Update pages/Data_CLeaning_and_Preprocessing.py

pages/Data_CLeaning_and_Preprocessing.py

@@ -32,15 +32,23 @@ if uploaded_file is not None:
 
     # Visualizations for numeric columns
     st.write("### Numeric Column Visualizations:")
+
+    # Histograms for numeric data
     st.write("Histograms:")
-    fig, ax = plt.subplots()
-    data.hist(ax=ax, figsize=(10, 8))
-    st.pyplot(fig)
+    numeric_columns = data.select_dtypes(include=['float64', 'int64']).columns
+    for col in numeric_columns:
+        fig, ax = plt.subplots()
+        sns.histplot(data[col], kde=True, ax=ax)
+        ax.set_title(f'Histogram of {col}')
+        st.pyplot(fig)
 
-    st.write("Boxplot:")
-    fig, ax = plt.subplots()
-    sns.boxplot(data=data, orient='h', ax=ax)
-    st.pyplot(fig)
+    # Boxplots for numeric data
+    st.write("Boxplots:")
+    for col in numeric_columns:
+        fig, ax = plt.subplots()
+        sns.boxplot(x=data[col], ax=ax)
+        ax.set_title(f'Boxplot of {col}')
+        st.pyplot(fig)
 
     # Value counts and bar plot for categorical data
     categorical_columns = data.select_dtypes(include=['object', 'category']).columns
@@ -52,25 +60,25 @@ if uploaded_file is not None:
         st.write(f"Bar Plot for '{selected_cat_col}':")
         fig, ax = plt.subplots()
         sns.countplot(x=selected_cat_col, data=data, ax=ax)
+        ax.set_title(f'Bar Plot of {selected_cat_col}')
         st.pyplot(fig)
     else:
         st.write("No categorical columns available for analysis.")
 
     # Correlation matrix
-    numeric_columns = data.select_dtypes(include=['float64', 'int64']).columns
     if len(numeric_columns) > 1:
         st.write("### Correlation Matrix:")
-        st.write(data[numeric_columns].corr())
+        corr_matrix = data[numeric_columns].corr()
+        st.write(corr_matrix)
 
         st.write("Heatmap of Correlation Matrix:")
-        fig, ax = plt.subplots()
-        sns.heatmap(data[numeric_columns].corr(), annot=True, cmap='coolwarm', ax=ax)
+        fig, ax = plt.subplots(figsize=(10, 8))
+        sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', ax=ax)
         st.pyplot(fig)
 
     # Clean the data: Handle missing values and duplicates
     st.write("### Cleaned Dataset:")
     cleaned_data = data.drop_duplicates()  # Remove duplicate rows
-    #cleaned_data = cleaned_data.fillna(cleaned_data.mean())  # Replace missing values with the mean for numeric columns
     st.dataframe(cleaned_data)
 
     # Download button for the cleaned dataset
@@ -87,4 +95,4 @@ if uploaded_file is not None:
     You can now download the cleaned dataset and proceed with further analysis or modeling.
     """)
 else:
-    st.warning("Please upload a dataset to proceed with Simple EDA.")
+    st.warning("Please upload a dataset to proceed with Simple EDA.")