Jupyter notebook 在使用 MinMaxScalar 或 StandardScalar 时出错？

Question

使用 PythonAdv kernel 执行 StandardScalar 或 MinMaxScalar 时，jupyter notebook 打印错误。 但是，当使用 Python 3 环境时，同一个 jupyter 笔记本工作正常：

from sklearn.preprocessing import MinMaxScaler

# Scale X values
X_scalar = MinMaxScaler().fit(X_train)
#print(X_scalar)
X_train_scaled = X_scaler.transform(X_train)
X_test_scaled = X_scaler.transform(X_test)

错误：

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-5-e5dc00a586d3> in <module>
      4 X_scalar = MinMaxScaler().fit(X_train)
      5 #print(X_scalar)
----> 6 X_train_scaled = X_scaler.transform(X_train)
      7 X_test_scaled = X_scaler.transform(X_test)

NameError: name 'X_scaler' is not defined

I have Anaconda 3, python 3.6 and PythonAdv environments on Git Bash on Windows.

Answer 1

from sklearn.preprocessing import MinMaxScaler

# Scale X values
X_scaler = MinMaxScaler().fit(X_train)
#print(X_scalar)
X_train_scaled = X_scaler.transform(X_train)
X_test_scaled = X_scaler.transform(X_test)

有一个小错字。 您定义 X_scalar 然后使用 X_scaler。