easy_rec.python.input

easy_rec.python.input.input

class easy_rec.python.input.input.Input(data_config, feature_configs, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None, **kwargs)

Bases: object

DATA_OFFSET = 'DATA_OFFSET'

__init__(data_config, feature_configs, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None, **kwargs)

property num_epochs

get_feature_input_fields()

should_stop(curr_epoch)

Check whether have run enough num epochs.

create_multi_placeholders(export_config)

Create multiply placeholders on export, one for each feature.

Parameters:

export_config – ExportConfig instance.

create_placeholders(export_config)

classmethod create_class(name)

restore(checkpoint_path)

stop()

create_input(export_config=None)

easy_rec.python.input.csv_input

class easy_rec.python.input.csv_input.CSVInput(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.csv_input_v2

class easy_rec.python.input.csv_input_v2.CSVInputV2(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.kafka_input

class easy_rec.python.input.kafka_input.KafkaInput(data_config, feature_config, kafka_config, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

DATA_OFFSET = 'DATA_OFFSET'

__init__(data_config, feature_config, kafka_config, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

restore(checkpoint_path)

classmethod create_class(name)

easy_rec.python.input.odps_input

class easy_rec.python.input.odps_input.OdpsInput(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.odps_input_v2

class easy_rec.python.input.odps_input_v2.OdpsInputV2(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.odps_rtp_input

class easy_rec.python.input.odps_rtp_input.OdpsRTPInput(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

RTPInput for parsing rtp fg new input format on odps.

Our new format(csv in table) of rtp output:

label0, item_id, …, user_id, features

For the feature column, features are separated by ,

multiple values of one feature are separated by , such as: …20beautysmartParis…

The features column and labels are specified by data_config.selected_cols,

columns are selected by names in the table such as: clk,features, the last selected column is features, the first selected columns are labels

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.rtp_input

class easy_rec.python.input.rtp_input.RTPInput(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

RTPInput for parsing rtp fg new input format.

Our new format(csv in csv) of rtp output:

label0, item_id, …, user_id, features

here the separator(,) could be specified by data_config.rtp_separator For the feature column, features are separated by ,

multiple values of one feature are separated by , such as: …20beautysmartParis…

The features column and labels are specified by data_config.selected_cols,

columns are selected by indices as our csv file has no header, such as: 0,1,4, means the 4th column is features, the 1st and 2nd columns are labels

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)

easy_rec.python.input.rtp_input_v2

class easy_rec.python.input.rtp_input_v2.RTPInputV2(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

Bases: Input

RTPInput for parsing rtp fg input format.

the original rtp format, it is not efficient for training, the performance have to be tuned.

__init__(data_config, feature_config, input_path, task_index=0, task_num=1, check_mode=False, pipeline_config=None)

classmethod create_class(name)