>>> from sklearn.decomposition import PCA
>>> from sklearn.cluster import KMeans
>>> from techminer2.factor_analysis.co_occurrence import cluster_to_terms_mapping
>>> mapping = cluster_to_terms_mapping(
... #
... # PARAMS:
... field="author_keywords",
... association_index=None,
... #
... # ITEM PARAMS:
... top_n=20,
... occ_range=(None, None),
... gc_range=(None, None),
... custom_terms=None,
... #
... # DESOMPOSITION:
... decomposition_estimator = PCA(
... n_components=5,
... whiten=False,
... svd_solver="auto",
... tol=0.0,
... iterated_power="auto",
... n_oversamples=10,
... power_iteration_normalizer="auto",
... random_state=0,
... ),
... #
... # CLUSTERING:
... clustering_estimator_or_dict = KMeans(
... n_clusters=6,
... init="k-means++",
... n_init=10,
... max_iter=300,
... tol=0.0001,
... algorithm="elkan",
... random_state=0,
... ),
... #
... # DATABASE PARAMS:
... root_dir="example/",
... database="main",
... year_filter=(None, None),
... cited_by_filter=(None, None),
... )
>>> from pprint import pprint
>>> pprint(mapping)
{0: ['BUSINESS_MODELS 02:0759',
'ARTIFICIAL_INTELLIGENCE 02:0327',
'FINANCE 02:0309',
'ROBOTS 02:0289',
'REGTECH 02:0266'],
1: ['FINANCIAL_INCLUSION 03:0590',
'CROWDFUNDING 03:0335',
'CYBER_SECURITY 02:0342',
'CASE_STUDY 02:0340',
'BLOCKCHAIN 02:0305'],
2: ['MARKETPLACE_LENDING 03:0317',
'LENDINGCLUB 02:0253',
'PEER_TO_PEER_LENDING 02:0253',
'SHADOW_BANKING 02:0253'],
3: ['FINANCIAL_SERVICES 04:0667',
'FINANCIAL_TECHNOLOGY 03:0461',
'TECHNOLOGY 02:0310',
'BANKING 02:0291'],
4: ['FINTECH 31:5168'],
5: ['INNOVATION 07:0911']}