You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

58 lines
1.4 KiB
YAML

# _________________________________________________________________________
# loading some data catalogs
3 years ago
actors:
type: pandas.CSVDataSet
filepath: data/01_raw/csv/actors.csv
load_args:
sep: ";"
3 years ago
3 years ago
corpus-agnes-bourgogne:
type: pandas.CSVDataSet
filepath: data/01_raw/csv/corpus-agnes-bourgogne.csv
load_args:
sep: ";"
corpus-charles-i:
type: pandas.CSVDataSet
filepath: data/01_raw/csv/corpus-charles-i.csv
load_args:
sep: ";"
# _________________________________________________________________________
# custom csv dataset test sample
dataset_test:
type: myowndataset.MyOwnDataSet
filepath: data/01_raw/csv/actors.csv
load_args:
sep: ";"
preprocessed_dataset_test:
type: myowndataset.MyOwnDataSet
filepath: data/02_intermediate/csv/preprocessed_test_dataset.csv
3 years ago
save_args:
sep: ";"
# _________________________________________________________________________
# custom xml dataset sample
load_xml:
type: actesdataset.XMLDataSet
3 years ago
filepath: data/01_raw/xml/Anjou/anj_is_i_1441_08_05a.xml
preprocess_html:
type: actesdataset.XMLDataSet
3 years ago
filepath: data/02_intermediate/xml/Anjou/anj_is_i_1441_08_05a.html
# _________________________________________________________________________
preprocessed_actors:
type: pandas.CSVDataSet
filepath: data/02_intermediate/csv/preprocessed_actors.csv
save_args:
sep: ";"