我正在尝试使用来自艾姆斯住房数据集的数值和分类特征来评估决策树模型的准确性。对于数值特征的预处理，我使用了 SimpleImputer 和 StandardScalar。至于分类特征，我使用了 one hot encoder。我尝试使用 10 折交叉验证来评估决策树模型（决策树回归器），但我得到了测试分数的 Nan 值。这是我的代码：
import pandas as pd
ames_housing = pd.read_csv("../datasets/house_prices.csv", na_values="?")
target_name = "SalePrice"
data = ames_housing.drop(columns=target_name)
target = ames_housing[target_name]
numerical_features = [
"LotFrontage", "LotArea", "MasVnrArea", "BsmtFinSF1", "BsmtFinSF2",
"BsmtUnfSF", "TotalBsmtSF", "1stFlrSF", "2ndFlrSF", "LowQualFinSF",
"GrLivArea", "BedroomAbvGr", "KitchenAbvGr", "TotRmsAbvGrd", "Fireplaces",
"GarageCars", "GarageArea", "WoodDeckSF", "OpenPorchSF", "EnclosedPorch",
"3SsnPorch", "ScreenPorch", "PoolArea", "MiscVal",]
data_numerical = data[numerical_features]
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_validate
from sklearn.tree import DecisionTreeRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer
from sklearn.pipeline import make_pipeline
from sklearn.compose import make_column_selector as selector
from sklearn.compose import make_column_transformer
from sklearn.preprocessing import OneHotEncoder
categorical_columns = selector(dtype_include=object)(data)
numerical_columns = selector(dtype_exclude=object)(data)
preprocessor = make_column_transformer(
(OneHotEncoder(handle_unknown="ignore"), categorical_columns),
(StandardScaler(), SimpleImputer(), numerical_columns),
)
model = make_pipeline(preprocessor, DecisionTreeRegressor())
cv_results = cross_validate(
model, data, target, cv=10, return_estimator=True, n_jobs=2,
)
scores = cv_results["test_score"]
print(f"Accuracy score by cross-validation "
f"search:\n{scores.mean():.3f} +/- {scores.std():.3f}")
这是我得到的考试成绩：
Accuracy score by cross-validation search:
nan +/- nan
为了找出问题的根源，我在交叉验证中传递了 (error_score='raise') 作为参数。结果，发现错误是：
ValueError: No valid specification of the columns. Only a scalar, list or slice of all integers
or all strings, or boolean mask is allowed
我该如何解决这个问题？任何帮助都感激不尽。谢谢:)
这是我的模型的样子：
Pipeline(steps=[('columntransformer',
ColumnTransformer(transformers=[('onehotencoder',
OneHotEncoder(handle_unknown='ignore'),
['MSZoning', 'Street',
'Alley', 'LotShape',
'LandContour', 'Utilities',
'LotConfig', 'LandSlope',
'Neighborhood', 'Condition1',
'Condition2', 'BldgType',
'HouseStyle', 'RoofStyle',
'RoofMatl', 'Exterior1st',
'Exterior2nd', 'MasVnrType',
'ExterQual', 'ExterCond',
'Foundation', 'BsmtQual',
'BsmtCond', 'BsmtExposure',
'BsmtFinType1',
'BsmtFinType2', 'Heating',
'HeatingQC', 'CentralAir',
'Electrical', ...]),
('standardscaler',
StandardScaler(),
SimpleImputer())])),
('decisiontreeregressor', DecisionTreeRegressor())])
数据：
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 80 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Id 1460 non-null int64
1 MSSubClass 1460 non-null int64
2 MSZoning 1460 non-null object
3 LotFrontage 1201 non-null float64
4 LotArea 1460 non-null int64
5 Street 1460 non-null object
6 Alley 91 non-null object
7 LotShape 1460 non-null object
8 LandContour 1460 non-null object
9 Utilities 1460 non-null object
10 LotConfig 1460 non-null object
11 LandSlope 1460 non-null object
12 Neighborhood 1460 non-null object
13 Condition1 1460 non-null object
14 Condition2 1460 non-null object
15 BldgType 1460 non-null object
16 HouseStyle 1460 non-null object
17 OverallQual 1460 non-null int64
18 OverallCond 1460 non-null int64
19 YearBuilt 1460 non-null int64
20 YearRemodAdd 1460 non-null int64
21 RoofStyle 1460 non-null object
22 RoofMatl 1460 non-null object
23 Exterior1st 1460 non-null object
24 Exterior2nd 1460 non-null object
25 MasVnrType 1452 non-null object
26 MasVnrArea 1452 non-null float64
27 ExterQual 1460 non-null object
28 ExterCond 1460 non-null object
29 Foundation 1460 non-null object
30 BsmtQual 1423 non-null object
31 BsmtCond 1423 non-null object
32 BsmtExposure 1422 non-null object
33 BsmtFinType1 1423 non-null object
34 BsmtFinSF1 1460 non-null int64
35 BsmtFinType2 1422 non-null object
36 BsmtFinSF2 1460 non-null int64
37 BsmtUnfSF 1460 non-null int64
38 TotalBsmtSF 1460 non-null int64
39 Heating 1460 non-null object
40 HeatingQC 1460 non-null object
41 CentralAir 1460 non-null object
42 Electrical 1459 non-null object
43 1stFlrSF 1460 non-null int64
44 2ndFlrSF 1460 non-null int64
45 LowQualFinSF 1460 non-null int64
46 GrLivArea 1460 non-null int64
47 BsmtFullBath 1460 non-null int64
48 BsmtHalfBath 1460 non-null int64
49 FullBath 1460 non-null int64
50 HalfBath 1460 non-null int64
51 BedroomAbvGr 1460 non-null int64
52 KitchenAbvGr 1460 non-null int64
53 KitchenQual 1460 non-null object
54 TotRmsAbvGrd 1460 non-null int64
55 Functional 1460 non-null object
56 Fireplaces 1460 non-null int64
57 FireplaceQu 770 non-null object
58 GarageType 1379 non-null object
59 GarageYrBlt 1379 non-null float64
60 GarageFinish 1379 non-null object
61 GarageCars 1460 non-null int64
62 GarageArea 1460 non-null int64
63 GarageQual 1379 non-null object
64 GarageCond 1379 non-null object
65 PavedDrive 1460 non-null object
66 WoodDeckSF 1460 non-null int64
67 OpenPorchSF 1460 non-null int64
68 EnclosedPorch 1460 non-null int64
69 3SsnPorch 1460 non-null int64
70 ScreenPorch 1460 non-null int64
71 PoolArea 1460 non-null int64
72 PoolQC 7 non-null object
73 Fence 281 non-null object
74 MiscFeature 54 non-null object
75 MiscVal 1460 non-null int64
76 MoSold 1460 non-null int64
77 YrSold 1460 non-null int64
78 SaleType 1460 non-null object
79 SaleCondition 1460 non-null object
dtypes: float64(3), int64(34), object(43)
memory usage: 912.6+ KB
目标：
0 208500
1 181500
2 223500
3 140000
4 250000
...
1455 175000
1456 210000
1457 266500
1458 142125
1459 147500
Name: SalePrice, Length: 1460, dtype: int64
答案 0 :(得分：0)
如果你的一个转换器有 1 个以上的估计器，在这种情况下，对于数字列，你有 StandardScaler(), SimpleImputer() ，你需要用管道包装它，例如：
np.random.seed(111)
data = pd.DataFrame(np.random.uniform(0,1,(100,3)),columns=['n1','n2','n3'])
data['c1'] = np.random.choice(['A','B',],100)
target = np.random.normal(0,1,100)
cat_columns = selector(dtype_include=object)(data)
num_columns = selector(dtype_exclude=object)(data)
num_transformer = Pipeline(steps=[
('scaler', StandardScaler()),
('imputer', SimpleImputer())
])
preprocessor = make_column_transformer(
(OneHotEncoder(handle_unknown="ignore"), cat_columns),
(num_transformer, num_columns),
)
只需在数据集上进行测试，它就可以工作：
preprocessor.fit_transform(data)[:2]
array([[ 0. , 1. , 0.42472149, -1.23160187, -0.1782728 ],
[ 0. , 1. , 0.95749076, -0.79751471, -1.12825996]])
然后运行一切：
model = make_pipeline(preprocessor, DecisionTreeRegressor())
cv_results = cross_validate(
model, data, target, cv=10, return_estimator=True, n_jobs=2,
)
scores = cv_results["test_score"]
array([-2.45981423, -7.88563769, -1.15523361, -0.56772717, -0.84663734,
-0.61938564, -3.1854688 , -1.44865232, -0.41933732, -3.13719368])