict(symbol='triangle-down', size=10, color=cs.neg_impacts_color), name='Negative Impact', 
-        customdata=plot_sub_neg['Feature'], hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>',)
+        customdata=set(plot_sub_neg['Feature']), hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>',)
     figure.update_layout(
         title={
             'text': title,
@@ -356,31 +356,37 @@ with news_analysis:
     figure.update_yaxes(fixedrange=False)
     st.plotly_chart(figure)
 
-    # news = events[events['Date'].between(start_date, end_date, inclusive='both')]
+    news = events[events['Date'].between(start_date, end_date, inclusive='both')]
+    news = news[['Date', 'Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']]
    
-    pos_news = plot_sub_pos[['Date', 'Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']]
-    neg_news = plot_sub_neg[['Date', 'Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']]
+    # pos_news = plot_sub_pos[['Date', 'Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']]
+    # neg_news = plot_sub_neg[['Date', 'Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']]
     
     cols = ['Raw_Headline', 'Bold_KW', 'Feature', 'Raw_News', 'Sources', 'Urls']
     for col in cols:
-        pos_news[col] = pos_news[col].apply(convert_str_to_list)
-        neg_news[col] = neg_news[col].apply(convert_str_to_list)
+        news[col] = news[col].apply(convert_str_to_list)
+        # pos_news[col] = pos_news[col].apply(convert_str_to_list)
+        # neg_news[col] = neg_news[col].apply(convert_str_to_list)
     # Extract only the date part
-    neg_news['Date'] = neg_news['Date'].dt.date
-    pos_news['Date'] = pos_news['Date'].dt.date
+    news['Date'] = news['Date'].dt.date
+    # neg_news['Date'] = neg_news['Date'].dt.date
+    # pos_news['Date'] = pos_news['Date'].dt.date
     # Sort DataFrame based on the 'Date' column in descending order
-    neg_news = neg_news.sort_values(by='Date', ascending=False)
-    pos_news = pos_news.sort_values(by='Date', ascending=False)
+    news = news.sort_values(by='Date', ascending=False)
+    # neg_news = neg_news.sort_values(by='Date', ascending=False)
+    # pos_news = pos_news.sort_values(by='Date', ascending=False)
 
     # Reset index to reflect the new order
-    pos_news.reset_index(drop=True, inplace=True)
-    neg_news.reset_index(drop=True, inplace=True)
+    news.reset_index(drop=True, inplace=True)
+    # pos_news.reset_index(drop=True, inplace=True)
+    # neg_news.reset_index(drop=True, inplace=True)
     st.subheader("News Events")
     # st.dataframe(news, hide_index=True)
     # st.table(news)
-    dates_neg = list(neg_news['Date'].unique())
-    dates_pos = list(pos_news['Date'].unique())
-    dates = dates_pos + dates_neg
+    dates = list(news['Date'].unique())
+    # dates_neg = list(neg_news['Date'].unique())
+    # dates_pos = list(pos_news['Date'].unique())
+    # dates = dates_pos + dates_neg
     dates = np.sort(dates)
     # Reverse the array to have the latest date at index 0
     dates = dates[::-1]
@@ -389,62 +395,87 @@ with news_analysis:
     items_per_page = min(num_dates, 5)
     for i, date in paginator("Select Page Number", dates,  items_per_page=items_per_page, on_sidebar=False, ukey='news_pages'):
         st.write(f'<span style="font-size: large;"><b>Date:</b> <u>{date}</u></span>', unsafe_allow_html=True)
+        filtered_news = news[news['Date'] == date]
+        print(filtered_news.shape)
+        features = filtered_news['Feature'].sum()
+        headlines = filtered_news['Raw_Headline'].sum()
+        news_list = filtered_news['Raw_News'].sum() 
+        sources = filtered_news['Sources'].sum()
+        urls = filtered_news['Urls'].sum()
+
+        main_container = st.container(height = 250, border=True)
+        # main_container.write(f"Date: {date}")
         
-        if date in dates_pos:
-            filtered_news = pos_news[pos_news['Date'] == date]
-            print(filtered_news.shape)
-            features = filtered_news['Feature'].sum()
-            headlines = filtered_news['Raw_Headline'].sum()
-            news_list = filtered_news['Raw_News'].sum() 
-            sources = filtered_news['Sources'].sum()
-            urls = filtered_news['Urls'].sum()
-
-            main_container = st.container(height = 250, border=True)
-            # main_container.write(f"Date: {date}")
+        col1, col2 = main_container.columns([0.7, 0.3], gap='medium')
+
+        # Merge lists of headlines into a single list
+        for index, headline in enumerate(headlines):
+            col1.page_link(urls[index], label=f"**:blue[{headline}]**")
+            # col1.write(f"<span style='font-size: large;'><b><u>{headline}</u></b></span>", unsafe_allow_html=True)
+            col1.write(f"<span style='font-size: small;'>By {sources[index]}</span><br>", unsafe_allow_html=True)
+            with col1:              
+                with st.expander("Show Full Article"):
+                    st.write(news_list[index])
+
+        with col2:
+            # st.divider()
+            with st.expander("Oil Sector Features"):
+                st.write(set(features))
+    #     if date in dates_pos:
+    #         filtered_news = pos_news[pos_news['Date'] == date]
+    #         print(filtered_news.shape)
+    #         features = filtered_news['Feature'].sum()
+    #         headlines = filtered_news['Raw_Headline'].sum()
+    #         news_list = filtered_news['Raw_News'].sum() 
+    #         sources = filtered_news['Sources'].sum()
+    #         urls = filtered_news['Urls'].sum()
+
+    #         main_container = st.container(height = 250, border=True)
+    #         # main_container.write(f"Date: {date}")
             
-            col1, col2 = main_container.columns([0.7, 0.3], gap='medium')
-
-            # Merge lists of headlines into a single list
-            for index, headline in enumerate(headlines):
-                col1.page_link(urls[index], label=f"**:blue[{headline}]**")
-                # col1.write(f"<span style='font-size: large;'><b><u>{headline}</u></b></span>", unsafe_allow_html=True)
-                col1.write(f"<span style='font-size: small;'>By {sources[index]}</span><br>", unsafe_allow_html=True)
-                with col1:              
-                    with st.expander("Show Full Article"):
-                        st.write(news_list[index])
-
-            with col2:
-                # st.divider()
-                with st.expander("Oil Sector Features"):
-                    st.write(set(features))
+    #         col1, col2 = main_container.columns([0.7, 0.3], gap='medium')
+
+    #         # Merge lists of headlines into a single list
+    #         for index, headline in enumerate(headlines):
+    #             col1.page_link(urls[index], label=f"**:blue[{headline}]**")
+    #             # col1.write(f"<span style='font-size: large;'><b><u>{headline}</u></b></span>", unsafe_allow_html=True)
+    #             col1.write(f"<span style='font-size: small;'>By {sources[index]}</span><br>", unsafe_allow_html=True)
+    #             with col1:              
+    #                 with st.expander("Show Full Article"):
+    #                     st.write(news_list[index])
+
+    #         with col2:
+    #             # st.divider()
+    #             with st.expander("Oil Sector Features"):
+    #                 st.write(set(features))
         
-        if date in dates_neg:
-            filtered_news = neg_news[neg_news['Date'] == date]
-            print(filtered_news.shape)
-            features = filtered_news['Feature'].sum()
-            headlines = filtered_news['Raw_Headline'].sum()
-            news_list = filtered_news['Raw_News'].sum() 
-            sources = filtered_news['Sources'].sum()
-            urls = filtered_news['Urls'].sum()
-
-            main_container = st.container(height = 250, border=True)
-            # main_container.write(f"Date: {date}")
+    #     if date in dates_neg:
+    #         filtered_news = neg_news[neg_news['Date'] == date]
+    #         print(filtered_news.shape)
+    #         features = filtered_news['Feature'].sum()
+    #         headlines = filtered_news['Raw_Headline'].sum()
+    #         news_list = filtered_news['Raw_News'].sum() 
+    #         sources = filtered_news['Sources'].sum()
+    #         urls = filtered_news['Urls'].sum()
+
+    #         main_container = st.container(height = 250, border=True)
+    #         # main_container.write(f"Date: {date}")
             
-            col1, col2 = main_container.columns([0.7, 0.3], gap='medium')
-
-            # Merge lists of headlines into a single list
-            for index, headline in enumerate(headlines):
-                col1.page_link(urls[index], label=f"**:blue[{headline}]**")
-                # col1.write(f"<span style='font-size: large;'><b><u>{headline}</u></b></span>", unsafe_allow_html=True)
-                col1.write(f"<span style='font-size: small;'>By {sources[index]}</span><br>", unsafe_allow_html=True)
-                with col1:              
-                    with st.expander("Show Full Article"):
-                        st.write(news_list[index])
-
-            with col2:
-                # st.divider()
-                with st.expander("Oil Sector Features"):
-                    st.write(set(features))
+    #         col1, col2 = main_container.columns([0.7, 0.3], gap='medium')
+
+    #         # Merge lists of headlines into a single list
+    #         for index, headline in enumerate(headlines):
+    #             col1.page_link(urls[index], label=f"**:blue[{headline}]**")
+    #             # col1.write(f"<span style='font-size: large;'><b><u>{headline}</u></b></span>", unsafe_allow_html=True)
+    #             col1.write(f"<span style='font-size: small;'>By {sources[index]}</span><br>", unsafe_allow_html=True)
+    #             with col1:              
+    #                 with st.expander("Show Full Article"):
+    #                     st.write(news_list[index])
+
+    #         with col2:
+    #             # st.divider()
+    #             with st.expander("Oil Sector Features"):
+    #                 st.write(set(features))
 
     st.markdown("""
     <div style='background-color:#b43c42; color:#ffffff; padding:8px; border-radius:3px; font-size:12px''>
@@ -687,10 +718,10 @@ with final_recs:
     figure = go.Figure(data=[line_stock], layout=layout)
     figure.add_scatter(x=plot_sub_pos['Date'], y=plot_sub_pos['Price'], mode='markers', 
         marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Positive Impact', 
-        customdata=plot_sub_pos['Feature'], hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>')  
+        customdata=set(plot_sub_pos['Feature']), hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>')  
     figure.add_scatter(x=plot_sub_neg['Date'], y=plot_sub_neg['Price'], mode='markers', 
         marker=dict(symbol='triangle-down', size=10, color=cs.neg_impacts_color), name='Negative Impact', 
-        customdata=plot_sub_neg['Feature'], hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>',)
+        customdata=set(plot_sub_neg['Feature']), hovertemplate='%{x}<br>Close: %{y}<br>Feature: %{customdata}<br>',)
     figure.update_layout(
         title={
             'text': title,