train test validation split code example

Example 1: 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 2: train,test,dev python

import numpy as np
import pandas as pd

def train_validate_test_split(df, train_percent=.6, validate_percent=.2, seed=None):
    np.random.seed(seed)
    perm = np.random.permutation(df.index)
    m = len(df.index)
    train_end = int(train_percent * m)
    validate_end = int(validate_percent * m) + train_end
    train = df.iloc[perm[:train_end]]
    validate = df.iloc[perm[train_end:validate_end]]
    test = df.iloc[perm[validate_end:]]
    return train, validate, test

Example 3: train test validation split

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 4: splitting data into training and testing sklearn

train_features, test_features, train_labels, test_labels = 
train_test_split(features, labels)
#This is using sklearn