def manifold_sk_quadradicdiscriminantanalysis(content):
""" discriminant_analysis_sk_QuadraticDiscriminantAnalysis """
_config = QuadraticDiscriminantAnalysis(
priors=None,
reg_param=0.0, #content['reg_param'],
store_covariance=content['store_covariance'],
tol=content['tol'])
_result = _config.fit_transform(content['data'])
return httpWrapper(
json.dumps({
'result': _result.tolist(),
'covariance': _config.covariance_,
'means': _config.means_,
'priors': _config.priors_,
'rotations': _config.rotations_,
'scalings': _config.scalings_
}))
y_pred = gnb.fit(XTrain, Y).predict(XTrain)
print("Predicted (GNB) Class labels on Training Set:")
print(y_pred)
print("")
#QDA
clf = QuadraticDiscriminantAnalysis()
clf.fit(XTrain, Y)
print("Predicted (QDA) Class labels on Training Set:")
Z = clf.predict(XTrain)
print(Z)
#LDA
clf = LinearDiscriminantAnalysis()
XTrain_new = clf.fit_transform(XTrain, Y)
print("")
print("Predicted (LDA) Class labels on Training Set:")
Z = clf.predict(XTrain)
print(Z)
fig = plt.figure(figsize=(8, 8))
x = np.transpose(XTrain_new)[0]
y = np.transpose(XTrain_new)[1]
c = Y
class_colours = ['r', 'b', 'g', 'y']
recs = []
for i in range(0, len(class_colours)):
recs.append(mpatches.Rectangle((0, 0), 1, 1, fc=class_colours[i]))
