def parse_lutkepohl_data(path): # pragma: no cover
"""
Parse data files from Lutkepohl (2005) book
Source for data files: www.jmulti.de
"""
from collections import deque
from datetime import datetime
import pandas
import pandas.core.datetools as dt
import re
from statsmodels.compatnp.py3k import asbytes
regex = re.compile(asbytes('<(.*) (\w)([\d]+)>.*'))
lines = deque(open(path, 'rb'))
to_skip = 0
while asbytes('*/') not in lines.popleft():
#while '*/' not in lines.popleft():
to_skip += 1
while True:
to_skip += 1
line = lines.popleft()
m = regex.match(line)
if m:
year, freq, start_point = m.groups()
break
data = np.genfromtxt(path, names=True, skip_header=to_skip+1)
n = len(data)
# generate the corresponding date range (using pandas for now)
start_point = int(start_point)
year = int(year)
offsets = {
asbytes('Q') : dt.BQuarterEnd(),
asbytes('M') : dt.BMonthEnd(),
asbytes('A') : dt.BYearEnd()
}
# create an instance
offset = offsets[freq]
inc = offset * (start_point - 1)
start_date = offset.rollforward(datetime(year, 1, 1)) + inc
offset = offsets[freq]
try:
from pandas import DatetimeIndex # pylint: disable=E0611
date_range = DatetimeIndex(start=start_date, freq=offset, periods=n)
except ImportError:
from pandas import DateRange
date_range = DateRange(start_date, offset=offset, periods=n)
return data, date_range
def parse_lutkepohl_data(path): # pragma: no cover
"""
Parse data files from Lutkepohl (2005) book
Source for data files: www.jmulti.de
"""
from collections import deque
from datetime import datetime
import pandas
import pandas.core.datetools as dt
import re
regex = re.compile('<(.*) (\w)([\d]+)>.*')
lines = deque(open(path))
to_skip = 0
while '*/' not in lines.popleft():
to_skip += 1
while True:
to_skip += 1
line = lines.popleft()
m = regex.match(line)
if m:
year, freq, start_point = m.groups()
break
data = np.genfromtxt(path, names=True, skip_header=to_skip+1)
n = len(data)
# generate the corresponding date range (using pandas for now)
start_point = int(start_point)
year = int(year)
offsets = {
'Q' : dt.BQuarterEnd(),
'M' : dt.BMonthEnd(),
'A' : dt.BYearEnd()
}
# create an instance
offset = offsets[freq]
inc = offset * (start_point - 1)
start_date = offset.rollforward(datetime(year, 1, 1)) + inc
offset = offsets[freq]
date_range = pandas.DateRange(start_date, offset=offset, periods=n)
return data, date_range
