机器学习_07_数据特征、分布情况

001查看前10行数据

from pandas import read_csv
#  03.采用pandas 导入数据
filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.shape)
#001查看前10行数据
peek = data.head(10)
print(peek)

002.sahpe 属性查看数据维度：多少行多少列

from pandas import read_csv
#  002.sahpe 属性查看数据维度：多少行多少列
filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.shape)

003.type 属性查看数据类型：int,float

from pandas import read_csv
#  003.type 属性查看数据类型：int,float

filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.dtypes)

004.describe() 方法查看统计内容的描述： max,min,etc.

from pandas import read_csv
#  004.describe() 方法查看统计内容的描述： max,min,etc

filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin',
	'test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.describe())

005.查看数据分类分布状况 groupby().class()

from pandas import read_csv
#  005.查看数据分类分布状况 groupby().class()

filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.groupby('class').size())

006.corr()方法——计算属性相互影响的矩阵

from pandas import read_csv
from pandas import set_option
#  006.corr()方法——计算属性相互影响的矩阵
#   显示数据相关性
filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
set_option("display.width",100)
#设置数据的精度
set_option("precision",2)
print(data.corr(method='pearson'))

007.计算数据的正态分布偏离程度

from pandas import read_csv
#  007.计算数据的正态分布偏离程度

filename = 'Pima_Indians.csv'
names = ['preg','plas','pres','skin','test','mess','pedi','age','class']
data = read_csv(filename,names=names)
print(data.skew())