# -*- coding: utf-8 -*-import pandas as pd
 data=pd.read_csv(open('d:/data/datafile.csv'))
 print(data.head(10))

1 data2 = open('E:\data\datafile.txt')
2 s=data2.read()

#-*- coding:utf-8 -*-import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import mysql.connector
conn = mysql.connector.connect(host='localhost',user='root',passwd='123456',db='python')#链接本地数据库
sql = 'select * from taob'#sql语句
data = pd.read_sql(sql,conn)#获取数据
print(data.describe())

# -*- coding: utf-8 -*-import pandas as pdfrom datetime import date,datetimedef read_dataFrame(fileName,sheetName ='' ):print('File:',end='')print(fileName)print('Sheet:',end='')print(sheetName)df = pd.read_excel(io=fileName, sheet_name=sheetName, header=0, skiprows=None, skip_footer=0, index_col=None, names=None, usecols=None, parse_dates=False, date_parser=None, na_values=None, thousands=None, convert_float=True, converters=None, dtype=None, true_values=None, false_values=None, engine=None, squeeze=False)df = append_dataFrame(df)path = 'C://input//'  fileName = path+'input.xlsx'  data = read_dataFrame(fileName,'sheet1')

---------------------
原文：https://blog.csdn.net/flora_zhl/article/details/80269604 

1 print(data.head(10))#显示data的前十行
2 print(data.shape)#显示data的行数和列数
3 print(data.dtypes)#显示data的各字段的数据类型
4 print(data.describe())#进行data的各字段的描述性统计
5 print(data.groupby('colname1').size())#统计data的1字段每一类指标有多少记录
6 print(data.corr(method='pearson'))#计算data的各字段相关性矩阵
7 print(data.skew())#data的高斯分布检验，其大小表示左偏和右偏，接近0为偏差小

1 import matplotlib.pyplot as plt
2 data.hist()#直方图
3 plt.show()#绘图

1 import matplotlib.pyplot as plt
2 data.plot(kind='density',subplots=True,layout=(3,3),sharex=False)#3x3的密度图
3 plt.show()#绘图

1 import matplotlib.pyplot as plt
2 data.plot(kind='box',subplots=True,layout=(3,3),sharex=False)#3x3的箱线图
3 plt.show()#绘图

1 from pandas.plotting import scatter_matrix
2 scatter_matrix(data)
3 plt.show()