Update pages/2_Data_CLeaning_and_Preprocessing.py

pages/2_Data_CLeaning_and_Preprocessing.py

@@ -28,24 +28,32 @@ if df is not None:
     st.subheader("Shape of the Dataset:")
     st.write(df.shape)
 
-    # Visualize Numeric Data
+    # Visualize Numeric Data (Histograms and Boxplots in subplots)
     numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
     if len(numeric_columns) > 0:
         st.subheader("Histograms for Numeric Columns:")
-        for col in numeric_columns:
-            plt.figure(figsize=(10, 5))
-            sns.histplot(df[col], bins=30, kde=True)
-            plt.title(f'Histogram of {col}')
-            st.pyplot(plt)
-            plt.clf()
+        # Create a subplot for all histograms
+        fig, axs = plt.subplots(len(numeric_columns), 1, figsize=(10, 5 * len(numeric_columns)))
+        
+        color_palettes_hist = ['Set1', 'Set2', 'Set3', 'Paired', 'Pastel1']  # Different color palettes for histograms
+        for i, col in enumerate(numeric_columns):
+            palette = sns.color_palette(color_palettes_hist[i % len(color_palettes_hist)])  # Ensure different palette for each plot
+            sns.histplot(df[col], bins=30, kde=True, color=palette[0], ax=axs[i])  # Apply the color palette
+            axs[i].set_title(f'Histogram of {col}')
+        st.pyplot(fig)
+        plt.clf()
 
         st.subheader("Boxplots for Numeric Columns:")
-        for col in numeric_columns:
-            plt.figure(figsize=(10, 5))
-            sns.boxplot(x=df[col])
-            plt.title(f'Boxplot of {col}')
-            st.pyplot(plt)
-            plt.clf()
+        # Create a subplot for all boxplots
+        fig, axs = plt.subplots(len(numeric_columns), 1, figsize=(10, 5 * len(numeric_columns)))
+        
+        color_palettes_box = ['coolwarm', 'Blues', 'viridis', 'cubehelix', 'crest']  # Different color palettes for boxplots
+        for i, col in enumerate(numeric_columns):
+            palette = sns.color_palette(color_palettes_box[i % len(color_palettes_box)])  # Ensure different palette for each plot
+            sns.boxplot(x=df[col], ax=axs[i], palette=palette)
+            axs[i].set_title(f'Boxplot of {col}')
+        st.pyplot(fig)
+        plt.clf()
     else:
         st.warning("No numeric columns available for visualization.")
 
@@ -59,7 +67,7 @@ if df is not None:
         st.write(df[selected_cat_col].value_counts())
 
         plt.figure(figsize=(10, 5))
-        sns.countplot(x=selected_cat_col, data=df)
+        sns.countplot(x=selected_cat_col, data=df, palette='coolwarm')  # Unique palette for categorical data
         plt.title(f'Bar Plot of {selected_cat_col}')
         st.pyplot(plt)
         plt.clf()
@@ -110,7 +118,7 @@ st.markdown(
         /* Styling the content to ensure text visibility */
         .stMarkdown {{
             color: white;  /* White text to ensure visibility */
-            font-size: 50px;  /* Adjust font size for better readability */
+            font-size: 30px;  /* Adjust font size for better readability */
         }}
     </style>
     """,