def get_distributions_for_columns(data, columns):
"""Compute the distributions for columns.
Parameters
----------
data : data.Table
List of column indices into the `data.domain` (indices can be
:class:`int` or instances of `Orange.data.Variable`)
"""
domain = data.domain
# Normailze the columns to int indices
columns = [
col if isinstance(col, int) else domain.index(col) for col in columns
]
try:
# Try the optimized code path (query the table|storage directly).
dist_unks = data._compute_distributions(columns)
except NotImplementedError:
# Use default slow(er) implementation.
return [get_distribution(data, i) for i in columns]
else:
# dist_unkn is a list of (values, unknowns)
return [
get_distribution(dist, domain[col], unknown)
for col, (dist, unknown) in zip(columns, dist_unks)
]
def from_data(cls, variable, data):
variable = _get_variable(data, variable)
try:
dist, unknowns = data._compute_distributions([variable])[0]
except NotImplementedError:
col = data[:, variable]
dtype = col.dtype
if data.has_weights():
if not "float" in dtype.name and "float" in col.dtype.name:
dtype = col.dtype.name
dist = np.empty((2, len(col)), dtype=dtype)
dist[0, :] = col
dist[1, :] = data.W
else:
dist = np.ones((2, len(col)), dtype=dtype)
dist[0, :] = col
dist.sort(axis=0)
dist = np.array(_orange.valuecount(dist))
unknowns = len(col) - dist.shape[1]
self = super().__new__(cls, dist.shape)
self[:] = dist
self.unknowns = unknowns
self.variable = variable
return self
def from_data(cls, data, variable):
variable = _get_variable(data, variable)
try:
dist, unknowns = data._compute_distributions([variable])[0]
self = super().__new__(cls, len(dist))
self[:] = dist
self.unknowns = unknowns
except NotImplementedError:
self = super().__new__(cls, len(variable.values))
self[:] = np.zeros(len(variable.values))
self.unknowns = 0
if data.has_weights():
for inst, w in zip(data, data.W):
val = inst[variable]
if not np.isnan(val):
self[int(val)] += w
else:
self.unknowns += w
else:
for inst in data:
val = inst[variable]
if val == val:
self[int(val)] += 1
else:
self.unknowns += 1
self.variable = variable
return self
def from_data(cls, data, variable):
variable = _get_variable(data, variable)
try:
dist, unknowns = data._compute_distributions([variable])[0]
self = super().__new__(cls, len(dist))
self[:] = dist
self.unknowns = unknowns
except NotImplementedError:
self = np.zeros(len(variable.values))
self.unknowns = 0
if data.has_weights():
for val, w in zip(data[:, variable], data.W):
if not math.isnan(val):
self[val] += w
else:
self.unknowns += w
else:
for inst in data:
val = inst[variable]
if val == val:
self[val] += 1
else:
self.unknowns += 1
self.variable = variable
return self
def from_data(cls, variable, data):
variable = _get_variable(data, variable)
try:
dist, unknowns = data._compute_distributions([variable])[0]
except NotImplementedError:
col = data[:, variable]
dtype = col.dtype
if data.has_weights():
if not "float" in dtype.name and "float" in col.dtype.name:
dtype = col.dtype.name
dist = np.empty((2, len(col)), dtype=dtype)
dist[0, :] = col
dist[1, :] = data.W
else:
dist = np.ones((2, len(col)), dtype=dtype)
dist[0, :] = col
dist.sort(axis=0)
dist = np.array(_orange.valuecount(dist))
unknowns = len(col) - dist.shape[1]
self = super().__new__(cls, dist.shape)
self[:] = dist
self.unknowns = unknowns
self.variable = variable
return self
def get_distributions_for_columns(data, columns):
"""Compute the distributions for columns.
Parameters
----------
data : data.Table
List of column indices into the `data.domain` (indices can be
:class:`int` or instances of `Orange.data.Variable`)
"""
domain = data.domain
# Normailze the columns to int indices
columns = [col if isinstance(col, int) else domain.index(col) for col in columns]
try:
# Try the optimized code path (query the table|storage directly).
dist_unks = data._compute_distributions(columns)
except NotImplementedError:
# Use default slow(er) implementation.
return [get_distribution(data, i) for i in columns]
else:
# dist_unkn is a list of (values, unknowns)
return [get_distribution(dist, domain[col], unknown)
for col, (dist, unknown) in zip(columns, dist_unks)]
