sklearn：TypeError：fit() 缺少 1 個必需的位置參數：“x”

Question

在嘗試運行時

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values ="NaN", strategy = "mean")
imputer = SimpleImputer.fit(X[:,1:3])
X[:,1:3] = SimpleImputer.transform(X[:,1:3])

我收到一個錯誤

類型錯誤：fit() 缺少 1 個必需的位置參數：'X'

但是我已經提供了x，對嗎？ 解決這個問題的方法是什么？

Answer 1

根據這個 Scikit-learn 模塊，正確的語法應該是：

imputer.fit(X[:,1:3])

代替：

imputer = SimpleImputer.fit(X[:,1:3])

Answer 2

完全工作的代碼如下所示：

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values = np.nan, strategy = "mean")
imputer = imputer.fit(X[:,1:3])
X[:,1:3] = imputer.transform(X[:,1:3])

請注意：

missing_values = np.nan

Answer 3

你的代碼：

from sklearn.impute import SimpleImputer
# PAY ATTENTION: to NaN as np.nan
imputer = SimpleImputer(**missing_values ="NaN"**, strategy = "mean")
imputer = SimpleImputer.fit(X[:,1:3])
# PAY ATTENTION: instead of "SimpleImputer.transform" use "imputer.transform"
X[:,1:3] = **SimpleImputer**.transform(X[:,1:3])

正確代碼：

from sklearn.impute import SimpleImputer  
imputer = SimpleImputer(missing_values=np.nan, strategy='mean',fill_value=None, verbose=0, copy=True)  
imputer = imputer.fit(X[:, 1:3])  
X[:, 1:3] = imputer.transform(X[:, 1:3])