from sklearn.cross_validation import train_test_split

num_train = 300

# Set the number of testing points
num_test = X_all.shape[0] - num_train
X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=num_test, random_state=42)

# Show the results of the split
print("Training set has {} samples.".format(X_train.shape[0]))
print("Testing set has {} samples.".format(X_test.shape[0]))
print(X_train.head())