Predictive Hacks

Train and Test Dataset with Pandas

You can easily create a train and test dataset with Pandas as follows:

# use a random state to be reproducible
# 80% train and 20% for test

train=df.sample(frac=0.8,random_state=5) 
test=df.drop(train.index)



# if you want an absolute number for the train
train=df.sample(n=1000000,random_state=5) 

Share This Post

Share on facebook
Share on linkedin
Share on twitter
Share on email

Subscribe To Our Newsletter

Get updates and learn from the best

More To Explore