etcbc 4.8.3¶
Submodules¶
etcbc.preprocess module¶
etcbc.annotating module¶
-
class
GenForm
(API, form_name, config)[source]¶ Bases:
object
Generates input forms for new annotations and creates new annotations based on filled in forms.
Upon creation, takes in the config information for a new form.
- Args:
- API(object):
- the API object of the LAF processor, so that the form creator can use its methods for creating files and issuing messages and accessing features.
form_name(string): the base name of the form to be created
config(dict): which nodes and feature data to fill the form with, which new feature columns to make.
etcbc.featuredoc module¶
-
class
FeatureDoc
(processor, study)[source]¶ Bases:
object
Extracts feature information for selected features.
The information returned consists of value lists, number of occurrences, and an summary spreadsheet.
Upon creation, re-initializes the laf processor with requested features plus some needed features.
- Args:
- study:
A dictionary directing the feature study. Contains:
- a list of features to be studied. It is a list of feature names
- a set of absence values, i.e. values like
none
orunknown
that somehow count as the absence of a value. - VALUE_THRESHOLD: a parameter that indicates how many distinct values to list in the summary.
-
feature_doc
()[source]¶ Create the feature information.
Based on the study information given at the creation of the FeatureDoc object, a set of files is created.
- A tab separated overview of statistical feature/value information.
- For each feature, a file with its values and number of occurrences.
- A file of node types and the features they carry.