python - 为什么 cross_validate 返回 NaN 分数？

Question

数据来自: https://www.kaggle.com/andieminogue/newspaper-churn

代码如下所示，df_og是加载的数据帧，一些列已被删除，NaN行被删除，除此之外，数据尚未转换:

df_og2 = df_og.drop(['Address','State','City','SubscriptionID','Zip Code'], axis = 1)
df_og2 = df_og2.dropna()
df_og2.reset_index(drop=True, inplace=True)

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, OrdinalEncoder
from sklearn.compose import ColumnTransformer
from sklearn.base import BaseEstimator, TransformerMixin
from category_encoders import ordinal
from scipy.sparse import csr_matrix
from sklearn.preprocessing import StandardScaler
from imblearn.under_sampling import RandomUnderSampler
from sklearn.model_selection import cross_validate
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.metrics import classification_report
from imblearn.pipeline import Pipeline
from sklearn.inspection import permutation_importance
from imblearn.under_sampling import RandomUnderSampler

X = df_og2.drop(['Subscriber'], axis=1)
y = df_og2[['Subscriber']]
X, y = RandomUnderSampler(random_state=2).fit_resample(X,y)

numeric = df_og2.select_dtypes(include=['int64']).columns.tolist()
multi_label_cat = ['HH Income', 'Age range', 'weekly fee']
binary_label_cat = ['Home Ownership', 'dummy for Children']
onehot_cat = ['County','Deliveryperiod','Ethnicity','Language','Nielsen Prizm', 'Source Channel']

def getScores(model):
    
    HH = df_og2['HH Income'].unique().tolist()
    AR = df_og2['Age range'].unique().tolist()
    WF = df_og2['weekly fee'].unique().tolist()
    HH.sort()
    HH.insert(0,HH.pop())
    AR.sort()
    WF.sort()
    WF.append(WF.pop(5))
    HH_map = {i:j for i,j in zip(HH,[i for i in range(len(HH))])}
    AR_map = {i:j for i,j in zip(AR,[i for i in range(len(AR))])}
    WF_map = {i:j for i,j in zip(WF,[i for i in range(len(WF))])}
    col_map = [{'col': 'HH Income', 'mapping': HH_map}, {'col': 'Age range', 'mapping': AR_map}, 
                                                        {'col': 'weekly fee', 'mapping': WF_map}]
    encode_pipeline = ColumnTransformer([
            ('multi_label_cat', ordinal.OrdinalEncoder(mapping=col_map), multi_label_cat),
            ('binary_label_cat', OrdinalEncoder(), binary_label_cat),
            ('onehot_cat', OneHotEncoder(), onehot_cat),
    ], remainder = 'passthrough', sparse_threshold = 0)
    
    full_pipeline = Pipeline([
            ('encode',encode_pipeline),
            ('scale', StandardScaler()),
            ('model', model)
    ])

    cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=2)
    scoring = {'acc': 'accuracy',
               'f1': 'f1',
               'prec': 'precision',
               'rec': 'recall'}
    scores = cross_validate(full_pipeline, X, y, scoring=scoring , cv=cv, n_jobs=-1)
    print(scores)

from sklearn.linear_model import LogisticRegression
getScores(LogisticRegression())

有时，将折叠和重复次数更改为较大的数字会在分数中产生一些值(在相同的过程中)，其中大多数为 NaN。然而，在尝试修复它之后，我无法再重现该现象。

Answer 1

我通过使用显示错误消息的 cross_val_score 解决了该问题。有 2 个错误，第一个是 OneHot 编码的问题，由于某些奇怪的原因，它没有对仅与一行关联的唯一值进行编码，将 handle_unknown='ignore' 参数添加到 OneHotEncoder() 修复了这个问题。之后遇到的另一个问题是 invalid pos_label=1 can only be one of ['YES','NO']，我假设 y 的序数编码已完成当情况不成立时，由 cross_validate() 函数自动执行。我通过预先编码 y 解决了这个问题。