def quantile_transform():
a, b = _randint(100, 1000), _randint(1000, 1e5)
c = _randchoice(['normal', 'uniform'])
scaler = QuantileTransformer(n_quantiles=a,
output_distribution=c,
subsample=b)
tmp = str(a) + "_" + str(b) + "_" + c + "_" + QuantileTransformer.__name__
return scaler, tmp
def KNN():
a = _randint(2, 25)
b = _randchoice(['uniform', 'distance'])
c = _randchoice(['minkowski', 'chebyshev'])
if c == 'minkowski':
d = _randint(1, 15)
else:
d = 2
model = KNeighborsClassifier(n_neighbors=a,
weights=b,
algorithm='auto',
p=d,
metric=c,
n_jobs=-1)
tmp = str(a) + "_" + b + "_" + c + "_" + str(
d) + "_" + KNeighborsClassifier.__name__
return model, tmp
def polynomial():
a = _randint(2, 10)
b = _randchoice([True, False])
c = _randchoice([True, False])
scaler = PolynomialFeatures(degree=a, interaction_only=b, include_bias=c)
tmp = str(a) + "_" + str(b) + "_" + str(
c) + "_" + PolynomialFeatures.__name__
return scaler, tmp
def LDA_():
a, b = _randint(100, 1000), _randint(1, 10)
vect = CountVectorizer(max_df=a, min_df=b)
a, b, c = _randint(10, 50), _randuniform(0, 1), _randuniform(0, 1)
d, e, f = _randuniform(0.51, 1.0), _randuniform(1, 50), _randchoice(
[150, 180, 210, 250, 300])
lda = LatentDirichletAllocation(n_components=a,
doc_topic_prior=b,
topic_word_prior=c,
learning_decay=d,
learning_offset=e,
batch_size=f,
max_iter=100,
learning_method='online')
tmp = str(a) + "_" + str(b) + "_" + str(c) + "_" + str(d) + "_" + str(
e) + "_" + str(f) + "_" + LatentDirichletAllocation.__name__
return [vect, lda], tmp
def LR():
a = _randchoice(['l1', 'l2'])
b = _randuniform(0.0, 0.1)
c = _randint(1, 500)
model = LogisticRegression(penalty=a,
tol=b,
C=float(c),
solver='liblinear',
multi_class='warn')
tmp = a + "_" + str(round(
b, 5)) + "_" + str(c) + "_" + LogisticRegression.__name__
return model, tmp
def SVM():
# from sklearn.preprocessing import MinMaxScaler
# scaling = MinMaxScaler(feature_range=(-1, 1)).fit(train_data)
# train_data = scaling.transform(train_data)
# test_data = scaling.transform(test_data)
a = _randint(1, 500)
b = _randchoice(['linear', 'poly', 'rbf', 'sigmoid'])
c = _randint(2, 10)
d = _randuniform(0.0, 1.0)
e = _randuniform(0.0, 0.1)
f = _randuniform(0.0, 0.1)
model = SVC(C=float(a),
kernel=b,
degree=c,
gamma=d,
coef0=e,
tol=f,
cache_size=20000)
tmp = str(a) + "_" + b + "_" + str(c) + "_" + str(round(d, 5)) + "_" + str(
round(e, 5)) + "_" + str(round(f, 5)) + "_" + SVC.__name__
return model, tmp
def RF():
a = _randint(50, 150)
b = _randchoice(['gini', 'entropy'])
c = _randuniform(0.0, 1.0)
model = RandomForestClassifier(n_estimators=a,
criterion=b,
min_samples_split=c,
max_features=None,
min_impurity_decrease=0.0,
n_jobs=-1)
tmp = str(a) + "_" + b + "_" + str(round(
c, 5)) + "_" + RandomForestClassifier.__name__
return model, tmp
def robust_scaler():
a, b = _randint(0, 50), _randint(51, 100)
scaler = RobustScaler(quantile_range=(a, b))
tmp = str(a) + "_" + str(b) + "_" + RobustScaler.__name__
return scaler, tmp
def TF():
a, b = _randint(100, 1000), _randint(1, 10)
vect = CountVectorizer(max_df=a, min_df=b)
tmp = str(a) + "_" + str(b) + "_" + CountVectorizer.__name__
return vect, tmp
def TFIDF():
a, b = _randint(100, 1000), _randint(1, 10)
c = _randchoice(['l1', 'l2', None])
vect = TfidfVectorizer(max_df=a, min_df=b, norm=c)
tmp = str(a) + "_" + str(b) + "_" + str(c) + "_" + TfidfVectorizer.__name__
return vect, tmp