Data Frame

Example

>>> from techminer2.metrics.tfidf import DataFrame

>>> # Create, configure, and run the data frame generator:
>>> generator = (
...     DataFrame()
...     #
...     .with_field("author_keywords_raw")
...     .having_terms_in_top(10)
...     .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)
...     #
...     # TFIDF:
...     .using_binary_term_frequencies(False)
...     .using_tfidf_norm(None)
...     .using_tfidf_smooth_idf(False)
...     .using_tfidf_sublinear_tf(False)
...     .using_tfidf_use_idf(False)
...     #
...     # 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)
... )
>>> df = generator.run()
>>> df.head()  
author_keywords_raw                             FINTECH 31:5168  ...  CASE_STUDY 02:0340
record_id                                                        ...
Anagnostopoulos I., 2018, J ECON BUS, V100, P7                1  ...                   0
Anshari M., 2019, ENERGY PROCEDIA, V156, P234                 0  ...                   0
Buchak G., 2018, J FINANC ECON, V130, P453                    1  ...                   0
Cai C.W., 2018, ACCOUNT FINANC, V58, P965                     1  ...                   0
Chen L., 2016, CHINA ECON J, V9, P225                         1  ...                   0

[5 rows x 10 columns]