Update pages/3_EDA_and_Feature_Engineering.py

pages/3_EDA_and_Feature_Engineering.py

@@ -400,6 +400,8 @@ if 'df' in st.session_state:
     st.write("### HEATMAP | CORRELATION MATRIX")
     st.write("#### Label Encoding")
     import pandas as pd
+    import seaborn as sns
+    import matplotlib.pyplot as plt
     from sklearn.preprocessing import LabelEncoder
     import streamlit as st
     
@@ -423,13 +425,16 @@ if 'df' in st.session_state:
     
     # Display the mapping in Streamlit
     st.write(f"Label Encoding Mapping for Category: {category_mapping}")
-
+    
+    # Calculate correlation matrix (only for numeric columns)
+    df_numeric = df.select_dtypes(include=['number'])
+    
     # Calculate correlation matrix
-    corr = df.corr()
+    corr = df_numeric.corr()
     
     # Create the heatmap plot
     fig, ax = plt.subplots(figsize=(20, 10))
-    sns.heatmap(corr, annot=True, ax=ax)
+    sns.heatmap(corr, annot=True, ax=ax, cmap='coolwarm')
     
     # Add title
     ax.set_title('Correlation Matrix')
@@ -437,13 +442,15 @@ if 'df' in st.session_state:
     # Adjust layout and render plot in Streamlit
     plt.tight_layout()
     st.pyplot(fig)
-
-    st.markdown('''**Insights :**
-
+    
+    # Display insights in Streamlit
+    st.markdown('''**Insights:**
+    
     Correlation is a statistical measure that indicates the strength and direction of the linear relationship between two variables. The correlation coefficient ranges from -1 to 1, with the following interpretations:
+    
+    - -1: Perfect negative correlation (as one variable increases, the other decreases)
+    - 0: No correlation (the variables are independent)
+    - 1: Perfect positive correlation (as one variable increases, the other increases)''')
 
-- -1: Perfect negative correlation (as one variable increases, the other decreases)
-- 0: No correlation (the variables are independent)
-- 1: Perfect positive correlation (as one variable increases, the other increases)''')
 else:
     st.error("No dataset found. Please upload a dataset on the main page first.")