def save(img, value):
base64Img = imageToBase64(img)
binpix = getBinaryPix(img).tolist()
binpix = [str(i) for i in binpix]
content = ','.join(binpix)
collection = persistence.openConnection()
persistence.addImageToCollection(collection, base64Img, content, value)
return base64Img
def cross_validation():
dataSet, labels = persistence.allData(persistence.openConnection())
# dataMatrix = mat(dataSet)
# labelMatrix = mat(labels)
clf = SVC(kernel='rbf', C=1000)
clf.fit(dataSet, labels)
scores = cs.cross_val_score(clf, dataSet, labels, cv=5)
print('Accuracy: %0.2f (+- %0.2f)' % (scores.mean(), scores.std()))
return clf
def handleQuerySets(self):
import persistence
collection = persistence.openConnection()
keys = persistence.querySets(collection)
keys.sort()
result = {}
for key in keys:
result[key] = persistence.querySet(collection, key)
return result
def searchBestParameter():
parameters = {
'kernel': ('linear', 'poly', 'rbf', 'sigmoid'),
'C': [1, 100]
}
dataSet, labels = persistence.allData(persistence.openConnection())
svr = SVC()
clf = grid_search.GridSearchCV(svr, parameters)
clf.fit(dataSet, labels)
print(clf.best_params_)
def predict(binImg1, binImg2, binImg3):
parameters = {
'kernel': ('linear', 'poly', 'rbf', 'sigmoid'),
'C': [1, 100]
}
dataSet, labels = persistence.allData(persistence.openConnection())
svr = SVC()
clf = grid_search.GridSearchCV(svr, parameters)
clf.fit(dataSet, labels)
v1 = clf.predict(binImg1)
v2 = clf.predict(binImg2)
v3 = clf.predict(binImg3)
return (v1, v2, v3)