機器學習:sklearn&pydotplus實現Decision Tree
阿新 • • 發佈:2018-12-25
import csv from sklearn.feature_extraction import DictVectorizer from sklearn import preprocessing from sklearn import tree import pydotplus ''' 資料集 play.csv 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 yes 7 middle_aged low yes excellent no 8 youth medium no fair yes 9 youth low yes fair no 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 ''' file = open("E:\\play.csv", 'rt', encoding='utf-8') reader = csv.reader(file) ''' headers = reader.next() 報錯 python csv2libsvm.py: AttributeError: '_csv.reader' object has no attribute 'next' This is because of the differences between python 2 and python 3. Use the built-in function next in python 3. That is, write next(reader) instead of reader.next() ''' headers = next(reader) print("表頭資訊\n" + str(headers)) feature_list,result_list = [],[] for row in reader: result_list.append(row[-1]) feature_list.append(dict(zip(headers[1:-1],row[1:-1]))) print("結果\n"+str(result_list),"\n特徵值\n"+str(feature_list)) vec = DictVectorizer() # 將dict型別的list資料,轉換成numpy array DummyX = vec.fit_transform(feature_list).toarray() DummyY = preprocessing.LabelBinarizer().fit_transform(result_list) #注意,dummyX是按首字母排序的 print("DummyX\n"+str(DummyX),"\nDummyY\n"+str(DummyY)) clf = tree.DecisionTreeClassifier(criterion="entropy",random_state=0) # clf = tree.DecisionTreeClassifier() clf = clf.fit(DummyX,DummyY) print("clf\n"+str(clf)) #輸出dot檔案 with open("E:\\play.dot","w") as f: f = tree.export_graphviz(clf,out_file=f) print( '特徵向量\n',vec.get_feature_names() ) # help(tree.export_graphviz) dot_data = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), special_characters=True, filled=True, rounded=True, out_file=None,) print("dot_data\n"+str(dot_data)) ''' pydotplus 畫句子的依存結構樹 pip install pydotplus 安裝不上 pip install --upgrade --ignore-installed pydotplus 可以安裝上 pydotplus.graphviz.InvocationException: GraphViz's executables not found 這是《機器學習升級版III》中“決策樹隨機森林實踐”章節的問題。 解決方法:conda install graphviz ,安裝完成,重啟IDE整合開發工具 先安裝GraphViz軟體,將GraphViz解壓後的目錄新增到環境變數path裡,然後pip 安裝pydotplus,按照這個順序 安裝,如果還不行,重啟一下ide或者電腦就行了 ''' graph = pydotplus.graph_from_dot_data(dot_data) graph.write_pdf("E:\\play.pdf") #根據特徵向量可知:0.0.1.|0.1.|1.0.0.|1.0.表示youth,fair,high,no oneRowX=dummyX[0] twoRowX=dummyX[1] print("oneRowX:\n",str(oneRowX),"\ntwoRowX\n",str(twoRowX)) #進行預測 A = ([[0,0,1,0,1,1,0,0,1,0]]) B = ([[1,0,0,0,1,1,0,0,1,0]]) predict_A = clf.predict(A) predict_B = clf.predict(B) print("predict_A",str(predict_A),"predict_B",str(predict_B))