You can apply the fillna() method with ' ' as the argument to the specific column that contains NaN. It will replace NaN with ' '.
Here is an example:
>>> import numpy as np>>> import pandas as pd>>> df = pd.DataFrame({'a':[1,2,3,4], 'b':[11,12,13,14], 'c':[21,np.nan,23,np.nan]})>>> df a b c0 1 11 21.01 2 12 NaN2 3 13 23.03 4 14 NaN>>> df['c']=df['c'].fillna(' ')>>> df a b c0 1 11 21.01 2 12 2 3 13 23.03 4 14 >>>