python 数据基本分析

import pandas as pd

catering_sale = 'B:\pycharm\DataMining\catering_sale.xls'
data = pd.read_excel(catering_sale, index_col=u'日期')
data = data[(data[u'销量'] > 400) & (data[u'销量'] < 5000)] #过滤异常数据
describe = data.describe()
#print(describe)
print("非空数据项数为 ：%f" % describe.loc['count'])
print("销量平均数为 : %f" % describe.loc['mean'])
print("标准差为 : %f" % describe.loc['std'])
print("最小值为 : %f" % describe.loc['min'])
print("最大值为 : %f" % describe.loc['max'])
print("下四分位点为 : %f" % describe.loc['25%'])
print("上四分位点为 : %f" % describe.loc['75%'])
print("中位数为 : %f" % describe.loc['50%'])
describe.loc['range'] = describe.loc['max'] - describe.loc['min'] #极差
describe.loc['var'] = describe.loc['std'] / describe.loc['mean'] #变异系数
describe.loc['dis'] = describe.loc['75%'] - describe.loc['25%'] #四分位数间距

print(describe)