def update(self):
# Handle to storage for model parameters
params = self._parameters
# Make sure all my meta data is ready to go
params.validateMeta()
observation_vectors = []
truth_vectors = []
# Make sure my model data is ready to go
self._model_data.validate()
self._model_data.validateViews(self.getMetaData("db_views"))
# Check my model data
observation_vectors = self._model_data.getMetaData(
"observation_vectors")
truth_vectors = self._model_data.getMetaData("truth_vectors")
params.setMetaData("db_views", [])
# Houston we are go
mnb = MultinomialNB()
mnb.alpha = self.getMetaData("alpha")
mnb.fit_prior = self.getMetaData("fit_prior")
class_prior = self.getMetaData("class_prior")
if (class_prior != None):
mnb.class_prior = class_prior
mnb.fit(observation_vectors, truth_vectors)
params.setBinaryData("mnb_model", "application/pickle",
pickle.dumps(mnb))
self.finalize()
dual=True,
tol=0.0001,
C=0.5,
multi_class='ovr',
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
verbose=0,
random_state=None,
max_iter=1000)
clf_nb = MultinomialNB(alpha=0.04, fit_prior=True, class_prior=None)
#clf_svm = neighbors.KNeighborsClassifier(1)
clf_svm.C = 0.3
clf_nb.alpha = 0.04
l_svm_score = []
l_nb_score = []
l_blend_score = []
alpha = 1.
beta = 20.
#sss = StratifiedShuffleSplit(Y, 5, test_size=0.2, random_state=0)
sss = KFold(len(Y), n_folds=5, shuffle=True)
kbest = SelectKBest(chi2, k=300000)
for train_idx, val_idx in sss:
x_train, y_train, x_val, y_val = X[train_idx], Y[train_idx], X[val_idx], Y[
val_idx]
x_train = kbest.fit_transform(x_train, y_train)
print "Hstack fini"
X = pipeline.fit_transform(df_train)
X_test = pipeline.transform(df_test)
# print X.shape
# TRAINING
clf_svm = svm.LinearSVC(penalty='l2', loss='squared_hinge', dual=True, tol=0.0001, C=0.5, multi_class='ovr', fit_intercept=True, intercept_scaling=1, class_weight=None, verbose=0, random_state=None, max_iter=1000)
clf_nb = MultinomialNB(alpha=0.04, fit_prior=True, class_prior=None)
#clf_svm = neighbors.KNeighborsClassifier(1)
clf_svm.C = 0.3
clf_nb.alpha = 0.04
l_svm_score = []
l_nb_score = []
l_blend_score = []
alpha = 1.
beta = 20.
#sss = StratifiedShuffleSplit(Y, 5, test_size=0.2, random_state=0)
sss = KFold(len(Y), n_folds=5, shuffle=True)
kbest = SelectKBest(chi2, k=300000)
for train_idx, val_idx in sss:
x_train, y_train, x_val, y_val = X[train_idx], Y[train_idx], X[val_idx], Y[val_idx]
x_train = kbest.fit_transform(x_train, y_train)
x_val = kbest.transform(x_val)
