Sample two pandas dataframes the same way

I’m doing a machine learning computations having two dataframes – one for factors and other one for target values. I have to split both into training and testing parts. It seems to me that I’ve found the way but I’m looking for more elegant solution. Here is my code:

import pandas as pd
import numpy as np
import random

df_source = pd.DataFrame(np.random.randn(5,2),index = range(0,10,2), columns=list('AB'))
df_target = pd.DataFrame(np.random.randn(5,2),index = range(0,10,2), columns=list('CD'))

rows = np.asarray(random.sample(range(0, len(df_source)), 2))

df_source_train = df_source.iloc[rows]
df_source_test = df_source[~df_source.index.isin(df_source_train.index)]
df_target_train = df_target.iloc[rows]
df_target_test = df_target[~df_target.index.isin(df_target_train.index)]

print('rows')
print(rows)
print('source')
print(df_source)
print('source train')
print(df_source_train)
print('source_test')
print(df_source_test)

—- edited – solution by unutbu (midified) —

np.random.seed(2013)
percentile = .6
rows = np.random.binomial(1, percentile, size=len(df_source)).astype(bool)

df_source_train = df_source[rows]
df_source_test = df_source[~rows]
df_target_train = df_target[rows]
df_target_test = df_target[~rows]

Best answer

If you make rows a boolean array of length len(df), then you can get the True rows with df[rows] and get the False rows with df[~rows]:

import pandas as pd
import numpy as np
import random
np.random.seed(2013)

df_source = pd.DataFrame(
    np.random.randn(5, 2), index=range(0, 10, 2), columns=list('AB'))

rows = np.random.randint(2, size=len(df_source)).astype('bool')

df_source_train = df_source[rows]
df_source_test = df_source[~rows]

print(rows)
# [ True  True False  True False]

# if for some reason you need the index values of where `rows` is True
print(np.where(rows))  
# (array([0, 1, 3]),)

print(df_source)
#           A         B
# 0  0.279545  0.107474
# 2  0.651458 -1.516999
# 4 -1.320541  0.679631
# 6  0.833612  0.492572
# 8  1.555721  1.741279

print(df_source_train)
#           A         B
# 0  0.279545  0.107474
# 2  0.651458 -1.516999
# 6  0.833612  0.492572

print(df_source_test)
#           A         B
# 4 -1.320541  0.679631
# 8  1.555721  1.741279