TypeError:无法使用灵活类型执行reduce

Question

我一直在使用scikit学习库。我试图在scikit学习库下使用高斯朴素贝叶斯模块，但遇到了以下错误。TypeError：无法使用灵活类型执行reduce

下面是代码片段。

training = GaussianNB()
training = training.fit(trainData, target)
prediction = training.predict(testData)

这是目标

['ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'ALL', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML', 'AML']

这是trainData

[['-214' '-153' '-58' ..., '36' '191' '-37']
['-139' '-73' '-1' ..., '11' '76' '-14']
['-76' '-49' '-307' ..., '41' '228' '-41']
..., 
['-32' '-49' '49' ..., '-26' '133' '-32']
['-124' '-79' '-37' ..., '39' '298' '-3']
['-135' '-186' '-70' ..., '-12' '790' '-10']]

下面是堆栈跟踪

Traceback (most recent call last):
File "prediction.py", line 90, in <module>
  gaussianNaiveBayes()
File "prediction.py", line 76, in gaussianNaiveBayes
  training = training.fit(trainData, target)
File "/Library/Python/2.7/site-packages/sklearn/naive_bayes.py", line 163, in fit
  self.theta_[i, :] = np.mean(Xi, axis=0)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/numpy/ core/fromnumeric.py", line 2716, in mean
  out=out, keepdims=keepdims)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/numpy/core/_methods.py", line 62, in _mean
  ret = um.add.reduce(arr, axis=axis, dtype=dtype, out=out, keepdims=keepdims)
TypeError: cannot perform reduce with flexible type

Answer 1

看起来您的"trainData"是一个字符串列表：

['-214' '-153' '-58' ..., '36' '191' '-37']

将"trainData"更改为数字类型。

 import numpy as np
 np.array(['1','2','3']).astype(np.float)

Answer 2

当您尝试在字符串上应用prod类型的值时，如：

['-214' '-153' '-58' ..., '36' '191' '-37']

你会得到错误。

解决方案：只附加像[1,2,3]这样的整数值，就会得到预期的输出。

如果值在追加之前是字符串格式，那么在数组中，您可以将类型转换为int类型并将其存储在list中。

Answer 3

我面对这个错误的最佳建议。通常，您必须检查数据的类型兼容性。花几分钟检查一下，打印一下，你就会发现不兼容。