Skip to content

run

Config location: conf/run

__help__.yaml

defaults:
  - __init__

_description_: |
  A template for run configuration to instantiate a partial function.
  List all parameters to the partial function at the root level except for the first parameter, which is the pipe object.
  If the first parameter is not the pipe object, set use_pipe_obj to false in the pipe configuration and set the first parameter name in pipe_obj_arg_name.

  from the 'pipe' configuration:
  use_pipe_obj: true # if true, the pipe target function will be called with the pipe object as the first argument
  pipe_obj_arg_name: # if use_pipe_obj is true, the pipe object will be passed to the pipe target function with this argument name

__init__.yaml

_target_: null
_partial_: true

dataframe_combine_str_columns.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_combine_str_columns
columns: null
sep: null
fillna: null
new_column_name: null
drop_old_columns: false
verbose: false

dataframe_drop.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_drop
labels: null
axis: 1
level: null
errors: raise
verbose: false

dataframe_drop_columns.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_drop_columns
columns: null
level: null
errors: raise
verbose: false

dataframe_eval_columns.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_eval_columns
expressions: null
engine: python
verbose: false

dataframe_eval_columns_with_pd_eval.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_eval_columns_with_pd_eval
expressions: null
engine: python
verbose: false

dataframe_print_head_and_tail.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_print_head_and_tail
num_heads: 5
num_tails: 5
columns: null
verbose: false

dataframe_select_columns.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_select_columns
columns: null
verbose: false

dataframe_split_str_column.yaml

_target_: hyfi.utils.datasets.basic.DSBasic.dataframe_split_str_column
column: null
sep: null
new_column_name: null
drop_old_column: false
verbose: false

dict_to_dataframe.yaml

_target_: hyfi.utils.datasets.utils.DSUtils.dict_to_dataframe
orient: columns
dtype: null
columns: null

filter_and_sample_data.yaml

_target_: hyfi.utils.datasets.slice.DSSlice.filter_and_sample_data
queries: null
sample_size: null
sample_seed: 42
output_dir: .
sample_filename: null
train_filename: train.parquet
discard_filename: null
returning_data: train
verbose: false

filter_data_by_queries.yaml

_target_: hyfi.utils.datasets.slice.DSSlice.filter_data_by_queries
queries: null
verbose: false

load_data.yaml

_target_: hyfi.utils.datasets.load.DSLoad.load_data
path: pandas
name: null
data_dir: null
data_files: null
split: train
filetype: null
concatenate: false
use_cached: false
verbose: false

load_dataframe.yaml

_target_: hyfi.utils.datasets.load.DSLoad.load_dataframe
data_file: null
data_dir: null
filetype: null
columns: null
index_col: null
verbose: false

load_dataframes.yaml

_target_: hyfi.utils.datasets.load.DSLoad.load_dataframes
data_files: null
data_dir: null
filetype: null
split: null
concatenate: false
ignore_index: false
use_cached: false
verbose: false

load_dataset.yaml

_target_: hyfi.utils.datasets.load.DSLoad.load_dataset
path: null
name: null
data_dir: null
data_files: null
split: null
cache_dir: null
features: null
download_config: null
download_mode: null
verification_mode: null
num_proc: null

load_dataset_from_disk.yaml

_target_: hyfi.utils.datasets.load.DSLoad.load_dataset_from_disk
dataset_path: null
keep_in_memory: null
storage_options: null
num_heads: 1
num_tails: 1
verbose: false

merge_dataframes.yaml

_target_: hyfi.utils.datasets.combine.DSCombine.merge_dataframes
right: null
how: inner
'on': null
left_on: null
right_on: null
left_index: false
right_index: false
sort: false
suffixes:
- _x
- _y
copy: true
indicator: false
validate: null
verbose: false

records_to_dataframe.yaml

_target_: hyfi.utils.datasets.utils.DSUtils.records_to_dataframe
index: null
exclude: null
columns: null
coerce_float: false
nrows: null

sample_data.yaml

_target_: hyfi.utils.datasets.slice.DSSlice.sample_data
sample_size_per_group: null
sample_seed: 123
group_by: null
value_col: null
remove_columns: null
verbose: false

sample_dataset.yaml

_target_: hyfi.utils.datasets.slice.DSSlice.sample_dataset
split: null
sample_size: 100
sample_seed: 42
randomize: true
num_heads: 1
num_tails: 1
verbose: false

save_dataframes.yaml

_target_: hyfi.utils.datasets.save.DSSave.save_dataframes
data_file: null
data_dir: null
columns: null
index: false
filetype: parquet
suffix: null
verbose: false

save_dataset_to_disk.yaml

_target_: hyfi.utils.datasets.save.DSSave.save_dataset_to_disk
dataset_path: null
max_shard_size: null
num_shards: null
num_proc: null
storage_options: null
verbose: false

split_dataframe.yaml

_target_: hyfi.utils.datasets.slice.DSSlice.split_dataframe
indices_or_sections: null
verbose: false