Update app.py

app.py

@@ -47,9 +47,8 @@ DF_PREVIEW_ROWS = 100
 # -------------
 
 def setup_streamlit():
-    st.set_page_config(page_title="GSC", layout="wide")
-    st.title("GSC")
-    #st.markdown(f"### Lightweight GSC Data Extractor. (Max {MAX_ROWS:,} Rows)")
+    st.set_page_config(page_title="Keyword Relevance Test Using Vector Embedding", layout="wide")
+    st.title("Keyword Relevance Test Using Vector Embedding")
     st.divider()
 
 def init_session_state():
@@ -108,11 +107,8 @@ def calculate_relevancy_scores(df, model_type):
     return df
 
 def process_gsc_data(df):
-    # Filter for queries below position 10
-    df_filtered = df[df['position'] > 10].copy()
-    
     # Sort by impressions in descending order
-    df_sorted = df_filtered.sort_values(['impressions'], ascending=[False])
+    df_sorted = df.sort_values(['impressions'], ascending=[False])
     
     # Keep only the highest impression query for each page
     df_unique = df_sorted.drop_duplicates(subset='page', keep='first')
@@ -249,145 +245,74 @@ def show_google_sign_in(auth_url):
     with st.sidebar:
         if st.button("Sign in with Google"):
             st.write('Please click the link below to sign in:')
-            st.markdown(f'[Google Sign-In]({auth_url})', unsafe_allow_html=True)
-
-def show_property_selector(properties, account):
-    selected_property = st.selectbox(
-        "Select a Search Console Property:",
-        properties,
-        index=properties.index(
-            st.session_state.selected_property) if st.session_state.selected_property in properties else 0,
-        key='selected_property_selector',
-        on_change=property_change
-    )
-    return account[selected_property]
-
-def show_search_type_selector():
-    return st.selectbox(
-        "Select Search Type:",
-        SEARCH_TYPES,
-        index=SEARCH_TYPES.index(st.session_state.selected_search_type),
-        key='search_type_selector'
-    )
+            st.markdown(f'<a href="{auth_url}" target="_blank">Sign in with Google</a>', unsafe_allow_html=True)
 
-def show_model_type_selector():
-    return st.selectbox(
-        "Select the embedding model:",
-        ["english", "multilingual"],
-        key='model_type_selector'
-    )
+def show_config_options():
+    st.sidebar.header("Configuration Options")
 
-def show_date_range_selector():
-    return st.selectbox(
-        "Select Date Range:",
-        DATE_RANGE_OPTIONS,
-        index=DATE_RANGE_OPTIONS.index(st.session_state.selected_date_range),
-        key='date_range_selector'
-    )
+    # Site Property Selection
+    st.sidebar.subheader("1. Select Site Property")
+    site_properties = st.session_state.site_properties
+    selected_property = st.sidebar.selectbox("Select Site Property", options=site_properties, index=0, key='selected_property_selector', on_change=property_change)
 
-def show_custom_date_inputs():
-    st.session_state.custom_start_date = st.date_input("Start Date", st.session_state.custom_start_date)
-    st.session_state.custom_end_date = st.date_input("End Date", st.session_state.custom_end_date)
-
-def show_dimensions_selector(search_type):
-    available_dimensions = update_dimensions(search_type)
-    return st.multiselect(
-        "Select Dimensions:",
-        available_dimensions,
-        default=st.session_state.selected_dimensions,
-        key='dimensions_selector'
-    )
+    # Search Type Selection
+    st.sidebar.subheader("2. Select Search Type")
+    selected_search_type = st.sidebar.selectbox("Search Type", options=SEARCH_TYPES, index=0, key='selected_search_type')
 
-def show_paginated_dataframe(report, rows_per_page=20):
-    # Convert 'position' column to integer
-    report['position'] = report['position'].astype(int)
-    
-    # Create a clickable URL column
-    def make_clickable(url):
-        return f'<a href="{url}" target="_blank">{url}</a>'
-    
-    report['clickable_url'] = report['page'].apply(make_clickable)
-    
-    # Reorder columns to put clickable_url first and sort by impressions
-    columns = ['clickable_url', 'query', 'impressions', 'clicks', 'ctr', 'position', 'relevancy_score']
-    report = report[columns].sort_values('impressions', ascending=False)
-
-    total_rows = len(report)
-    total_pages = (total_rows - 1) // rows_per_page + 1
-
-    if 'current_page' not in st.session_state:
-        st.session_state.current_page = 1
-
-    col1, col2, col3 = st.columns([1,3,1])
-    with col1:
-        if st.button("Previous", disabled=st.session_state.current_page == 1):
-            st.session_state.current_page -= 1
-    with col2:
-        st.write(f"Page {st.session_state.current_page} of {total_pages}")
-    with col3:
-        if st.button("Next", disabled=st.session_state.current_page == total_pages):
-            st.session_state.current_page += 1
-
-    start_idx = (st.session_state.current_page - 1) * rows_per_page
-    end_idx = start_idx + rows_per_page
-    
-    # Use st.markdown to display the dataframe with clickable links
-    st.markdown(report.iloc[start_idx:end_idx].to_html(escape=False, index=False), unsafe_allow_html=True)
-# -------------
-# Main Streamlit App Function
-# -------------
+    # Date Range Selection
+    st.sidebar.subheader("3. Select Date Range")
+    selected_date_range = st.sidebar.selectbox("Date Range", options=DATE_RANGE_OPTIONS, index=0, key='selected_date_range')
+
+    # Custom Date Range Selection
+    if selected_date_range == 'Custom Range':
+        st.sidebar.date_input("Start Date", key='custom_start_date')
+        st.sidebar.date_input("End Date", key='custom_end_date')
+
+    # Device Type Selection
+    st.sidebar.subheader("4. Select Device Type")
+    selected_device = st.sidebar.selectbox("Device Type", options=DEVICE_OPTIONS, index=0, key='selected_device')
+
+    # Dimension Selection
+    st.sidebar.subheader("5. Select Dimensions")
+    selected_dimensions = update_dimensions(selected_search_type)
+    st.sidebar.multiselect("Dimensions", options=selected_dimensions, default=selected_dimensions[:2], key='selected_dimensions')
 
-def main():
+def run():
     setup_streamlit()
+    init_session_state()
     client_config = load_config()
     
-    if 'auth_flow' not in st.session_state or 'auth_url' not in st.session_state:
-        st.session_state.auth_flow, st.session_state.auth_url = google_auth(client_config)
-
-    # Directly access query parameters using st.query_params
-    query_params = st.query_params
-
-    # Retrieve the 'code' parameter
-    auth_code = query_params.get("code", None)
+    if IS_LOCAL:
+        credentials = auth_search_console(client_config, None)
+        st.session_state.site_properties = list_gsc_properties(credentials)
+        show_config_options()
+    else:
+        flow, auth_url = google_auth(client_config)
+        show_google_sign_in(auth_url)
+        code = st.experimental_get_query_params().get("code")
+        if code:
+            flow.fetch_token(authorization_response=st.experimental_get_query_params()["code"])
+            credentials = flow.credentials
+            st.session_state.site_properties = list_gsc_properties(credentials)
+            show_config_options()
     
+    if st.session_state.selected_property:
+        if st.sidebar.button("Fetch Data"):
+            start_date, end_date = calc_date_range(
+                st.session_state.selected_date_range, 
+                st.session_state.custom_start_date, 
+                st.session_state.custom_end_date
+            )
+            report = fetch_data_loading(
+                st.session_state.selected_property, 
+                st.session_state.selected_search_type, 
+                start_date, 
+                end_date, 
+                st.session_state.selected_dimensions, 
+                st.session_state.selected_device
+            )
+            show_dataframe(report)
+            download_csv_link(report)
 
-    if auth_code and 'credentials' not in st.session_state:
-        st.session_state.auth_flow.fetch_token(code=auth_code)
-        st.session_state.credentials = st.session_state.auth_flow.credentials
-
-    if 'credentials' not in st.session_state:
-        show_google_sign_in(st.session_state.auth_url)
-    else:
-        init_session_state()
-        account = auth_search_console(client_config, st.session_state.credentials)
-        properties = list_gsc_properties(st.session_state.credentials)
-
-        if properties:
-            webproperty = show_property_selector(properties, account)
-            search_type = show_search_type_selector()
-            date_range_selection = show_date_range_selector()
-            model_type = show_model_type_selector()  # Add this line
-            if date_range_selection == 'Custom Range':
-                show_custom_date_inputs()
-                start_date, end_date = st.session_state.custom_start_date, st.session_state.custom_end_date
-            else:
-                start_date, end_date = calc_date_range(date_range_selection)
-
-            selected_dimensions = show_dimensions_selector(search_type)
-
-            if 'report_data' not in st.session_state:
-                st.session_state.report_data = None
-
-            if st.button("Fetch Data"):
-                with st.spinner('Fetching data...'):
-                    st.session_state.report_data = fetch_data_loading(webproperty, search_type, start_date, end_date, selected_dimensions, model_type=model_type)  # Update this line
-
-            if st.session_state.report_data is not None and not st.session_state.report_data.empty:
-                show_paginated_dataframe(st.session_state.report_data)
-                download_csv_link(st.session_state.report_data)
-            elif st.session_state.report_data is not None:
-                st.warning("No data found for the selected criteria.")
-
-                
 if __name__ == "__main__":
-    main()
+    run()