一文解决基因表达数据的聚类转换

# -*- coding: utf-8 -*-
"""
Created on Mon Dec  2 00:32:59 2019

@author: czh
"""


# In[*]
%reset -f
%clear
# In[*]
import pandas as pd
from sklearn.cluster import KMeans #导入K均值聚类算法
import os
os.chdir("D:\\train\\diff")

# In[*]
data = pd.read_csv("5year.csv",header=0,index_col=0)

d = data.iloc[:,1:78]
# In[*]
data.head()

# In[*]
d.head()


# In[*]
d.columns = d.columns.map(lambda x :str(x))

d.columns = d.columns+ "gene_exp"

d.columns
# In[*]
def f(x):
    from sklearn.cluster import KMeans
    model = KMeans(n_clusters=2)
    model.fit(d[[x]].as_matrix())

    centers_d = pd.DataFrame(model.cluster_centers_).sort_values(by = 0)
    group = [0] + list(centers_d.rolling(2).mean().iloc[1:][0]) + [d[x].max()]
    s = pd.cut(d[x], group, labels = [ x + str(i) for i in range(2)])

    return s
    

# In[*]
aprioriData = pd.DataFrame()

for i in range(77):
    col_name = d.columns
    col = col_name[i]
    Data = f(col)
    aprioriData =  pd.concat([aprioriData,Data],axis=1)

# In[*]
discretization_d =  pd.concat([aprioriData,data['Class']],axis =1)


# In[*]
discretization_d.head()

data.head()
Out[50]: 
      Class    ADGRA2    ANGPTL2  ...     TPST1    TSC22D3     VSTM4
id                                ...                               
AA80      0  0.776205   3.942062  ...  7.347908  10.512511  0.209625
A9TC      0  2.857827   3.229691  ...  2.324581   7.113074  0.485731
A5W6      0  1.161271   5.802349  ...  7.360124  21.058854  0.629902
A6DX      0  1.465745   7.821838  ...  6.256095  29.304477  1.290819
A8HH      0  9.702574  18.361627  ...  6.382861  29.900405  1.442875

[5 rows x 78 columns]

d.head()
Out[51]: 
      ADGRA2gene_exp  ANGPTL2gene_exp  ...  TSC22D3gene_exp  VSTM4gene_exp
id                                     ...                                
AA80        0.776205         3.942062  ...        10.512511       0.209625
A9TC        2.857827         3.229691  ...         7.113074       0.485731
A5W6        1.161271         5.802349  ...        21.058854       0.629902
A6DX        1.465745         7.821838  ...        29.304477       1.290819
A8HH        9.702574        18.361627  ...        29.900405       1.442875

[5 rows x 77 columns]