1.Python

2.Python機器學習的庫：scikit-learn

2.1 特性：

簡單高效的資料探勘和機器學習分析
對所有使用者開放，根據不同需求高度可重用性
基於Numpy，SciPy和matplotlib
開源的，且可達到商用級別，獲得BSD許可
安裝 Graphviz—-轉化dot檔案至pdf視覺化決策樹：dot -Tpdf *.dot -o

2.2覆蓋問題領域

分類(classifaction),迴歸(regression),聚類(clustering),降維(dimensionality reduction)
模型選擇(model selection),預處理(preprocessing)

3.使用scikit-learn

安裝scikit-learn:
安裝必要package：numpy,Scipy和matplotlib。
sklearn兩篇優質文章：

4.例子

5.實現

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO

#sklearn對資料有格式要求，首先要對資料進行格式預處理。
# Read in the csv file and put features into list of dict and list of class label
#讀取csv檔案，並把屬性放到字典列表和類標籤中
#Python2.x 
#allElectronicsData = open(r'AllElectronics.csv', 'rb')
#reader = csv.reader(allElectronicsData)
#headers = reader.next()
#上面的語句在python3.X會報錯，'_csv.reader' object has no attribute 'next' 
#在python3.x需改為如下語句
allElectronicsData = open(r'AllElectronics.csv', 'rt')
reader = csv.reader(allElectronicsData)
headers = next(reader)

print(headers)
#['RID', 'age', 'income', 'student', 'credit_rating', 'class_buys_computer']

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)
'''
[{'age': 'youth', 'credit_rating': 'fair', 'income': 'high', 'student': 'no'}, 
{'age': 'youth', 'credit_rating': 'excellent', 'income': 'high', 'student': 'no'}, 
{'age': 'middle_aged', 'credit_rating': 'fair', 'income': 'high', 'student': 'no'}, 
{'age': 'senior', 'credit_rating': 'fair', 'income': 'medium', 'student': 'no'}, 
{'age': 'senior', 'credit_rating': 'fair', 'income': 'low', 'student': 'yes'}, 
{'age': 'senior', 'credit_rating': 'excellent', 'income': 'low', 'student': 'yes'}, 
{'age': 'middle_aged', 'credit_rating': 'excellent', 'income': 'low', 'student': 'yes'}, 
{'age': 'youth', 'credit_rating': 'fair', 'income': 'medium', 'student': 'no'}, 
{'age': 'youth', 'credit_rating': 'fair', 'income': 'low', 'student': 'yes'}, 
{'age': 'senior', 'credit_rating': 'fair', 'income': 'medium', 'student': 'yes'}, 
{'age': 'youth', 'credit_rating': 'excellent', 'income': 'medium', 'student': 'yes'}, 
{'age': 'middle_aged', 'credit_rating': 'excellent', 'income': 'medium', 'student': 'no'},
{'age': 'middle_aged', 'credit_rating': 'fair', 'income': 'high', 'student': 'yes'}, 
{'age': 'senior', 'credit_rating': 'excellent', 'income': 'medium', 'student': 'no'}]
'''
#從表中可以看出是用字典儲存，所以是無序的。

# Vetorize features
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList) .toarray()

print("dummyX: " + str(dummyX))
#將每一行轉化為如下格式
#youth  middle_age senor   high medium low   yes no   fair excellent    buy
# 1        0         0      1     0     0     0   1    1     0           0  
'''
dummyX: 
[[ 0.  0.  1.  0.  1.  1.  0.  0.  1.  0.]
 [ 0.  0.  1.  1.  0.  1.  0.  0.  1.  0.]
 [ 1.  0.  0.  0.  1.  1.  0.  0.  1.  0.]
 [ 0.  1.  0.  0.  1.  0.  0.  1.  1.  0.]
 [ 0.  1.  0.  0.  1.  0.  1.  0.  0.  1.]
 [ 0.  1.  0.  1.  0.  0.  1.  0.  0.  1.]
 [ 1.  0.  0.  1.  0.  0.  1.  0.  0.  1.]
 [ 0.  0.  1.  0.  1.  0.  0.  1.  1.  0.]
 [ 0.  0.  1.  0.  1.  0.  1.  0.  0.  1.]
 [ 0.  1.  0.  0.  1.  0.  0.  1.  0.  1.]
 [ 0.  0.  1.  1.  0.  0.  0.  1.  0.  1.]
 [ 1.  0.  0.  1.  0.  0.  0.  1.  1.  0.]
 [ 1.  0.  0.  0.  1.  1.  0.  0.  0.  1.]
 [ 0.  1.  0.  1.  0.  0.  0.  1.  1.  0.]]
'''
print(vec.get_feature_names())
'''
['age=middle_aged', 'age=senior', 'age=youth', 
 'credit_rating=excellent', 'credit_rating=fair', 
 'student=no', 'student=yes']
'''
print("labelList: " + str(labelList))
#labelList: 
#['no', 'no', 'yes', 'yes', 'yes', 'no', 'yes', 'no', 'yes', 'yes', 'yes', 'yes', 'yes', 'no']

# vectorize class labels
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))
'''
dummyY: 
[[0]
 [0]
 [1]
 [1]
 [1]
 [0]
 [1]
 [0]
 [1]
 [1]
 [1]
 [1]
 [1]
 [0]]
'''

# Using decision tree for classification
# clf = tree.DecisionTreeClassifier()
'''
clf就是生成的決策樹，引數可以選擇決策樹的演算法種類，這裡使用entropy即ID3資訊熵演算法。
'''
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print("clf: " + str(clf))


# Visualize model
'''
建立.dot檔案用於存放視覺化決策樹資料，決策樹已經數值化，如果要還原屬性到決策樹，需要傳入屬性引數feature_names=vec.get_feature_names()
'''
with open("allElectronicInformationGainOri.dot", 'w') as f:
    f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)

'''
最後把生成的.dot檔案轉換成視覺化的pdf檔案，dot -Tpdf input.dot -o output.pdf

'''

#決策樹生成後，用demo例項預測結果

#取第一行資料，並稍做改動
oneRowX = dummyX[0, :]
print("oneRowX: " + str(oneRowX))
#oneRowX: [ 0.  0.  1.  0.  1.  1.  0.  0.  1.  0.]

newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
print("newRowX: " + str(newRowX))
#newRowX: [ 1.  0.  0.  0.  1.  1.  0.  0.  1.  0.]
#predictedY = clf.predict(newRowX)
'''
直接執行會報如下錯誤
    "if it contains a single sample.".format(array))
ValueError: Expected 2D array, got 1D array instead:
array=[ 0.  0.  1.  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.
提示需要reshape，所以入參改為newRowX.reshape(1,-1)
reshape作用可參考http://www.cnblogs.com/iamxyq/p/6683147.html
'''
predictedY = clf.predict(newRowX.reshape(1,-1))
print("predictedY: " + str(predictedY))
#predictedY: [1]

生成的決策樹如下：

RID age income student credit_rating class_buys_computer
1 youth high no fair no
2 youth high no excellent no
3 middle_aged high no fair yes
4 senior medium no fair yes
5 senior low yes fair yes
6 senior low yes excellent no
7 middle_aged low yes excellent yes
8 youth medium no fair no
9 youth low yes fair yes
10 senior medium yes fair yes
11 youth medium yes excellent yes
12 middle_aged medium no excellent yes
13 middle_aged high yes fair yes
14 senior medium no excellent no