def main():
dirList = list()
temp = listdir("./data/Asthma/2010/")
dirList.append(temp)
temp = listdir("./data/Asthma/2011/")
dirList.append(temp)
temp = listdir("./data/Asthma/2012/")
dirList.append(temp)
temp = listdir("./data/Asthma/2013/")
dirList.append(temp)
temp = listdir("./data/Asthma/2014/")
dirList.append(temp)
pre = PreProcessor()
clf = SVM(kernel=GaussianKernel(5.0), C=1.0)
X_train, y_train = pre.loadTrainingSet(
"training_data/Asthma_Sample_Tokenized.csv")
clf.fit(X_train, y_train)
# Author Alvaro Esperanca
from SVM import SVM
from PreProcessor import PreProcessor
from Validator import Validator
from GaussianKernel import GaussianKernel
import numpy as np
if __name__ == "__main__":
pre = PreProcessor()
val = Validator()
clf = SVM(kernel=GaussianKernel(5.0), C=1.0)
X_train, y_train = pre.loadTrainingSet(
"training_data/Cancer_Sample_Tokenized.csv")
X_test = pre.loadTestSet("test_data/Tokenized_Cancer_test.csv")
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
validFile = open("validation_set/validation_set_labels.txt", "r")
temp = validFile.readlines()
validationLabels = [float(num) for num in temp]
val.validate(validationLabels, predictions)
val.report()
# predFile = open("results/gaussian_kernel_s_5000_c_5.txt", "w")
# statFile = open("results/gaussian_kernel_s_5000_c_5_stats.txt", "w")
