Skip to content

Commit

Permalink
refactor experiments
Browse files Browse the repository at this point in the history
  • Loading branch information
v1docq committed Aug 8, 2023
1 parent eb77c61 commit 9181266
Show file tree
Hide file tree
Showing 4 changed files with 103 additions and 64 deletions.
4 changes: 2 additions & 2 deletions fedot_ind/api/exper.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,8 @@
# 'wavelet_basis',
'data_driven_basis'
],
tuning_iterations=30,
tuning_timeout=15.0,
tuning_iterations=10,
tuning_timeout=10.0,
use_cache=False,
timeout=10,
n_jobs=6,
Expand Down
134 changes: 87 additions & 47 deletions fedot_ind/api/multi_ts_example.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,8 @@
from matplotlib import pyplot as plt

from fedot_ind.core.architecture.preprocessing.DatasetLoader import DataLoader
from fedot_ind.core.models.signal.RecurrenceExtractor import RecurrenceExtractor
from fedot_ind.core.models.statistical.StatsExtractor import StatsExtractor
from fedot_ind.core.models.recurrence.RecurrenceExtractor import RecurrenceExtractor
from fedot_ind.core.models.quantile.quantile_extractor import QuantileExtractor
from fedot_ind.core.operation.transformation.basis.data_driven import DataDrivenBasisImplementation
from fedot_ind.core.operation.transformation.basis.fourier import FourierBasisImplementation
from sklearn.decomposition import PCA
Expand All @@ -33,36 +33,45 @@ def init_input(X, y):
return input_data


def prepare_features(dataset_name, pca_n_components: float = 0.9):
def prepare_features(dataset_name,
pca_n_components: float = 0.95,
feature_generator: list = ['statistical'],
reduce_dimension: bool = False):
train_data, test_data = DataLoader(dataset_name=dataset_name).load_data()

train_target = np.array([float(i) for i in train_data[1]])
test_target = np.array([float(i) for i in test_data[1]])
train_input_data = init_input(train_data[0], train_target)
test_input_data = init_input(test_data[0], test_target)

# extractor = StatsExtractor({'window_mode': False,
# 'window_size': 10,
# 'var_threshold': 0})
extractor = RecurrenceExtractor({'window_mode': False,
'min_signal_ratio': 0.3,
'max_signal_ratio': 0.8,
'rec_metric': 'euclidean'
})

pca = PCA(n_components=pca_n_components,
svd_solver='full')

extracted_features_train = extractor.transform(train_input_data)
train_size = extracted_features_train.features.shape
train_features = extracted_features_train.features.reshape(train_size[0], train_size[1] * train_size[2])
train_features = pca.fit_transform(train_features)

extracted_features_test = extractor.transform(test_input_data)
test_size = extracted_features_test.features.shape
test_features = extracted_features_test.features.reshape(test_size[0], test_size[1] * test_size[2])
test_features = pca.transform(test_features)
return train_features, train_target, test_features, test_target
generator_dict = {'statistical': QuantileExtractor({'window_mode': False,
'window_size': 10,
'var_threshold': 0}),
'reccurence': RecurrenceExtractor({'window_mode': True,
'min_signal_ratio': 0.7,
'max_signal_ratio': 0.9,
'rec_metric': 'cosine'
})
}
train_features_list, test_features_list = [], []
for extractor in feature_generator:
extractor = generator_dict[extractor]
extracted_features_train = extractor.transform(train_input_data)
train_size = extracted_features_train.predict.shape
train_features = extracted_features_train.predict

extracted_features_test = extractor.transform(test_input_data)
test_size = extracted_features_test.predict.shape
test_features = extracted_features_test.predict

if reduce_dimension:
pca = PCA(n_components=pca_n_components,
svd_solver='full')
train_features = pca.fit_transform(train_features)
test_features = pca.transform(test_features)
train_features_list.append(train_features), test_features_list.append(test_features)

return train_features_list, train_target, test_features_list, test_target


def calculate_metric(test_target, labels):
Expand All @@ -81,17 +90,17 @@ def calculate_metric(test_target, labels):
return df


def evaluate_baseline(train_features, train_target, test_features, test_target):
def evaluate_baseline(train, train_target, test, test_target):
node_scaling = PipelineNode('scaling')
node_rfr = PipelineNode('lasso', nodes_from=[node_scaling])
baseline_model = Pipeline(node_rfr)
input_fit = InputData(idx=np.arange(len(train_features)),
features=train_features,
input_fit = InputData(idx=np.arange(len(train)),
features=train,
target=train_target.reshape(-1, 1),
task=Task(TaskTypesEnum.regression),
data_type=DataTypesEnum.image)
input_predict = InputData(idx=np.arange(len(test_features)),
features=test_features,
input_predict = InputData(idx=np.arange(len(test)),
features=test,
target=test_target.reshape(-1, 1),
task=Task(TaskTypesEnum.regression),
data_type=DataTypesEnum.image)
Expand All @@ -111,21 +120,34 @@ def evaluate_baseline(train_features, train_target, test_features, test_target):

if __name__ == "__main__":
dataset_list = [
'AppliancesEnergy',
# 'Gazprom',
# 'AppliancesEnergy',
# 'AustraliaRainfall',
# 'BeijingPM10Quality',
# 'BeijingPM25Quality',
# 'BenzeneConcentration',
# 'BeijingPM10Quality',
#'BeijingPM25Quality',
#'BenzeneConcentration',
# 'HouseholdPowerConsumption1',
'HouseholdPowerConsumption2',
# 'IEEEPPG',
# 'FloodModeling1',
# 'FloodModeling2',
# 'FloodModeling3'
# 'LiveFuelMoistureContent',
#'HouseholdPowerConsumption2',
#'IEEEPPG',
#'FloodModeling1',
'FloodModeling2',
'FloodModeling3'
'LiveFuelMoistureContent',
'BIDMC32HR',
'BIDMC32RR',
'BIDMC32SpO2'
'BIDMC32SpO2',
'DailyOilGasPrices',
'ElectricityPredictor',
'OccupancyDetectionLight',
'SolarRadiationAndalusia',
'TetuanEnergyConsumption',
'WindTurbinePower',
'ElectricMotorTemperature',
'LPGasMonitoringHomeActivity',
'GasSensorArrayAcetone',
'GasSensorArrayEthanol',
'WaveTensionData'

]
ten_minutes = range(0, 3, 1)
one_hour = ['1hr']
Expand All @@ -135,17 +157,35 @@ def evaluate_baseline(train_features, train_target, test_features, test_target):
except Exception:
_ = 1

train_features, train_target, test_features, test_target = prepare_features(dataset_name=dataset_name)
metric_df_baseline = evaluate_baseline(train_features, train_target, test_features, test_target)
train_features, train_target, test_features, test_target = prepare_features(dataset_name=dataset_name,
reduce_dimension=False,
feature_generator=[
'statistical'
# ,'reccurence'
])
if len(train_features) > 1:
concatenate_train = np.concatenate(train_features, axis=1)
concatenate_test = np.concatenate(test_features, axis=1)
train_features.append(concatenate_train)
test_features.append(concatenate_test)
else:
concatenate_train = train_features[0]
concatenate_test = test_features[0]

for train, test in zip(train_features, test_features):
metric_df_baseline = evaluate_baseline(train, train_target, test, test_target)
print(metric_df_baseline)
metric_df_baseline.to_csv(f'./{dataset_name}/baseline_metrics.csv')

for run in ten_minutes:
for run in one_hour:
predictor = Fedot(problem='regression',
timeout=10,
metric='rmse',
timeout=60,
early_stopping_timeout=30,
logging_level=20,
n_jobs=6)
model = predictor.fit(features=train_features, target=train_target)
labels = predictor.predict(features=test_features)
model = predictor.fit(features=concatenate_train, target=train_target)
labels = predictor.predict(features=concatenate_test)
metric_df = calculate_metric(test_target, labels)
metric_df.to_csv(f'./{dataset_name}/metrics_run_{run}.csv')
pipeline = predictor.current_pipeline
Expand Down
4 changes: 2 additions & 2 deletions fedot_ind/api/rank_experiment.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
from sklearn.metrics import f1_score, roc_auc_score
from fedot_ind.api.main import FedotIndustrial
from fedot_ind.core.architecture.preprocessing.DatasetLoader import DataLoader
from fedot_ind.core.models.statistical.StatsExtractor import StatsExtractor
from fedot_ind.core.models.quantile.quantile_extractor import QuantileExtractor
from fedot_ind.core.operation.transformation.basis.data_driven import DataDrivenBasisImplementation
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import StandardScaler
Expand Down Expand Up @@ -115,7 +115,7 @@ def evaluate_model(feature_train, bss, test_data, model_type: str = 'MLP'):
# 'DistalPhalanxOutlineCorrect'
]

stats_model = StatsExtractor({'window_mode': False, 'window_size': 5, 'use_cache': False, 'n_jobs': 4})
stats_model = QuantileExtractor({'window_mode': False, 'window_size': 5, 'use_cache': False, 'n_jobs': 4})
for group in [
datasets_bad_f1,
datasets_good_f1,
Expand Down
25 changes: 12 additions & 13 deletions fedot_ind/core/operation/transformation/DataTransformer.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -191,24 +191,23 @@ class TSTransformer:
def __init__(self, time_series, min_signal_ratio, max_signal_ratio, rec_metric):
self.time_series = time_series
self.recurrence_matrix = None
self.threshold_baseline = [1, 5, 10, 15, 20, 25, 30]
self.threshold_baseline = [0.95, 0.7] #cosine
self.min_signal_ratio = min_signal_ratio
self.max_signal_ratio = max_signal_ratio
self.rec_metric = rec_metric

def ts_to_recurrence_matrix(self,
eps=0.10,
steps=None):
distance_matrix = pdist(metric=self.rec_metric, X=self.time_series[:, None])
distance_matrix = np.floor(distance_matrix / eps)
distance_matrix, steps = self.binarization(distance_matrix, threshold=steps)
distance_matrix[distance_matrix > steps] = steps
threshold=None):
distance_matrix = pdist(metric=self.rec_metric, X=self.time_series.T)
distance_matrix = np.ones(shape=distance_matrix.shape[0])-distance_matrix
distance_matrix = self.binarization(distance_matrix, threshold=threshold)
self.recurrence_matrix = squareform(distance_matrix)
return self.recurrence_matrix

def binarization(self, distance_matrix, threshold):
best_threshold_flag = False
signal_ratio_list = []
reccurence_matrix = None
if threshold is None:
for threshold_baseline in self.threshold_baseline:
threshold = threshold_baseline
Expand All @@ -219,20 +218,20 @@ def binarization(self, distance_matrix, threshold):

if self.min_signal_ratio < signal_ratio < self.max_signal_ratio:
best_ratio = signal_ratio
distance_matrix = tmp_array
reccurence_matrix = tmp_array
best_threshold_flag = True
if signal_ratio > best_ratio:
distance_matrix = tmp_array
reccurence_matrix = tmp_array
else:
signal_ratio_list.append(abs(self.max_signal_ratio - signal_ratio))

del tmp_array

if not best_threshold_flag:
threshold = self.threshold_baseline[signal_ratio_list.index(min(signal_ratio_list))]
distance_matrix[distance_matrix < threshold] = 0.0
distance_matrix[distance_matrix >= threshold] = 1.0
return distance_matrix, threshold
distance_matrix[distance_matrix < self.threshold_baseline[0]] = 0.0
distance_matrix[distance_matrix >= self.threshold_baseline[0]] = 1.0
reccurence_matrix = distance_matrix
return reccurence_matrix

def get_recurrence_metrics(self):
if self.recurrence_matrix is None:
Expand Down

0 comments on commit 9181266

Please sign in to comment.