import pandas as pd
raw_data = {'regiment': ['Nighthawks', 'Nighthawks', 'Nighthawks', 'Nighthawks', 'Dragoons', 'Dragoons', 'Dragoons', 'Dragoons', 'Scouts', 'Scouts', 'Scouts', 'Scouts'],
'company': ['1st', '1st', '2nd', '2nd', '1st', '1st', '2nd', '2nd','1st', '1st', '2nd', '2nd'],
'name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze', 'Jacon', 'Ryaner', 'Sone', 'Sloan', 'Piger', 'Riani', 'Ali'],
'preTestScore': [4, 24, 31, 2, 3, 4, 24, 31, 2, 3, 2, 3],
'postTestScore': [25, 94, 57, 62, 70, 25, 94, 57, 62, 70, 62, 70]}
df = pd.DataFrame(raw_data, columns = ['regiment', 'company', 'name', 'preTestScore', 'postTestScore'])
df
regiment | company | name | preTestScore | postTestScore | |
---|---|---|---|---|---|
0 | Nighthawks | 1st | Miller | 4 | 25 |
1 | Nighthawks | 1st | Jacobson | 24 | 94 |
2 | Nighthawks | 2nd | Ali | 31 | 57 |
3 | Nighthawks | 2nd | Milner | 2 | 62 |
4 | Dragoons | 1st | Cooze | 3 | 70 |
5 | Dragoons | 1st | Jacon | 4 | 25 |
6 | Dragoons | 2nd | Ryaner | 24 | 94 |
7 | Dragoons | 2nd | Sone | 31 | 57 |
8 | Scouts | 1st | Sloan | 2 | 62 |
9 | Scouts | 1st | Piger | 3 | 70 |
10 | Scouts | 2nd | Riani | 2 | 62 |
11 | Scouts | 2nd | Ali | 3 | 70 |
# Create a variable that drop columns with column names where the first three letters of the column names was 'pre'
cols = [c for c in df.columns if c.lower()[:3] != 'pre']
# Create a df of the columns in the variable cols
df=df[cols]
df
regiment | company | name | postTestScore | |
---|---|---|---|---|
0 | Nighthawks | 1st | Miller | 25 |
1 | Nighthawks | 1st | Jacobson | 94 |
2 | Nighthawks | 2nd | Ali | 57 |
3 | Nighthawks | 2nd | Milner | 62 |
4 | Dragoons | 1st | Cooze | 70 |
5 | Dragoons | 1st | Jacon | 25 |
6 | Dragoons | 2nd | Ryaner | 94 |
7 | Dragoons | 2nd | Sone | 57 |
8 | Scouts | 1st | Sloan | 62 |
9 | Scouts | 1st | Piger | 70 |
10 | Scouts | 2nd | Riani | 62 |
11 | Scouts | 2nd | Ali | 70 |