#-*- coding: utf-8 -*-
#数据规范化
import pandas as pd
import numpy as npdatafile = '../data/normalization_data.xls' #参数初始化
data = pd.read_excel(datafile, header = None) #读取数据print (data - data.min())/(data.max() - data.min()) #最小-最大规范化
print (data - data.mean())/data.std() #零-均值规范化
print data/10**np.ceil(np.log10(data.abs().max())) #小数定标规范化#output：
#          0         1         2         3
#0  0.074380  0.937291  0.923520  1.000000
#1  0.619835  0.000000  0.000000  0.850941
#2  0.214876  0.119565  0.813322  0.000000
#3  0.000000  1.000000  1.000000  0.563676
#4  1.000000  0.942308  0.996711  0.804149
#5  0.264463  0.838629  0.814967  0.909310
#6  0.636364  0.846990  0.786184  0.929571
#          0         1         2         3
#0 -0.905383  0.635863  0.464531  0.798149
#1  0.604678 -1.587675 -2.193167  0.369390
#2 -0.516428 -1.304030  0.147406 -2.078279
#3 -1.111301  0.784628  0.684625 -0.456906
#4  1.657146  0.647765  0.675159  0.234796
#5 -0.379150  0.401807  0.152139  0.537286
#6  0.650438  0.421642  0.069308  0.595564
#       0      1      2       3
#0  0.078  0.521  0.602  0.2863
#1  0.144 -0.600 -0.521  0.2245
#2  0.095 -0.457  0.468 -0.1283
#3  0.069  0.596  0.695  0.1054
#4  0.190  0.527  0.691  0.2051
#5  0.101  0.403  0.470  0.2487#

#-*- coding: utf-8 -*-
#数据规范化
import pandas as pddatafile = '../data/discretization_data.xls' #参数初始化
data = pd.read_excel(datafile) #读取数据
data = data[u'肝气郁结证型系数'].copy()
k = 4d1 = pd.cut(data, k, labels = range(k)) #等宽离散化，各个类比依次命名为0,1,2,3#等频率离散化
w = [1.0*i/k for i in range(k+1)]
w = data.describe(percentiles = w)[4:4+k+1] #使用describe函数自动计算分位数
w[0] = w[0]*(1-1e-10)
d2 = pd.cut(data, w, labels = range(k))def cluster_plot(d, k): #自定义作图函数来显示聚类结果import matplotlib.pyplot as pltplt.rcParams['font.sans-serif'] = ['SimHei'] #用来正常显示中文标签plt.rcParams['axes.unicode_minus'] = False #用来正常显示负号plt.figure(figsize = (8, 3))for j in range(0, k):plt.plot(data[d==j], [j for i in d[d==j]], 'o')plt.ylim(-0.5, k-0.5)return pltcluster_plot(d1, k).show()cluster_plot(d2, k).show()

#-*- coding: utf-8 -*-
#线损率属性构造
import pandas as pd#参数初始化
inputfile= '../data/electricity_data.xls' #供入供出电量数据
outputfile = '../tmp/electricity_data.xls' #属性构造后数据文件data = pd.read_excel(inputfile) #读入数据
data[u'线损率'] = (data[u'供入电量'] - data[u'供出电量'])/data[u'供入电量']data.to_excel(outputfile, index = False) #保存结果