python中离散数据插到格点_Python 数据离散化

import pandas as pd

data =

pd.read_excel(r"F:\BaiduYunDownload\python数据分析和挖掘实战\chapter4\chapter4\demo\data\discretization_data.xls")

data = data['肝气郁结证型系数']

k = 4

#等宽离散化

d1 = pd.cut(data, k, labels = range(k))

#等频离散化

w = [i/k for i in range(k+1)]

w = data.describe(percentiles = w)[4:4+k+1]

w[0] = w[0]*(1 - le - 10)

d2 = pd.cut(data, w, labels = range(k))

#(一维)聚类

from sklearn.cluster import KMeans

kmodel = KMeans(n_clusters = k, n_jobs = 8)

kmodel.fit(data.reshape((len(data), 1)))

c =

pd.DataFrame(kmodel.cluster_centers_).sort(0)

w = pd.rolling_mean(c, 2).iloc[1:]

w = [0] + list(w[0]) + [data.max()]

d3 = pd.cut(data, w, labels = range(k))

#绘图

def c