JuniorTheoryCommon

What does this program print?

Python

import numpy as np
from sklearn.model_selection import train_test_split

X = np.array([[1, 0], [2, 1], [3, 0], [4, 1], [5, 0], [6, 1], [7, 0], [8, 1]])
y = np.array([10, 20, 30, 40, 50, 60, 70, 80])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)
print(X_train.shape[0], X_test.shape[0], y_test.shape[0])

6 2 2

Expecting 2 6 6: test_size=0.25 is the share of rows that go to the test set, so 2 of the 8 rows are test rows and 6 stay for training.
Expecting y to stay whole: train_test_split splits every array it gets by the same rows, so y_test holds the 2 answers of the 2 test rows.

How many test rows would the same call produce for 10 rows, and why?
Why does a fixed random_state matter when you compare two versions of a model?

Back to questions Open topic in roadmap →Answer it yourself — Quiz

Back to questions

JuniorTheoryCommon

What does this program print?

Python

import numpy as np
from sklearn.model_selection import train_test_split

X = np.array([[1, 0], [2, 1], [3, 0], [4, 1], [5, 0], [6, 1], [7, 0], [8, 1]])
y = np.array([10, 20, 30, 40, 50, 60, 70, 80])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)
print(X_train.shape[0], X_test.shape[0], y_test.shape[0])

6 2 2

Expecting 2 6 6: test_size=0.25 is the share of rows that go to the test set, so 2 of the 8 rows are test rows and 6 stay for training.
Expecting y to stay whole: train_test_split splits every array it gets by the same rows, so y_test holds the 2 answers of the 2 test rows.

How many test rows would the same call produce for 10 rows, and why?
Why does a fixed random_state matter when you compare two versions of a model?

Back to questions Open topic in roadmap →Answer it yourself — Quiz