def url_request(url):
table_header = url[url.find('v1') + 3:url.find('?')]
try:
r = etl.fromtext(url, header=[table_header])
except urllib.error.URLError:
print('Connection error or Wrong token')
r = ''
return r
def main(
plates_file,
ticket_numbers_file,
centroid_file,
latlon_input,
):
global logger, plates, plates_counter, ticket_numbers, ticket_numbers_counter, centroids
logger = get_logging()
plates = load_index_file(plates_file, 'plates_file')
plate_numbers_values = plates.values()
if len(plate_numbers_values) > 0:
plates_counter = max(map(lambda x: int(x['id']), plate_numbers_values))
else:
plates_counter = 0
logger.info('Plates autoincrement starting at: {}'.format(plates_counter))
ticket_numbers = load_index_file(ticket_numbers_file, 'license_file')
ticket_numbers_values = ticket_numbers.values()
if len(ticket_numbers_values) > 0:
ticket_numbers_counter = max(
map(lambda x: int(x), ticket_numbers_values))
else:
ticket_numbers_counter = 0
logger.info('Ticket number autoincrement starting at: {}'.format(
ticket_numbers_counter))
centroids = load_index_file(centroid_file, 'centroid_file')
(petl.fromtext(strip=False).rowmap(
get_transform_row(latlon_input), header=headers, failonerror=True
).select(
'{fine} > 0.0 and ({issue_datetime}).isoformat() >= "2012-01-01T00:00:00Z"'
).rowmap(anonymize, header=headers,
failonerror=True).rowmap(geocode,
header=headers,
failonerror=True).tocsv())
logger.info(
'Geocode stats - success rate: {:.2%}, successes: {}, gps: {}, zip: {}, failed_segment: {}, failed_address: {}'
.format(
geocode_stats['success'] /
(geocode_stats['total'] - geocode_stats['gps']),
geocode_stats['success'], geocode_stats['gps'],
geocode_stats['zip'], geocode_stats['failed_segment'],
geocode_stats['failed_address']))
if len(geocode_stats['failed_segments']) > 0:
logger.info('Failed Segments - {}'.format(','.join(
geocode_stats['failed_segments'])))
save_index_file(plates_file, plates,
['id', 'plate', 'state', 'date_added'], 'plates_file')
save_index_file(ticket_numbers_file, ticket_numbers,
['ticket_number', 'anon_ticket_number'], 'license_file')
def test_fromtext():
# initial data
f = NamedTemporaryFile(delete=False)
f.write('foo\tbar\n')
f.write('a\t1\n')
f.write('b\t2\n')
f.write('c\t3\n')
f.close()
actual = fromtext(f.name)
expect = (('lines', ), ('foo\tbar', ), ('a\t1', ), ('b\t2', ), ('c\t3', ))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def test_fromtext():
# initial data
f = NamedTemporaryFile(delete=False)
f.write("foo\tbar\n")
f.write("a\t1\n")
f.write("b\t2\n")
f.write("c\t3\n")
f.close()
actual = fromtext(f.name)
expect = (("lines",), ("foo\tbar",), ("a\t1",), ("b\t2",), ("c\t3",))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def test_fromtext_gz():
# initial data
f = NamedTemporaryFile(delete=False)
f.close()
fn = f.name + ".gz"
os.rename(f.name, fn)
with gzip.open(fn, "wb") as f:
f.write("foo\tbar\n")
f.write("a\t1\n")
f.write("b\t2\n")
f.write("c\t3\n")
actual = fromtext(fn)
expect = (("lines",), ("foo\tbar",), ("a\t1",), ("b\t2",), ("c\t3",))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def test_fromtext_gz():
# initial data
f = NamedTemporaryFile(delete=False)
f.close()
fn = f.name + '.gz'
os.rename(f.name, fn)
with gzip.open(fn, 'wb') as f:
f.write('foo\tbar\n')
f.write('a\t1\n')
f.write('b\t2\n')
f.write('c\t3\n')
actual = fromtext(fn)
expect = (('lines', ), ('foo\tbar', ), ('a\t1', ), ('b\t2', ), ('c\t3', ))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def test_fromtext():
# initial data
f = NamedTemporaryFile(delete=False)
f.write('foo\tbar\n')
f.write('a\t1\n')
f.write('b\t2\n')
f.write('c\t3\n')
f.close()
actual = fromtext(f.name)
expect = (('lines',),
('foo\tbar',),
('a\t1',),
('b\t2',),
('c\t3',))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
def extract(file):
tb = list()
if file == "sql":
host = raw_input("Enter Host:")
user = raw_input("Enter Username:"******"Enter pwd:")
dtb = raw_input("Enter Database Name:")
table = raw_input("Enter Table Name:")
conn = pymysql.connect(host=host,
user=user,
password=pwd,
db=dtb,
charset='utf8mb4',
cursorclass=pymysql.cursors.DictCursor)
temp = etl.fromdb(conn, "SELECT * FROM " + table)
tb = d2l(temp)
elif ".csv" in file:
tb = etl.fromcsv(file)
elif ".xlsx" in file:
tb = etl.fromxls(file)
elif ".json" in file:
tb = etl.fromjson(file)
print tb
elif ".xml" in file:
f = open(file, 'r').read()
options = optparse.Values({"pretty": True})
jsn = json.dumps(xml2json.xml2json(f, options))
ob = json.loads(jsn.decode('string-escape').strip('"'))
temp = dict()
for key in ob.keys():
for skey in ob[key].keys():
temp = json.dumps(ob[key][skey])
with open("temp.json", "w") as tmp:
tmp.write(temp)
tb = etl.fromjson("temp.json")
print tb[0]
#tb = etl.fromxml(file,'.//ROW',{'Service_Name':'Service_Name','Status':'Status','Service_Type':'Service_Type','Time':'Time'})
elif ".txt" in file:
tb = etl.fromtext(file)
print tb
return tb
def test_fromtext_gz():
# initial data
f = NamedTemporaryFile(delete=False)
f.close()
fn = f.name + '.gz'
os.rename(f.name, fn)
with gzip.open(fn, 'wb') as f:
f.write('foo\tbar\n')
f.write('a\t1\n')
f.write('b\t2\n')
f.write('c\t3\n')
actual = fromtext(fn)
expect = (('lines',),
('foo\tbar',),
('a\t1',),
('b\t2',),
('c\t3',))
ieq(expect, actual)
ieq(expect, actual) # verify can iterate twice
pickle.dump(a, fileObject)
# here we close the fileObject
fileObject.close()
table3 = etl.frompickle('pickel_file.p')
print('Pick')
print(table3)
###################Reading Text Files#################################
text = 'a,1\nb,2\nc,2\n'
with open('example.txt', 'w') as f:
f.write(text)
table4 = etl.fromtext('example.txt')
print(table4)
################Reading XML files##################################
table5 = etl.fromxml('data.xml', 'tr', 'td')
print(table5)
################Reading JASON files###############################
data = '''
[{"foo": "a", "bar": 1},
{"foo": "b", "bar": 2},
{"foo": "c", "bar": 2}]
'''
with open('example.json', 'w') as f:
h = '#%02x%02x%02x' % tuple(int(255 * c) for c in pop_colors[p])
# chromatin
_data_chromatin = b"""CHX chro X 20009764 24393108
CH2R chro 2R 58984778 61545105
CH2L chro 2L 1 2431617
PEU2L chro 2L 2487770 5042389
IH2L chro 2L 5078962 5788875
IH3R chro 3R 38988757 41860198
CH3R chro 3R 52161877 53200684
CH3L chro 3L 1 1815119
PEU3L chro 3L 1896830 4235209
IH3L chro 3L 4264713 5031692
"""
tbl_chromatin = (etl.fromtext(etl.MemorySource(_data_chromatin)).split(
'lines', '\s+', ['name', 'type', 'chrom', 'start', 'stop']).convert(
('start', 'stop'), int).cutout('type'))
# genome regions
region_X_speciation = 'X-speciation', 'X', 15000000, 24000000
region_X_free = 'X-free', 'X', 1, 14000000
region_3L_free = '3L-free', '3L', 15000000, 41000000
region_3R_free = '3R-free', '3R', 1, 37000000
# noinspection PyGlobalUndefined
def init(release_dir, load_geneset=False):
"""Initialise data resources.
Parameters
----------
from __future__ import division, print_function, absolute_import
# fromtext()
############
import petl as etl
# setup example file
text = 'a,1\nb,2\nc,2\n'
with open('example.txt', 'w') as f:
f.write(text)
table1 = etl.fromtext('example.txt')
table1
# post-process, e.g., with capture()
table2 = table1.capture('lines', '(.*),(.*)$', ['foo', 'bar'])
table2
# totext()
##########
import petl as etl
table1 = [['foo', 'bar'],
['a', 1],
['b', 2],
['c', 2]]
prologue = '''{| class="wikitable"
|-
! foo
! bar
def load(filename):
sequence = petl.fromtext(filename).skip(1).setheader(['lines']).split(
'lines', '\s+').setheader(['lon', 'lat', 'value']).convertall(
float).select("115 < {lon} < 125 and 20 < {lat} < 28").tuple()
return sequence[1:] # skip header
