def estimate_pmc_coverage(query, start_year="1800", end_year="3000"):
pubmed_query = query + ' AND ("' + start_year + '"[pdat] : "' + end_year + '"[pdat])'
pubmed_ids = pubmed.search(pubmed_query)
num_pubmed = len(pubmed_ids)
pmc_query = query + ' AND ("' + start_year + '"[PubDate] : "' + end_year + '"[PubDate])'
pmc_ids = pubmedcentral.search(pmc_query)
num_pmc = len(pmc_ids)
ratio = num_pmc / (num_pubmed + 0.0)
return (num_pmc, num_pubmed, ratio)
def estimate_pmc_coverage(query, start_year="1800", end_year="3000"):
pubmed_query = query + ' AND ("' + start_year + '"[pdat] : "' + end_year + '"[pdat])'
pubmed_ids = pubmed.search(pubmed_query)
num_pubmed = len(pubmed_ids)
pmc_query = query + ' AND ("' + start_year + '"[PubDate] : "' + end_year + '"[PubDate])'
pmc_ids = pubmedcentral.search(pmc_query)
num_pmc = len(pmc_ids)
ratio = num_pmc / (num_pubmed + 0.0)
return(num_pmc, num_pubmed, ratio)
feature_sources = ["mesh_basic", "mesh_major", "mesh_qualifier", "article_title", "tiabs", "abstract"]
#A = healthy_1991to2008_5or6
#B = healthy_2002to2008_not5or6
#A = healthy_1991to2001_3or4
#B = healthy_1991to2001_1or2 + healthy_1991to2001_5or6 # + healthy_1991to2001_7
#A = healthy_1991to2001_5or6
#B = healthy_1991to2001_1or2 + healthy_1991to2001_3or4
from data import neuroethicslike
#A = neuroethicslike.pubmed_neurethicslike_query_results
#A = neuroethicslike.pubmed_fmri_neuroethicslike_query_results
base_query = """("fmri"[text] OR "magnetic resonance imaging"[mesh]) AND ((neurosciences[mesh] OR neuroscience[Title/Abstract] OR neurology[mesh]) AND (ethics[sh] OR ethical[Title/Abstract] OR "bioethical issues"[mesh] OR "ethics, medical"[mesh] OR "legislation and jurisprudence"[Subheading])) OR neuroethic*[Title/Abstract]"""
base = pubmed.search(base_query)
A = pubmed.filter_pmids(base, "Personal Autonomy")
dist = coveyquery.get_mesh_frequency_distributions(A, getter=pubmed.mesh_basic)
print "\n\nTop list for (A, getter=pubmed.mesh_basic):"
coveyquery.print_frequency_proportion(A, dist, 150)
if False:
dist = coveyquery.get_text_frequency_distributions(A, getter=pubmed.article_title)
print "\n\nTop list for (A, getter=pubmed.article_title):"
coveyquery.print_frequency_proportion(A, dist, 30)
dist = coveyquery.get_text_frequency_distributions(A, getter=pubmed.abstract)
print "\n\nTop list for (A, getter=pubmed.abstract):"
coveyquery.print_frequency_proportion(A, dist, 30)
