def _sanitize_column(self, key, value, **kwargs):
"""
Creates a new SparseArray from the input value.
Parameters
----------
key : object
value : scalar, Series, or array-like
kwargs : dict
Returns
-------
sanitized_column : SparseArray
"""
sp_maker = lambda x, index=None: SparseArray(x,
index=index,
fill_value=self.
_default_fill_value,
kind=self._default_kind)
if isinstance(value, SparseSeries):
clean = value.reindex(self.index).as_sparse_array(
fill_value=self._default_fill_value, kind=self._default_kind)
elif isinstance(value, SparseArray):
if len(value) != len(self.index):
raise AssertionError('Length of values does not match '
'length of index')
clean = value
elif hasattr(value, '__iter__'):
if isinstance(value, Series):
clean = value.reindex(self.index)
if not isinstance(value, SparseSeries):
clean = sp_maker(clean)
else:
if len(value) != len(self.index):
raise AssertionError('Length of values does not match '
'length of index')
clean = sp_maker(value)
# Scalar
else:
clean = sp_maker(value, self.index)
# always return a SparseArray!
return clean
def _init_dict(self, data, index, columns, dtype=None):
# pre-filter out columns if we passed it
if columns is not None:
columns = _ensure_index(columns)
data = dict(
(k, v) for k, v in compat.iteritems(data) if k in columns)
else:
columns = Index(_try_sort(list(data.keys())))
if index is None:
index = extract_index(list(data.values()))
sp_maker = lambda x: SparseArray(x,
kind=self._default_kind,
fill_value=self._default_fill_value,
copy=True,
dtype=dtype)
sdict = DataFrame()
for k, v in compat.iteritems(data):
if isinstance(v, Series):
# Force alignment, no copy necessary
if not v.index.equals(index):
v = v.reindex(index)
if not isinstance(v, SparseSeries):
v = sp_maker(v.values)
elif isinstance(v, SparseArray):
v = v.copy()
else:
if isinstance(v, dict):
v = [v.get(i, nan) for i in index]
v = sp_maker(v)
sdict[k] = v
# TODO: figure out how to handle this case, all nan's?
# add in any other columns we want to have (completeness)
nan_vec = np.empty(len(index))
nan_vec.fill(nan)
for c in columns:
if c not in sdict:
sdict[c] = sp_maker(nan_vec)
return to_manager(sdict, columns, index)
def _init_dict(self, data, index, columns, dtype=None):
# pre-filter out columns if we passed it
if columns is not None:
columns = _ensure_index(columns)
data = {k: v for k, v in compat.iteritems(data) if k in columns}
else:
keys = com._dict_keys_to_ordered_list(data)
columns = Index(keys)
if index is None:
index = extract_index(list(data.values()))
sp_maker = lambda x: SparseArray(x,
kind=self._default_kind,
fill_value=self._default_fill_value,
copy=True,
dtype=dtype)
sdict = {}
for k, v in compat.iteritems(data):
if isinstance(v, Series):
# Force alignment, no copy necessary
if not v.index.equals(index):
v = v.reindex(index)
if not isinstance(v, SparseSeries):
v = sp_maker(v.values)
elif isinstance(v, SparseArray):
v = v.copy()
else:
if isinstance(v, dict):
v = [v.get(i, np.nan) for i in index]
v = sp_maker(v)
sdict[k] = v
# TODO: figure out how to handle this case, all nan's?
# add in any other columns we want to have (completeness)
nan_arr = np.empty(len(index), dtype='float64')
nan_arr.fill(np.nan)
nan_arr = sp_maker(nan_arr)
sdict.update((c, nan_arr) for c in columns if c not in sdict)
return to_manager(sdict, columns, index)
def __init__(self, data=None, index=None, columns=None, default_kind=None,
default_fill_value=None, dtype=None, copy=False):
# pick up the defaults from the Sparse structures
if isinstance(data, SparseDataFrame):
if index is None:
index = data.index
if columns is None:
columns = data.columns
if default_fill_value is None:
default_fill_value = data.default_fill_value
if default_kind is None:
default_kind = data.default_kind
elif isinstance(data, (SparseSeries, SparseArray)):
if index is None:
index = data.index
if default_fill_value is None:
default_fill_value = data.fill_value
if columns is None and hasattr(data, 'name'):
columns = [data.name]
if columns is None:
raise Exception("cannot pass a series w/o a name or columns")
data = {columns[0]: data}
if default_fill_value is None:
default_fill_value = np.nan
if default_kind is None:
default_kind = 'block'
self._default_kind = default_kind
self._default_fill_value = default_fill_value
if is_scipy_sparse(data):
mgr = self._init_spmatrix(data, index, columns, dtype=dtype,
fill_value=default_fill_value)
elif isinstance(data, dict):
mgr = self._init_dict(data, index, columns, dtype=dtype)
elif isinstance(data, (np.ndarray, list)):
mgr = self._init_matrix(data, index, columns, dtype=dtype)
elif isinstance(data, SparseDataFrame):
mgr = self._init_mgr(data._data,
dict(index=index, columns=columns),
dtype=dtype, copy=copy)
elif isinstance(data, DataFrame):
mgr = self._init_dict(data, data.index, data.columns, dtype=dtype)
elif isinstance(data, Series):
mgr = self._init_dict(data.to_frame(), data.index,
columns=None, dtype=dtype)
elif isinstance(data, BlockManager):
mgr = self._init_mgr(data, axes=dict(index=index, columns=columns),
dtype=dtype, copy=copy)
elif data is None:
data = DataFrame()
if index is None:
index = Index([])
else:
index = _ensure_index(index)
if columns is None:
columns = Index([])
else:
for c in columns:
data[c] = SparseArray(np.nan, index=index,
kind=self._default_kind,
fill_value=self._default_fill_value)
mgr = to_manager(data, columns, index)
if dtype is not None:
mgr = mgr.astype(dtype)
else:
msg = ('SparseDataFrame called with unknown type "{data_type}" '
'for data argument')
raise TypeError(msg.format(data_type=type(data).__name__))
generic.NDFrame.__init__(self, mgr)
def sp_maker(x, index=None):
return SparseArray(x, index=index,
fill_value=self._default_fill_value,
kind=self._default_kind)
def sp_maker(x):
return SparseArray(x, kind=self._default_kind,
fill_value=self._default_fill_value,
copy=True, dtype=dtype)
