fix column reference to TXT file analysis work

app.py

@@ -17,14 +17,14 @@ def compatison1(selected_column):
     # type_of_comparison 1
     row2_col1, row2_col2 = st.columns(2)
     with row2_col1:
-        first_source = st.selectbox("Choose First Source", df['Source title'].unique(), key='first_source_select')
+        first_source = st.selectbox("Choose First Source", df[source_title_col].unique(), key='first_source_select')
     with row2_col2:
-        second_source = st.selectbox("Choose Second Source", df['Source title'].unique(),
+        second_source = st.selectbox("Choose Second Source", df[source_title_col].unique(),
                                      key='second_source_select')
 
     # filter data
-    first_data = df[df['Source title'] == first_source].copy()
-    second_data = df[df['Source title'] == second_source].copy()
+    first_data = df[df[source_title_col] == first_source].copy()
+    second_data = df[df[source_title_col] == second_source].copy()
     filtered_data = pd.concat([first_data, second_data])
     st.write(filtered_data)
 
@@ -50,12 +50,12 @@ def compatison1(selected_column):
 
         # type_of_comparison 2
 def comparison2(selected_column):
-    df['Year'] = pd.to_numeric(df['Year'], errors='coerce')
-    df.dropna(subset=['Year'], inplace=True)
-    df['Year'] = df['Year'].astype(int)
+    df[year_col] = pd.to_numeric(df[year_col], errors='coerce')
+    df.dropna(subset=[year_col], inplace=True)
+    df[year_col] = df[year_col].astype(int)
 
-    min_year = int(df['Year'].min())
-    max_year = int(df['Year'].max())
+    min_year = int(df[year_col].min())
+    max_year = int(df[year_col].max())
     # layout row2
     row2_col1, row2_col2 = st.columns(2)
     with row2_col1:
@@ -64,10 +64,10 @@ def comparison2(selected_column):
         second_range = st.slider("Second range", min_value = min_year, max_value= max_year, step = 1, value= (min_year, max_year))
 
     # filter data
-    first_range_filter_df = df[(df['Year'] >= first_range[0]) & (df['Year'] <= first_range[1])].copy()
+    first_range_filter_df = df[(df[year_col] >= first_range[0]) & (df[year_col] <= first_range[1])].copy()
     first_range_filter_df['Topic Range'] = 'First range'
 
-    second_range_filter_df = df[(df['Year'] >= second_range[0]) & (df['Year'] <= second_range[1])].copy()
+    second_range_filter_df = df[(df[year_col] >= second_range[0]) & (df[year_col] <= second_range[1])].copy()
     second_range_filter_df['Topic Range'] = 'Second range'
 
     filtered_df = pd.concat([first_range_filter_df, second_range_filter_df])
@@ -101,11 +101,15 @@ if __name__ == '__main__':
             df = pd.read_csv(uploaded_file)
             abstract_col = 'Abstract'
             title_col = 'Title'
+            source_title_col = 'Source Title'
+            year_col = 'Year'
             # preview the uploaded file
         elif uploaded_file.name.endswith(".txt"):
             df = pd.read_table(uploaded_file, sep='\t')  # Doc: assume contents are seperated by Tabs.
             abstract_col = 'AB'
             title_col = 'TI'
+            source_title_col = 'SO'
+            year_col = 'PY'
             # preview the uploaded file
         else:
             st.error("Unsupported file format.")