from sklearn.linear_model import LogisticRegression
from skrobot.core import Experiment
from skrobot.tasks import HyperParametersSearchCrossValidationTask
######### Initialization Code
random_seed = 42
lr_estimator = LogisticRegression(solver='liblinear', random_state=random_seed)
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').build()
# Run Hyperparameters Search Task
results = experiment.run(
HyperParametersSearchCrossValidationTask(
estimator=lr_estimator,
search_params={
"C": [1.e-01, 1.e+00, 1.e+01],
"penalty": ["l1", "l2"]
},
train_data_set_file_path=path.join('data',
'money-laundering-data-train.csv'),
random_seed=random_seed).grid_search().custom_folds(
folds_file_path=path.join('data', 'money-laundering-folds.csv')))
# Print in-memory results
test_data_set_file_path = path.join('data','money-laundering-data-test.csv')
new_data_set_file_path = path.join('data','money-laundering-data-new.csv')
folds_file_path = path.join('data', 'money-laundering-folds.csv')
random_seed = 42
lr_estimator = LogisticRegression(solver='liblinear', random_state=random_seed)
search_params = { "C" : [1.e-01, 1.e+00, 1.e+01], "penalty" : [ "l1", "l2" ] }
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(__file__).set_experimenter('echatzikyriakidis').build()
# Run Feature Selection Task
features_columns = experiment.run(FeatureSelectionCrossValidationTask (estimator=lr_estimator,
train_data_set_file_path=train_data_set_file_path,
random_seed=random_seed).custom_folds(folds_file_path=folds_file_path))
# Run Hyperparameters Search Task
hyperparameters_search_results = experiment.run(HyperParametersSearchCrossValidationTask (estimator=lr_estimator,
search_params=search_params,
train_data_set_file_path=train_data_set_file_path,
feature_columns=features_columns,
random_seed=random_seed).random_search().custom_folds(folds_file_path=folds_file_path))
# Run Evaluation Task
search_params = {
'classifier__max_iter': [20, 50, 80],
'classifier__alpha': [0.00001, 0.000001],
'classifier__penalty': ['l2', 'elasticnet'],
"vectorizer__stop_words": ["english", None],
"vectorizer__ngram_range": [(1, 1), (1, 2)],
"vectorizer__max_df": [0.5, 0.75, 1.0],
"tfidf__use_idf": [True, False],
"tfidf__norm": ['l1', 'l2'],
"feature_selection__percentile": [70, 60, 50]
}
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').build()
# Run Hyperparameters Search Task
hyperparameters_search_results = experiment.run(
HyperParametersSearchCrossValidationTask(
estimator=pipe,
search_params=search_params,
train_data_set_file_path=train_data_set_file_path,
field_delimiter=field_delimiter,
random_seed=random_seed).random_search().stratified_folds(
total_folds=5, shuffle=True))
# Run Evaluation Task
evaluation_results = experiment.run(
EvaluationCrossValidationTask(
estimator=pipe,
from os import path
from sklearn.linear_model import LogisticRegression
from skrobot.core import Experiment
from skrobot.tasks import FeatureSelectionCrossValidationTask
######### Initialization Code
random_seed = 42
lr_estimator = LogisticRegression(solver='liblinear', random_state=random_seed)
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').build()
# Run Feature Selection Task
features_columns = experiment.run(
FeatureSelectionCrossValidationTask(
estimator=lr_estimator,
train_data_set_file_path=path.join('data',
'money-laundering-data-train.csv'),
random_seed=random_seed).custom_folds(
folds_file_path=path.join('data', 'money-laundering-folds.csv')))
# Print in-memory results
print(features_columns)
from skrobot.tasks import TrainTask
######### Initialization Code
random_seed = 42
lr_estimator = LogisticRegression(solver='liblinear', random_state=random_seed)
######### skrobot Code
# Define a Notifier (This is optional and you can implement any notifier you want, e.g. for Slack / Trello / Discord)
class ConsoleNotifier(BaseNotifier):
def notify(self, message):
print(message)
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').set_notifier(
ConsoleNotifier()).build()
# Run Train Task
results = experiment.run(
TrainTask(estimator=lr_estimator,
train_data_set=path.join('data',
'money-laundering-data-train.csv'),
random_seed=random_seed))
# Print in-memory results
print(results['estimator'])
"preprocessor__numerical_transformer__imputer__strategy":
["mean", "median"]
}
######### skrobot Code
# Define a Notifier (This is optional and you can implement any notifier you want, e.g. for Slack / Trello / Discord)
class ConsoleNotifier(BaseNotifier):
def notify(self, message):
print(message)
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').set_notifier(
ConsoleNotifier()).build()
# Run Feature Selection Task
features_columns = experiment.run(
FeatureSelectionCrossValidationTask(
estimator=classifier,
train_data_set_file_path=train_data_set_file_path,
preprocessor=preprocessor,
min_features_to_select=4,
id_column=id_column,
label_column=label_column,
random_seed=random_seed).stratified_folds(total_folds=5, shuffle=True))
pipe = Pipeline(
steps=[('preprocessor',
from sklearn.linear_model import LogisticRegression
from skrobot.core import Experiment
from skrobot.tasks import EvaluationCrossValidationTask
######### Initialization Code
random_seed = 42
lr_estimator = LogisticRegression(solver='liblinear', random_state=random_seed)
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(__file__).set_experimenter('echatzikyriakidis').build()
# Run Evaluation Task
results = experiment.run(EvaluationCrossValidationTask(estimator=lr_estimator,
train_data_set_file_path=path.join('data','money-laundering-data-train.csv'),
test_data_set_file_path=path.join('data','money-laundering-data-test.csv'),
export_classification_reports=True,
export_confusion_matrixes=True,
export_pr_curves=True,
export_roc_curves=True,
export_false_positives_reports=True,
export_false_negatives_reports=True,
export_also_for_train_folds=True,
random_seed=random_seed).custom_folds(folds_file_path=path.join('data','money-laundering-folds.csv')))
# Print in-memory results
["mean", "median"]
}
######### skrobot Code
# Create a Notifier
notifier = EmailNotifier(email_subject="skrobot notification",
sender_account=os.environ['EMAIL_SENDER_ACCOUNT'],
sender_password=os.environ['EMAIL_SENDER_PASSWORD'],
smtp_server=os.environ['EMAIL_SMTP_SERVER'],
smtp_port=os.environ['EMAIL_SMTP_PORT'],
recipients=os.environ['EMAIL_RECIPIENTS'])
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(
__file__).set_experimenter('echatzikyriakidis').set_notifier(
notifier).build()
# Run Deep Feature Synthesis Task
feature_synthesis_results = experiment.run(
DeepFeatureSynthesisTask(
entities={"passengers": (raw_data_set, id_column)},
target_entity="passengers",
trans_primitives=['add_numeric', 'multiply_numeric'],
export_feature_information=True,
export_feature_graphs=True,
label_column=label_column))
data_set = feature_synthesis_results['synthesized_dataset']
feature_defs = feature_synthesis_results['feature_definitions']
products_df = data["products"]
entities = {
"customers" : (customers_df, "customer_id"),
"sessions" : (sessions_df, "session_id", "session_start"),
"transactions" : (transactions_df, "transaction_id", "transaction_time"),
"products" : (products_df, "product_id")
}
relationships = [
("sessions", "session_id", "transactions", "session_id"),
("products", "product_id", "transactions", "product_id"),
("customers", "customer_id", "sessions", "customer_id")
]
######### skrobot Code
# Build an Experiment
experiment = Experiment('experiments-output').set_source_code_file_path(__file__).set_experimenter('echatzikyriakidis').build()
# Run Deep Feature Synthesis Task
feature_synthesis_results = experiment.run(DeepFeatureSynthesisTask (entities=entities,
relationships=relationships,
target_entity="transactions",
export_feature_information=True,
export_feature_graphs=True,
label_column='amount'))
# Print in-memory results
print(feature_synthesis_results['synthesized_dataset'])
print(feature_synthesis_results['feature_definitions'])