sklearn中train_test_split()函數詳解

train_test_split函數用於將矩陣隨機劃分爲訓練子集和測試子集，並返回劃分好的訓練集測試集樣本和訓練集測試集標籤。html corpus總數爲10001條的數據，train_X, test_X爲文本數據， train_Y, test_Y爲標籤數據數組 test_size = 0.3 train_X, test_X, train_Y, test_Y = train_test_split(

>>阅读原文<<