def test_simple_example_params(digits, param, expected):
X_train, X_test, y_train, y_test = digits
mod = BasicSGDClassifier(**{param: expected})
mod.fit(X_train, y_train)
preds = mod.predict(X_test)
acc = accuracy_score(y_test, preds)
if not (param == "max_iter" and expected <= 1):
assert acc >= 0.90
def fit_basic_sgd_classifier_with_crossvalidation(X, y):
basemod = BasicSGDClassifier()
cv = 5
param_grid = {'eta': [0.01, 0.1, 1.0], 'max_iter': [10]}
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, basemod, cv, param_grid)
return best_mod
def fit_basic_sgd_classifier(X, y):
"""Wrapper for `BasicSGDClassifier`.
Parameters
----------
X : 2d np.array
The matrix of features, one example per row.
y : list
The list of labels for rows in `X`.
Returns
-------
BasicSGDClassifier
A trained `BasicSGDClassifier` instance.
"""
mod = BasicSGDClassifier()
mod.fit(X, y)
return mod
def test_cross_validation_nlu(digits):
X_train, X_test, y_train, y_test = digits
param_grid = {'eta': [0.02, 0.03]}
mod = BasicSGDClassifier(max_iter=2)
best_mod = utils.fit_classifier_with_hyperparameter_search(
X_train, y_train, mod, cv=2, param_grid=param_grid)
def test_cross_validation_sklearn(digits):
X_train, X_test, y_train, y_test = digits
mod = BasicSGDClassifier(max_iter=5)
xval = cross_validate(mod, X_train, y_train, cv=2)
def test_hyperparameter_selection(digits):
X_train, X_test, y_train, y_test = digits
param_grid = {'eta': [0.02, 0.03]}
mod = BasicSGDClassifier(max_iter=5)
xval = RandomizedSearchCV(mod, param_grid, cv=2)
xval.fit(X_train, y_train)
def test_parameter_setting(param, expected):
mod = BasicSGDClassifier()
mod.set_params(**{param: expected})
result = getattr(mod, param)
assert result == expected
def test_params(param, expected):
mod = BasicSGDClassifier(**{param: expected})
result = getattr(mod, param)
assert result == expected