def sgd( name, loss=None, #default - 'hinge' penalty=None, #default - 'l2' alpha=None, #default - 0.0001 l1_ratio=None, #default - 0.15, must be within [0, 1] fit_intercept=None, #default - True n_iter=None, #default - 5 shuffle=None, #default - False random_state=None, #default - None epsilon=None, n_jobs=1, #default - 1 (-1 means all CPUs) learning_rate=None, #default - 'invscaling' eta0=None, #default - 0.01 power_t=None, #default - 0.5 class_weight=None, warm_start=False, verbose=False, ): def _name(msg): return '%s.%s_%s' % (name, 'sgd', msg) rval = scope.sklearn_SGDClassifier( loss=hp.pchoice(_name('loss'), [(0.25, 'hinge'), (0.25, 'log'), (0.25, 'modified_huber'), (0.05, 'squared_hinge'), (0.05, 'perceptron'), (0.05, 'squared_loss'), (0.05, 'huber'), (0.03, 'epsilon_insensitive'), (0.02, 'squared_epsilon_insensitive')]) if loss is None else loss, penalty=hp.pchoice(_name('penalty'), [(0.40, 'l2'), (0.35, 'l1'), (0.25, 'elasticnet')]) if penalty is None else penalty, alpha=hp.loguniform(_name('alpha'), np.log(1e-7), np.log(1)) if alpha is None else alpha, l1_ratio=hp.uniform(_name('l1_ratio'), 0, 1) if l1_ratio is None else l1_ratio, fit_intercept=hp.pchoice(_name('fit_intercept'), [(0.8, True), (0.2, False)]) if fit_intercept is None else fit_intercept, learning_rate='invscaling' if learning_rate is None else learning_rate, eta0=hp.loguniform(_name('eta0'), np.log(1e-5), np.log(1e-1)) if eta0 is None else eta0, power_t=hp.uniform(_name('power_t'), 0, 1) if power_t is None else power_t, n_jobs=n_jobs, verbose=verbose, ) return rval
def sgd(name, loss=None, # default - 'hinge' penalty=None, # default - 'l2' alpha=None, # default - 0.0001 l1_ratio=None, # default - 0.15, must be within [0, 1] fit_intercept=True, # default - True n_iter=5, # default - 5 shuffle=True, # default - True random_state=None, # default - None epsilon=None, n_jobs=1, # default - 1 (-1 means all CPUs) learning_rate=None, # default - 'optimal' eta0=None, # default - 0.0 power_t=None, # default - 0.5 class_weight='choose', warm_start=False, verbose=False): def _name(msg): return '%s.%s_%s' % (name, 'sgdc', msg) rval = scope.sklearn_SGDClassifier( loss=hp.pchoice(_name('loss'), [ (0.25, 'hinge'), (0.25, 'log'), (0.25, 'modified_huber'), (0.05, 'squared_hinge'), (0.05, 'perceptron'), (0.05, 'squared_loss'), (0.05, 'huber'), (0.03, 'epsilon_insensitive'), (0.02, 'squared_epsilon_insensitive') ]) if loss is None else loss, penalty=_sgd_penalty(_name('penalty')) if penalty is None else penalty, alpha=_sgd_alpha(_name('alpha')) if alpha is None else alpha, l1_ratio=(_sgd_l1_ratio(_name('l1ratio')) if l1_ratio is None else l1_ratio), fit_intercept=fit_intercept, n_iter=n_iter, learning_rate=(_sgdc_learning_rate(_name('learning_rate')) if learning_rate is None else learning_rate), eta0=_sgd_eta0(_name('eta0')) if eta0 is None else eta0, power_t=_sgd_power_t(_name('power_t')) if power_t is None else power_t, class_weight=(_class_weight(_name('clsweight')) if class_weight == 'choose' else class_weight), n_jobs=n_jobs, verbose=verbose, random_state=_random_state(_name('rstate'), random_state), ) return rval
def sgd(name, loss=None, #default - 'hinge' penalty=None, #default - 'l2' alpha=None, #default - 0.0001 l1_ratio=None, #default - 0.15, must be within [0, 1] fit_intercept=None, #default - True n_iter=None, #default - 5 shuffle=None, #default - False random_state=None, #default - None epsilon=None, n_jobs=1, #default - 1 (-1 means all CPUs) learning_rate=None, #default - 'invscaling' eta0=None, #default - 0.01 power_t=None, #default - 0.5 class_weight=None, warm_start=False, verbose=False, ): def _name(msg): return '%s.%s_%s' % (name, 'sgd', msg) rval = scope.sklearn_SGDClassifier( loss=hp.pchoice( _name('loss'), [ (0.25, 'hinge'), (0.25, 'log'), (0.25, 'modified_huber'), (0.05, 'squared_hinge'), (0.05, 'perceptron'), (0.05, 'squared_loss'), (0.05, 'huber'), (0.03, 'epsilon_insensitive'), (0.02, 'squared_epsilon_insensitive') ] ) if loss is None else loss, penalty=hp.pchoice( _name('penalty'), [ (0.40, 'l2'), (0.35, 'l1'), (0.25, 'elasticnet') ] ) if penalty is None else penalty, alpha=hp.loguniform( _name('alpha'), np.log(1e-7), np.log(1)) if alpha is None else alpha, l1_ratio=hp.uniform( _name('l1_ratio'), 0, 1 ) if l1_ratio is None else l1_ratio, fit_intercept=hp.pchoice( _name('fit_intercept'), [ (0.8, True), (0.2, False) ]) if fit_intercept is None else fit_intercept, learning_rate='invscaling' if learning_rate is None else learning_rate, eta0=hp.loguniform( _name('eta0'), np.log(1e-5), np.log(1e-1)) if eta0 is None else eta0, power_t=hp.uniform( _name('power_t'), 0, 1) if power_t is None else power_t, n_jobs=n_jobs, verbose=verbose, ) return rval