今天写关于决策树的一些算法的时候,卧槽,mmp,竟然出现了红色的警示错误,
oneRowX: [0. 0. 1. 0. 1. 1. 0. 0. 1. 0.]
newRowX: [1. 0. 0. 0. 1. 1. 0. 0. 1. 0.]
Traceback (most recent call last):
File "D:/pythoncode/jqxi/tree/tree.py", line 64, in <module>
predictedY = clf.predict(newRowX)
File "F:\python\python3\lib\site-packages\sklearn\tree\tree.py", line 412, in predict
X = self._validate_X_predict(X, check_input)
File "F:\python\python3\lib\site-packages\sklearn\tree\tree.py", line 373, in _validate_X_predict
X = check_array(X, dtype=DTYPE, accept_sparse="csr")
File "F:\python\python3\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=[1. 0. 0. 0. 1. 1. 0. 0. 1. 0.].
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.
正确解决办法
# encoding=utf-8
__author__ = 'SK'
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO
# Read in the csv file and put features into list of dict and list of class label
allElectronicsData = open(r'D://pythoncode/jqxi/tree/AllElectronics.csv', 'rt')
reader = csv.reader(allElectronicsData)
headers = next(reader)
print(headers)
featureList = []
labelList = []
for row in reader:
labelList.append(row[len(row)-1])
rowDict = {}
for i in range(1, len(row)-1):
rowDict[headers[i]] = row[i]
featureList.append(rowDict)
print(featureList)
# Vetorize features
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList) .toarray()
print("dummyX: " + str(dummyX))
print(vec.get_feature_names())
print("labelList: " + str(labelList))
# vectorize class labels
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))
# Using decision tree for classification
# clf = tree.DecisionTreeClassifier()
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print("clf: " + str(clf))
# Visualize model
with open("allElectronicInformationGainOri.dot", 'w') as f:
f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)
oneRowX = dummyX[0, :]
print("oneRowX: " + str(oneRowX))
newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
print("newRowX: " + str(newRowX))
predictedY = clf.predict([newRowX])
print("predictedY: " + str(predictedY))