autoflow.utils package
Submodules
autoflow.utils.array module
autoflow.utils.concurrence module
-
autoflow.utils.concurrence.
get_chunks
(iterable, chunks=1)[source]
-
autoflow.utils.concurrence.
parse_n_jobs
(n_jobs)[source]
autoflow.utils.config_space module
-
class
autoflow.utils.config_space.
ConfigSpaceGrid
(configuration_space: ConfigSpace.configuration_space.ConfigurationSpace)[source]
Bases: object
-
generate_grid
(num_steps_dict: Union[None, Dict[str, int]] = None) → List[ConfigSpace.configuration_space.Configuration][source]
Generates a grid of Configurations for a given ConfigurationSpace. Can be used, for example, for grid search.
- Parameters
configuration_space (ConfigurationSpace
) – The Configuration space over which to create a grid of HyperParameter Configuration values. It knows the types for all parameter values.
num_steps_dict (dict) – A dict containing the number of points to divide the grid side formed by Hyperparameters which are either of type UniformFloatHyperparameter or type UniformIntegerHyperparameter. The keys in the dict should be the names of the corresponding Hyperparameters and the values should be the number of points to divide the grid side formed by the corresponding Hyperparameter in to.
- Returns
List containing Configurations. It is a cartesian product of tuples of HyperParameter values. Each tuple lists the possible values taken by the corresponding HyperParameter. Within the cartesian product, in each element, the ordering of HyperParameters is the same for the OrderedDict within the ConfigurationSpace.
- Return type
list
-
get_cartesian_product
(value_sets, hp_names)[source]
-
get_value_set
(num_steps_dict, hp_name)[source]
-
autoflow.utils.config_space.
estimate_config_space_numbers
(cs: ConfigSpace.configuration_space.ConfigurationSpace)[source]
-
autoflow.utils.config_space.
get_grid_initial_configs
(shps: ConfigSpace.configuration_space.ConfigurationSpace, n_configs=- 1, random_state=42)[source]
-
autoflow.utils.config_space.
get_random_initial_configs
(shps: ConfigSpace.configuration_space.ConfigurationSpace, n_configs, random_state=42) → List[ConfigSpace.configuration_space.Configuration][source]
-
autoflow.utils.config_space.
replace_phps
(shps: ConfigSpace.configuration_space.ConfigurationSpace, key, value)[source]
autoflow.utils.data module
-
autoflow.utils.data.
convert_to_bin
(Ycont, nval, verbose=True)[source]
-
autoflow.utils.data.
convert_to_num
(Ybin)[source]
Convert binary targets to numeric vector
typically classification target values
:param Ybin:
:return:
-
autoflow.utils.data.
densify
(X)[source]
-
autoflow.utils.data.
finite_array
(array)[source]
Replace NaN and Inf (there should not be any!)
:param array:
:return:
-
autoflow.utils.data.
is_cat
(s: Union[pandas.core.series.Series, numpy.ndarray], consider_ordinal_as_cat)[source]
-
autoflow.utils.data.
is_date
(s, cat_been_checked=False)[source]
-
autoflow.utils.data.
is_highC_cat
(s: pandas.core.series.Series, threshold)[source]
-
autoflow.utils.data.
is_highR_nan
(s: pandas.core.series.Series, threshold)[source]
-
autoflow.utils.data.
is_nan
(s: pandas.core.series.Series)[source]
-
autoflow.utils.data.
is_target_need_label_encode
(target_col)[source]
-
autoflow.utils.data.
is_text
(s, cat_been_checked=False)[source]
-
autoflow.utils.data.
predict_RAM_usage
(X, categorical)[source]
-
autoflow.utils.data.
softmax
(df)[source]
-
autoflow.utils.data.
to_array
(X)[source]
autoflow.utils.dataframe module
-
class
autoflow.utils.dataframe.
DataFrameValuesWrapper
(X: Union[pandas.core.frame.DataFrame, pandas.core.series.Series, numpy.ndarray])[source]
Bases: object
-
wrap_to_dataframe
(array)[source]
-
autoflow.utils.dataframe.
get_object_columns
(df_: pandas.core.frame.DataFrame) → List[str][source]
-
autoflow.utils.dataframe.
get_unique_col_name
(columns: Union[pandas.core.indexes.base.Index, pandas.core.series.Series], wanted: str)[source]
-
autoflow.utils.dataframe.
inverse_dict
(dict_: dict)[source]
-
autoflow.utils.dataframe.
process_dataframe
(X: Union[pandas.core.frame.DataFrame, numpy.ndarray], copy=True) → pandas.core.frame.DataFrame[source]
-
autoflow.utils.dataframe.
process_duplicated_columns
(columns: pandas.core.indexes.base.Index) → Tuple[pandas.core.indexes.base.Index, Dict[str, str]][source]
-
autoflow.utils.dataframe.
rectify_dtypes
(df: pandas.core.frame.DataFrame)[source]
-
autoflow.utils.dataframe.
replace_dict
(dict_: dict, from_, to_)[source]
-
autoflow.utils.dataframe.
replace_dicts
(dicts, from_, to_)[source]
-
autoflow.utils.dataframe.
replace_nan_to_None
(df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame[source]
autoflow.utils.dict module
autoflow.utils.hash module
-
autoflow.utils.hash.
get_hash_decimal_of_str
(x, m=None)[source]
-
autoflow.utils.hash.
get_hash_of_Xy
(X: Union[pandas.core.frame.DataFrame, numpy.ndarray, None], y: Union[pandas.core.frame.DataFrame, numpy.ndarray, pandas.core.series.Series, None] = None, m=None)[source]
-
autoflow.utils.hash.
get_hash_of_array
(X, m=None)[source]
-
autoflow.utils.hash.
get_hash_of_config
(config: Union[ConfigSpace.configuration_space.Configuration, Dict[str, Any]], m=None)[source]
-
autoflow.utils.hash.
get_hash_of_dataframe
(df: pandas.core.frame.DataFrame, m=None, L=500)[source]
-
autoflow.utils.hash.
get_hash_of_dataframe_csv
(df: pandas.core.frame.DataFrame, m=None, L=500)[source]
-
autoflow.utils.hash.
get_hash_of_dataframe_deprecated
(df: pandas.core.frame.DataFrame, m=None)[source]
-
autoflow.utils.hash.
get_hash_of_dict
(dict_, m=None)[source]
-
autoflow.utils.hash.
get_hash_of_file
(fname)[source]
-
autoflow.utils.hash.
get_hash_of_str
(s: Union[str, bytes], m=None)[source]
autoflow.utils.klass module
-
class
autoflow.utils.klass.
StrSignatureMixin
[source]
Bases: object
-
autoflow.utils.klass.
gather_kwargs_from_signature_and_attributes
(klass, instance)[source]
-
autoflow.utils.klass.
get_class_full_name
(klass: Type) → str[source]
-
autoflow.utils.klass.
get_valid_params_in_kwargs
(func, kwargs: Dict[str, Any])[source]
-
autoflow.utils.klass.
instancing
(variable, klass, kwargs)[source]
-
autoflow.utils.klass.
sequencing
(variable, klass)[source]
-
autoflow.utils.klass.
set_if_not_None
(obj, variable_name, value)[source]
autoflow.utils.list module
autoflow.utils.logging_ module
-
class
autoflow.utils.logging_.
PickableLoggerAdapter
(name)[source]
Bases: object
-
critical
(msg, *args, **kwargs)[source]
-
debug
(msg, *args, **kwargs)[source]
-
error
(msg, *args, **kwargs)[source]
-
exception
(msg, *args, **kwargs)[source]
-
info
(msg, *args, **kwargs)[source]
-
isEnabledFor
(level)[source]
-
log
(level, msg, *args, **kwargs)[source]
-
warning
(msg, *args, **kwargs)[source]
-
autoflow.utils.logging_.
get_logger
(name)[source]
-
autoflow.utils.logging_.
setup_logger
(output_file=None, logging_config=None)[source]
autoflow.utils.math_ module
-
autoflow.utils.math_.
float_gcd
(a, b)[source]
-
autoflow.utils.math_.
get_int_length
(number)[source]
autoflow.utils.ml_task module
-
class
autoflow.utils.ml_task.
MLTask
[source]
Bases: autoflow.utils.ml_task.Task
Create new instance of Task(mainTask, subTask, role)
-
autoflow.utils.ml_task.
get_ml_task_from_y
(y)[source]
autoflow.utils.packages module
-
autoflow.utils.packages.
find_components
(package, directory, base_class)[source]
-
autoflow.utils.packages.
get_class_name_of_module
(input_module)[source]
-
autoflow.utils.packages.
get_class_object_in_pipeline_components
(key1, key2, model_registry)[source]
-
autoflow.utils.packages.
import_by_package_url
(package_url: str)[source]
autoflow.utils.pipeline module
-
autoflow.utils.pipeline.
concat_pipeline
(*args) → Optional[autoflow.workflow.ml_workflow.ML_Workflow][source]
-
autoflow.utils.pipeline.
purify_node
(node)[source]
-
autoflow.utils.pipeline.
union_pipeline
(preprocessors: Dict) → Optional[sklearn.pipeline.Pipeline][source]
autoflow.utils.sys module
autoflow.utils.typing_ module
-
class
autoflow.utils.typing_.
GenericEstimator
(*args, **kwargs)[source]
Bases: typing_extensions.Protocol
-
fit
(X, y)[source]
-
predict
(X)[source]
-
predict_proba
(X)[source]
Module contents