Update app.py

app.py

@@ -5,6 +5,7 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from Levenshtein import distance as levenshtein_distance
 import matplotlib.pyplot as plt
+import seaborn as sns
 
 
 ms = st.session_state
@@ -108,6 +109,20 @@ def plot_correlation(df, column):
     return plt.gcf()  # Return the matplotlib figure
 
 
+def plot_correlation_matrix(df):
+    # Filter for numeric columns, if the DataFrame has non-numeric columns
+    numeric_df = df.select_dtypes(include=['number'])
+    correlation_matrix = numeric_df.corr()
+
+    # Plotting the heatmap
+    plt.figure(figsize=(10, 8))
+    sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True, linewidths=0.5)
+    plt.title("Correlation Matrix")
+    plt.xticks(rotation=45, ha="right")
+    plt.yticks(rotation=0)
+    plt.tight_layout()  # Adjusts plot to ensure everything fits without overlap
+    st.pyplot()  # Use Streamlit's method to display the plot
+
 def main():
     st.title("Item Comparison App")
 
@@ -173,13 +188,19 @@ def main():
         # Show correlation plot for each dataset
         if st.button("Correlation for each dataset"):
             
-            st.subheader("Correlation Plot for Warehouse Dataset")
+            st.subheader("Correlation Plot for 1st Dataset")
             warehouse_corr_plot = plot_correlation(warehouse_df, warehouse_column)
             st.pyplot(warehouse_corr_plot)
                 
-            st.subheader("Correlation Plot for Industry Dataset")
+            st.subheader("Correlation Plot for 2nd Dataset")
             industry_corr_plot = plot_correlation(industry_df, industry_column)
             st.pyplot(industry_corr_plot)
 
+            st.subheader("Correlation Matrix for 1st Dataset")
+            plot_correlation_matrix(warehouse_df)
+
+            st.subheader("Correlation Matrix for 2nd Dataset")
+            plot_correlation_matrix(industry_df)
+
 if __name__ == "__main__":
     main()