def __init__(self, val):
super().__init__()
if isinstance(val, bcolz.carray):
self._carray = val
elif isinstance(val, list) or isinstance(val, np.ndarray):
self._carray = bcolz.carray(val, expectedlen=Column.DEFAULT_BLOCK_LEN)
else:
raise DazzleError("Invalid argument in ResultColumn.%s()" % method_name())
def replace_value(self, old, new):
"""
Replace old by new in my values
"""
if type(new) != int and type(new) != float and type(new) != bool:
raise ValueError("new must be int, float or bool: in %s()" % (method_name()))
ca = self.carray
idx = bcolz.eval('ca == ' + str(old))
self.carray[idx] = new
def rename(self, new_name):
if not re.match("[A-Za-z][_a-zA-Z0-9]*$", new_name):
raise DazzleError("Invalid column identifier: '%s' in %s" % (new_name, method_name()))
ct = self.table.ctable
if new_name in ct.names:
raise DazzleError("LiteralColumn identifier already in use: '%s' in %s" % (new_name, method_name()))
col_pos = self.position
carray = self.carray
ct.delcol(self._name) # TODO should use keep=True, but didn't succeed
ct.addcol(carray, name=new_name, pos=col_pos)
self._name = new_name
def replace_list(self, old, new):
"""
Replace each ith value in old by each ith value in new in my values
"""
# TODO rewrite this method: it takes very long when there are many replacements to perform
# for instance, replacing CategoryID in userinfo in avito dataset is very sloooow
if len([x for x in new if type(x) != int and type(x) != float and type(x) != bool]) > 0:
raise ValueError("Values in new must be int, float or bool: in %s()" % (method_name()))
ca = self.carray
cond = "(" + ") | (". join(["ca == " + str(o) for o in old]) + ")"
mask = bcolz.eval(cond)
rep = [i for i in mask.wheretrue()]
pairs = dict(zip(old, new))
if len(rep) > 0:
self.carray[rep] = [pairs[o] for o in self.carray[rep]]
def __init__(self, name, table, data=None): # TODO add default value (when resize), and expected_length params
super().__init__()
if not re.match("[A-Za-z][_a-zA-Z0-9]*$", name):
raise DazzleError("Invalid column identifier: '%s' in %s()" % (name, method_name()))
if type(table).__name__ != "Table":
raise DazzleError("Table parameter expected %s" % (table))
if table.get_column(name) is not None:
raise DazzleError("there is already a column with name %s' in table %s" % (name, table.name))
self._name = name
self._ref_column = None # defined here and not in RefColumn because this property is set *before* the Column is transformed into a RefColumn
self._table = table
table.columns.append(self)
if data is not None:
if len(self._table.columns) > 0 and len(self._table.columns[0].carray) != len(data):
raise DazzleError("Column %s should have same number of values as existing columns" % (name))
self.table.ctable.addcol(data, name, expectedlen=self.table.expected_length)
def mean(self, dtype=np.float64, skipna=True):
raise DazzleError("RefColumn.%() should not be called" % method_name())
def table(self):
if self._table is None:
raise DazzleError('Invalid call to %s: table is undefined' % method_name())
return self._table
