Combine Keys

Smoke tests:

>>> from techminer2.thesaurus.user import InitializeThesaurus
>>> (
...     InitializeThesaurus()
...     .with_thesaurus_file("demo.the.txt")
...     .with_field("raw_descriptors")
...     .where_root_directory("examples/fintech/")
...     .using_colored_output(False)
...     .run()
... )
INFO: Thesaurus initialized successfully.
  Success : True
  File    : examples/fintech/data/thesaurus/demo.the.txt
  Status  : 1721 keys found
  Header  :
    A_A_THEORY
      A_A_THEORY
    A_BASIC_RANDOM_SAMPLING_STRATEGY
      A_BASIC_RANDOM_SAMPLING_STRATEGY
    A_BEHAVIOURAL_PERSPECTIVE
      A_BEHAVIOURAL_PERSPECTIVE
    A_BETTER_UNDERSTANDING
      A_BETTER_UNDERSTANDING
    A_BLOCKCHAIN_IMPLEMENTATION_STUDY
      A_BLOCKCHAIN_IMPLEMENTATION_STUDY
    A_CASE_STUDY
      A_CASE_STUDY
    A_CHALLENGE
      A_CHALLENGE
    A_CLUSTER_ANALYSIS
      A_CLUSTER_ANALYSIS

>>> from techminer2.thesaurus.user import ApplyThesaurus
>>> (
...     ApplyThesaurus()
...     .with_thesaurus_file("demo.the.txt")
...     .with_field("raw_descriptors")
...     .with_other_field("descriptors_cleaned")
...     .where_root_directory("examples/fintech/")
...     .using_colored_output(False)
...     .run()
... )
INFO: Thesaurus applied successfully.
  Success : True
  File    : examples/fintech/data/thesaurus/demo.the.txt
  Status  : 1788 keys applied

>>> from techminer2.thesaurus.user import CombineKeys
>>> df = (
...     CombineKeys()
...     #
...     # FIELD:
...     .with_field("descriptors_cleaned")
...     .having_terms_in_top(100)
...     .having_terms_ordered_by("OCC")
...     .having_term_occurrences_between(5, None)
...     .having_term_citations_between(None, None)
...     .having_terms_in(None)
...     #
...     # DATABASE:
...     .where_root_directory("examples/fintech/")
...     .where_database("main")
...     .where_record_years_range(None, None)
...     .where_record_citations_range(None, None)
...     .where_records_match(None)
...     #
...     .run()
... )
>>> df.head()
                   lead               candidate  probability combine?
0       FINANCE 20:2992    TECHNOLOGIES 16:1847        0.550      yes
1      SERVICES 07:1226      INVESTMENT 06:1294        0.571      yes
2  PRACTITIONER 06:1194  BUSINESS_MODEL 05:1578        0.500      yes