Answers for "train test split in pandas"

sklearn split train test

import numpy as np
from sklearn.model_selection import train_test_split

X, y = np.arange(10).reshape((5, 2)), range(5)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.33, random_state=42)

X_train
# array([[4, 5],
#        [0, 1],
#        [6, 7]])

y_train
# [2, 0, 3]

X_test
# array([[2, 3],
#        [8, 9]])

y_test
# [1, 4]

pandas split dataframe to train and test

train=df.sample(frac=0.8,random_state=200) #random state is a seed value
test=df.drop(train.index)

pandas split train test

from sklearn.model_selection import train_test_split


y = df.pop('output')
X = df

X_train,X_test,y_train,y_test = train_test_split(X.index,y,test_size=0.2)
X.iloc[X_train] # return dataframe train

pandas split train test

from sklearn.model_selection import train_test_split

train, test = train_test_split(df, test_size=0.2)