weixin_43844229的博客

import pandas as pd import numpy as np #创建特征列表 column_names=['sample code number','clump thickness','uniformity of cell size', \ 'uniformity of cell shape','marginal adhesion','single epithelical cell...

import pandas as pd import numpy as np #导入手写体数字加载器 from sklearn.datasets import load_digits #获得手写体数字的数码图像数据，存储在digits变量中 digits=load_digits() digits.data.shape #共有1797条，每幅图片由8*8=64的像素矩阵表示 from sklea...

#导入新闻数据抓取器 from sklearn.datasets import fetch_20newsgroups #即时从互联网下载数据 news=fetch_20newsgroups(subset='all') #共有18846条新闻 len(news.data) #第一条数据 news.data[0] from sklearn.cross_validation import trai...

#导入 iris 数据加载器 from sklearn.datasets import load_iris iris=load_iris() #查看数据规模 iris.data.shape #查看数据说明 print(iris.DESCR) #数据分割 from sklearn.cross_validation import train_test_split X_train,X_test,...

import pandas as pd titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt') 观察前几行的数据，发现数据种类各异，有数值型，类别型，还有缺失数据 titanic.head() #查看数据的统计特性,1313条乘客信息 titanic.info() ...

import pandas as pd titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt') #数据预处理 #特征选择 X=titanic[['pclass','age','sex']] y=titanic['survived'] #查看特征统计信息，发现age列...

import pandas as pd titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt') X=titanic[['pclass','age','sex']] y=titanic['survived'] X['age'].fillna(X['age'].mean(),i...

import pandas as pd #本地读取训练集和测试集 train=pd.read_csv('train.csv') test=pd.read_csv('test.csv') #输出基本信息 print(train.info()) print(test.info()) selected_features=['Pclass','Sex','Age','Emarked','SibSip','...