James McCool commited on
Commit
a87b532
·
1 Parent(s): 1ba31e0

Enhance lineup processing in `load_file.py` to improve data extraction

Browse files

- Updated the logic for splitting the `Lineup` column into individual player entries, now including an additional column for accurate position mapping.
- Added functionality to remove position indicators from the beginning of each player entry, ensuring cleaner data and preventing misinterpretation of player names.

Files changed (1) hide show
  1. global_func/load_file.py +4 -2
global_func/load_file.py CHANGED
@@ -26,9 +26,11 @@ def load_file(upload):
26
  # and not those that might appear within player names
27
  df['Lineup'] = df['Lineup'].str.replace(r'\b(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
28
 
29
- # Split into individual columns
30
- for i in range(0,9):
31
  df[i] = df['Lineup'].str.split(',').str[i].str.strip()
 
 
32
  position_dict = dict(zip(df['Player'], df['Pos']))
33
  ownership_dict = dict(zip(df['Player'], df['Own']))
34
  entry_list = list(set(df['EntryName']))
 
26
  # and not those that might appear within player names
27
  df['Lineup'] = df['Lineup'].str.replace(r'\b(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
28
 
29
+ # Split into individual columns and remove position indicators
30
+ for i in range(0,10):
31
  df[i] = df['Lineup'].str.split(',').str[i].str.strip()
32
+ # Remove position indicators from the beginning of each entry
33
+ df[i] = df[i].str.replace(r'^(' + '|'.join(pos_values) + r')\s+', '', regex=True)
34
  position_dict = dict(zip(df['Player'], df['Pos']))
35
  ownership_dict = dict(zip(df['Player'], df['Own']))
36
  entry_list = list(set(df['EntryName']))