def _asarray_tuplesafe(values, dtype=None):
from pandas.core.index import Index
if not (isinstance(values, (list, tuple)) or hasattr(values, '__array__')):
values = list(values)
elif isinstance(values, Index):
return values.values
if isinstance(values, list) and dtype in [np.object_, object]:
return lib.list_to_object_array(values)
result = np.asarray(values, dtype=dtype)
if issubclass(result.dtype.type, compat.string_types):
result = np.asarray(values, dtype=object)
if result.ndim == 2:
if isinstance(values, list):
return lib.list_to_object_array(values)
else:
# Making a 1D array that safely contains tuples is a bit tricky
# in numpy, leading to the following
try:
result = np.empty(len(values), dtype=object)
result[:] = values
except ValueError:
# we have a list-of-list
result[:] = [tuple(x) for x in values]
return result
def _asarray_tuplesafe(values, dtype=None):
from pandas.core.index import Index
if not isinstance(values, (list, tuple, np.ndarray)):
values = list(values)
elif isinstance(values, Index):
return values.values
if isinstance(values, list) and dtype in [np.object_, object]:
return lib.list_to_object_array(values)
result = np.asarray(values, dtype=dtype)
if issubclass(result.dtype.type, basestring):
result = np.asarray(values, dtype=object)
if result.ndim == 2:
if isinstance(values, list):
return lib.list_to_object_array(values)
else:
# Making a 1D array that safely contains tuples is a bit tricky
# in numpy, leading to the following
result = np.empty(len(values), dtype=object)
result[:] = values
return result
def _asarray_tuplesafe(values, dtype=None):
from pandas.core.index import Index
if not (isinstance(values, (list, tuple)) or hasattr(values, '__array__')):
values = list(values)
elif isinstance(values, Index):
return values.values
if isinstance(values, list) and dtype in [np.object_, object]:
return lib.list_to_object_array(values)
result = np.asarray(values, dtype=dtype)
if issubclass(result.dtype.type, compat.string_types):
result = np.asarray(values, dtype=object)
if result.ndim == 2:
if isinstance(values, list):
return lib.list_to_object_array(values)
else:
# Making a 1D array that safely contains tuples is a bit tricky
# in numpy, leading to the following
try:
result = np.empty(len(values), dtype=object)
result[:] = values
except ValueError:
# we have a list-of-list
result[:] = [tuple(x) for x in values]
return result
def _asarray_tuplesafe(values, dtype=None):
from pandas.core.index import Index
if not isinstance(values, (list, tuple, np.ndarray)):
values = list(values)
elif isinstance(values, Index):
return values.values
if isinstance(values, list) and dtype in [np.object_, object]:
return lib.list_to_object_array(values)
result = np.asarray(values, dtype=dtype)
if issubclass(result.dtype.type, basestring):
result = np.asarray(values, dtype=object)
if result.ndim == 2:
if isinstance(values, list):
return lib.list_to_object_array(values)
else:
# Making a 1D array that safely contains tuples is a bit tricky
# in numpy, leading to the following
result = np.empty(len(values), dtype=object)
result[:] = values
return result
def na_op(x, y):
if com.is_categorical_dtype(x) != (not np.isscalar(y) and com.is_categorical_dtype(y)):
msg = "Cannot compare a Categorical for op {op} with type {typ}. If you want to \n" \
"compare values, use 'series <op> np.asarray(cat)'."
raise TypeError(msg.format(op=op,typ=type(y)))
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (pa.Array, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def na_op(x, y):
try:
result = op(x, y)
except TypeError:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if (is_bool_dtype(x.dtype) and is_bool_dtype(y.dtype)):
result = op(x, y) # when would this be hit?
else:
x = com._ensure_object(x)
y = com._ensure_object(y)
result = lib.vec_binop(x, y, op)
else:
try:
# let null fall thru
if not isnull(y):
y = bool(y)
result = lib.scalar_binop(x, y, op)
except:
raise TypeError("cannot compare a dtyped [{0}] array with "
"a scalar of type [{1}]".format(
x.dtype, type(y).__name__))
return result
def na_op(x, y):
# dispatch to the categorical if we have a categorical
# in either operand
if com.is_categorical_dtype(x):
return op(x, y)
elif com.is_categorical_dtype(y) and not lib.isscalar(y):
return op(y, x)
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def na_op(x, y):
try:
result = op(x, y)
except TypeError:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if (x.dtype == np.bool_
and y.dtype == np.bool_): # pragma: no cover
result = op(x, y) # when would this be hit?
else:
x = com._ensure_object(x)
y = com._ensure_object(y)
result = lib.vec_binop(x, y, op)
else:
try:
# let null fall thru
if not isnull(y):
y = bool(y)
result = lib.scalar_binop(x, y, op)
except:
raise TypeError("cannot compare a dtyped [{0}] array with "
"a scalar of type [{1}]".format(
x.dtype,
type(y).__name__))
return result
def na_op(x, y):
if com.is_categorical_dtype(x) != com.is_categorical_dtype(y):
msg = "Cannot compare a Categorical for op {op} with type {typ}. If you want to \n" \
"compare values, use 'series <op> np.asarray(cat)'."
raise TypeError(msg.format(op=op, typ=type(y)))
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (pa.Array, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def na_op(x, y):
# dispatch to the categorical if we have a categorical
# in either operand
if com.is_categorical_dtype(x):
return op(x,y)
elif com.is_categorical_dtype(y) and not lib.isscalar(y):
return op(y,x)
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def _possibly_convert_platform(values):
""" try to do platform conversion, allow ndarray or list here """
if isinstance(values, (list, tuple)):
values = lib.list_to_object_array(list(values))
if getattr(values, 'dtype', None) == np.object_:
if hasattr(values, '_values'):
values = values._values
values = lib.maybe_convert_objects(values)
return values
def _possibly_convert_platform(values):
""" try to do platform conversion, allow ndarray or list here """
if isinstance(values, (list, tuple)):
values = lib.list_to_object_array(list(values))
if getattr(values, 'dtype', None) == np.object_:
if hasattr(values, '_values'):
values = values._values
values = lib.maybe_convert_objects(values)
return values
def _comp_method_OBJECT_ARRAY(op, x, y):
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, ABCSeries, ABCIndex)):
if not is_object_dtype(y.dtype):
y = y.astype(np.object_)
if isinstance(y, (ABCSeries, ABCIndex)):
y = y.values
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
return result
def na_op(x, y):
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (pa.Array, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x,name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def na_op(x, y):
if x.dtype == np.object_:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (pa.Array, pd.Series)):
if y.dtype != np.object_:
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except (AttributeError):
result = op(x, y)
return result
def unique1d(values):
"""
Hash table-based unique
"""
if np.issubdtype(values.dtype, np.floating):
table = lib.Float64HashTable(len(values))
uniques = np.array(table.unique(com._ensure_float64(values)),
dtype=np.float64)
elif np.issubdtype(values.dtype, np.datetime64):
table = lib.Int64HashTable(len(values))
uniques = np.array(table.unique(com._ensure_int64(values)),
dtype=np.int64)
uniques = uniques.view('M8[ns]')
elif np.issubdtype(values.dtype, np.integer):
table = lib.Int64HashTable(len(values))
uniques = np.array(table.unique(com._ensure_int64(values)),
dtype=np.int64)
else:
table = lib.PyObjectHashTable(len(values))
uniques = table.unique(com._ensure_object(values))
uniques = lib.list_to_object_array(uniques)
return uniques
def __getitem__(self, key):
"""
Retrieve column or slice from DataFrame
"""
try:
# unsure about how kludgy this is
s = self._series[key]
s.name = key
return s
except (TypeError, KeyError):
if isinstance(key, slice):
date_rng = self.index[key]
return self.reindex(date_rng)
elif isinstance(key, (np.ndarray, list)):
if isinstance(key, list):
key = lib.list_to_object_array(key)
# also raises Exception if object array with NA values
if com._is_bool_indexer(key):
key = np.asarray(key, dtype=bool)
return self._getitem_array(key)
else: # pragma: no cover
raise
def __getitem__(self, key):
"""
Retrieve column or slice from DataFrame
"""
try:
# unsure about how kludgy this is
s = self._series[key]
s.name = key
return s
except (TypeError, KeyError):
if isinstance(key, slice):
date_rng = self.index[key]
return self.reindex(date_rng)
elif isinstance(key, (np.ndarray, list)):
if isinstance(key, list):
key = lib.list_to_object_array(key)
# also raises Exception if object array with NA values
if com._is_bool_indexer(key):
key = np.asarray(key, dtype=bool)
return self._getitem_array(key)
else: # pragma: no cover
raise
def _zip2(*args):
return lib.list_to_object_array(zip(*args))
def na_op(x, y):
# dispatch to the categorical if we have a categorical
# in either operand
if is_categorical_dtype(x):
return op(x,y)
elif is_categorical_dtype(y) and not isscalar(y):
return op(y,x)
if is_object_dtype(x.dtype):
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if not is_object_dtype(y.dtype):
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
# we want to compare like types
# we only want to convert to integer like if
# we are not NotImplemented, otherwise
# we would allow datetime64 (but viewed as i8) against
# integer comparisons
if is_datetimelike_v_numeric(x, y):
raise TypeError("invalid type comparison")
# numpy does not like comparisons vs None
if isscalar(y) and isnull(y):
y = np.nan
# we have a datetime/timedelta and may need to convert
mask = None
if needs_i8_conversion(x) or (not isscalar(y) and needs_i8_conversion(y)):
if isscalar(y):
y = _index.convert_scalar(x,_values_from_object(y))
else:
y = y.view('i8')
if name == '__ne__':
mask = notnull(x)
else:
mask = isnull(x)
x = x.view('i8')
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except AttributeError:
result = op(x, y)
if mask is not None and mask.any():
result[mask] = False
return result
def _zip2(*args):
return lib.list_to_object_array(lzip(*args))
def na_op(x, y):
# dispatch to the categorical if we have a categorical
# in either operand
if is_categorical_dtype(x):
return op(x,y)
elif is_categorical_dtype(y) and not isscalar(y):
return op(y,x)
if is_object_dtype(x.dtype):
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if not is_object_dtype(y.dtype):
result = lib.vec_compare(x, y.astype(np.object_), op)
else:
result = lib.vec_compare(x, y, op)
else:
result = lib.scalar_compare(x, y, op)
else:
# we want to compare like types
# we only want to convert to integer like if
# we are not NotImplemented, otherwise
# we would allow datetime64 (but viewed as i8) against
# integer comparisons
if is_datetimelike_v_numeric(x, y):
raise TypeError("invalid type comparison")
# numpy does not like comparisons vs None
if isscalar(y) and isnull(y):
y = np.nan
# we have a datetime/timedelta and may need to convert
mask = None
if needs_i8_conversion(x) or (not isscalar(y) and needs_i8_conversion(y)):
if isscalar(y):
y = _index.convert_scalar(x,_values_from_object(y))
else:
y = y.view('i8')
if name == '__ne__':
mask = notnull(x)
else:
mask = isnull(x)
x = x.view('i8')
try:
result = getattr(x, name)(y)
if result is NotImplemented:
raise TypeError("invalid type comparison")
except AttributeError:
result = op(x, y)
if mask is not None and mask.any():
result[mask] = False
return result