Question

import numpy as np
import pandas as pd

dataset=pd.read_csv('iris.csv')
dataset.shape
dataset.head(10)
feature_column = ['sepal_length','sepal_width','petal_length','petal_width']
x=dataset[feature_column].values
=dataset['species'].values
dataset[feature_column].values
dataset['species'].values

from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
y=le.fit_transform(y)
y[:10]

from sklearn.model_selection import train_test_split
X_train, y_train,X_test, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-65776283812c> in <module>
      1 from sklearn.model_selection import train_test_split
----> 2 X_train, y_train,X_test, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

NameError: name 'X' is not defined

Answer 1

错误非常具体...它来自此行：

<a [routerLink]="['',{ outlets: { center: ['gi', 10] } }]" > GI Link </a>

您将X_train, y_train,X_test, y_test = train_test_split(X, y, test_size=0.2, random_state=0)（大写）作为第一个参数传递给X 函数，但之前未定义。我相信您打算改用train_test_split()（小写）。

PS：请注意，根据PEP8，大写名称只能用于常量：PEP8 constants

Answer 2

在您的代码中，您从未定义X，而是定义了x。请记住，python会区分大小写。因此，您应该尝试将x重新定义为X，或者将x传递给函数。

X_train, y_train,X_test, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

否则：

X=dataset[feature_column].values
X_train, y_train,X_test, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

下面的代码有什么错误？如何解决错误

2 个答案: