James McCool commited on
Commit
99e552f
·
1 Parent(s): 62a6685

Add dupe formatting for duplication frame in app.py

Browse files

- Introduced a new formatting dictionary for duplicate metrics, enhancing the display of 'uniques%', 'under_5%', and 'under_10%' in the duplication frame.
- Updated the DataFrame formatting to utilize the new dictionary, improving clarity and consistency in data presentation.

Files changed (1) hide show
  1. app.py +3 -2
app.py CHANGED
@@ -71,6 +71,7 @@ def is_valid_input(file):
71
  return file is not None # For Streamlit uploader objects
72
 
73
  player_exposure_format = {'Exposure Overall': '{:.2%}', 'Exposure Top 1%': '{:.2%}', 'Exposure Top 5%': '{:.2%}', 'Exposure Top 10%': '{:.2%}', 'Exposure Top 20%': '{:.2%}'}
 
74
 
75
  tab1, tab2 = st.tabs(["Data Load", "Contest Analysis"])
76
  with tab1:
@@ -187,7 +188,7 @@ with tab2:
187
  axis=1
188
  )
189
  working_df['dupes'] = working_df.groupby('sorted').transform('size')
190
-
191
  working_df['uniques'] = working_df.groupby('BaseName').apply(
192
  lambda x: (x['dupes'] == 1).sum()
193
  ).reindex(working_df['BaseName']).values
@@ -450,4 +451,4 @@ with tab2:
450
  st.dataframe(st.session_state['duplication_frame'].style.
451
  background_gradient(cmap='RdYlGn', subset=['uniques%', 'under_5%', 'under_10%'], axis=0).
452
  background_gradient(cmap='RdYlGn_r', subset=['uniques', 'under_5', 'under_10'], axis=0).
453
- format(precision=2), hide_index=True)
 
71
  return file is not None # For Streamlit uploader objects
72
 
73
  player_exposure_format = {'Exposure Overall': '{:.2%}', 'Exposure Top 1%': '{:.2%}', 'Exposure Top 5%': '{:.2%}', 'Exposure Top 10%': '{:.2%}', 'Exposure Top 20%': '{:.2%}'}
74
+ dupe_format = {'uniques%': '{:.2%}', 'under_5%': '{:.2%}', 'under_10%': '{:.2%}'}
75
 
76
  tab1, tab2 = st.tabs(["Data Load", "Contest Analysis"])
77
  with tab1:
 
188
  axis=1
189
  )
190
  working_df['dupes'] = working_df.groupby('sorted').transform('size')
191
+
192
  working_df['uniques'] = working_df.groupby('BaseName').apply(
193
  lambda x: (x['dupes'] == 1).sum()
194
  ).reindex(working_df['BaseName']).values
 
451
  st.dataframe(st.session_state['duplication_frame'].style.
452
  background_gradient(cmap='RdYlGn', subset=['uniques%', 'under_5%', 'under_10%'], axis=0).
453
  background_gradient(cmap='RdYlGn_r', subset=['uniques', 'under_5', 'under_10'], axis=0).
454
+ format(dupe_format, precision=2), hide_index=True)