ValueError：预期的二维数组，而不是一维数组。用于线性回归的 Python 函数答案

【问题标题】：ValueError: Expected 2D array, got 1D array instead. Python Function for Linear RegressionValueError：预期的二维数组，而不是一维数组。用于线性回归的 Python 函数
【发布时间】：2020-06-05 12:31:51
【问题描述】：

我不确定如何解决此错误消息。我希望有人能帮帮忙。谢谢。

import numpy as np
from sklearn import linear_model
from sklearn.model_selection import train_test_split


def desired_marketing_expenditure(x_train_marketing_expenditure, y_train_units_sold, x_test_units_sold):

    X_train, X_test, y_train, y_test = train_test_split(x_train_marketing_expenditure, y_train_units_sold, test_size=0.4, random_state=101)
    lm = linear_model.LinearRegression()
    lm.fit(X_train,y_train)
    print(lm.intercept_)
    print(lm.coef_)

    #predictions = lm.predict(x_test_units_sold)

print(desired_marketing_expenditure([300000, 200000, 400000, 300000, 100000],[60000, 50000, 90000, 80000, 30000],60000))

OUT:ValueError: 预期 2D 数组，得到 1D 数组：数组=[400000 200000 300000]。如果您的数据具有单个特征，则使用 array.reshape(-1, 1) 重塑您的数据，如果数据包含单个样本，则使用 array.reshape(1, -1)。

【问题讨论】：

标签： python-3.x pandas numpy

【解决方案1】：

期望向量。在 numpy 中，向量是垂直数组。

[[1], [2]] 而不是[1, 2]。

import numpy as np
from sklearn import linear_model
from sklearn.model_selection import train_test_split


def desired_marketing_expenditure(x_train_marketing_expenditure, y_train_units_sold, x_test_units_sold):

    X_train, X_test, y_train, y_test = train_test_split(x_train_marketing_expenditure, y_train_units_sold, test_size=0.4, random_state=101)
    lm = linear_model.LinearRegression()
    lm.fit(X_train,y_train)
    print(lm.intercept_)
    print(lm.coef_)

    #predictions = lm.predict(x_test_units_sold)

print(desired_marketing_expenditure([[300000], [200000], [400000], [300000], [100000]],[[60000], [50000], [90000], [80000], [30000]], [[60000]]))

[13333.33333333]
[[0.2]]
None

注意：您不能转置一维数组。 np.array([1, 2, 3]).T 与 np.array([1, 2, 3]) 相同，因为转置需要第二个轴。您可以添加一个额外的轴并转置如下：np.array([1, 2, 3])[np.newaxis].T 与 np.array([[1], [2], [3]]) 相同。

【讨论】：

【解决方案2】：

尝试将您的X_train 重塑为(-1,1)，如错误中所述

import numpy as np
from numpy import array
from sklearn import linear_model
from sklearn.model_selection import train_test_split


def desired_marketing_expenditure(x_train_marketing_expenditure, y_train_units_sold, x_test_units_sold):

    X_train, X_test, y_train, y_test = train_test_split(x_train_marketing_expenditure, y_train_units_sold, test_size=0.4, random_state=101)
    lm = LinearRegression()
    X_train=array(X_train).reshape(-1,1)
    lm.fit(X_train,y_train)
    print(lm.intercept_)
    print(lm.coef_)

    #predictions = lm.predict(x_test_units_sold)

print(desired_marketing_expenditure([300000, 200000, 400000, 300000, 100000],[60000, 50000, 90000, 80000, 30000],60000))

输出：

13333.333333333343
[0.2]
None

【讨论】：