scikit-learn处理缺失数据的方法与实践

from sklearn.impute import SimpleImputer

# 创建一个包含缺失值的数据集
data = pd.DataFrame({
    'A': [1, 2, None, 4],
    'B': [None, 2, 3, 4]
})

# 删除含有缺失值的行
data.dropna(inplace=True)

imputer = SimpleImputer(strategy='mean')
data['A'] = imputer.fit_transform(data[['A']])

imputer = SimpleImputer(strategy='median')
data['A'] = imputer.fit_transform(data[['A']])

imputer = SimpleImputer(strategy='constant', fill_value=0)
data['A'] = imputer.fit_transform(data[['A']])

imputer = SimpleImputer(strategy='most_frequent')
data['A'] = imputer.fit_transform(data[['A']])

from sklearn.impute import KNNImputer

imputer = KNNImputer(n_neighbors=2)
data[['A', 'B']] = imputer.fit_transform(data[['A', 'B']])

data = pd.DataFrame({
    'C': ['apple', 'banana', None, 'banana'],
    'D': [None, 'orange', 'apple', 'banana']
})

imputer = SimpleImputer(strategy='most_frequent')
data['C'] = imputer.fit_transform(data[['C']])

from sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer

imputer = IterativeImputer()
data[['A', 'B', 'C', 'D']] = imputer.fit_transform(data[['A', 'B', 'C', 'D']])

from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()
scores = cross_val_score(model, data, cv=5)
print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))