Update app.py

app.py

@@ -206,7 +206,7 @@ def get_picture_from_url(url):
         return None
 
 def show_top_category():
-    topCategory = pd.read_csv('topCategory.csv')
+    topCategory = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topCategory.csv')
     # Sort the DataFrame in ascending order based on predicted_prob column
     topCategory_sorted = topCategory.sort_values('predicted_prob')
 
@@ -229,16 +229,16 @@ def show_top_category():
     st.pyplot(fig)
 
 def show_top_duration():
-    topDuration = pd.read_csv('topDuration.csv')
+    topDuration = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topDuration.csv')
     topDuration_sorted = topDuration.sort_values('predicted_prob', ascending=False)
 
     # Set the duration as the x-axis and predicted_prob as the y-axis
     x = topDuration_sorted['duration']
     y = topDuration_sorted['predicted_prob']
-
-    # Create a scatter plot of duration vs predicted_prob
+  
+    # Create a scatter plot of duration vs predicted_prob using seaborn
     plt.figure(figsize=(8, 5))  # Adjust the figure size here (width, height)
-    plt.scatter(x, y)
+    sns.scatterplot(x=x, y=y, palette='coolwarm')  # Use coolwarm palette for colorful plot
     plt.xlabel('Duration')
     plt.ylabel('Predicted Probability')
     plt.title('Top Durations')
@@ -247,15 +247,16 @@ def show_top_duration():
     st.pyplot(plt)
 
 def show_top_title():
-    topTitle = pd.read_csv('topTitle.csv')
+    topTitle = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topTitle.csv')
     # Sort the DataFrame in ascending order based on predicted_prob column
     topTitle_sorted = topTitle.sort_values('Importance Score')
-    
-    plt.subplots(figsize=(5, 5))
-    plt.barh(topTitle_sorted['Feature'], topTitle_sorted['Importance Score'])
-    plt.xlabel('Importance Score')
-    plt.ylabel('Feature')
-    plt.title('Top Title Features')
+    sns.set(style="whitegrid")
+    plt.figure(figsize=(8, 6))
+    sns.barplot(x='Importance Score', y='Feature', data=topTitle_sorted, palette="rocket")
+    plt.xlabel('Importance Score', fontsize=12)
+    plt.ylabel('Feature', fontsize=12)
+    plt.title('Top Title Features', fontsize=14)
+    plt.tight_layout()
     st.pyplot(plt)
 
 
@@ -264,7 +265,7 @@ def round_interval(interval_str):
     return f"({int(start)}, {int(end)})"
 
 def show_top_titleLength():
-    topTitleLength = pd.read_csv('topTitleLength.csv')
+    topTitleLength = pd.read_csv(r'C:\Users\LEGION\Desktop\MMU\Data Science Fundamental\Project\Prediction of Video\topTitleLength.csv')
     
     title_length_ranges = topTitleLength['titleLength']
     predicted_probs = topTitleLength['predicted_prob']