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'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)#建模
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))
newRowX=newRowX.reshape(1,-1) #将预测数据进行类型转换, 参数的shape为[n_samples,n_features]
print (newRowX)
predictedY = clf.predict(newRowX)
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'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)#建模
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))
newRowX=newRowX.reshape(1,-1) #将预测数据进行类型转换, 参数的shape为[n_samples,n_features]
print (newRowX)
predictedY = clf.predict(newRowX)
print("predictedY: " + str(predictedY))
#错误类型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.