def tslice(unit, start=None, end=None, step=1, count=None):
'''tslice(unit,start=None,end=None,step=1,count=None) -> generator of Sandglass object
unit in ['year', 'month', 'day', 'hour', 'minute', 'second', 'microsecond']
this is some kind xrange-like
'''
if unit not in Sandglass._units:
raise AttributeError()
if isinstance(start, basestring):
start = ben(start)
if isinstance(end, basestring):
end = ben(end)
start = start or ben()
count = count or float('inf')
cur = start
cnt = 0
if step > 0:
end = end or ben(datetime.max)
while cur < end and cnt < count:
yield cur
cur = cur.shifted(**{unit: step})
cnt += 1
elif step < 0:
end = end or ben(datetime.min)
while cur > end and cnt < count:
yield cur
cur = cur.shifted(**{unit: step})
cnt += 1
def tslice(unit,start=None,end=None,step=1,count=None):
'''tslice(unit,start=None,end=None,step=1,count=None) -> generator of Sandglass object
unit in ['year', 'month', 'day', 'hour', 'minute', 'second', 'microsecond']
this is some kind xrange-like
'''
if unit not in Sandglass._units:
raise AttributeError()
if isinstance(start,basestring):
start = ben(start)
if isinstance(end,basestring):
end = ben(end)
start = start or ben()
count = count or float('inf')
cur = start
cnt = 0
if step>0:
end = end or ben(datetime.max)
while cur<end and cnt<count:
yield cur
cur = cur.shifted(**{unit:step})
cnt += 1
elif step<0:
end = end or ben(datetime.min)
while cur>end and cnt<count:
yield cur
cur = cur.shifted(**{unit:step})
cnt += 1
def __init__(self, expr, base=None):
self.base = ben(base) if base else ben()
if self.base.second or self.base.microsecond: #minute is min unit
self.base = self.base.shift(minute=1).floor(
'minute') #discard second and microsecond
self.cur = self.base.clone()
self.entry = Entry()
self.last_fit_year = self.cur.year
self.range_len = {
'month': 12,
'day': getattr(self.cur, 'days_in_month'),
'isoweekday': 7,
'hour': 24,
'minute': 60,
}
tokens = expr.strip().split()
if len(tokens) != 5:
raise Exception('invalid expr')
self.has_day = (tokens[2] != '*')
self.has_isoweekday = (tokens[4] != '*')
for i, tok in enumerate(tokens):
item_list = tok.split(',')
res = []
while item_list:
item = item_list.pop(0)
mat = re.search(
r'^(\d+)-(\d+)(/(.*))?$',
str(item).replace(
'*', '{0[1]}-{0[2]}'.format(self.field_range[i])))
if mat:
start, end, _, step = mat.groups()
step = step or 1
start, end, step = map(int, (start, end, step))
_range_start, _range_end = self.field_range[i][1:3]
if not _range_start <= start <= _range_end:
raise Exception('invalid expr')
if not _range_start <= end <= _range_end:
raise Exception('invalid expr')
if start > end:
_rotate = range(_range_start, _range_end + 1)
_rotate = _rotate[_rotate.index(start):]+\
_rotate[:_rotate.index(end)+1]
_list = _rotate[::step]
else:
_list = range(start, end + 1, step)
item_list += _list
else:
res.append(int(item))
self.entry[i] = sorted(res)
if not self.has_isoweekday:
self.entry.isoweekday = []
else:
if not self.has_day:
self.entry.day = []
def timediff(timestr, factor=86400, base=None):
'''Get the distance to the next time
>>>timediff('20:00:00',factor=86400,base='19:30:00')
1800
>>>timediff('20:00:00',factor=86400,base='21:30:00')
81000
'''
base = ben(base) if base else ben()
sg = ben(timestr)
diff = int((sg - base).total_seconds())
return diff % factor
def timediff(timestr,factor=86400,base=None):
'''Get the distance to the next time
>>>timediff('20:00:00',factor=86400,base='19:30:00')
1800
>>>timediff('20:00:00',factor=86400,base='21:30:00')
81000
'''
base = ben(base) if base else ben()
sg = ben(timestr)
diff = int((sg - base).total_seconds())
return diff%factor
def __init__(self,expr,base=None):
self.base = ben(base) if base else ben()
if self.base.second or self.base.microsecond:#minute is min unit
self.base = self.base.shift(minute=1).floor('minute')#discard second and microsecond
self.cur = self.base.clone()
self.entry = Entry()
self.last_fit_year = self.cur.year
self.range_len = {
'month':12,
'day':getattr(self.cur,'days_in_month'),
'isoweekday':7,
'hour':24,
'minute':60,
}
tokens = expr.strip().split()
if len(tokens)!=5:
raise Exception('invalid expr')
self.has_day = (tokens[2] != '*')
self.has_isoweekday = (tokens[4] != '*')
for i,tok in enumerate(tokens):
item_list = tok.split(',')
res = []
while item_list:
item = item_list.pop(0)
mat = re.search(r'^(\d+)-(\d+)(/(.*))?$',str(item).replace('*','{0[1]}-{0[2]}'.format(self.field_range[i])))
if mat:
start,end,_,step = mat.groups()
step = step or 1
start,end,step = map(int,(start,end,step))
_range_start,_range_end = self.field_range[i][1:3]
if not _range_start<=start<=_range_end:
raise Exception('invalid expr')
if not _range_start<=end<=_range_end:
raise Exception('invalid expr')
if start>end:
_rotate = range(_range_start,_range_end+1)
_rotate = _rotate[_rotate.index(start):]+\
_rotate[:_rotate.index(end)+1]
_list = _rotate[::step]
else:
_list = range(start,end+1,step)
item_list += _list
else:
res.append(int(item))
self.entry[i] = sorted(res)
if not self.has_isoweekday:
self.entry.isoweekday = []
else:
if not self.has_day:
self.entry.day = []
def gen_submission(best_hotels_search_dest, best_hotels_od_ulc,
popular_hotel_cluster):
print('Generate submission...')
path = '../../kaggle_data/hotel_recommendation/result/submission_' + ben(
).sql + '.csv'
out = open(path, "w")
f = open("../../kaggle_data/hotel_recommendation/data/test.csv", "r")
f.readline()
total = 0
out.write("id,hotel_cluster\n")
topclasters = nlargest(5,
sorted(popular_hotel_cluster.items()),
key=itemgetter(1))
while 1:
line = f.readline().strip()
total += 1
if total % 1000000 == 0:
print('Write {} lines...'.format(total))
if line == '':
break
arr = line.split(",")
id = arr[0]
user_location_city = arr[6]
orig_destination_distance = arr[7]
srch_destination_id = arr[17]
hotel_country = arr[20]
hotel_market = arr[21]
out.write(str(id) + ',')
filled = []
s1 = (user_location_city, orig_destination_distance)
if s1 in best_hotels_od_ulc:
d = best_hotels_od_ulc[s1]
topitems = nlargest(5, sorted(d.items()), key=itemgetter(1))
for i in range(len(topitems)):
if topitems[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topitems[i][0])
filled.append(topitems[i][0])
s2 = (srch_destination_id, hotel_country, hotel_market)
if s2 in best_hotels_search_dest:
d = best_hotels_search_dest[s2]
topitems = nlargest(5, d.items(), key=itemgetter(1))
for i in range(len(topitems)):
if topitems[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topitems[i][0])
filled.append(topitems[i][0])
for i in range(len(topclasters)):
if topclasters[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topclasters[i][0])
filled.append(topclasters[i][0])
out.write("\n")
out.close()
print('Completed!')
def gen_submission(best_hotels_search_dest, best_hotels_od_ulc, popular_hotel_cluster):
print('Generate submission...')
path = '../../kaggle_data/hotel_recommendation/result/submission_' + ben().sql + '.csv'
out = open(path, "w")
f = open("../../kaggle_data/hotel_recommendation/data/test.csv", "r")
f.readline()
total = 0
out.write("id,hotel_cluster\n")
topclasters = nlargest(5, sorted(popular_hotel_cluster.items()), key=itemgetter(1))
while 1:
line = f.readline().strip()
total += 1
if total % 1000000 == 0:
print('Write {} lines...'.format(total))
if line == '':
break
arr = line.split(",")
id = arr[0]
user_location_city = arr[6]
orig_destination_distance = arr[7]
srch_destination_id = arr[17]
hotel_country = arr[20]
hotel_market = arr[21]
out.write(str(id) + ',')
filled = []
s1 = (user_location_city, orig_destination_distance)
if s1 in best_hotels_od_ulc:
d = best_hotels_od_ulc[s1]
topitems = nlargest(5, sorted(d.items()), key=itemgetter(1))
for i in range(len(topitems)):
if topitems[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topitems[i][0])
filled.append(topitems[i][0])
s2 = (srch_destination_id, hotel_country, hotel_market)
if s2 in best_hotels_search_dest:
d = best_hotels_search_dest[s2]
topitems = nlargest(5, d.items(), key=itemgetter(1))
for i in range(len(topitems)):
if topitems[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topitems[i][0])
filled.append(topitems[i][0])
for i in range(len(topclasters)):
if topclasters[i][0] in filled:
continue
if len(filled) == 5:
break
out.write(' ' + topclasters[i][0])
filled.append(topclasters[i][0])
out.write("\n")
out.close()
print('Completed!')
