Refactor code to replace 'preprocessor' with 'helper' for improved organization and clarity

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-import preprocessor
+import helper
 import matplotlib.pyplot as plt
 
 
@@ -10,7 +10,7 @@ uploaded_file = st.sidebar.file_uploader('Choose a file')
 
 if uploaded_file is not None:
     chat_data = uploaded_file.getvalue().decode('utf-8')
-    df = preprocessor.preprocess_data(chat_data)
+    df = helper.preprocess_data(chat_data)
     # st.write(df)
 
     #unique users dropdown menu to select user
@@ -22,7 +22,7 @@ if uploaded_file is not None:
     st.sidebar.write(selected_user)
 
     #fetch stats
-    user_df, total_messages, media_messages, links, emojis, total_words = preprocessor.fetch_stats(selected_user, df)
+    user_df, total_messages, media_messages, links, emojis, total_words = helper.fetch_stats(selected_user, df)
     st.title(f'User: {selected_user}')
     # st.write(user_df)
     #display below data side by side 
@@ -39,43 +39,50 @@ if uploaded_file is not None:
     #busiest users (users with most messages)
     with st.expander('Busiest users'):
         if selected_user == 'All':
-            busiest_users, plot = preprocessor.busiest_users(df)
+            busiest_users, plot = helper.busiest_users(df)
             st.write('Busiest users:')
             st.write(busiest_users)
             st.pyplot(plot)
 
     with st.expander('View word cloud and most common words'):
-        st.pyplot(preprocessor.word_cloud(df, selected_user))
+        st.pyplot(helper.word_cloud(df, selected_user))
         st.write('Most common words')
-        temp_df, plot = preprocessor.most_common_words(selected_user, df)
+        temp_df, plot = helper.most_common_words(selected_user, df)
         st.write(temp_df)
         st.pyplot(plot)
         st.write("Most common emojis")
-        temp_df = preprocessor.most_common_emojis(selected_user, df)
+        temp_df = helper.most_common_emojis(selected_user, df)
         st.write(temp_df)
 
     with st.expander("Activity over time"):
         col1, col2 = st.columns(2)
         with col1: #left
-            _, plot = preprocessor.daily_timeline(selected_user, df)
+            _, plot = helper.daily_timeline(selected_user, df)
             st.pyplot(plot)
-            _, plot = preprocessor.weekday_activity_map(selected_user, df)
+            _, plot = helper.weekday_activity_map(selected_user, df)
             st.pyplot(plot)
         with col2: #right
-            _, plot = preprocessor.monthly_timeline(selected_user, df)
+            _, plot = helper.monthly_timeline(selected_user, df)
             st.pyplot(plot)
-            _, plot = preprocessor.month_activity_map(selected_user, df)
+            _, plot = helper.month_activity_map(selected_user, df)
             st.pyplot(plot)
         
         st.write("Messages sent by hour")
-        _, plot = preprocessor.hour_activity_map(selected_user, df)
+        _, plot = helper.hour_activity_map(selected_user, df)
         st.pyplot(plot)
 
         st.write("weekly heatmap")
-        plot = preprocessor.activity_heatmap(selected_user, df)
+        plot = helper.activity_heatmap(selected_user, df)
         st.pyplot(plot)
 
+    with st.expander("Links shared"):
+        temp_df = helper.extract_links(df)
+        st.write(temp_df)
 
+        common_domains, plot = helper.plot_common_domains(df)
+        st.pyplot(plot)
+        st.write("Most common domains")
+        st.write(common_domains)
     
 
 

preprocessor.py → helper.py

@@ -228,3 +228,5 @@ def activity_heatmap(selected_user, df):
     plt.xlabel('Hour of Day')
     plt.ylabel('Day of Week')
     return plt
+
+

main.ipynb

@@ -11227,7 +11227,7 @@
    "outputs": [],
    "source": [
     "import emoji\n",
-    "from preprocessor import *\n",
+    "from helper import *\n",
     "from collections import Counter"
    ]
   },