def __init__(self,
x,
n_components,
nkernel_components=100,
kernel='rbf',
preprocess=True,
gamma=None,
coef0=1,
degree=3):
self.x = x
self.kernel = kernel
self.n_components = n_components
self.preprocess = preprocess
self.gamma = gamma
self.coef0 = coef0
self.degree = degree
self.nkernel_components = nkernel_components
self.kX = ks.Nystroem(kernel=self.kernel,
gamma=self.gamma,
coef0=self.coef0,
degree=self.degree,
n_components=self.nkernel_components)
self.Xkernel = self.kX.fit_transform(x)
if self.preprocess:
self.Xscaler = preprocessing.StandardScaler().fit(self.Xkernel)
self.Xkernel = self.Xscaler.transform(self.Xkernel)
def convert_to_kernel(self, X0):
kX = ks.Nystroem(kernel=self.kernel,
gamma=self.gamma,
coef0=self.coef0,
degree=self.degree,
n_components=self.nkernel_components)
Xkernel = kX.fit_transform(X0)
if self.preprocess:
Xscaler = preprocessing.StandardScaler().fit(Xkernel)
Xkernel = Xscaler.transform(Xkernel)
self.Xscaler = Xscaler
#print(Xkernel)
self.Xkernel = Xkernel
self.X0 = X0
self.kX = kX
return Xkernel
def __init__(self,
x,
y,
copy=True,
max_iter=500,
n_components=1,
nkernel_components=100,
scale=True,
tol=1e-06,
kernel='linear',
preprocess=True,
gamma=None,
coef0=1,
degree=3):
super(MspmKernelPartialLeastSquares,
self).__init__(copy=copy,
max_iter=max_iter,
n_components=n_components,
scale=scale,
tol=tol)
self.x = x
self.y = y
self.kernel = kernel
self.preprocess = preprocess
self.gamma = gamma
self.coef0 = coef0
self.degree = degree
self.nkernel_components = nkernel_components
self.kX = ks.Nystroem(kernel=self.kernel,
gamma=self.gamma,
coef0=self.coef0,
degree=self.degree,
n_components=self.nkernel_components)
self.Xkernel = self.kX.fit_transform(x)
if self.preprocess:
self.Xscaler = preprocessing.StandardScaler().fit(self.Xkernel)
self.Xkernel = self.Xscaler.transform(self.Xkernel)
def _eval_search_params(params_builder):
search_params = {}
for p in params_builder['param_set']:
search_list = p['sp_list'].strip()
if search_list == '':
continue
param_name = p['sp_name']
if param_name.lower().endswith(NON_SEARCHABLE):
print("Warning: `%s` is not eligible for search and was "
"omitted!" % param_name)
continue
if not search_list.startswith(':'):
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
ev = safe_eval(search_list)
search_params[param_name] = ev
else:
# Have `:` before search list, asks for estimator evaluatio
safe_eval_es = SafeEval(load_estimators=True)
search_list = search_list[1:].strip()
# TODO maybe add regular express check
ev = safe_eval_es(search_list)
preprocessings = (
preprocessing.StandardScaler(), preprocessing.Binarizer(),
preprocessing.MaxAbsScaler(), preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(), feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(), feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS), skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0))
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessings[0:35])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessings[0:7])
elif obj == 'fs_all':
newlist.extend(preprocessings[7:14])
elif obj == 'decomp_all':
newlist.extend(preprocessings[14:25])
elif obj == 'k_appr_all':
newlist.extend(preprocessings[25:29])
elif obj == 'reb_all':
newlist.extend(preprocessings[30:35])
elif obj == 'imb_all':
newlist.extend(preprocessings[35:54])
elif type(obj) is int and -1 < obj < len(preprocessings):
newlist.append(preprocessings[obj])
elif hasattr(obj, 'get_params'): # user uploaded object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported estimator type: %r" % (obj))
search_params[param_name] = newlist
return search_params
tab_score = np.array([apply_svm_cross_validation(X_train, y_train, {'loss':'hinge', 'penalty':penalty, 'max_iter':1000, 'alpha':1e-9, 'tol':1e-3, 'random_state':123456, 'class_weight':None}) for penalty in tab_penalty])
print(tab_score)
plt.plot(tab_penalty, tab_score[:, 0])
plt.plot(tab_penalty, tab_score[:, 1])
plt.plot(tab_penalty, tab_score[:, 2])
plt.legend(["test_precision", "test_recall", "test_f1"])
plt.xlabel("Regularization Penalty")
plt.tight_layout(rect=[0, 0.03, 1, 0.95])
plt.savefig("cross_validation_svm_penalty.pdf", format="pdf")
plt.show()
feature_map_nystroem = kernel_approximation.Nystroem(kernel='poly', gamma=None, degree=2, n_components=200, random_state=123456)
feature_map_nystroem.fit(X_train)
X_train_new = feature_map_nystroem.transform(X_train)
X_test_new = feature_map_nystroem.transform(X_test)
clf = linear_model.SGDClassifier(loss='hinge', penalty='l2', max_iter=1000, alpha=1e-9, tol=1e-3, random_state=123456, class_weight=None, verbose=1)
clf.fit(X_train_new, y_train)
print("Train")
y_pred_train = clf.predict(X_train_new)
print("accuracy score = ", metrics.balanced_accuracy_score(y_train, y_pred_train))
precision, recall, fbeta_score, support = metrics.precision_recall_fscore_support(y_train, y_pred_train)
print("precision = ", precision[1])
print("recall = ", recall[1])
print("fbeta_score = ", fbeta_score[1])
print("support = ", support[1])
def get_search_params(params_builder):
search_params = {}
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
safe_eval_es = SafeEval(load_estimators=True)
for p in params_builder['param_set']:
search_p = p['search_param_selector']['search_p']
if search_p.strip() == '':
continue
param_type = p['search_param_selector']['selected_param_type']
lst = search_p.split(':')
assert (
len(lst) == 2
), "Error, make sure there is one and only one colon in search parameter input."
literal = lst[1].strip()
param_name = lst[0].strip()
if param_name:
if param_name.lower() == 'n_jobs':
sys.exit("Parameter `%s` is invalid for search." % param_name)
elif not param_name.endswith('-'):
ev = safe_eval(literal)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name] = ev
else:
# only for estimator eval, add `-` to the end of param
#TODO maybe add regular express check
ev = safe_eval_es(literal)
for obj in ev:
if 'n_jobs' in obj.get_params():
obj.set_params(n_jobs=N_JOBS)
if param_type == 'final_estimator_p':
search_params['estimator__' + param_name[:-1]] = ev
else:
search_params['preprocessing_' + param_type[5:6] + '__' +
param_name[:-1]] = ev
elif param_type != 'final_estimator_p':
#TODO regular express check ?
ev = safe_eval_es(literal)
preprocessors = [
preprocessing.StandardScaler(),
preprocessing.Binarizer(),
preprocessing.Imputer(),
preprocessing.MaxAbsScaler(),
preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(),
feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(),
feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS),
skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0)
]
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessors[0:36])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessors[0:8])
elif obj == 'fs_all':
newlist.extend(preprocessors[8:15])
elif obj == 'decomp_all':
newlist.extend(preprocessors[15:26])
elif obj == 'k_appr_all':
newlist.extend(preprocessors[26:30])
elif obj == 'reb_all':
newlist.extend(preprocessors[31:36])
elif obj == 'imb_all':
newlist.extend(preprocessors[36:55])
elif type(obj) is int and -1 < obj < len(preprocessors):
newlist.append(preprocessors[obj])
elif hasattr(obj, 'get_params'): # user object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported preprocessor type: %r" % (obj))
search_params['preprocessing_' + param_type[5:6]] = newlist
else:
sys.exit("Parameter name of the final estimator can't be skipped!")
return search_params
y,
test_size=.5,
random_state=42,
stratify=y)
log(f"Start Time: {(arrow.now() - lap_time).seconds // 60}:{(arrow.now() - lap_time).seconds % 60} minutes."
)
#sgd = svm.SVC()
logreg = linear_model.LogisticRegression()
logreg.fit(X_tr, y_tr)
y_pred = logreg.predict(X_te)
log(metrics.classification_report(y_te, y_pred))
# for _ in range(1):
# log(f"Start Time: {(arrow.now() - lap_time).seconds // 60}:{(arrow.now() - lap_time).seconds % 60} minutes.")
#
# GBC.fit(X_tr, y_tr)
# print('train done')
# log(f"Start Time: {(arrow.now() - lap_time).seconds // 60}:{(arrow.now() - lap_time).seconds % 60} minutes.")
#
# print(metrics.classification_report(GBC.predict(X_te),y_te))
# log(f"Start Time: {(arrow.now() - lap_time).seconds // 60}:{(arrow.now() - lap_time).seconds % 60} minutes.")
svm_sgd = linear_model.SGDClassifier(max_iter=500, tol=1e-3)
svm_sgd = pipeline.make_pipeline(
kernel_approximation.Nystroem(kernel='rbf'), svm_sgd)
svm_sgd.fit(X_tr, y_tr)
y_pred = svm_sgd.predict(X_te)
log(metrics.classification_report(y_te, y_pred))
for i in range(10):
sklearn.base.clone(reducer).fit_transform(x_pipe, y_pipe)
end = time.time()
duration = end - start
print("reducer", duration)
# 2
reducer.fit(x_pipe, y_pipe)
x_pipe = reducer.transform(x_pipe)
#Approximator NYS_kernel NYS_gamma NYS_n_components
#NYS, rbf, 100,
approximator = kernel_approximation.Nystroem()
approximator.set_params(kernel = 'rbf', gamma = None, n_components = 100)
start = time.time()
for i in range(10):
sklearn.base.clone(approximator).fit_transform(x_pipe, y_pipe)
end = time.time()
duration = end - start
print("approximator", duration)
# .24
approximator.fit(x_pipe, y_pipe)
x_pipe = approximator.transform(x_pipe)