def gen_groups(self, records, chunksize=None):
"""Generate the QIF groups"""
for chnk in chunk(records, chunksize):
keyfunc = self.id if self.is_split else self.account
for gee in group(chnk, keyfunc):
yield gee
def gen_groups(self, records, chunksize=None):
""" Generate the QIF groups """
for chnk in chunk(records, chunksize):
keyfunc = self.id if self.is_split else self.account
for gee in group(chnk, keyfunc):
yield gee
def solution2(debug=False):
# Set `debug` to True if you would like to view debugging statements
from urllib.request import urlopen
from operator import itemgetter
from functools import partial
from pprint import pprint
from meza import process as pr, fntools as ft
from meza.io import read_json
url4 = 'https://api.github.com/search/repositories?q=data&sort=stars&order=desc'
f = urlopen(url4)
records = read_json(f, path='items.item')
# repos without a language have a value of None, which meza doesn't like
filled = pr.fillempty(records, value='', fields=['language'])
filled, preview = pr.peek(filled)
print(preview[0]) if debug else None
# meza doesn't do well with nested dicts
flat = (dict(ft.flatten(r)) for r in filled)
flat, preview = pr.peek(flat)
print(preview[0]) if debug else None
# `watchers` is the pivot field to aggregate by
# `language` is the pivot field to group by
args = ('watchers', 'language')
# the pivot fields we want to include in each row
rows = ['has_pages', 'owner_type']
pivotted = pr.pivot(flat, *args, rows=rows, op=sum)
pivotted, preview = pr.peek(pivotted)
print(preview[0]) if debug else None
# `rows` are the fields we don't want to normalize (since `invert` is true)
kwargs = {'rows': rows, 'invert': True}
# `watchers` is the field to use for the normalized values
# `language` is the field to use for the normalized key
normal = pr.normalize(pivotted, *args, **kwargs)
normal, preview = pr.peek(normal)
print(preview[0]) if debug else None
# aggregate by `watchers`
agg_keyfunc = itemgetter('watchers')
# group by `has_pages` and `owner_type`
group_keyfunc = lambda x: tuple(x[r] for r in rows)
aggregator = partial(max, key=agg_keyfunc)
# Only emit the groups, not the group key (since `tupled` is False)
kwargs = {'tupled': False, 'aggregator': aggregator}
grouped = pr.group(normal, group_keyfunc, **kwargs)
grouped, preview = pr.peek(grouped)
print(preview[0]) if debug else None
sgrouped = sorted(grouped, key=agg_keyfunc, reverse=True)
for record in sgrouped:
pprint(record)
def gen_groups(self, records, chunksize=None):
for chnk in chunk(records, chunksize):
cleansed = [
{k: next(xmlize([v])) for k, v in c.items()} for c in chnk]
keyfunc = self.id if self.is_split else self.account
for g in group(cleansed, keyfunc):
yield g
def gen_groups(self, records, chunksize=None):
""" Generate the OFX groups """
for chnk in chunk(records, chunksize):
cleansed = [
{k: next(xmlize([v])) for k, v in c.items()} for c in chnk]
keyfunc = self.id if self.is_split else self.account
for gee in group(cleansed, keyfunc):
yield gee
def gen_trxns(self, groups, collapse=False):
for grp, transactions in groups:
if self.is_split and collapse:
# group transactions by `collapse` field and sum the amounts
byaccount = group(transactions, collapse)
op = lambda values: sum(map(utils.convert_amount, values))
merger = partial(merge, pred=self.amount, op=op)
trxns = [merger(dicts) for _, dicts in byaccount]
else:
trxns = transactions
yield (grp, trxns)
def gen_trxns(self, groups, collapse=False):
""" Generate transactions """
for grp, transactions in groups:
if self.is_split and collapse:
# group transactions by `collapse` field and sum the amounts
byaccount = group(transactions, collapse)
oprtn = lambda values: sum(map(utils.convert_amount, values))
merger = partial(merge, pred=self.amount, op=oprtn)
trxns = [merger(dicts) for _, dicts in byaccount]
else:
trxns = transactions
yield (grp, trxns)
url4 = 'https://api.github.com/search/repositories?q=data&sort=stars&order=desc'
f = '???'
records = '???'
# Some of the functions you will use are `ft.flatten`, `pr.pivot`, `pr.normalize`
# `pr.group`, `pr.fillempty`, and `pr.aggregate`. You can view documentation for
# these functions in the doc-blocks at the links below:
#
# https://github.com/reubano/meza/blob/master/meza/process.py
# https://github.com/reubano/meza/blob/master/meza/fntools.py
# ...
keyfunc = lambda x: True
kwargs = {}
grouped = pr.group([], keyfunc, **kwargs)
for key, group in grouped:
# ...
pass
if __name__ == "__main__":
print('-----------')
print('Solution #1')
print('-----------')
solution1()
print('\n-----------')
print('Solution #2')
print('-----------')
solution2()
