updated

app.py

@@ -122,6 +122,7 @@ def process_extra_curricular(df):
 
 # Analyze the impact of extra-curricular activities
 def analyze_extra_curricular_impact(df):
+    images = []
     for activity in ['Cricket', 'Debating', 'Football', 'Art Club', 'Drama Club', 'Rugby']:
         if activity in df.columns:
             data = df.copy()
@@ -133,11 +134,15 @@ def analyze_extra_curricular_impact(df):
             plt.xlabel('Participation Status', fontsize=12)
             plt.ylabel('Average Credit Achievement Rate', fontsize=12)
             plt.tight_layout()
-            plt.savefig(f'{activity}_impact.png')
+            img_path = f'{activity}_impact.png'
+            plt.savefig(img_path)
             plt.close()
+            images.append(img_path)
+    return images
 
 # Analyze teacher performance
 def analyze_teacher_performance(df):
+    images = []
     teacher_year_levels = {
         'year_11_english_teacher': 'Year 11',
         'year_11_maths_teacher': 'Year 11',
@@ -155,8 +160,11 @@ def analyze_teacher_performance(df):
             plt.ylabel('Average Credit Achievement Rate', fontsize=12)
             plt.xticks(rotation=45)
             plt.tight_layout()
-            plt.savefig(f'teacher_performance_{col}.png')
+            img_path = f'teacher_performance_{col}.png'
+            plt.savefig(img_path)
             plt.close()
+            images.append(img_path)
+    return images
 
 # Analyze the impact of primary languages
 def analyze_language_impact(df):
@@ -170,8 +178,10 @@ def analyze_language_impact(df):
         plt.ylabel('Average Credit Achievement Rate', fontsize=12)
         plt.xticks(rotation=45)
         plt.tight_layout()
-        plt.savefig('language_impact.png')
+        img_path = 'language_impact.png'
+        plt.savefig(img_path)
         plt.close()
+        return img_path
 
 # Perform clustering using KMeans and PCA
 def perform_clustering(df):
@@ -192,8 +202,10 @@ def perform_clustering(df):
     plt.ylabel('Principal Component 2', fontsize=12)
     plt.legend(title='Cluster')
     plt.tight_layout()
-    plt.savefig('clustering_plot.png')
+    img_path = 'clustering_plot.png'
+    plt.savefig(img_path)
     plt.close()
+    return img_path
 
 # Plot correlation with credit achievement rate
 def plot_correlation_with_credit_achievement(df):
@@ -207,14 +219,17 @@ def plot_correlation_with_credit_achievement(df):
     plt.title('Correlation with Credit Achievement Rate', fontsize=16)
     plt.xticks(rotation=45, ha='right', fontsize=10)
     plt.tight_layout()
-    plt.savefig('correlation_heatmap.png')
+    img_path = 'correlation_heatmap.png'
+    plt.savefig(img_path)
     plt.close()
+    return img_path
 
 # Plot top features vs credit achievement rate
 def plot_top_features_vs_credit(df):
     numeric_cols = df.select_dtypes(include=['float64', 'int64']).columns
     corr_matrix = df[numeric_cols].corr()
     top_corr_features = corr_matrix['credit_achievement_rate'].abs().sort_values(ascending=False).index[1:6]
+    images = []
     for feature in top_corr_features:
         if pd.api.types.is_numeric_dtype(df[feature]):
             df_sorted = df[[feature, 'credit_achievement_rate']].sort_values(by=feature)
@@ -224,33 +239,35 @@ def plot_top_features_vs_credit(df):
             plt.xlabel(feature.replace('_', ' ').title(), fontsize=12)
             plt.ylabel('Credit Achievement Rate', fontsize=12)
             plt.tight_layout()
-            plt.savefig(f'{feature}_vs_credit.png')
+            img_path = f'{feature}_vs_credit.png'
+            plt.savefig(img_path)
             plt.close()
+            images.append(img_path)
+    return images
 
 # Comprehensive analysis function
 def perform_comprehensive_analysis(df):
     df = clean_data(df)
     report = identify_at_risk_students(df)
-    df = process_extra_curricular(df)
-    analyze_extra_curricular_impact(df)
-    analyze_teacher_performance(df)
-    analyze_language_impact(df)
-    perform_clustering(df)
-    plot_correlation_with_credit_achievement(df)
-    plot_top_features_vs_credit(df)
-    return report
+    extra_curricular_imgs = analyze_extra_curricular_impact(df)
+    teacher_performance_imgs = analyze_teacher_performance(df)
+    language_impact_img = analyze_language_impact(df)
+    clustering_img = perform_clustering(df)
+    correlation_img = plot_correlation_with_credit_achievement(df)
+    top_features_imgs = plot_top_features_vs_credit(df)
+    return report, extra_curricular_imgs + teacher_performance_imgs + [language_impact_img, clustering_img, correlation_img] + top_features_imgs
 
 # Gradio interface
 def process_csv(file):
     df = pd.read_csv(file.name)
-    report = perform_comprehensive_analysis(df)
-    return report, 'teacher_performance_year_11_english_teacher.png', 'correlation_heatmap.png', 'clustering_plot.png'
+    report, images = perform_comprehensive_analysis(df)
+    return [report] + images
 
 # Gradio Interface setup
 interface = gr.Interface(
     fn=process_csv,
     inputs="file",
-    outputs=["text", "image", "image", "image"],
+    outputs=["text"] + ["image"] * 20,  # Assuming we have up to 20 image outputs
     title="Student Data Analysis",
     description="Upload a CSV file to perform a comprehensive analysis.",
 )