def train_project():
static_data = write_database()
project_train_manager = ProjectsTrainManager(static_data)
for _ in range(3):
# try:
project_train_manager.fit()
def test_fs_permute(cvs, X_test1, y_test1, cluster_dir):
logger = logging.getLogger('log_rbf_cnn_test.log')
logger.setLevel(logging.INFO)
handler = logging.FileHandler(
os.path.join(cluster_dir, 'log_rbf_cnn_test.log'), 'a')
handler.setLevel(logging.INFO)
# create a logging format
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)
# add the handlers to the logger
logger.addHandler(handler)
rated = None
static_data = write_database()
logger.info('Permutation Evaluation')
logger.info('/n')
method = 'svm'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
metrics_svm = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('before feature selection metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_svm)
fs = FS(cluster_dir, static_data['sklearn']['njobs'])
features = fs.fit(cvs)
logger.info('Number of variables %s', str(features.shape[0]))
for i in range(3):
cvs[i][0] = cvs[i][0][:, features]
cvs[i][2] = cvs[i][2][:, features]
cvs[i][4] = cvs[i][4][:, features]
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1[:, features])
metrics_svm = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('After feature selection metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_svm)
def prepare_data():
static_data = write_database()
project_data_manager = ProjectsDataManager(static_data, is_test=False)
nwp_response = project_data_manager.nwp_extractor()
if nwp_response == 'Done':
data_response = project_data_manager.create_datasets()
else:
raise RuntimeError('Something was going wrong with NWP extractor')
if data_response == 'Done':
project_data_manager.create_projects_relations()
else:
raise RuntimeError('Something was going wrong with data manager')
if hasattr(project_data_manager, 'data_eval'):
project_data_manager = ProjectsDataManager(static_data, is_test=True)
nwp_response = project_data_manager.nwp_extractor()
if nwp_response == 'Done':
_ = project_data_manager.create_datasets()
else:
raise RuntimeError(
'Something was going wrong with NWP extractor on evaluation')
def save(self):
f = open(os.path.join(self.path_model, 'manager' + '.pickle'), 'wb')
dict = {}
for k in self.__dict__.keys():
if k not in [
'logger', 'db', 'path_model', 'static_data', 'thres_act',
'thres_split', 'use_db'
]:
dict[k] = self.__dict__[k]
pickle.dump(dict, f)
f.close()
if __name__ == '__main__':
from util_database import write_database
from Fuzzy_clustering.ver_tf2.Projects_train_manager import ProjectsTrainManager
static_data = write_database()
project_manager = ProjectsTrainManager(static_data)
project_manager.initialize()
project_manager.create_datasets()
project_manager.create_projects_relations()
project = [
pr for pr in project_manager.group_static_data if pr['_id'] == 'Lach'
][0]
static_data = project['static_data']
model = ModelTrainManager(static_data['path_model'])
model.init(project['static_data'], project_manager.data_variables)
model.train()
def backup_project():
static_data = write_database()
project_backup_manager = ProjectsTrainManager(static_data)
project_backup_manager.clear_backup_projects()
def eval_project():
static_data = write_database()
project_eval_manager = ProjectsEvalManager(static_data)
project_eval_manager.evaluate()
def test_skopt(cvs, X_test1, y_test1, cluster_dir):
logger = logging.getLogger('log_rbf_cnn_test.log')
logger.setLevel(logging.INFO)
handler = logging.FileHandler(
os.path.join(cluster_dir, 'log_rbf_cnn_test.log'), 'a')
handler.setLevel(logging.INFO)
# create a logging format
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)
# add the handlers to the logger
logger.addHandler(handler)
rated = None
static_data = write_database()
logger.info('Scikit Optimize Evaluation')
logger.info('/n')
logger.info('/n')
logger.info('SVM train')
method = 'svm'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
if model_sklearn.istrained == True:
model_sklearn.istrained = False
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
logger.info('Best params')
logger.info(model_sklearn.best_params)
logger.info('Final mae %s', str(model_sklearn.acc_test))
logger.info('Final total %s', str(model_sklearn.accuracy))
metrics_svm = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('SVM metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_svm)
logger.info('finish train for model %s', model_sklearn.model_type)
logger.info('/n')
logger.info('nu-SVM train')
method = 'nusvm'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
if model_sklearn.istrained == True:
model_sklearn.istrained = False
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
logger.info('Best params')
logger.info(model_sklearn.best_params)
logger.info('Final mae %s', str(model_sklearn.acc_test))
logger.info('Final total %s', str(model_sklearn.accuracy))
metrics_svm = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('nu-SVM metricsv')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_svm)
logger.info('finish train for model %s', model_sklearn.model_type)
logger.info('/n')
logger.info('XGB train')
method = 'xgb'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
if model_sklearn.istrained == True:
model_sklearn.istrained = False
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
logger.info('Best params')
logger.info(model_sklearn.best_params)
logger.info('Final mae %s', str(model_sklearn.acc_test))
logger.info('Final total %s', str(model_sklearn.accuracy))
metrics_xgb = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('Xboost metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_xgb)
logger.info('finish train for model %s', model_sklearn.model_type)
logger.info('/n')
logger.info('RF train')
method = 'RF'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
if model_sklearn.istrained == True:
model_sklearn.istrained = False
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
logger.info('Best params')
logger.info(model_sklearn.best_params)
logger.info('Final mae %s', str(model_sklearn.acc_test))
logger.info('Final total %s', str(model_sklearn.accuracy))
metrics_mlp = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('RF metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_mlp)
logger.info('/n')
logger.info('finish train for model %s', model_sklearn.model_type)
logger.info('MLP train')
method = 'mlp'
model_sklearn = sklearn_model(cluster_dir, rated, method,
static_data['sklearn']['njobs'])
if model_sklearn.istrained == True:
model_sklearn.istrained = False
model_sklearn.train(cvs)
pred = model_sklearn.predict(X_test1)
logger.info('Best params')
logger.info(model_sklearn.best_params)
logger.info('Final mae %s', str(model_sklearn.acc_test))
logger.info('Final total %s', str(model_sklearn.accuracy))
metrics_mlp = model_sklearn.compute_metrics(pred, y_test1, rated)
logger.info('MLP metrics')
logger.info('sse, %s rms %s, mae %s, mse %s', *metrics_mlp)
logger.info('finish train for model %s', model_sklearn.model_type)
logger.info('/n')