# 6.3.1 數據集的準備import pandas as pddata=pd.read_csv('adult.csv',header=None,index_col=False,names=['年齡','單位性質','權重','學歷','受教育時長','婚姻狀況','職業','家庭狀況','種族','性別','資產所得','資產損失','周工作時長','原籍','收入']) data_lite=data[['年齡','單位性質','學歷','性別','周工作時長','職業','收入']]display(data_lite.head()) 年齡單位性質學歷性別周工作時長職業收入01234

39	State-gov	Bachelors	Male	40	Adm-clerical	<=50K
50	Self-emp-not-inc	Bachelors	Male	13	Exec-managerial	<=50K
38	Private	HS-grad	Male	40	Handlers-cleaners	<=50K
53	Private	11th	Male	40	Handlers-cleaners	<=50K
28	Private	Bachelors	Female	40	Prof-specialty	<=50K

# 6.3.2 用get_dummies處理數據data_dummies=pd.get_dummies(data_lite)print('樣本原始特征：\n',list(data_lite.columns),'\n')print('虛擬變量特征：\n',list(data_dummies.columns),'\n')print('data_dummies.shape:\n',data_dummies.shape,'\n')print('data_dummies的類型：\n',type(data_dummies)) 樣本原始特征：['年齡', '單位性質', '學歷', '性別', '周工作時長', '職業', '收入'] 虛擬變量特征：['年齡', '周工作時長', '單位性質_ ?', '單位性質_ Federal-gov', '單位性質_ Local-gov', '單位性質_ Never-worked', '單位性質_ Private', '單位性質_ Self-emp-inc', '單位性質_ Self-emp-not-inc', '單位性質_ State-gov', '單位性質_ Without-pay', '學歷_ 10th', '學歷_ 11th', '學歷_ 12th', '學歷_ 1st-4th', '學歷_ 5th-6th', '學歷_ 7th-8th', '學歷_ 9th', '學歷_ Assoc-acdm', '學歷_ Assoc-voc', '學歷_ Bachelors', '學歷_ Doctorate', '學歷_ HS-grad', '學歷_ Masters', '學歷_ Preschool', '學歷_ Prof-school', '學歷_ Some-college', '性別_ Female', '性別_ Male', '職業_ ?', '職業_ Adm-clerical', '職業_ Armed-Forces', '職業_ Craft-repair', '職業_ Exec-managerial', '職業_ Farming-fishing', '職業_ Handlers-cleaners', '職業_ Machine-op-inspct', '職業_ Other-service', '職業_ Priv-house-serv', '職業_ Prof-specialty', '職業_ Protective-serv', '職業_ Sales', '職業_ Tech-support', '職業_ Transport-moving', '收入_ <=50K', '收入_ >50K'] data_dummies.shape:(32561, 46) data_dummies的類型：<class 'pandas.core.frame.DataFrame'> # 顯示數據集中的前五行#顯示所有列 pd.set_option('display.max_columns', None) #顯示所有行 pd.set_option('display.max_rows', None)data_dummies.head() 年齡周工作時長單位性質_ ?單位性質_ Federal-gov單位性質_ Local-gov單位性質_ Never-worked單位性質_ Private單位性質_ Self-emp-inc單位性質_ Self-emp-not-inc單位性質_ State-gov單位性質_ Without-pay學歷_ 10th學歷_ 11th學歷_ 12th學歷_ 1st-4th學歷_ 5th-6th學歷_ 7th-8th學歷_ 9th學歷_ Assoc-acdm學歷_ Assoc-voc學歷_ Bachelors學歷_ Doctorate學歷_ HS-grad學歷_ Masters學歷_ Preschool學歷_ Prof-school學歷_ Some-college性別_ Female性別_ Male職業_ ?職業_ Adm-clerical職業_ Armed-Forces職業_ Craft-repair職業_ Exec-managerial職業_ Farming-fishing職業_ Handlers-cleaners職業_ Machine-op-inspct職業_ Other-service職業_ Priv-house-serv職業_ Prof-specialty職業_ Protective-serv職業_ Sales職業_ Tech-support職業_ Transport-moving收入_ <=50K收入_ >50K01234

39	40	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0
50	13	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	1	0
38	40	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	1	0
53	40	0	0	0	0	1	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	1	0
28	40	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	1	0

features=data_dummies.loc[:,'年齡':'職業_ Transport-moving']print('features的類型：\n',type(features),'\n')X=features.valuesprint('X的類型：\n',type(X),'\n')print('打印X的前五行:\n',X[:5,:])y=data_dummies['收入_ >50K'].valuesprint('特征形態：{} 標簽形態{}'.format(X.shape,y.shape))# 避免顯示不全： # import numpy as np # np.set_printoptions(threshold=np.inf) features的類型：<class 'pandas.core.frame.DataFrame'> X的類型：<class 'numpy.ndarray'> 打印X的前五行:[[39 40 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 00 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0][50 13 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 1 0 0 00 0 0 0 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0][38 40 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 00 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0][53 40 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 00 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0][28 40 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 00 0 0 1 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0]] 特征形態：(32561, 44) 標簽形態(32561,) features.columnstype(features.columns) pandas.core.indexes.base.Index # 用決策樹建模并作出預測 from sklearn.model_selection import train_test_splitX_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0)from sklearn import treego_dating_tree=tree.DecisionTreeClassifier(max_depth=5)go_dating_tree.fit(X_train,y_train)print('模型的分：{:.2f}'.format(go_dating_tree.score(X_test,y_test))) 模型的分：0.80

總結

以上是生活随笔為你收集整理的深入浅出python机器学习_6.3.1_随机森林实例——要不要和相亲对象进一步发展的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。