def test_build_param_grid_set_estimator():
clf1 = SVC()
clf2 = LogisticRegression()
clf3 = SVC()
clf4 = SGDClassifier()
estimator = set_grid(Pipeline([('sel', set_grid(SelectKBest(), k=[2, 3])),
('clf', None)]),
clf=[
set_grid(clf1, kernel=['linear']), clf2,
set_grid(clf3, kernel=['poly'], degree=[2, 3]),
clf4
])
param_grid = [{
'clf': [clf1],
'clf__kernel': ['linear'],
'sel__k': [2, 3]
}, {
'clf': [clf3],
'clf__kernel': ['poly'],
'clf__degree': [2, 3],
'sel__k': [2, 3]
}, {
'clf': [clf2, clf4],
'sel__k': [2, 3]
}]
assert build_param_grid(estimator) == param_grid
def test_rnn(datafnc):
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from searchgrid import set_grid, build_param_grid
from noxer.sequences import PadSubsequence
X, y = datafnc()
X_train, X_test, y_train, y_test = train_test_split(X, y)
estimator = make_pipeline(
set_grid(GRUClassifier(n_neurons=64, n_layers=1, epochs=100),
alpha=[1e-4, 1e-3, 1e-2]))
estimator = make_pipeline(
set_grid(CNN1DClassifier(epochs=64),
alpha=[0.01],
n_layers=[1],
n_neurons=[32],
dropout=[0.2, 0.3, 0.4]))
model = GridSearchCV(estimator=estimator,
param_grid=build_param_grid(estimator),
verbose=1000,
cv=3,
n_jobs=1)
model.fit(X_train, y_train)
print(datafnc.__name__)
print(model.score(X_test, y_test))
def test_dnn_v_dnn(datafnc):
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from searchgrid import set_grid, build_param_grid
X, y = datafnc()
X_train, X_test, y_train, y_test = train_test_split(X, y)
estimator = make_pipeline(
StandardScaler(),
set_grid(PMLPClassifier(),
epochs=[2**i for i in range(1, 8)],
n_layers=list(range(1, 4)),
n_neurons=[2**i for i in range(1, 8)],
alpha=[1e-4, 1e-3, 1e-2]))
model = GridSearchCV(estimator=estimator,
param_grid=build_param_grid(estimator),
verbose=1000,
cv=3,
n_jobs=2)
mlp = GridSearchCV(
estimator=make_pipeline(
StandardScaler(),
MLPClassifier(),
),
param_grid={'mlpclassifier__max_iter': [2**i for i in range(1, 8)]},
verbose=1000,
cv=3)
model.fit(X_train, y_train)
mlp.fit(X_train, y_train)
print(datafnc.__name__)
print(model.score(X_test, y_test))
print(mlp.score(X_test, y_test))
models = [
set_grid(DecisionTreeClassifier(),
min_samples_split=[2**-i for i in range(1, 8)],
max_depth=list(range(1, 21))),
set_grid(LinearSVC(), C=np.logspace(-6, 6, num=20)),
]
estimator = set_grid(estimator,
model=[
set_grid(GradientBoostingClassifier(),
n_estimators=[2**i for i in range(1, 11)],
learning_rate=np.logspace(-4, 0, num=10)),
],
scaler=[StandardScaler()])
param_grid = build_param_grid(estimator)
gsearch = GridSearchCV(estimator=estimator,
param_grid=param_grid,
verbose=1,
cv=3,
n_jobs=-1)
model = gsearch
dummy = DummyClassifier(strategy='most_frequent')
model.fit(X_train, y_train)
dummy.fit(np.zeros((len(y_train), 1)), y_train)
print(model.best_params_)
print(model.score(X_test, y_test))
print(dummy.score(np.zeros((len(y_test), 1)), y_test))
def test_build_param_grid(estimator, param_grid):
assert build_param_grid(estimator) == param_grid