Update app.py

app.py

@@ -120,11 +120,11 @@ 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 create_time_series(df, time_unit='day'):
-    if time_unit == 'month':
-        # Group by month and year
-        df_by_date = df.groupby(df['date_posted'].dt.to_period('M')).size().reset_index(name='count')
+    if time_unit == 'week':
+        # Group by week and year
+        df_by_date = df.groupby(df['date_posted'].dt.to_period('W')).size().reset_index(name='count')
         df_by_date['date_posted'] = df_by_date['date_posted'].dt.to_timestamp()
     else:
         # Keep daily grouping as before
@@ -139,122 +139,15 @@ def create_time_series(df, time_unit='day'):
         yaxis_title="Number of Job Postings"
     )
     
-    # Adjust x-axis ticks for monthly view
-    if time_unit == 'month':
+    # Adjust x-axis ticks for weekly view
+    if time_unit == 'week':
         fig.update_xaxes(
-            dtick="M1",
-            tickformat="%b %Y"
+            dtick="W1",
+            tickformat="%d %b %Y",
+            ticklabelmode="period"
         )
     
     return fig
-
-@st.cache_data
-def prepare_dashboard_data(df):
-    top_companies = df['company'].value_counts().head(10)
-    top_locations = df['location'].value_counts().head(10)
-    top_job_titles = df['title'].value_counts().head(20)
-    df_by_date = df.groupby('date_posted').size().reset_index(name='count')
-    return top_companies, top_locations, top_job_titles, df_by_date
-
-def display_dashboard(df):
-    top_companies, top_locations, top_job_titles, df_by_date = prepare_dashboard_data(df)
-    
-    today = datetime.now().date()
-    jobs_today = df[df['date_posted'].dt.date == today].shape[0]
-    
-    col1, col2 = st.columns(2)
-
-    with col1:
-        st.subheader("Job Postings Overview")
-        st.metric("Total Job Postings", len(df))
-        st.metric("Unique Companies", df['company'].nunique())
-        st.metric("Job Postings Today", jobs_today)
-
-        min_date = df['date_posted'].min().date()
-        max_date = df['date_posted'].max().date()
-        st.write(f"Job postings from {min_date} to {max_date}")
-
-    with col2:
-        fig = create_chart(top_companies, top_companies.index, top_companies.values, "Top 10 Companies", ['#4e79a7'])
-        st.plotly_chart(fig, use_container_width=True)
-
-    # Job Postings Over Time Chart
-    fig_time_series = create_time_series(df,time_unit='month')
-    st.plotly_chart(fig_time_series, use_container_width=True)
-
-    col3, col4 = st.columns(2)
-
-    with col3:
-        fig = create_chart(top_locations, top_locations.index, top_locations.values, "Top 10 Locations", ['#f28e2b'])
-        st.plotly_chart(fig, use_container_width=True)
-
-    with col4:
-        fig = create_chart(top_job_titles, top_job_titles.index, top_job_titles.values, "Top 20 Job Titles", ['#59a14f'])
-        st.plotly_chart(fig, use_container_width=True)
-@st.cache_data
-def filter_dataframe(df, companies, locations, job_types,Role_Name,Date_posted):
-    filtered_df = df
-    if companies:
-        filtered_df = filtered_df[filtered_df['company'].isin(companies)]
-    if locations:
-        filtered_df = filtered_df[filtered_df['location'].isin(locations)]
-    if job_types:
-        filtered_df = filtered_df[filtered_df['job_type'].isin(job_types)]
-    if Role_Name:
-        filtered_df = filtered_df[filtered_df['title'].isin(Role_Name)]
-    if Date_posted:
-        filtered_df = filtered_df[filtered_df['date_posted'].isin(Date_posted)]
-    return filtered_df
-
-def display_data_explorer(df):
-    st.subheader("Data Explorer")
-
-    show_all = st.radio("Display", ("All Data", "Filtered Data"))
-
-    if show_all == "Filtered Data":
-        unique_values = get_unique_values(df)
-        col1, col2, col3, col4,col5 = st.columns(5)
-        with col1:
-            companies = st.multiselect("Select Companies", options=unique_values['companies'])
-        with col2:
-            locations = st.multiselect("Select Locations", options=unique_values['locations'])
-        with col3:
-            job_types = st.multiselect("Select Job Types", options=unique_values['job_types'])
-        with col4:
-            Role_Name = st.multiselect("Select Role Types", options=unique_values['Role_Name'])
-        with col5:
-            Date_posted = st.multiselect("Select Date Posted", options=unique_values['Date_posted'])
-        
-        filtered_df = filter_dataframe(df, companies, locations, job_types, Role_Name,Date_posted)
-    else:
-        filtered_df = df
-
-    st.write(f"Showing {len(filtered_df)} job listings")
-    
-    # Pagination
-    items_per_page = 15
-    num_pages = math.ceil(len(filtered_df) / items_per_page)
-    
-    col1, col2, col3 = st.columns([1, 3, 1])
-    with col2:
-        page = st.number_input("Page", min_value=1, max_value=num_pages, value=1)
-    
-    start_idx = (page - 1) * items_per_page
-    end_idx = start_idx + items_per_page
-    
-    page_df = filtered_df.iloc[start_idx:end_idx]
-    
-    def make_clickable(url):
-        return f'<a href="{url}" target="_blank" style="color: #4e79a7;">Link</a>'
-
-    page_df['job_url'] = page_df['job_url'].apply(make_clickable)
-    page_df['company_url'] = page_df['company_url'].apply(make_clickable)
-
-    st.write(page_df.to_html(escape=False, index=False), unsafe_allow_html=True)
-    
-    col1, col2, col3 = st.columns([1, 3, 1])
-    with col2:
-        st.write(f"Page {page} of {num_pages}")
 def display_about_page():
     st.markdown("""
     ## What is this application?