Python代码机器学习中的错误(Iris Flower)

Question

我刚开始学习机器学习的基础知识，我无意中发现了这个错误。

在机器学习中的虹膜花问题中，我面临着一个错误，我无法弄清楚为什么我要得到它。你能解释一下我为什么要面对这样的错误吗。

代码

from sklearn.datasets import load_iris
from sklearn import tree
import numpy as np
#load data
iris= load_iris()

#position of the start of the flower names or indexes
test_index=[0,50,100]

#Training data
train_target = np.delete(iris.target,test_index)
train_data=np.delete(iris.data,test_index)

test_target=iris.target[test_index]
test_data=iris.data[test_index]

clf = tree.DecisionTreeClassifier()
clf=clf.fit(train_data , train_target)

print(test_target)

错误

Traceback (most recent call last):
  File "MachineLearning2.py", line 29, in <module>
    clf=clf.fit(train_data , train_target)
  File "C:\Anacondas\lib\site-packages\sklearn\tree\tree.py", line 790, in fit
    X_idx_sorted=X_idx_sorted)
  File "C:\Anacondas\lib\site-packages\sklearn\tree\tree.py", line 116, in fit
    X = check_array(X, dtype=DTYPE, accept_sparse="csc")
  File "C:\Anacondas\lib\site-packages\sklearn\utils\validation.py", line 441, in check_array
    "if it contains a single sample.".format(array))
ValueError: Expected 2D array, got 1D array instead:
array=[ 3.5         1.39999998  0.2         4.9000001   3.          1.39999998
  0.2         4.69999981  3.20000005  1.29999995  0.2         4.5999999
  3.0999999   1.5         0.2         5.          3.5999999   1.39999998
  0.2         5.4000001   3.9000001   1.70000005  0.40000001  4.5999999
  3.4000001   1.39999998  0.30000001  5.          3.4000001   1.5         0.2
  4.4000001   2.9000001   1.39999998  0.2         4.9000001   3.0999999
  1.5         0.1         5.4000001   3.70000005  1.5         0.2
  4.80000019  3.4000001   1.60000002  0.2         4.80000019  3.          0.1
  4.30000019  3.          1.10000002  0.1         5.80000019  4.
  1.20000005  0.2         5.69999981  4.4000001   1.5         0.40000001
  5.4000001   3.9000001   1.29999995  0.40000001  5.0999999   3.5
  1.39999998  0.30000001  5.69999981  3.79999995  1.70000005  0.30000001
  5.0999999   3.79999995  1.5         0.30000001  5.4000001   3.4000001
  1.70000005  0.2         5.0999999   3.70000005  1.5         0.40000001
  4.5999999   3.5999999   1.          0.2         5.0999999   3.29999995
  1.70000005  0.5         4.80000019  3.4000001   1.89999998  0.2         3.
  1.60000002  0.2         5.          3.4000001   1.60000002  0.40000001
  5.19999981  3.5         1.5         0.2         5.19999981  3.4000001
  1.39999998  0.2         4.69999981  3.20000005  1.60000002  0.2
  4.80000019  3.0999999   1.60000002  0.2         5.4000001   3.4000001
  1.5         0.40000001  5.19999981  4.0999999   1.5         0.1         5.5
  4.19999981  1.39999998  0.2         4.9000001   3.0999999   1.5         0.1
  5.          3.20000005  1.20000005  0.2         5.5         3.5
  1.29999995  0.2         4.9000001   3.0999999   1.5         0.1
  4.4000001   3.          1.29999995  0.2         5.0999999   3.4000001
  1.5         0.2         5.          3.5         1.29999995  0.30000001
  4.5         2.29999995  1.29999995  0.30000001  4.4000001   3.20000005
  1.29999995  0.2         5.          3.5         1.60000002  0.60000002
  5.0999999   3.79999995  1.89999998  0.40000001  4.80000019  3.
  1.39999998  0.30000001  5.0999999   3.79999995  1.60000002  0.2
  4.5999999   3.20000005  1.39999998  0.2         5.30000019  3.70000005
  1.5         0.2         5.          3.29999995  1.39999998  0.2         7.
  3.20000005  4.69999981  1.39999998  6.4000001   3.20000005  4.5         1.5
  6.9000001   3.0999999   4.9000001   1.5         5.5         2.29999995
  4.          1.29999995  6.5         2.79999995  4.5999999   1.5
  5.69999981  2.79999995  4.5         1.29999995  6.30000019  3.29999995
  4.69999981  1.60000002  4.9000001   2.4000001   3.29999995  1.          6.5999999
  2.9000001   4.5999999   1.29999995  5.19999981  2.70000005  3.9000001
  1.39999998  5.          2.          3.5         1.          5.9000001   3.
  4.19999981  1.5         6.          2.20000005  4.          1.          6.0999999
  2.9000001   4.69999981  1.39999998  5.5999999   2.9000001   3.5999999
  1.29999995  6.69999981  3.0999999   4.4000001   1.39999998  5.5999999   3.
  4.5         1.5         5.80000019  2.70000005  4.0999999   1.
  6.19999981  2.20000005  4.5         1.5         5.5999999   2.5
  3.9000001   1.10000002  5.9000001   3.20000005  4.80000019  1.79999995
  6.0999999   2.79999995  4.          1.29999995  6.30000019  2.5
  4.9000001   1.5         6.0999999   2.79999995  4.69999981  1.20000005
  6.4000001   2.9000001   4.30000019  1.29999995  6.5999999   3.          4.4000001
  1.39999998  6.80000019  2.79999995  4.80000019  1.39999998  6.69999981
  3.          5.          1.70000005  6.          2.9000001   4.5         1.5
  5.69999981  2.5999999   3.5         1.          5.5         2.4000001
  3.79999995  1.10000002  5.5         2.4000001   3.70000005  1.
  5.80000019  2.70000005  3.9000001   1.20000005  6.          2.70000005
  5.0999999   1.60000002  5.4000001   3.          4.5         1.5         6.
  3.4000001   4.5         1.60000002  6.69999981  3.0999999   4.69999981
  1.5         6.30000019  2.29999995  4.4000001   1.29999995  5.5999999   3.
  4.0999999   1.29999995  5.5         2.5         4.          1.29999995
  5.5         2.5999999   4.4000001   1.20000005  6.0999999   3.          4.5999999
  1.39999998  5.80000019  2.5999999   4.          1.20000005  5.
  2.29999995  3.29999995  1.          5.5999999   2.70000005  4.19999981
  1.29999995  5.69999981  3.          4.19999981  1.20000005  5.69999981
  2.9000001   4.19999981  1.29999995  6.19999981  2.9000001   4.30000019
  1.29999995  5.0999999   2.5         3.          1.10000002  5.69999981
  2.79999995  4.0999999   1.29999995  6.30000019  3.29999995  6.          2.5
  5.80000019  2.70000005  5.0999999   1.89999998  7.0999999   3.          5.9000001
  2.0999999   6.30000019  2.9000001   5.5999999   1.79999995  6.5         3.
  5.80000019  2.20000005  7.5999999   3.          6.5999999   2.0999999
  4.9000001   2.5         4.5         1.70000005  7.30000019  2.9000001
  6.30000019  1.79999995  6.69999981  2.5         5.80000019  1.79999995
  7.19999981  3.5999999   6.0999999   2.5         6.5         3.20000005
  5.0999999   2.          6.4000001   2.70000005  5.30000019  1.89999998
  6.80000019  3.          5.5         2.0999999   5.69999981  2.5         5.
  2.          5.80000019  2.79999995  5.0999999   2.4000001   6.4000001
  3.20000005  5.30000019  2.29999995  6.5         3.          5.5
  1.79999995  7.69999981  3.79999995  6.69999981  2.20000005  7.69999981
  2.5999999   6.9000001   2.29999995  6.          2.20000005  5.          1.5
  6.9000001   3.20000005  5.69999981  2.29999995  5.5999999   2.79999995
  4.9000001   2.          7.69999981  2.79999995  6.69999981  2.
  6.30000019  2.70000005  4.9000001   1.79999995  6.69999981  3.29999995
  5.69999981  2.0999999   7.19999981  3.20000005  6.          1.79999995
  6.19999981  2.79999995  4.80000019  1.79999995  6.0999999   3.          4.9000001
  1.79999995  6.4000001   2.79999995  5.5999999   2.0999999   7.19999981
  3.          5.80000019  1.60000002  7.4000001   2.79999995  6.0999999
  1.89999998  7.9000001   3.79999995  6.4000001   2.          6.4000001
  2.79999995  5.5999999   2.20000005  6.30000019  2.79999995  5.0999999
  1.5         6.0999999   2.5999999   5.5999999   1.39999998  7.69999981
  3.          6.0999999   2.29999995  6.30000019  3.4000001   5.5999999
  2.4000001   6.4000001   3.0999999   5.5         1.79999995  6.          3.
  4.80000019  1.79999995  6.9000001   3.0999999   5.4000001   2.0999999
  6.69999981  3.0999999   5.5999999   2.4000001   6.9000001   3.0999999
  5.0999999   2.29999995  5.80000019  2.70000005  5.0999999   1.89999998
  6.80000019  3.20000005  5.9000001   2.29999995  6.69999981  3.29999995
  5.69999981  2.5         6.69999981  3.          5.19999981  2.29999995
  6.30000019  2.5         5.          1.89999998  6.5         3.
  5.19999981  2.          6.19999981  3.4000001   5.4000001   2.29999995
  5.9000001   3.          5.0999999   1.79999995].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.
>>> 

您还能解释一下为什么会发生这种数组错误的整形吗？

预先谢谢.

Answer 1

更改以下行：

train_data=np.delete(iris.data,test_index)

至：

train_data=np.delete(iris.data,test_index, axis=0)

你就可以走了。根据numpy.delete的文档

轴: int，可选 删除obj定义的子数组的轴。如果轴为None，则将obj应用于扁平数组。

由于您没有提供要从行或列中删除索引的信息，所以numpy正在将数组扁平化，这可能是错误的。

通过使用axis=0，我们指定要删除行。

Answer 2

错误消息是

ValueError: Expected 2D array, got 1D array instead

以下似乎是图书馆提出的建议。照它说的去做。reshape实际上是调节机器学习输入大小的一种非常有用的技术。这将是一个良好的做法，以跟踪您正在输入的训练和测试的形状。

Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.