概述
import pandas as pd
import numpy as np
import random
df_source = pd.DataFrame(np.random.randn(5,2),index = range(0,10,columns=list('AB'))
df_target = pd.DataFrame(np.random.randn(5,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)—-编辑 – unutbu解决方案(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]
import pandas as pd
import numpy as np
import random
np.random.seed(2013)
df_source = pd.DataFrame(
np.random.randn(5,index=range(0,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总结
以上是编程之家为你收集整理的python – 以相同的方式对两个pandas数据帧进行采样全部内容，希望文章能够帮你解决python – 以相同的方式对两个pandas数据帧进行采样所遇到的程序开发问题。
如果您也喜欢它,动动您的小指点个赞吧
602392714
清零编程群