Terms by Cluster Summary

Example

>>> from techminer2.experimental.co_occurrence import TermsByClusterSummary
>>> df = (
...     TermsByClusterSummary()
...     #
...     # FIELD:
...     .having_terms_in_top(20)
...     .having_terms_ordered_by("OCC")
...     .having_term_occurrences_between(None, None)
...     .having_term_citations_between(None, None)
...     .having_terms_in(None)
...     #
...     # COUNTERS:
...     .using_term_counters(True)
...     #
...     # NETWORK:
...     .using_clustering_algorithm_or_dict("louvain")
...     .using_association_index("association")
...     .using_minimum_terms_in_cluster(5)
...     #
...     # DATABASE:
...     .where_root_directory_is("examples/fintech/")
...     .where_database_is("main")
...     .where_record_years_range_is(None, None)
...     .where_record_citations_range_is(None, None)
...     .where_records_match(None)
...     #
...     .run()
... )
>>> df 
   Cluster  ...                                              Terms
0        0  ...  FINTECH 38:6131; THE_FINANCIAL_INDUSTRY 09:200...
1        1  ...  TECHNOLOGIES 15:1633; FINANCIAL_TECHNOLOGIES 1...
2        2  ...  THE_DEVELOPMENT 09:1293; INNOVATION 08:1816; T...
3        3  ...  BANKS 08:1049; DATA 07:1086; CONSUMERS 07:0925...

[4 rows x 4 columns]