def gaussian_nb_model_tpe():
estim = HyperoptEstimator(classifier=gaussian_nb('my_clf'),
preprocessing=[pca('my_pca')],
algo=tpe.suggest,
max_evals=150,
trial_timeout=60,
verbose=0)
estim.fit(x_train, y_train)
print("f1score", f1_score(estim.predict(x_test), y_test))
print("accuracy score", accuracy_score(estim.predict(x_test), y_test))
print(estim.best_model())
def bench_classifiers(name):
classifiers = [
ada_boost(name + '.ada_boost'), # boo
gaussian_nb(name + '.gaussian_nb'), # eey
knn(name + '.knn', sparse_data=True), # eey
linear_discriminant_analysis(name + '.linear_discriminant_analysis', n_components=1), # eey
random_forest(name + '.random_forest'), # boo
sgd(name + '.sgd') # eey
]
if xgboost:
classifiers.append(xgboost_classification(name + '.xgboost')) # boo
return hp.choice('%s' % name, classifiers)
def tpe_classifier(name='clf'):
linear_svc_space = hp.choice('liblinear_combination',
[{'penalty': "l1", 'loss': "squared_hinge", 'dual': False},
{'penalty': "l2", 'loss': "hinge", 'dual': True},
{'penalty': "l2", 'loss': "squared_hinge", 'dual': True},
{'penalty': "l2", 'loss': "squared_hinge", 'dual': False}])
return hp.choice(name,
[gaussian_nb('hpsklearn_gaussian_nb'),
liblinear_svc('hpsklearn_liblinear_svc',
C=hp.choice('hpsklearn_liblinear_svc_c',
[1e-4, 1e-3, 1e-2, 1e-1, 0.5, 1., 5., 10., 15., 20., 25.]),
loss=linear_svc_space['loss'],
penalty=linear_svc_space['penalty'],
dual=linear_svc_space['dual'],
tol=hp.choice('hpsklearn_liblinear_svc_tol', [1e-5, 1e-4, 1e-3, 1e-2, 1e-1])
),
decision_tree('decision_tree',
criterion=hp.choice('decision_tree_criterion', ["gini", "entropy"]),
max_depth=hp.randint('decision_tree_max_depth', 10) + 1,
min_samples_split=hp.randint('decision_tree_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('decision_tree_min_samples_leaf', 20) + 1),
knn('knn',
n_neighbors=hp.randint('knn_n', 100) + 1,
weights=hp.choice('knn_weights', ['uniform', 'distance']),
p=hp.choice('knn_p', [1, 2])),
extra_trees('et',
n_estimators=100,
criterion=hp.choice('et_criterion', ["gini", "entropy"]),
max_features=hp.randint('et_max_features', 20) * 0.05 + 0.05,
min_samples_split=hp.randint('et_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('et_min_samples_leaf', 20) + 1,
bootstrap=hp.choice('et_bootstrap', [True, False])),
random_forest('rf',
n_estimators=100,
criterion=hp.choice('rf_criterion', ["gini", "entropy"]),
max_features=hp.randint('rf_max_features', 20) * 0.05 + 0.05,
min_samples_split=hp.randint('rf_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('rf_min_samples_leaf', 20) + 1,
bootstrap=hp.choice('rf_bootstrap', [True, False])),
gradient_boosting('gb',
n_estimators=100,
learning_rate=hp.choice('gb_lr', [1e-3, 1e-2, 1e-1, 0.5, 1.]),
max_depth=hp.randint('gb_max_depth', 10) + 1,
min_samples_split=hp.randint('gb_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('gb_min_samples_leaf', 20) + 1,
subsample=hp.randint('gb_subsample', 20) * 0.05 + 0.05,
max_features=hp.randint('gb_max_features', 20) * 0.05 + 0.05,
)
])
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:].values, df_train.iloc[:, 0].values
X_test, y_test = df_test.iloc[:, 2:].values, df_test.iloc[:, 0].values
estim = HyperoptEstimator(classifier=gaussian_nb('myNB'),
algo=tpe.suggest,
max_evals=150,
trial_timeout=120,
verbose=True)
estim.fit(X_train, y_train)
print("\n\n{}\n\n".format(estim.score(X_test, y_test)))
print("\n\n{}\n\n".format(estim.best_model()))
Y_val_mini.sum(axis=0),
Y_test_mini.sum(axis=0)
])))
print(seed_val)
print("\ndata is loaded - next step > model testing\n")
n_job = 6
select_classes = [0, 1, 2, 3, 4, 5]
val_dist = X_val_mini.shape[0] / X_train_mini.shape[0]
name = 'my_est_oVa'
tic_mod_all = time.time()
select_alg = [
ada_boost(name + '.ada_boost'),
gaussian_nb(name + '.gaussian_nb'),
knn(name + '.knn', sparse_data=True),
linear_discriminant_analysis(name +
'.linear_discriminant_analysis',
n_components=1),
random_forest(name + '.random_forest'),
sgd(name + '.sgd'),
xgboost_classification(name + '.xgboost')
]
# fitting models
estim_one_vs_rest = dict()
# scoring models
algo_scoring = dict()
save_score_path = r'C:/Users/anden/PycharmProjects/NovelEEG/results'
for alg in [select_alg[args.index]]:
print("\ndata is loaded - next step > model testing\n")
n_job = 6
select_classes = [0, 1, 2, 3, 4, 5]
val_dist = X_val_mini.shape[0] / X_train_mini.shape[0]
name = 'my_est_oVa'
tic_mod_all = time.time()
#select_alg = [ada_boost(name + '.ada_boost'),
# gaussian_nb(name + '.gaussian_nb'),
# knn(name + '.knn', sparse_data=True),
# linear_discriminant_analysis(name + '.linear_discriminant_analysis', n_components=1),
# random_forest(name + '.random_forest'),
# sgd(name + '.sgd'),
# xgboost_classification(name + '.xgboost')]
select_alg = [gaussian_nb(name + '.gaussian_nb')]
# fitting models
estim_one_vs_rest = dict()
# scoring models
algo_scoring = dict()
save_score_path = os.getcwd() + r'/tmp'
for alg in select_alg:
tic_mod = time.time()
print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"running on %s" % (alg.name + '.one_V_all'),
"\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
clf_method = one_vs_rest(str(alg.name + '.one_V_all'),
estimator=alg,
n_jobs=n_job)
estim_one_vs_rest[alg.name + '.one_V_all'] = HyperoptEstimator(