def report_status_selection(selection): [dataset, features] = parse_theme(selection) [known_dataset, known_targets, unk] = split_dataset(dataset, targets) feats = feature_context(known_dataset, known_targets, features) print selection print feats print 'Nr selected features %d' % len(feats) print 'Nr total features %d' % len(features) print 'Features eliminated %s' % set(features).difference(feats) return feats
def thematic_data_from_feature_selection(orig_targets, theme, target): [dataset, features] = parse_theme(theme) [known_dataset, known_targets, unk] = split_dataset(dataset, orig_targets) nr_times = int(math.floor(TOP_FEATURES_PERCENTAGE_THRESHOLD * len(features))) known_targets = np.asarray(known_targets) ssa_features = select_proxy_features(theme, target, nr_times) sf = SelectedFeatures(known_dataset, known_targets, ssa_features, features) print '####### %s FEATURES ####### %d %s' % (theme, len(ssa_features), str(ssa_features)) return sf.extract_data_from_selected_features(), known_targets
def cv(theme, percentage, current_svm): [dataset, features] = parse_theme(theme) [known_dataset, known_targets, unk] = split_dataset(dataset, targets) known_targets = np.asarray(known_targets) # cv_features = features_cross_validation(known_dataset, known_targets, features, current_svm) # selected_features = select_final_features_from_cv(cv_features, percentage) selected_features = select_features(percentage, theme) sf = SelectedFeatures(known_dataset, known_targets, selected_features, features) combined_dataset = sf.extract_data_from_selected_features() std = StandardizedData(known_targets, combined_dataset) known_dataset_scaled, known_targets = std.split_and_standardize_dataset() print '####### FEATURES ####### %d \n %s' % (len(selected_features), str(selected_features)) return cross_validation(np.array(known_dataset_scaled), known_targets, ids, current_svm)
def thematic_data_from_feature_selection(orig_targets, theme, percentage): [dataset, features] = parse_theme(theme) [known_dataset, known_targets, unk] = split_dataset(dataset, orig_targets) known_targets = np.asarray(known_targets) # these come from feature_selection_cv # commented out because they were saved to decrease computation time # cv_features = features_cross_validation(known_dataset, known_targets, features) # selected_features = select_final_features_from_cv(cv_features, percentage) selected_features = select_features(percentage, theme) sf = SelectedFeatures(known_dataset, known_targets, selected_features, features) print '####### %s FEATURES ####### %d %s' % (theme, len(selected_features), str(selected_features)) return sf.extract_data_from_selected_features(), known_targets
import sys
sys.path.insert(0, 'utils/')
from load_data import *
from project_data import *
from parse_theme import *
from split_dataset import *
import numpy as np
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
[dataset, features] = parse_theme('all')
[known_dataset, known_targets, unk] = split_dataset(dataset, targets)
print 'NEG %d' % len([x for x in known_targets if x==0])
print 'POS %d' % len([x for x in known_targets if x==1])
print 'HIGHVAL %d' % len([x for x in known_targets if x==1])
print 'CIVIL %d' % len([x for x in known_targets if x==2])
def split_dataset(dataset, targets):
unknowns = []
known_dataset = []
known_targets = []
for i in range(0, len(targets)):
if targets[i] == 0:
unknowns.append(dataset[i])
else:
known_dataset.append(dataset[i])
known_targets.append(targets[i])
return [np.array(known_dataset), known_targets, np.array(unknowns)]
def decision_tree(dataset, targets):
[known_dataset, known_targets, unknowns, ] = split_dataset(dataset, targets)
model = DecisionTreeClassifier(criterion='entropy')
model.fit(known_dataset, known_targets)
print 'Model score: %f' % model.score(known_dataset, known_targets)
print model.feature_importances_
with open("tree.dot", 'w') as f:
f = export_graphviz(model, out_file=f)
### need to dot -Tpdf tree.dot -o tree.pdf
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
[dataset, features] = parse_theme(sys.argv[1])
decision_tree(dataset, targets)
print 'Civil recall %f' % cr
print 'Civil f1 %f' % cf
return error_rate, f1, (hp, hr, hf), (cp, cr, cf)
if __name__ == "__main__":
training_spreadsheet = Spreadsheet(project_data_file)
training_data = Data(training_spreadsheet)
training_targets = training_data.targets
testing_spreadsheet = Spreadsheet(addendum_data_file, upsampling=False)
testing_data = Data(testing_spreadsheet, upsampling=False)
testing_targets = testing_data.targets
[training_data, features] = parse_theme('all')
[testing_data, feats] = parse_theme_from_file('all', addendum_data_file)
assert features == feats
[training_data, training_targets, unk] = split_dataset(training_data, training_targets)
selected_features = single_features_90
sf = SelectedFeatures(training_data, training_targets, selected_features, features)
training_data = sf.extract_data_from_selected_features()
sf = SelectedFeatures(testing_data, testing_targets, selected_features, features)
testing_data = sf.extract_data_from_selected_features()
# standardize dataset - Gaussian with zero mean and unit variance
scaler = StandardScaler()
testing_data = replace_missings(testing_data)
def get_known_data_from_theme(self, theme): [theme_dataset, theme_features] = parse_theme(theme) [known_dataset, known_targets, unk] = split_dataset(theme_dataset, self.targets) known_targets = np.asarray(known_targets) return [known_dataset, known_targets]
Normalize.__init__(self, vmin, vmax, clip)
def __call__(self, value, clip=None):
x, y = [self.vmin, self.midpoint, self.vmax], [0, 0.5, 1]
return np.ma.masked_array(np.interp(value, x, y))
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
ids = data.ids
theme = raw_input("Theme.\n")
percentage = float(raw_input("Percentage as float.\n"))
[dataset, features] = parse_theme(theme)
[known_dataset, known_targets, unk] = split_dataset(dataset, targets)
known_targets = np.asarray(known_targets)
selected_features = select_features(percentage, theme)
sf = SelectedFeatures(known_dataset, known_targets, selected_features, features)
dataset = sf.extract_data_from_selected_features()
dataset = preprocessing.scale(dataset)
C_range = np.arange(0.1, 9, 0.1)
gamma_range = np.arange(0.1, 9, 0.1)
param_grid = dict(gamma=gamma_range, C=C_range)
# cv = StratifiedShuffleSplit(known_targets, random_state=42)
cv = StratifiedKFold(known_targets, n_folds=10)
grid = GridSearchCV(SVC(class_weight='auto'), param_grid=param_grid, cv=cv, scoring='f1')
