In [ ]:

    




    

In [1]:

    

from time import time
import psycopg2
from collections import Counter
import pandas as pd
import numpy as np
from sklearn.decomposition import NMF
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

np.set_printoptions(suppress=True,precision=10)


    

In [2]:

    

import sys 
import os
sys.path.append(os.path.abspath("/home/scidb/HeartRatePatterns/Python"))
from LogisticRegresion import ajustLogisticRegression


    

In [3]:

    

def selectMatrix(dbname="mimic") :
    conn = psycopg2.connect("dbname="+dbname)
    cur = conn.cursor()
    select_stament = ("SELECT m.subject_id,m.word,m.counting,s.isalive "
                      " FROM matrix m LEFT JOIN subjectwords s ON m.subject_id=s.subject_id "
     #                 " WHERE m.word in (select word from wordspearson where p1>0.01 order by p1 limit 400) "
    )
    cur.execute(select_stament)
    select = []
    for row in cur :
        select.append((row))
    cur.close()
    conn.close()
    return select


    

In [4]:

    

def convertMatrix() :
    labels = ['subject_id', 'Word', 'Counting','isAlive']
    df = pd.DataFrame.from_records(selectMatrix(), columns=labels)
    print(len(df))
    table = pd.pivot_table(df,index=["subject_id","isAlive"],columns=["Word"],values=["Counting"],
                       aggfunc={"Counting":[np.sum]},fill_value=0)
    table.columns = [value[2] for value in table.columns.values]
    return table


    

In [5]:

    

t0=time()
table = convertMatrix()
print("converMatrix done in %0.3fs." % (time() - t0))
print(table.shape)


    

    




134706
converMatrix done in 3.138s.
(658, 5610)






    
Out[5]:





14

In [6]:

    

survived = table.index.labels[1].tolist()
patients = table.values


    

In [7]:

    

print(table.shape)
print(len(survived))
print(patients.shape)


    

    




(658, 5610)
658
(658, 5610)

In [8]:

    

nmf = NMF(n_components=2, random_state=1,alpha=.1, l1_ratio=.5)
patients_trainnmf = nmf.fit_transform(patients)


    

In [9]:

    

components = nmf.components_
components.shape


    

    
Out[9]:





(2, 5610)

In [10]:

    

patients_trainnmf.shape


    

    
Out[10]:





(658, 2)

In [11]:

    

def survivered(survived_train):
    bal = []
    for survived in survived_train:
        if survived==0:
            bal.append('green')
        else:
            bal.append('red')
    return bal
plt.scatter(x=components[0],y=components[1],c='blue')
plt.scatter(x=patients_trainnmf[:,0],y=patients_trainnmf[:,1],c=survivered(survived))
plt.show()


    

In [12]:

    

nmf = NMF(n_components=3, random_state=1,alpha=.1, l1_ratio=.5)
patients_trainnmf = nmf.fit_transform(patients)
components = nmf.components_

fig = plt.figure()
ax2 = fig.add_subplot(111, projection='3d')
ax2.scatter(components[0],-components[1],components[2],c='blue',marker='o')
ax2.scatter(patients_trainnmf[:, 0], -patients_trainnmf[:, 1],patients_trainnmf[:, 2], marker='.', lw=0, alpha=0.7,c=survivered(survived), edgecolor='k')
plt.show()


    

In [ ]: