Error: init() got an unexpected keyword argument 'n_splits'

Question

我将为加州住房数据集（来源：https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html）执行 ShuffleSplit() 方法以拟合 SGD 回归。
但是，应用方法时出现'n_splits'错误。
代码如下：

from sklearn import cross_validation, grid_search, linear_model, metrics  
import numpy as np  
import pandas as pd


from sklearn.preprocessing import scale
from sklearn.cross_validation import ShuffleSplit


housing_data = pd.read_csv('cal_housing.csv', header = 0, sep = ',')
housing_data.fillna(housing_data.mean(), inplace=True)
df=pd.get_dummies(housing_data)


y_target = housing_data['median_house_value'].values
x_features = housing_data.drop(['median_house_value'], axis = 1)

from sklearn.cross_validation import train_test_split
from sklearn import model_selection

train_x, test_x, train_y, test_y = model_selection.train_test_split(x_features, y_target, test_size=0.2, random_state=4)
reg = linear_model.SGDRegressor(random_state=0)
cv = ShuffleSplit(n_splits = 10, test_size = 0.2, random_state = 0)

错误如下：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-22-8f8760b04f8c> in <module>()
----> 1 cv = ShuffleSplit(n_splits = 10, test_size = 0.2, random_state = 0)

TypeError: __init__() got an unexpected keyword argument 'n_splits'

我用 0.18 版本更新了 scikit-learn。

Anaconda 版本：4.5.8

你能就这个问题提出建议吗？

Answer 1

您混淆了两个不同的模块。

在 0.18 之前，cross_validation 用于 ShuffleSplit。其中，n_splits 不存在。 n用于定义分割数

但是由于您现在已经更新到 0.18，cross_validation 和 grid_search 已被弃用，取而代之的是 model_selection。

这个在docs here中有提到，这些模块将从0.20版本中移除

所以不是这个：

from sklearn.cross_validation import ShuffleSplit
from sklearn.cross_validation import train_test_split

这样做：

from sklearn.model_selection import ShuffleSplit
fro

m sklearn.model_selection 导入 train_test_split

那你可以用n_splits.

cv = ShuffleSplit(n_splits = 10, test_size = 0.2, random_state = 0)

Error: init() got an unexpected keyword argument 'n_splits'

Error: init() got an unexpected keyword argument 'n_splits'

python-2.7

scikit-learn

shuffle

cross-validation