test train validation split sklearn code example

Example 1: train test split sklearn

from sklearn.model_selection import train_test_split

X = df.drop(['target'],axis=1).values   # independant features
y = df['target'].values					# dependant variable

# Choose your test size to split between training and testing sets:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)

Example 2: 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]

Example 3: train test validation sklearn

# credit to the user of StackExchange in the source link
# set stratify=y in the function arguments for stratified selection
# random_state has been fixed for reproducibility

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test 
	= train_test_split(X, y, test_size=0.2, random_state=1) 

# 0.25 x 0.8 = 0.2
X_train, X_val, y_train, y_val 
    = train_test_split(X_train, y_train, test_size=0.25, random_state=1)

Example 4: train/test/validation split sklearn

X_train, X_test, y_train, y_test 
    = train_test_split(X, y, test_size=0.2, random_state=1)

 X_train, X_val, y_train, y_val 
    = train_test_split(X_train, y_train, test_size=0.25, random_state=1) # 0.25 x 0.8 = 0.2

Example 5: train slipt sklearn

from sklearn.model_selection import train_test_split 

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

Example 6: train-test split code in pandas

df_permutated = df.sample(frac=1)

train_size = 0.8
train_end = int(len(df_permutated)*train_size)

df_train = df_permutated[:train_end]
df_test = df_permutated[train_end:]