def arxiv_articles(chunk=None):
'''arxiv_articles
Get ArXiv article data chunks.
Parameters
----------
chunk : int
Specify a particular chunk of data to download. There are 17
chunks numbered 0 through 16.
Returns
-------
generator
A generator that returns ArXiv articles in chunks of 100,000
or
DataFrame
A dataframe from a single chunk.
'''
if chunk is None:
for i in range(16):
key = f'{folder}/arxiv_articles_{i:02}.pkl.bz2'
yield load_df_pkl(bucket, key)
else:
key = f'{folder}/arxiv_articles_{chunk:02}.pkl.bz2'
return load_df_pkl(bucket, key)
def patents_10k():
'''patents_10k
Gets a pre-selected sample of 10,000 patents from ONS.
'''
bucket='innovation-mapping-tutorials'
patents_10k_key='ons/ONS_y02_sample_10000.pkl.bz2'
return load_df_pkl(bucket, patents_10k_key)
def cordis_table(table):
'''cordis_table
Get a table from the CORDIS database.
Parameters
----------
table : str
Name of the table to load. Tables available include:
- organisations
- project_organisations
- project_proposal_calls
- project_topics
- projects
- proposal_calls
- publications
- reports
- topics
Returns
-------
DataFrame
A dataframe with containing the CORDIS table data.
'''
key=f'{folder}/cordis_{table}.pkl.bz2'
return load_df_pkl(bucket, key)
def mag_table(table='fields_of_study'):
'''grid_table
Get tables from the Microsoft Academic Graph database.
Parameters
----------
table : str
Name of the Microsoft Academic Graph table to load.
Tables available include:
- fields_of_study
Returns
-------
DataFrame
A dataframe with containing the Microsoft Academic Graph table data.
'''
key = f'{folder}/mag_{table}.pkl.bz2'
return load_df_pkl(bucket, key)
def grid_table(table):
'''grid_table
Get tables from the GRID database.
Parameters
----------
table : str
Name of the GRID table to load. Tables available include:
- aliases
- institutes
Returns
-------
DataFrame
A dataframe with containing the GRID table data.
'''
key = f'{folder}/grid_{table}.pkl.bz2'
return load_df_pkl(bucket, key)
def arxiv_table(table):
'''arxiv_table
Get a list of
Parameters
----------
table : str
Name of the ArXiv table to load. Tables available include:
- article_categories
- article_corex_topics
- article_fields_of_study
- article_institutes
- categories
- corex_topics
Returns
-------
DataFrame
A dataframe with containing the ArXiv table data.
'''
key = f'{folder}/arxiv_{table}.pkl.bz2'
return load_df_pkl(bucket, key)
def gtr_link_table(table):
'''gtr_link_table
Get a link table from the Gateway to Research database.
Link tables link project ids to other entities within GtR.
Parameters
----------
table : str
Name of the link table to load. Tables available include:
- funds
- organisations
- organisations_locations
- outcomes_artisticandcreativeproducts
- outcomes_collaborations
- outcomes_disseminations
- outcomes_furtherfundings
- outcomes_impactsummaries
- outcomes_intellectualproperties
- outcomes_keyfindings
- outcomes_policyinfluences
- outcomes_products
- outcomes_publications
- outcomes_researchdatabaseandmodels
- outcomes_researchmaterials
- outcomes_softwareandtechnicalproducts
- outcomes_spinouts
- participant
- persons
- topic
Returns
-------
DataFrame
A dataframe with containing the GtR table data.
'''
key = f'{folder}/link_tables/gtr_{table}_link.pkl.bz2'
return load_df_pkl(bucket, key)
def patents_10k():
'''patents_10k
Gets a pre-selected sample of 10,000 patents from ONS.
'''
patents_10k_key = 'ons/ONS_y02_sample_10000.pkl.bz2'
return load_df_pkl(bucket, patents_10k_key)
