Embedding#

>>> from techminer2.tech_mining.pca.tfidf_matrix import embedding
>>> embedding(
...     #
...     # PARAMS:
...     field="author_keywords",
...     #
...     # TF PARAMS:
...     is_binary=True,
...     cooc_within=1,
...     #
...     # TF-IDF parameters:
...     norm=None,
...     use_idf=False,
...     smooth_idf=False,
...     sublinear_tf=False,
...     #
...     # ITEM PARAMS:
...     top_n=20,
...     occ_range=(None, None),
...     gc_range=(None, None),
...     custom_items=None,
...     #
...     # PCA PARAMS:
...     n_components=5,
...     whiten=False,
...     svd_solver="auto",
...     tol=0.0,
...     iterated_power="auto",
...     n_oversamples=10,
...     power_iteration_normalizer="auto",
...     random_state=0,
...     #
...     # DATABASE PARAMS:
...     root_dir="example/",
...     database="main",
...     year_filter=(None, None),
...     cited_by_filter=(None, None),
... ).head()
                                 DIM_0     DIM_1     DIM_2     DIM_3     DIM_4
author_keywords
FINTECH 31:5168               4.887806 -0.043138 -0.014483  0.018812 -0.074537
INNOVATION 07:0911            0.149896  2.039274  0.737841  0.015960  0.269611
FINANCIAL_SERVICES 04:0667   -0.219131  0.551349 -0.797362  0.712416 -0.826560
FINANCIAL_TECHNOLOGY 04:0551 -0.369026 -0.091873 -0.202058  1.133968  1.054857
BUSINESS 03:0896             -0.144818 -0.220816 -0.865907  0.967946 -0.375656