def aux_filter(ctx):
return assoc(
ctx, 'aux',
dict(
list(
filter(lambda d: first(get('nlcdtrn', second(d))) != 0,
ctx['aux'].items()))))
def test_trim():
inputs = list()
inputs.append({'include': True, 'acquired': '2015-04-01'})
inputs.append({'include': True, 'acquired': '2017-04-01'})
inputs.append({'include': False, 'acquired': '2017-01-01'})
inputs.append({'include': True, 'acquired': '2016-04-01'})
included = chips.dates(filter(lambda d: d['include'] is True, inputs))
trimmed = chips.trim(dates=included, chips=inputs)
assert len(list(trimmed)) == len(included)
assert set(included) == set(map(lambda x: x['acquired'], trimmed))
def compact(specs):
"""Excludes nodata and fill values from the dataset
Args:
specs (dict): A spec with value, nodata and fill keys
Returns:
Filtered specs excluding nodata and fill
"""
return filter(lambda s: s['value'] not in (s['nodata'], s['fill']), specs)
def only(ubids, specs):
"""Filter specs on ubids.
Args:
ubids (seq): [ubid1, ubid3]
specs (seq): [{spec1}, {spec2}, {spec3}, ...})
Returns:
tuple: [{spec1}, {spec3}]
"""
return tuple(cytoolz.filter(lambda x: x['ubid'] in ubids, specs))
def create(x, y, acquired, cfg):
"""Create a timeseries.
Args:
x (int): x coordinate
y (int): y coordinate
acquired (string): iso8601 date range
cfg (dict): A Merlin configuration
Returns:
tuple - Results of format_fn applied to results of chips_fn
"""
x, y = get_in(['chip', 'proj-pt'], cfg['snap_fn'](x=x, y=y))
# get specs
specmap = cfg['specs_fn'](specs=cfg['registry_fn']())
# get function that will return chipmap.
# Don't create state with a realized variable to preserve memory
chipmap = partial(chips.mapped,
x=x,
y=y,
acquired=acquired,
specmap=specmap,
chips_fn=cfg['chips_fn'])
# calculate locations chip. There's another function
# here to be split out and organized.
grid = first(filter(lambda x: x['name'] == 'chip', cfg['grid_fn']()))
cw, ch = specs.refspec(specmap).get('data_shape')
locations = partial(chips.locations,
x=x,
y=y,
cw=cw,
ch=ch,
rx=grid.get('rx'),
ry=grid.get('ry'),
sx=grid.get('sx'),
sy=grid.get('sy'))
return cfg['format_fn'](x=x,
y=y,
locations=locations(),
dates_fn=cfg['dates_fn'],
specmap=specmap,
chipmap=chipmap())
def test_flat_map_square_filter_workers(nums):
def _generator(x):
yield x
yield x + 1
yield x + 2
nums_py = map(lambda x: x**2, nums)
nums_py = cz.mapcat(_generator, nums_py)
nums_py = cz.filter(lambda x: x > 1, nums_py)
nums_py = list(nums_py)
nums_pl = pl.sync.map(lambda x: x**2, nums)
nums_pl = pl.sync.flat_map(_generator, nums_pl, workers=3)
nums_pl = pl.sync.filter(lambda x: x > 1, nums_pl)
nums_pl = list(nums_pl)
assert sorted(nums_pl) == sorted(nums_py)
def test_flat_map_square_filter_workers(nums: tp.List[int]):
def generator(x):
yield x
yield x + 1
yield x + 2
nums_py = map(lambda x: x**2, nums)
nums_py = cz.mapcat(generator, nums_py)
nums_py = cz.filter(lambda x: x > 1, nums_py)
nums_py = list(nums_py)
nums_pl = pl.thread.map(lambda x: x**2, nums)
nums_pl = pl.thread.flat_map(generator, nums_pl, workers=2)
nums_pl = pl.thread.filter(lambda x: x > 1, nums_pl)
nums_pl = list(nums_pl)
assert sorted(nums_pl) == sorted(nums_py)
def test_flat_map_square_filter_workers_pipe(nums):
def _generator(x):
yield x
yield x + 1
yield x + 2
nums_py = map(lambda x: x**2, nums)
nums_py = cz.mapcat(_generator, nums_py)
nums_py = cz.filter(lambda x: x > 1, nums_py)
nums_py = list(nums_py)
nums_pl = (nums
| pl.task.map(lambda x: x**2)
| pl.task.flat_map(_generator, workers=3)
| pl.task.filter(lambda x: x > 1)
| list)
assert sorted(nums_pl) == sorted(nums_py)
def test_flat_map_square_filter_workers_pipe(nums: tp.List[int]):
def generator(x):
yield x
yield x + 1
yield x + 2
nums_py = map(lambda x: x**2, nums)
nums_py = cz.mapcat(generator, nums_py)
nums_py = cz.filter(lambda x: x > 1, nums_py)
nums_py = list(nums_py)
nums_pl = (nums
| pl.process.map(lambda x: x**2)
| pl.process.flat_map(generator, workers=3)
| pl.process.filter(lambda x: x > 1)
| list)
assert sorted(nums_pl) == sorted(nums_py)
async def test_flat_map_square_filter_workers_pipe_3(nums: tp.List[int]):
def _generator(x):
yield x
yield x + 1
yield x + 2
nums_py = map(lambda x: x ** 2, nums)
nums_py = cz.mapcat(_generator, nums_py)
nums_py = cz.filter(lambda x: x > 1, nums_py)
nums_py = list(nums_py)
async def gt1(x):
return x > 1
nums_pl = await (
nums
| pl.task.map(lambda x: x ** 2)
| pl.task.flat_map(_generator, workers=3)
| pl.task.filter(gt1)
)
assert sorted(nums_pl) == sorted(nums_py)
def mean_log_freq(indices):
return np.mean(log_freqs[indices]) if len(indices) else None
def min_log_freq(indices):
return np.min(log_freqs[indices]) if len(indices) else None
doc_sentence_indices = [[
lookup_indices(sent.split()) for sent in doc.split('\n')
] for doc in reviews.tokenized]
mean_llk = [
list(
cytoolz.filter(None,
[mean_log_freq(indices) for indices in doc_indices]))
for doc_indices in doc_sentence_indices
]
min_llk = [
list(
cytoolz.filter(None,
[min_log_freq(indices) for indices in doc_indices]))
for doc_indices in doc_sentence_indices
]
mean_mean_llk = pd.Series(
[np.mean(llks) if len(llks) > 0 else None for llks in mean_llk])
mean_min_llk = pd.Series(
[np.mean(llks) if len(llks) > 0 else None for llks in min_llk])
logging.info("Identify the best reviews.")
# Mark the top reviews: top-5 ranked reviews of restaurants with at least the median # reviews,
def chip_grid(config):
return first(filter(lambda x: x['name'] == 'chip',
config.get('grid_fn')()))
def tile_grid(config):
return first(filter(lambda x: x['name'] == 'tile',
config.get('grid_fn')()))
