split dataframe into train test and validation code example
Example 1: 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 2: train dev test 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)
Example 3: df split into train, validation, test
In [305]: train, validate, test = \
np.split(df.sample(frac=1, random_state=42),
[int(.6*len(df)), int(.8*len(df))])
In [306]: train
Out[306]:
A B C D E
0 0.046919 0.792216 0.206294 0.440346 0.038960
2 0.301010 0.625697 0.604724 0.936968 0.870064
1 0.642237 0.690403 0.813658 0.525379 0.396053
9 0.488484 0.389640 0.599637 0.122919 0.106505
8 0.842717 0.793315 0.554084 0.100361 0.367465
7 0.185214 0.603661 0.217677 0.281780 0.938540
In [307]: validate
Out[307]:
A B C D E
5 0.806176 0.008896 0.362878 0.058903 0.026328
6 0.145777 0.485765 0.589272 0.806329 0.703479
In [308]: test
Out[308]:
A B C D E
4 0.521640 0.332210 0.370177 0.859169 0.401087
3 0.333348 0.964011 0.083498 0.670386 0.169619