Update app.py

app.py

@@ -73,6 +73,7 @@ def load_and_concat_data():
     filtered_df = filtered_df.drop_duplicates()
     
     return filtered_df
+
 @st.cache_data()
 def get_unique_values(df):
     return {
@@ -81,28 +82,38 @@ def get_unique_values(df):
         'job_types': df['job_type'].unique()
     }
 
+def create_chart(data, _x, y, title, color_sequence):
+    fig = px.bar(data, x=_x, y=y, title=title, color_discrete_sequence=color_sequence)
+    fig.update_layout(plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font_color='#FFFFFF')
+    return fig
 
+def expand_time_series(df, date_col, start_date, end_date):
+    full_range = pd.date_range(start=start_date, end=end_date, freq='W')
+    df.set_index(date_col, inplace=True)
+    expanded_df = df.reindex(full_range).reset_index()  
+    expanded_df.columns = ['Week', 'Job Postings']
+    return expanded_df
 
-def main():
-    st.title("Job Listings Dashboard")
-
-    df = load_and_concat_data()
-
-    if df.empty:
-        st.error("No data available. Please check your dataset.")
-        return
-
-    # Sidebar for navigation
-    st.sidebar.title("Navigation")
-    page = st.sidebar.radio("Go to", ["Dashboard", "Data Explorer"])
-
-    if page == "Dashboard":
-        display_dashboard(df)
-    elif page == "Data Explorer":
-        display_data_explorer(df)
+def create_weekly_dashboard(df):
+    df['Week'] = df['date_posted'].dt.to_period('W').apply(lambda r: r.start_time)
+    weekly_data = df.groupby('Week').size().reset_index(name='Job Postings')
+    
+    start_date = weekly_data['Week'].min()
+    end_date = weekly_data['Week'].max()
+    
+    expanded_weekly_data = expand_time_series(weekly_data, 'Week', start_date, end_date)
+    return expanded_weekly_data
 
-def create_chart(data, _x, y, title, color_sequence):
-    fig = px.bar(data, x=_x, y=y, title=title, color_discrete_sequence=color_sequence)
+@st.cache_data
+def get_location_data(df):
+    location_counts = df['location'].value_counts().reset_index()
+    location_counts.columns = ['location', 'count']
+    return location_counts
+
+def create_heatmap(location_data):
+    fig = px.density_mapbox(location_data, lat='latitude', lon='longitude', z='count', radius=10,
+                            center=dict(lat=37.0902, lon=-95.7129), zoom=3,
+                            mapbox_style="carto-darkmatter", title="Job Postings Heatmap")
     fig.update_layout(plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font_color='#FFFFFF')
     return fig
 
@@ -124,10 +135,11 @@ def display_dashboard(df):
         fig = create_chart(top_companies, top_companies.index, top_companies.values, "Top 10 Companies", ['#4e79a7'])
         st.plotly_chart(fig, use_container_width=True)
 
-    df_by_date = df.groupby('date_posted').size().reset_index(name='count')
-    fig = px.line(df_by_date, x='date_posted', y='count', title="Job Postings Over Time", color_discrete_sequence=['#4e79a7'])
-    fig.update_layout(plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font_color='#FFFFFF')
-    st.plotly_chart(fig, use_container_width=True)
+    # Weekly Job Postings Chart
+    weekly_data = create_weekly_dashboard(df)
+    fig_weekly = px.line(weekly_data, x='Week', y='Job Postings', title="Weekly Job Postings", color_discrete_sequence=['#4e79a7'])
+    fig_weekly.update_layout(plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font_color='#FFFFFF')
+    st.plotly_chart(fig_weekly, use_container_width=True)
 
     col3, col4 = st.columns(2)
 
@@ -142,6 +154,12 @@ def display_dashboard(df):
         fig.update_layout(plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font_color='#FFFFFF')
         st.plotly_chart(fig, use_container_width=True)
 
+    # Job Postings Heatmap
+    st.subheader("Job Postings Heatmap")
+    location_data = get_location_data(df)
+    fig_heatmap = create_heatmap(location_data)
+    st.plotly_chart(fig_heatmap, use_container_width=True)
+
 @st.cache_data
 def filter_dataframe(df, companies, locations, job_types):
     filtered_df = df
@@ -182,5 +200,23 @@ def display_data_explorer(df):
 
     st.write(filtered_df.to_html(escape=False, index=False), unsafe_allow_html=True)
 
+def main():
+    st.title("Job Listings Dashboard")
+
+    df = load_and_concat_data()
+
+    if df.empty:
+        st.error("No data available. Please check your dataset.")
+        return
+
+    # Sidebar for navigation
+    st.sidebar.title("Navigation")
+    page = st.sidebar.radio("Go to", ["Dashboard", "Data Explorer"])
+
+    if page == "Dashboard":
+        display_dashboard(df)
+    elif page == "Data Explorer":
+        display_data_explorer(df)
+
 if __name__ == "__main__":
     main()