Update app.py

app.py

@@ -43,82 +43,101 @@ def filter_data(fiscal_year, employer, job_title, country_of_birth, country_of_n
 # Function to generate insights and visualizations
 def generate_visuals(filtered_data):
     # Gender Distribution Bar Chart
-    plt.figure(figsize=(10, 6))
-    sns.countplot(data=filtered_data, x='gender', order=filtered_data['gender'].value_counts().index)
-    plt.title("Gender Distribution")
-    plt.xlabel("Gender")
-    plt.ylabel("Count")
+    plt.figure(figsize=(12, 8))
+    sns.countplot(data=filtered_data, x='gender', order=filtered_data['gender'].value_counts().index, palette='viridis')
+    plt.title("Gender Distribution", fontsize=16)
+    plt.xlabel("Gender", fontsize=14)
+    plt.ylabel("Count", fontsize=14)
+    plt.xticks(fontsize=12)
+    plt.yticks(fontsize=12)
     gender_chart = gr.Plot(plt.gcf())
     plt.close()
-    
-    # Pie Chart for Top Employers
+
+    # Pie chart for top 10 employers
     employer_counts = filtered_data['employer_name'].value_counts().head(10)
-    plt.figure(figsize=(10, 6))
-    employer_counts.plot(kind='pie', autopct='%1.1f%%')
-    plt.title("Top 10 Employers")
+    plt.figure(figsize=(12, 8))
+    employer_counts.plot(kind='pie', autopct='%1.1f%%', colors=sns.color_palette('Set3'))
+    plt.title("Top 10 Employers", fontsize=16)
+    plt.ylabel("")  # Hide the default ylabel
     employer_chart = gr.Plot(plt.gcf())
     plt.close()
-    
-    # Bar Chart for Worksite States
-    plt.figure(figsize=(10, 6))
-    sns.countplot(data=filtered_data, y='worksite_state', order=filtered_data['worksite_state'].value_counts().index)
-    plt.title("Worksite States Distribution")
-    plt.xlabel("Count")
-    plt.ylabel("Worksite State")
-    state_chart = gr.Plot(plt.gcf())
+
+    # Salary Distribution
+    plt.figure(figsize=(12, 8))
+    sns.histplot(filtered_data['wage_amt'], kde=True, color="blue", bins=30)
+    plt.title("Salary Distribution", fontsize=16)
+    plt.xlabel("Salary (wage_amt)", fontsize=14)
+    plt.ylabel("Frequency", fontsize=14)
+    plt.xticks(fontsize=12)
+    plt.yticks(fontsize=12)
+    salary_chart = gr.Plot(plt.gcf())
     plt.close()
-    
-    return gender_chart, employer_chart, state_chart
+
+    return gender_chart, employer_chart, salary_chart
 
 # Gradio interface
 def gradio_app(fiscal_year, employer, job_title, country_of_birth, country_of_nationality, min_salary, max_salary, worksite_city, worksite_state):
     filtered_data = filter_data(fiscal_year, employer, job_title, country_of_birth, country_of_nationality, min_salary, max_salary, worksite_city, worksite_state)
-    gender_chart, employer_chart, state_chart = generate_visuals(filtered_data)
-    return filtered_data.head(10), gender_chart, employer_chart, state_chart
-
-# Dropdown options
-fiscal_year_options = ["All"] + sorted(data['fiscal_year'].dropna().astype(int).unique().astype(str))
-employer_options = ["All"] + sorted(data['employer_name'].unique())
-job_title_options = ["All"] + sorted(data['job_title'].unique())
-country_of_birth_options = ["All"] + sorted(data['country_of_birth'].unique())
-country_of_nationality_options = ["All"] + sorted(data['country_of_nationality'].unique())
-worksite_city_options = ["All"] + sorted(data['worksite_city'].unique())
-worksite_state_options = ["All"] + sorted(data['worksite_state'].unique())
-
-# Build Gradio Interface
+    gender_chart, employer_chart, salary_chart = generate_visuals(filtered_data)
+    return (
+        filtered_data.head(10),  # Display first 10 rows of filtered data
+        gender_chart,
+        employer_chart,
+        salary_chart,
+    )
+
+# Define dropdown options
+fiscal_year_options = ["All"] + sorted(data['fiscal_year'].dropna().unique().astype(str).tolist())
+employer_options = ["All"] + sorted(data['employer_name'].dropna().unique())
+job_title_options = ["All"] + sorted(data['job_title'].dropna().unique())
+country_birth_options = ["All"] + sorted(data['country_of_birth'].dropna().unique())
+country_nationality_options = ["All"] + sorted(data['country_of_nationality'].dropna().unique())
+worksite_city_options = ["All"] + sorted(data['worksite_city'].dropna().unique())
+worksite_state_options = ["All"] + sorted(data['worksite_state'].dropna().unique())
+
+# Gradio app interface
 with gr.Blocks() as app:
-    gr.Markdown("# Workforce Data Explorer")
-    
     with gr.Row():
-        fiscal_year = gr.Dropdown(label="Fiscal Year", choices=fiscal_year_options)
-        employer = gr.Dropdown(label="Employer Name", choices=employer_options)
+        gr.Markdown("<h1 style='color: #4CAF50;'>Visa Application Insights Dashboard</h1>")
     
     with gr.Row():
-        job_title = gr.Dropdown(label="Job Title", choices=job_title_options)
-        country_of_birth = gr.Dropdown(label="Country of Birth", choices=country_of_birth_options)
-        country_of_nationality = gr.Dropdown(label="Country of Nationality", choices=country_of_nationality_options)
-    
+        with gr.Column():
+            fiscal_year = gr.Dropdown(label="Fiscal Year", choices=fiscal_year_options, value="All")
+            employer = gr.Dropdown(label="Employer Name", choices=employer_options, value="All")
+            job_title = gr.Dropdown(label="Job Title", choices=job_title_options, value="All")
+            country_of_birth = gr.Dropdown(label="Country of Birth", choices=country_birth_options, value="All")
+            country_of_nationality = gr.Dropdown(label="Country of Nationality", choices=country_nationality_options, value="All")
+            min_salary = gr.Number(label="Minimum Salary (USD)", value=0)
+            max_salary = gr.Number(label="Maximum Salary (USD)", value=1000000)
+            worksite_city = gr.Dropdown(label="Worksite City", choices=worksite_city_options, value="All")
+            worksite_state = gr.Dropdown(label="Worksite State", choices=worksite_state_options, value="All")
+        
+        apply_filters = gr.Button("Apply Filters", elem_id="apply-filters-btn", style={"background-color": "#007BFF", "color": "white", "padding": "10px", "font-size": "16px"})
+
     with gr.Row():
-        min_salary = gr.Number(label="Minimum Salary")
-        max_salary = gr.Number(label="Maximum Salary")
-    
+        gr.Markdown("<h2>Filtered Data</h2>")
+        data_table = gr.Dataframe(label="Filtered Data")
+
     with gr.Row():
-        worksite_city = gr.Dropdown(label="Worksite City", choices=worksite_city_options)
-        worksite_state = gr.Dropdown(label="Worksite State", choices=worksite_state_options)
-    
-    apply_filters = gr.Button("Apply Filters")
-    
+        gr.Markdown("<h2>Gender Distribution</h2>")
+        gender_chart = gr.Plot()
+
     with gr.Row():
-        data_output = gr.Dataframe(label="Filtered Data")
-        gender_chart = gr.Plot(label="Gender Distribution")
-        employer_chart = gr.Plot(label="Top Employers")
-        state_chart = gr.Plot(label="Worksite States")
-    
+        gr.Markdown("<h2>Top 10 Employers</h2>")
+        employer_chart = gr.Plot()
+
+    with gr.Row():
+        gr.Markdown("<h2>Salary Distribution</h2>")
+        salary_chart = gr.Plot()
+
     apply_filters.click(
-        fn=gradio_app,
-        inputs=[fiscal_year, employer, job_title, country_of_birth, country_of_nationality, min_salary, max_salary, worksite_city, worksite_state],
-        outputs=[data_output, gender_chart, employer_chart, state_chart],
+        gradio_app,
+        inputs=[
+            fiscal_year, employer, job_title, country_of_birth, country_of_nationality,
+            min_salary, max_salary, worksite_city, worksite_state
+        ],
+        outputs=[data_table, gender_chart, employer_chart, salary_chart]
     )
 
-# Launch the app
+# Run the app
 app.launch()