def getPereiraDataAndLabels():
data = fileReading.readFile(r'data_RNA_Seq_expression_median_modified.txt')
data = data.transpose()
labels = fileReading.readFile(r'data_clinical_sample.txt')
labels = labels[4:, :]
patientIDInLabels = labels[1:, 0]
patientIDInExpression = data[1:, 0]
finalLabels = []
for patientID in patientIDInLabels:
ind = np.argwhere(patientIDInExpression == patientID)
if ind.size != 0:
val = labels[ind[0], 5].tolist()
if len(val):
finalLabels.append(val[0])
data = data[1:, 1:]
data = np.array(data, dtype=float)
nLabels = np.zeros((data.shape[0], ), dtype=np.int)
for idx in range(len(finalLabels)):
if finalLabels[idx] == 'Positive':
nLabels[idx] = 1
return data, nLabels
#labels = labels[4:,:]
#patientIDInLabels =labels[1:,0]
#patientIDInExpression = data[1:, 0]
#finalLabels = []
#for patientID in patientIDInLabels:
# ind = np.argwhere(patientIDInExpression == patientID)
# finalLabels.append(labels[ind,5])
#data = fileReading.readFile('Skin.txt')
#data = np.array(data)
#data = data.astype(float)
#C = onlineKmeans(data, 20)
data = fileReading.readFile('breast-cancer-wisconsin.data')
data = data[:, :-1]
data = np.array(data)
data = data.astype(float)
#X_train, X_test, y_train, y_test = train_test_split(data, data, test_size=0.3,random_state=109)
#clf = svm.SVC(kernel='linear')
#clf.fit(X_train, y_train)
list=cluster(data)
#list = []
#for k in range (10, 50, 10):
# C = onlineKmeans(data, k)
# print(k)
# list.append(len(C))
# -*- coding: utf-8 -*-
"""
Created on Thu Dec 6 10:35:43 2018
@author: Jubair
"""
import numpy as np
import fileReading
from sklearn.cluster import KMeans
k = 5
data = fileReading.readFile('lung-cancer.data')
labels = data[:, 0]
data = data[:, 1:]
data = np.array(data)
data = data.astype(float)
kmeans = KMeans(n_clusters=k, random_state=5).fit(data)
cost_offline = kmeans.inertia_
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 28 12:34:38 2018
@author: atifu
"""
"implementation of dcj-rna by Badr et al."
import numpy as np
from fileReading import readFile
from allignComponents import allignComponents
from result import result
structure_1 = readFile('Cyano-1.txt')
structure_2 = readFile('Flavo-1.txt')
no_inter_first = len(structure_1)
no_inter_second = len(structure_2)
structure_1 = structure_1.transpose()
structure_2 = structure_2.transpose()
opening_bracket_fs = structure_1[0:1, ]
closing_bracket_fs = structure_1[1:2, ]
length_first = structure_1[2:3, ]
opening_bracket_ss = structure_2[0:1, ]
closing_bracket_ss = structure_2[1:2, ]
length_second = structure_2[2:3, ]
wp = 1
def dataprocess():
data = fileReading.readFile('breast-cancer-wisconsin.data')
data = data[:, :-1]
data = np.array(data)
data = data.astype(float)
return data