End-to-End Machine Learning Project Part-2A

#1

I did not understand the whole program.

End-to-End Machine Learning Project Part-2

To make this notebook’s output identical at every run

np.random.seed(42)

np.random.permutation(5)

def split_train_set(data,test_ratio):

shuffled_indices=np.random.permutation(len(data))

test_set_size=int(len(data)*test_ratio)

test_indices=shuffled_indices[:test_set_size]
train_indices=shuffled_indices[test_set_size]

return data.iloc[train_indices],data.iloc[test_indices]

train_set,test_set = split_train_test(housing,0.2)

print(len(train_set),"train+",len(test_set),"test")

Please tell me the steps.

Please reply.

#2

Basically, here we have tried to create our own method to split the data into training and test set.

Please try to experiment with each of the methods separately.

#3

np.random.permutation(num) generates all the number from 0 upto num-1 in ramdom order.

image

Picks first few records to test_indices and rest into train_indices.

Picks the records from data at the train_indices and at test_indices and returns a tuple containing the two.

#4

i did not understand.

“returns a tuple containing the two.”

data.iloc[train_indices],data.iloc[test_indices]

How can i return a tuple?

Please tell me the steps.

Please reply.