def __init__(self):
print("Começo do treinamento")
data = CSVReader()
trainingX = data.getXTest()
trainingY = data.getYTest()
self.poly_features = PolynomialFeatures(degree=3)
polyX = self.poly_features.fit_transform(trainingX)
# fit final model
self.model = LinearRegression()
self.model = self.model.fit(polyX, trainingY)
print("Final do Treinamento")
def test_square_root(self):
test_data = CSVReader('Unit_Test_Square_Root.csv').data
for row in test_data:
self.assertAlmostEqual(
self.calculator.square_root(float(row['Value 1'])),
float(row['Result']))
self.assertAlmostEqual(self.calculator.result,
float(row['Result']))
def test_multiplication(self):
test_data = CSVReader('Unit_Test_Multiplication.csv').data
for row in test_data:
self.assertEqual(
self.calculator.multiply(float(row['Value 1']),
float(row['Value 2'])),
float(row['Result']))
self.assertEqual(self.calculator.result, float(row['Result']))
def test_subtraction(self):
test_data = CSVReader('Unit_Test_Subtraction.csv').data
for row in test_data:
self.assertEqual(
self.calculator.subtract(float(row['Value 2']),
float(row['Value 1'])),
float(row['Result']))
self.assertEqual(self.calculator.result, float(row['Result']))
def test_division(self):
test_data = CSVReader('Unit_Test_Division.csv').data
for row in test_data:
self.assertAlmostEqual(
self.calculator.divide(float(row['Value 2']),
float(row['Value 1'])),
float(row['Result']))
self.assertAlmostEqual(self.calculator.result,
float(row['Result']))
# graphing imports!
import matplotlib.pyplot as plt
import matplotlib.colors as colors
# clustering
from csvReader import CSVReader
from k_means import KMeans
inputFile = "microarraydata.csv"
k = 4
csvReader = CSVReader()
microarrayData = csvReader.read(inputFile)
print microarrayData
kmeans = KMeans(verbose=True)
finalClusters = kmeans.kmeans(microarrayData, k)
print "\nFinal set of gene clusters:"
for clusterIdx, cluster in enumerate(finalClusters):
print "\tCluster %d: %s" % (clusterIdx + 1, ["gene" + str(idx + 1) for gene, idx in cluster])
print ""
# k-means clustering
from k_means import KMeans
# QT clustering
from QT import QT
# Hierarchical clustering
from hierarchical import Hierarchical
# Print lots of stuff
VERBOSE = False
# the input file
inputFile = "ALL-AML-TRANSPOSED.csv"
# the output file
outputFile = "results.txt"
# A CSV file reader
csvReader = CSVReader()
# get the microarray data from the csv file
microarrayData = csvReader.read(inputFile)
microarrayLabels = csvReader.getLabels(inputFile)
print ("File %s parsed succesfully!\n\tRows:\t\t%d\n\tColumns:\t%d" % (inputFile, len(microarrayData), len(microarrayData[0])))
print ("\nLabels: {%s}" % (', '.join(microarrayLabels)))
## k-means algorithm!
# set the k-value (max potential clusters)
k = 3
# holds a reference to a KMeans object
kmeans = KMeans(verbose=VERBOSE)
# get the clusters determined by the algorithm
kMeansFinalClusters = kmeans.kmeans(microarrayData, k)