Cutoff Fuzzy MergingΒΆ
Example
>>> # Reset the thesaurus to initial state
>>> from techminer2.thesaurus.descriptors import InitializeThesaurus
>>> InitializeThesaurus(root_directory="examples/fintech/", quiet=True).run()
>>> from techminer2.thesaurus.descriptors import ReduceKeys
>>> (
... ReduceKeys()
... .where_root_directory("examples/fintech/")
... .run()
... )
>>> # Redirect stderr to capture output
>>> import sys
>>> from io import StringIO
>>> original_stderr = sys.stderr
>>> sys.stderr = StringIO()
>>> # Cutoff Fuzzy Merging
>>> from techminer2.thesaurus.descriptors import CutoffFuzzyMerging
>>> (
... CutoffFuzzyMerging(tqdm_disable=True, )
... # .where_root_directory("examples/fintech/")
... .where_root_directory("../tm2_economics_of_wind_energy/")
... .using_cutoff_threshold(85)
... .using_match_threshold(95)
... .run()
... )
>>> # Capture and print stderr output
>>> output = sys.stderr.getvalue()
>>> sys.stderr = original_stderr
>>> print(output)
Cutoff-Fuzzy Merging thesaurus keys...
File : examples/fintech/data/thesaurus/descriptors.the.txt
Keys reduced from 1569 to 1554
Merging process completed successfully