class SLRModelConfig:
predict: Feature = field("Label or the value to be predicted")
features: Features = field("Features to train on. For SLR only 1 allowed")
directory: pathlib.Path = field(
"Directory where state should be saved",
default=pathlib.Path("~", ".cache", "dffml", "slr"),
)
class LogisticRegressionConfig:
predict: Feature = field("Label or the value to be predicted")
features: Features = field("Features to train on")
directory: pathlib.Path = field(
"Directory where state should be saved",
default=pathlib.Path("~", ".cache", "dffml", "scratch"),
)
class SpacyNERModelConfig:
output_dir: str = field("Output directory")
model_name_or_path: str = field(
"Model name or path to saved model. Defaults to blank 'en' model.",
default=None,
)
n_iter: int = field("Number of training iterations", default=10)
dropout: float = field("Dropout rate to be used during training",
default=0.5)
def __post_init__(self):
self.output_dir = pathlib.Path(self.output_dir)
class SpacyNERModelConfig:
location: str = field("Output location.")
model_name: str = field(
"Name of one of the trained pipelines provided by spaCy.\
You can find complete list at: https://spacy.io/models\
Defaults to blank 'en' model.",
default=None,
)
n_iter: int = field("Number of training iterations", default=10)
dropout: float = field("Dropout rate to be used during training",
default=0.5)
def __post_init__(self):
self.location = pathlib.Path(self.location)
class ProjectCreateCMDConfig:
source: pathlib.Path = field(
"Path to directory containing source code of project", )
dbs: List[DependencyDB.load] = field(
"Databases to search for info on dependencies",
default_factory=lambda: [],
)
add: List[DependencyDB.load] = field(
"YAML files containing info to supplement or override auto-detected info",
default_factory=lambda: [],
)
authoritative: List[pathlib.Path] = field(
"Database to use as authoritative source",
default=YAMLDB(
pathlib.Path(__file__).parent.parent.parent / "db.yaml"),
)
Sources,
Record,
SourcesContext,
ModelContext,
ModelNotTrained,
Accuracy,
config,
field,
make_config_numpy,
)
AutoSklearnConfig = make_config_numpy(
"AutoSklearnConfig",
autosklearn.estimators.AutoSklearnEstimator.__init__,
properties={
"features": (Features, field("Features to train on")),
"predict": (Feature, field("Label or the value to be predicted")),
"directory": (
pathlib.Path,
field("Directory where state should be saved", ),
),
},
)
class AutoSklearnModelContext(ModelContext):
"""
Auto-Sklearn based model contexts should derive
from this model context.
"""
def __init__(self, parent):
class DAAL4PyLRModelConfig:
predict: Feature = field("Label or the value to be predicted")
features: Features = field("Features to train on. For SLR only 1 allowed")
directory: pathlib.Path = field("Directory where state should be saved",)
class MySQLSourceConfig:
user: str = field("Username")
password: str = field("Password")
db: str = field("Name of database to use")
key: str = field("Column name of record key")
features: Dict[str, str] = field(
"Mapping of feature names to column names"
)
predictions: Dict[str, Tuple[str, str]] = field(
"Mapping of prediction names to tuples of (value, confidence) column names"
)
update: str = field("Query to update a single record")
record: str = field("Query to get a single record")
records: str = field("Query to get a single record")
init: str = field("Query to run on initial connection", default=None)
host: str = field("Host/address to connect to", default="127.0.0.1")
port: int = field("Port to connect to", default=3306)
ca: str = field(
"Server certificate to use for TLS validation", default=None
)
insecure: bool = field(
"Must be true to accept risks of non-TLS connection", default=False
)
class UseConfig:
targets: List[str] = field("Git repo URLs or directories to analyze")
class LogisticRegressionConfig:
predict: Feature = field("Label or the value to be predicted")
features: Features = field("Features to train on")
directory: pathlib.Path = field("Directory where state should be saved", )
class MySLRModelConfig:
feature: Feature = field("Feature to train on")
predict: Feature = field("Label or the value to be predicted")
directory: pathlib.Path = field("Directory where state should be saved")
class MySLRModelConfig:
features: Features = field(
"Features to train on (myslr only supports one)")
predict: Feature = field("Label or the value to be predicted")
location: pathlib.Path = field("Location where state should be saved")
class AnomalyModelConfig:
features: Features = field("Features to train on")
predict: Feature = field("Label or the value to be predicted")
directory: pathlib.Path = field("Directory where state should be saved")
k: float = field("Validation set size", default=0.8)
class InstallConfig:
packages: List[str] = field("Package to check if we should install",)
class OrgsReposYAMLSourceConfig:
directory: pathlib.Path = field(
"Top level directory containing GitHub orgs as subdirectories")
class GitHubConfig:
token: str = field("GitHub API token")
