Python / Pandas - creating a new variable based on several variables and the if / elif / else function

Question

I am trying to create a new variable that depends on the values ​​of several other values. I am writing here because I tried to write this as a nested ifelse () statement in R, but it had too many nested ifelse, so it made a mistake, and I think there should be an easier way to figure this out in Python,

I have a dataframe (called df) that looks something like this (although in fact it is much larger with many other month / year variables), which I read as pandas DataFrame:

   ID  Sept_2015  Oct_2015  Nov_2015  Dec_2015  Jan_2016  Feb_2016  Mar_2016  \
0   1          0         0         0         0         1         1         1   
1   2          0         0         0         0         0         0         0   
2   3          0         0         0         0         1         1         1   
3   4          0         0         0         0         0         0         0   
4   5          1         1         1         1         1         1         1   

   grad_time  
0        240  
1        218  
2        236  
3          0  
4        206 

, , " " , if/elif/else :

if df['Sept_2015'] > 0 & df['grad_time'] <= 236:
    return 236
elif df['Oct_2015'] > 0 & df['grad_time'] <= 237:
    return 237
elif df['Nov_2015'] > 0 & df['grad_time'] <= 238:
    return 238
elif df['Dec_2015'] > 0 & df['grad_time'] <= 239:
    return 239
elif df['Jan_2016'] > 0 & df['grad_time'] <= 240:
    return 240
elif df['Feb_2016'] > 0 & df['grad_time'] <= 241:
    return 241
elif df['Mar_2016'] > 0 & df['grad_time'] <= 242:
    return 242
else:
    return 0

, , :

   trisk
0    240
1      0
2    240
3      0
4    236

​​:

def test_func(df):
    """ Test Function for generating new value"""
    if df['Sept_2015'] > 0 & df['grad_time'] <= 236:
        return 236
    elif df['Oct_2015'] > 0 & df['grad_time'] <= 237:
        return 237
    ...
    else:
        return 0

:

new_df = pd.DataFrame(map(test_func, df)) 

, , TypeError

 Traceback (most recent call last):

  File "<ipython-input-83-19b45bcda45a>", line 1, in <module>
     new_df = pd.DataFrame(map(new_func, test_df))

  File "<ipython-input-82-a2eb6f9d7a3a>", line 3, in new_func
     if df['Sept_2015'] > 0 & df['grad_time'] <= 236:

TypeError: string indices must be integers, not str

, , . . , , ( ), trisk. , .

Answer 1

df = pd.DataFrame([[0, 0, 0, 0, 1, 1, 1, 240],
                   [0, 0, 0, 0, 0, 0, 0, 218],
                   [0, 0, 0, 0, 1, 1, 1, 236],
                   [0, 0, 0, 0, 0, 0, 0,   0],
                   [1, 1, 1, 1, 1, 1, 1, 206]],
                  pd.Index(range(1, 6), name='ID'),
                  ['Sept_2015', 'Oct_2015', 'Nov_2015', 'Dec_2015',
                   'Jan_2016', 'Feb_2016', 'Mar_2016', 'grad_time'])

numpy

a = np.array([236, 237, 238, 239, 240, 241, 242])
b = df.values[:, :-1]
g = df.values[:, -1][:, None] <= a

a[(b & g).argmax(1)] * (b & g).any(1)

df['trisk'] = a[(b != 0).argmax(1)] * (b != 0).any(1)

df

Answer 2

( @piRSquared): test_func , .apply(test_func, axis=1) .

import io
import pandas as pd

data = io.StringIO('''\
   ID  Sept_2015  Oct_2015  Nov_2015  Dec_2015  Jan_2016  Feb_2016  Mar_2016  grad_time  
0   1          0         0         0         0         1         1         1        240
1   2          0         0         0         0         0         0         0        218   
2   3          0         0         0         0         1         1         1        236
3   4          0         0         0         0         0         0         0          0
4   5          1         1         1         1         1         1         1        206
''')
df = pd.read_csv(data, delim_whitespace=True)

def test_func(df):
    """ Test Function for generating new value"""
    if df['Sept_2015'] > 0 & df['grad_time'] <= 236:
        return 236
    elif df['Oct_2015'] > 0 & df['grad_time'] <= 237:
        return 237
    elif df['Nov_2015'] > 0 & df['grad_time'] <= 238:
        return 238
    elif df['Dec_2015'] > 0 & df['grad_time'] <= 239:
        return 239
    elif df['Jan_2016'] > 0 & df['grad_time'] <= 240:
        return 240
    elif df['Feb_2016'] > 0 & df['grad_time'] <= 241:
        return 241
    elif df['Mar_2016'] > 0 & df['grad_time'] <= 242:
        return 242
    else:
        return 0

trisk = df.apply(test_func, axis=1)
trick.name = 'trisk'
print(trisk)

:

0    240
1      0
2    240
3      0
4    236
Name: trisk, dtype: int64