def get_pubmed_data(self, max=None, pmids=None):
if pmids:
query_pmids = pmids
else:
all_pmids = datasources.ochsner.get_all_pmids()
if not max:
max = len(all_pmids)
query_pmids = all_pmids[0:max]
pubmed_request = """pubmed.pubmed_id,
ochsner.found_geo_data_submission,
ochsner.found_arrayexpress_data_submission,
ochsner.found_smd_data_submission,
ochsner.found_any_data_submission,
ochsner.list_data_ids,
pubmed.is_humans,
pubmed.is_animals,
pubmed.is_mice,
pubmed.is_fungi,
pubmed.is_bacteria,
pubmed.is_plants,
pubmed.is_viruses,
pubmed.is_cultured_cells,
pubmed.is_cancer,
pubmed.date_published,
pubmed.authors,
pubmed.journal,
pubmed.number_times_cited_in_pmc,
isi.impact_factor
"""
data = dataset.collect_data(query_pmids, pubmed_request)
csv_data = dataset.csv_format(data)
if False:
FILENAME = "../../results/aim2b_part2_pubmed.txt"
writer = open(FILENAME, "w")
for row in csv_data:
writer.write("\t".join([str(col) for col in row]))
writer.write("\r\n")
writer.close()
assert_equals(len(csv_data), 1 + len(query_pmids))
return (csv_data)
def get_pubmed_data(self, max=None, pmids=None):
if pmids:
query_pmids = pmids
else:
all_pmids = datasources.ochsner.get_all_pmids()
if not max:
max = len(all_pmids)
query_pmids = all_pmids[0:max]
pubmed_request = """pubmed.pubmed_id,
ochsner.found_geo_data_submission,
ochsner.found_arrayexpress_data_submission,
ochsner.found_smd_data_submission,
ochsner.found_any_data_submission,
ochsner.list_data_ids,
pubmed.is_humans,
pubmed.is_animals,
pubmed.is_mice,
pubmed.is_fungi,
pubmed.is_bacteria,
pubmed.is_plants,
pubmed.is_viruses,
pubmed.is_cultured_cells,
pubmed.is_cancer,
pubmed.date_published,
pubmed.authors,
pubmed.journal,
pubmed.number_times_cited_in_pmc,
isi.impact_factor
"""
data = dataset.collect_data(query_pmids, pubmed_request)
csv_data = dataset.csv_format(data)
if False:
FILENAME = "../../results/aim2b_part2_pubmed.txt"
writer = open(FILENAME, "w")
for row in csv_data:
writer.write("\t".join([str(col) for col in row]))
writer.write("\r\n")
writer.close()
assert_equals(len(csv_data), 1+len(query_pmids))
return(csv_data)
def write_to_file(self, data, filename):
file = open(filename, "w")
csv_data = dataset.csv_format(data)
for row in csv_data:
joined_row_contents = []
for col in row:
if col is None:
col = u""
if col == True:
col = u"1"
if col == False:
col = u"0"
try:
file.write(str(col))
except UnicodeEncodeError:
new_string = utils.unicode.clean_up_strange_unicode(col)
file.write(new_string)
file.write(u"\t")
file.write(u"\r\n")
file.close()
return (csv_data)
def write_to_file(self, data, filename):
file = open(filename, "w")
csv_data = dataset.csv_format(data)
for row in csv_data:
joined_row_contents = []
for col in row:
if col is None:
col = u""
if col==True:
col = u"1"
if col==False:
col = u"0"
try:
file.write(str(col))
except UnicodeEncodeError:
new_string = utils.unicode.clean_up_strange_unicode(col)
file.write(new_string)
file.write(u"\t")
file.write(u"\r\n")
file.close()
return(csv_data)
def test_csv_format(self):
input = test_data_has_geo_data_submission
response = dataset.csv_format(input)
assert_equals(response, test_data_csv_format)
def test_csv_format(self):
input = test_data_has_geo_data_submission
response = dataset.csv_format(input)
assert_equals(response, test_data_csv_format)