numpy - 运行 Kmeans 时如何解决“异常：数据必须是一维”错误
问题描述
到目前为止，我已经解决了所有错误。我不太确定我是否理解问题，除了我收到错误“异常：数据必须是一维的”。这是我的代码。这是我正在使用的excel文件的链接。
import pandas as pd
import numpy as np
import warnings
from sklearn import preprocessing
from sklearn.preprocessing import LabelBinarizer
from sklearn.cluster import KMeans
df1 = pd.read_excel('PERM_Disclosure_Data_FY2018_EOYV2.xlsx', 'PERM_FY2018')
warnings.filterwarnings("ignore")
df1 = df1.dropna(subset=['PW_AMOUNT_9089'])
df1 = df1.dropna(subset=['CASE_STATUS'])
df1 = df1.dropna(subset=['PW_SOC_TITLE'])
df1.CASE_STATUS[df1['CASE_STATUS']=='Certified-Expired'] = 'Certified'
df1 = df1[df1.CASE_STATUS != 'Withdrawn']
df1 = df1.dropna()
df1 = df1[df1.PW_AMOUNT_9089 != '#############']
df1 = df1.dropna(subset=['PW_AMOUNT_9089'])
df1 = df1.dropna(subset=['CASE_STATUS'])
df1 = df1.dropna(subset=['PW_SOC_TITLE'])
df1.PW_AMOUNT_9089 = df1.PW_AMOUNT_9089.astype(float)
df1=df1.iloc[:, [2,4,5]]
enc = LabelBinarizer()
y = enc.fit_transform(df1.CASE_STATUS)[:, [0]]
此时 y 的输出是一个数组：
array([[0],
[0],
[0],
...,
[1],
[1],
[0]])
然后我定义 XZ
le = preprocessing.LabelEncoder()
X = df1.iloc[:, [1]]
Z = df1.iloc[:, [2]]
X2 = X.apply(le.fit_transform)
XZ = pd.concat([X2,Z], axis=1)
XZ 的输出是：
PW_SOC_TITLE PW_AMOUNT_9089
12 176 60778.0
13 456 100901.0
14 134 134389.0
15 134 104936.0
16 134 95160.0
17 294 66976.0
18 73 38610.0
19 598 122533.0
20 220 109574.0
21 99 67850.0
22 399 132018.0
23 68 56118.0
24 139 136781.0
25 134 111405.0
26 598 58573.0
27 362 75067.0
28 598 85862.0
29 572 33301.0
30 598 112840.0
31 134 134971.0
32 176 100568.0
33 176 100568.0
34 626 19614.0
35 153 26354.0
36 405 79248.0
37 220 93350.0
38 139 153213.0
39 598 131997.0
40 598 131997.0
41 1 90438.0
... ... ...
119741 495 23005.0
119742 63 46030.0
119743 153 20301.0
119744 95 21965.0
119745 153 29890.0
119746 295 79680.0
119747 349 79498.0
119748 223 38930.0
119749 223 38930.0
119750 570 39160.0
119751 302 119392.0
119752 598 106001.0
119753 416 64230.0
119754 598 115482.0
119755 99 80205.0
119756 134 78329.0
119757 598 109325.0
119758 598 109325.0
119759 570 49770.0
119760 194 18117.0
119761 404 46987.0
119762 189 35131.0
119763 73 49900.0
119764 323 32240.0
119765 372 28122.0
119766 468 67974.0
119767 399 78520.0
119768 329 25875.0
119769 329 25875.0
119770 601 82098.0
然后我继续：
from sklearn.model_selection import train_test_split
XZ_train, XZ_test, y_train, y_test = train_test_split(XZ, y,
test_size = .25,
random_state=20,
stratify=y )
# loading library
from pandas_ml import ConfusionMatrix
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
# instantiate learning model loop(k = i)
for weights in ['uniform', 'distance']:
for i in range(1,11,2):
knn = KNeighborsClassifier(n_neighbors=i, weights=weights)
# fitting the model
knn.fit(XZ_train, y_train)
# predict the response
pred = knn.predict(XZ_test)
confusion = ConfusionMatrix(y_test, pred)
if i<11:
# evaluate accuracy
print('Weight Measure:', knn.weights)
print('n_neighbors=', knn.n_neighbors)
print('Accuracy=', accuracy_score(y_test, pred))
#print('')
#print('Confusion Matrix')
#print(confusion)
print('-----------------------------')
我得到的错误如下：
G:\Anaconda\lib\site-packages\ipykernel_launcher.py:11: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
# This is added back by InteractiveShellApp.init_path()
---------------------------------------------------------------------------
Exception Traceback (most recent call last)
<ipython-input-20-bf6054d911ba> in <module>
12 # predict the response
13 pred = knn.predict(XZ_test)
---> 14 confusion = ConfusionMatrix(y_test, pred)
15 if i<11:
16 # evaluate accuracy
G:\Anaconda\lib\site-packages\pandas_ml\confusion_matrix\cm.py in __new__(cls, y_true, y_pred, *args, **kwargs)
21 if len(set(uniq_true) - set(uniq_pred)) == 0:
22 from pandas_ml.confusion_matrix.bcm import BinaryConfusionMatrix
---> 23 return BinaryConfusionMatrix(y_true, y_pred, *args, **kwargs)
24 return LabeledConfusionMatrix(y_true, y_pred, *args, **kwargs)
25
G:\Anaconda\lib\site-packages\pandas_ml\confusion_matrix\bcm.py in __init__(self, *args, **kwargs)
19 def __init__(self, *args, **kwargs):
20 # super(BinaryConfusionMatrix, self).__init__(y_true, y_pred)
---> 21 super(BinaryConfusionMatrix, self).__init__(*args, **kwargs)
22 assert self.len() == 2, \
23 "Binary confusion matrix must have len=2 but \
G:\Anaconda\lib\site-packages\pandas_ml\confusion_matrix\abstract.py in __init__(self, y_true, y_pred, labels, display_sum, backend, true_name, pred_name)
31 self._y_true.name = self.true_name
32 else:
---> 33 self._y_true = pd.Series(y_true, name=self.true_name)
34
35 if isinstance(y_pred, pd.Series):
G:\Anaconda\lib\site-packages\pandas\core\series.py in __init__(self, data, index, dtype, name, copy, fastpath)
273 else:
274 data = _sanitize_array(data, index, dtype, copy,
--> 275 raise_cast_failure=True)
276
277 data = SingleBlockManager(data, index, fastpath=True)
G:\Anaconda\lib\site-packages\pandas\core\series.py in _sanitize_array(data, index, dtype, copy, raise_cast_failure)
4163 elif subarr.ndim > 1:
4164 if isinstance(data, np.ndarray):
-> 4165 raise Exception('Data must be 1-dimensional')
4166 else:
4167 subarr = com._asarray_tuplesafe(data, dtype=dtype)
Exception: Data must be 1-dimensional
我传递的数据类型不正确吗？数据类型与我在过去项目中使用的数据类型相匹配，所以我想我可以在这里复制它。对于那些想知道 X 是我编码的公司名称的人，Y 是二值化案例状态，Z 是 float dtype 中的工资金额。
解决方案
“...y 的输出是一个数组...”您显示的数组是二维的，形状为 (n, 1)。（其中一个维度是微不足道的，但它仍然是二维的。）做类似y[:, 0]或y.ravel()得到一维版本的事情。
推荐阅读
- ios - 如何阻止iOS App在react-native中截屏
- mysql - 我应该在多列索引中创建布尔字段索引吗？
- exception - F# 4.5.0.0：错误 FS0193：此表达式是函数值，即缺少参数。它的类型是 Exception -> 'a
- azure - 如何从视频中提取图像作为 Azure 媒体服务 v3 中编码的一部分？
- python - 在 Python 中将图像转换为黑白与将图像转换为单色（灰度）
- python - 将属性传递给新 Tkinter 框架中的类
- android - 使用协程对任务进行排队
- html - 对齐设置为基线时，CSS网格项目在macOS Safari中不填充宽度
- django - 与 Cube.js 集成的后端架构
- java - 有没有一种简单的方法来制作一个在 Java 中使用布局管理器的绝对定位 JPanel 克隆？