from fusion import cv10
from fusion import dt
from fusion import lr_feature_selection
from fusion import knn
from standardized_data import *
from thematic_data_combined import combine_data_from_feature_selection
from svms import svm_selected_for_features_fusion
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
ids = data.ids
percentage = float(raw_input("Enter percentage."))
combined_dataset, targets = combine_data_from_feature_selection(targets, percentage)
alg = raw_input("Enter algorithm. Choose lr, dt, knn, svm")
fusion_algorithm = raw_input("Enter algorithm. Choose between maj, wmaj, svm, nn")
for i in range(100):
if alg == "lr":
cv10(combined_dataset, targets, fusion_algorithm, ids, lr_feature_selection, prt=True, file_name="best_lr_"+str(percentage)+alg+"_"+fusion_algorithm+".txt")
elif alg == "dt":
cv10(combined_dataset, targets, fusion_algorithm, ids, dt, prt=True, file_name="best_dt_"+str(percentage)+alg+"_"+fusion_algorithm+".txt")
elif alg == "knn":
cv10(combined_dataset, targets, fusion_algorithm, ids, knn, prt=True, file_name="best_knn_"+str(percentage)+alg+"_"+fusion_algorithm+".txt")
elif alg == "svm":
std = StandardizedData(targets)
dataset = std.standardize_dataset(combined_dataset)
"""
Logistic Regression Classification
Combine LR for themes
Feature selection is applied before
"""
print(__doc__)
import sys
sys.path.insert(0, 'utils/')
sys.path.insert(0, 'feature context/')
from load_data import *
from project_data import *
from fusion import cv10
from fusion import lr_feature_selection
from thematic_data_combined import combine_data_from_feature_selection
from parameters import CV_PERCENTAGE_OCCURENCE_THRESHOLD
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
ids = data.ids
combined_dataset, targets = combine_data_from_feature_selection(targets, CV_PERCENTAGE_OCCURENCE_THRESHOLD)
fusion_algorithm = raw_input("Enter algorithm. Choose between maj, wmaj, svm, nn")
cv10(combined_dataset, targets, fusion_algorithm, ids, lr_feature_selection)
C_ideo, g_ideo = params()
C_range = [C_net, C_ill, C_ideo]
g_range = [g_net, g_ill, g_ideo]
for cs in itertools.product(*C_range):
for gs in itertools.product(*g_range):
c_net = cs[0]
c_ill = cs[1]
c_ideo = cs[2]
g_net = gs[0]
g_ill = gs[1]
g_ideo = gs[2]
best_svm = BestSVM(c_net, g_net, c_ill, g_ill, c_ideo, g_ideo)
combined_dataset, targets = combine_data_from_feature_selection(targets, 0.9)
std = StandardizedData(targets)
dataset = std.standardize_dataset(combined_dataset)
error, f1 = cross_validation(dataset, targets, best_svm)
if error <= 0.33 and f1 > 0:
with open("result.txt", "a") as myfile:
myfile.write('\n##############################\n')
with open("result.txt", "a") as myfile:
myfile.write(best_svm.to_string())
with open("result.txt", "a") as myfile:
myfile.write('\nerror_maj %f' % error)
with open("result.txt", "a") as myfile:
myfile.write('\nf1 %f' % f1)
