Update app.py

removed the filter with NAN and filtration based on year has been commented

app.py

@@ -85,10 +85,10 @@ def load_and_concat_data():
     filtered_df = concatenated_df[columns_to_keep].reset_index(drop=True)
     filtered_df['date_posted'] = pd.to_datetime(filtered_df['date_posted'], errors='coerce')
     
-    # Drop duplicates and rows with NaT in date_posted
-    filtered_df = filtered_df.drop_duplicates().dropna(subset=['date_posted'])
+    # Drop duplicates and rows with NaT in date_posted removed this to make it clear (jan13th)
+    #filtered_df = filtered_df.drop_duplicates().dropna(subset=['date_posted'])
     #filtering based on data in 2024
-    filtered_df = filtered_df[filtered_df['date_posted'].dt.year==2024]
+    #filtered_df = filtered_df[filtered_df['date_posted'].dt.year==2024]
     # Convert titles and company name to lowercase
     filtered_df['title'] = filtered_df['title'].str.lower()
     filtered_df['company'] = filtered_df['company'].str.lower()