python - KNN : Found input variables with inconsistent numbers of samples: [20, 499]

Question

完整重述如下:https://repl.it/@JacksonEnnis/KNNPercentage

我正在尝试使用 sci-kit learn 中的 KNN 工具进行一些预测。

我有两个函数，recurse()和predict()。 recurse() 旨在迭代每个可能的功能组合，而 Predict 则应该执行实际的操作

  def predict(self, data, answers):
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.model_selection import train_test_split as tts

    import numpy as np
    if len(data) > 1:

      print("length before transposition {}".format(len(data)))
      #n_data = np.transpose(data)

      #print("length after transposition {}".format(len(n_data)))
      knn = KNeighborsClassifier(n_neighbors=1)
      xTrain, xTest, yTrain, yTest = tts(data, answers)
      print("xTrain data: {}".format(len(xTrain)))
      knn.fit(xTrain, yTrain)
      print(knn.score(xTest, yTest))

  def recurse(self, data):
    self.predict(data, self.y)
    if len(data) > 0:
      self.recurse(self.rLeft(data))
    if len(data) > 1:
      self.recurse(self.rMid(data))
    if len(data) > 2:
      self.recurse(self.rRight(data))

但是，当我运行该程序时，它指出训练/测试线有问题。我检查了每个功能中的示例以及答案，发现它们的长度都是相同的，所以我不确定为什么会发生这种情况。

Traceback (most recent call last):
  File "main.py", line 12, in <module>
    best = Config(apple)
  File "/home/runner/Config.py", line 13, in __init__
    self.predict(self.features, self.y)
  File "/home/runner/Config.py", line 45, in predict
    xTrain, xTest, yTrain, yTest = tts(data, answers)
  File "/home/runner/.local/lib/python3.6/site-packages/sklearn/model_selection/_split.py", line 2096, in train_test_split
    arrays = indexable(*arrays)
  File "/home/runner/.local/lib/python3.6/site-packages/sklearn/utils/validation.py", line 230, in indexable
    check_consistent_length(*result)
  File "/home/runner/.local/lib/python3.6/site-packages/sklearn/utils/validation.py", line 205, in check_consistent_length
    " samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [20, 499]

Answer 1

你的轴颠倒了。格式是，对于每个数组，array.shape[0] 的大小必须相同。我建议您查看scikit docs了解更多示例。

tts(np.array(data).T, answers)