how to partition the data in python train test validation code example
Example 1: train dev test split sklearn
train, validate, test = np.split(df.sample(frac=1), [int(.6*len(df)), int(.8*len(df))])
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