Update app.py

app.py

@@ -3,7 +3,8 @@ import streamlit as st
 from difflib import SequenceMatcher
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-from Levenshtein import distance as levenshtein_distance
+from Levenshtein import distance as 
+import matplotlib.pyplot as plt
 
 
 ms = st.session_state
@@ -98,7 +99,13 @@ def find_similar_texts(df1, df2, column_name, threshold=0.3):
     
     return similar_texts, exact_matches
 
-
+def plot_correlation(df, column):
+    plt.figure(figsize=(8, 6))
+    plt.scatter(df.index, df[column])
+    plt.xlabel("Index")
+    plt.ylabel(column)
+    plt.title(f"Correlation Plot of {column}")
+    st.pyplot()
 
 
 def main():
@@ -154,6 +161,19 @@ def main():
                 st.write(f"____________________")
                 st.write()
 
+            # Calculate correlation
+            if warehouse_df[warehouse_column].dtype != "object" and industry_df[industry_column].dtype != "object":
+                correlation = warehouse_df[warehouse_column].corr(industry_df[industry_column])
+                st.header("Correlation")
+                st.write(f"The correlation between {warehouse_column} in warehouse item stocks and {industry_column} in industry item stocks is: {correlation}")
+
+            # Show correlation plot for each dataset
+            if st.button("Show for each dataset"):
+                st.subheader("Correlation Plot for Warehouse Dataset")
+                plot_correlation(warehouse_df, warehouse_column)
+                
+                st.subheader("Correlation Plot for Industry Dataset")
+                plot_correlation(industry_df, industry_column)
 
 if __name__ == "__main__":
     main()