def board_dimensions(self) -> Dimensions:
xs = {c.x for c in self.board}
ys = {c.y for c in self.board}
min_x, max_x = juxt(min, max)(xs)
min_y, max_y = juxt(min, max)(ys)
return Dimensions(Coord(min_x, min_y), Coord(max_x, max_y))
def get_text_from_xml_file(filename):
"""
This is setup for extracting text from the Stackoverflow posts data dump
that is stored in a xml file.
Returns a stream of Post bodies (just the text).
"""
@tlz.curry
def _get_xml_attr(key, xml_element):
return xml_element.attributes[key].value
@tlz.curry
def _try_to_get_xml_attr(key, xml_element, default=''):
try:
return _get_xml_attr(key, xml_element)
except(KeyError):
return default
return tlz.pipe(filename,
minidom.parse, # Not pure
lambda layer0: layer0.getElementsByTagName("posts")[0],
lambda layer1: layer1.getElementsByTagName("row"),
c_map(tlz.juxt(_try_to_get_xml_attr("Title"),
_get_xml_attr("Body"))),
c_map(lambda titleAndBody: '\n\n\n'.join(titleAndBody)))
def hist(self, *funcs):
alphabet = self.alphabet
length = self.length
seqs = ("".join(p) for p in itertools.product(*[alphabet] * length))
num = len(alphabet) ** length
f = juxt(*funcs)
counts = Counter(f(seq) for seq in seqs)
return {k: v / num for (k, v) in counts.items()}
def read(specs, filepath):
"""Reads values from file specified by locations
Args:
filepath (str): Full path of raster file to read
specs (sequence): dicts containing y_index, x_index, y, x
Returns:
sequence: dicts with 'value' key populated
"""
ds = None
try:
ds = gdal.Open(filepath)
val = partial(value, memarray=ds.GetRasterBand(1).GetVirtualMemArray())
reader = juxt([identity, lambda spec: dict(value=val(spec=spec))])
for spec in specs:
yield (merge(reader(spec)))
finally:
ds = None
def hash_values(self, key):
"""Return the hashes for the given key."""
return juxt(self.hash_functions)(key)
