def concatenate_join_units(join_units, concat_axis, copy):
"""
Concatenate values from several join units along selected axis.
"""
if concat_axis == 0 and len(join_units) > 1:
# Concatenating join units along ax0 is handled in _merge_blocks.
raise AssertionError("Concatenating join units along axis0")
empty_dtype, upcasted_na = get_empty_dtype_and_na(join_units)
to_concat = [
ju.get_reindexed_values(empty_dtype=empty_dtype,
upcasted_na=upcasted_na) for ju in join_units
]
if len(to_concat) == 1:
# Only one block, nothing to concatenate.
concat_values = to_concat[0]
if copy:
if isinstance(concat_values, np.ndarray):
# non-reindexed (=not yet copied) arrays are made into a view
# in JoinUnit.get_reindexed_values
if concat_values.base is not None:
concat_values = concat_values.copy()
else:
concat_values = concat_values.copy()
else:
concat_values = _concat._concat_compat(to_concat, axis=concat_axis)
return concat_values
def concatenate_join_units(join_units, concat_axis, copy):
"""
Concatenate values from several join units along selected axis.
"""
if concat_axis == 0 and len(join_units) > 1:
# Concatenating join units along ax0 is handled in _merge_blocks.
raise AssertionError("Concatenating join units along axis0")
empty_dtype, upcasted_na = get_empty_dtype_and_na(join_units)
to_concat = [ju.get_reindexed_values(empty_dtype=empty_dtype,
upcasted_na=upcasted_na)
for ju in join_units]
if len(to_concat) == 1:
# Only one block, nothing to concatenate.
concat_values = to_concat[0]
if copy:
if isinstance(concat_values, np.ndarray):
# non-reindexed (=not yet copied) arrays are made into a view
# in JoinUnit.get_reindexed_values
if concat_values.base is not None:
concat_values = concat_values.copy()
else:
concat_values = concat_values.copy()
else:
concat_values = _concat._concat_compat(to_concat, axis=concat_axis)
return concat_values
def get_result(self):
# series only
if self._is_series:
# stack blocks
if self.axis == 0:
# concat Series with length to keep dtype as much
non_empties = [x for x in self.objs if len(x) > 0]
if len(non_empties) > 0:
values = [x._values for x in non_empties]
else:
values = [x._values for x in self.objs]
new_data = _concat._concat_compat(values)
name = com._consensus_name_attr(self.objs)
cons = _concat._get_series_result_type(new_data)
return (cons(new_data, index=self.new_axes[0],
name=name, dtype=new_data.dtype)
.__finalize__(self, method='concat'))
# combine as columns in a frame
else:
data = dict(zip(range(len(self.objs)), self.objs))
cons = _concat._get_series_result_type(data)
index, columns = self.new_axes
df = cons(data, index=index)
df.columns = columns
return df.__finalize__(self, method='concat')
# combine block managers
else:
mgrs_indexers = []
for obj in self.objs:
mgr = obj._data
indexers = {}
for ax, new_labels in enumerate(self.new_axes):
if ax == self.axis:
# Suppress reindexing on concat axis
continue
obj_labels = mgr.axes[ax]
if not new_labels.equals(obj_labels):
indexers[ax] = obj_labels.reindex(new_labels)[1]
mgrs_indexers.append((obj._data, indexers))
new_data = concatenate_block_managers(
mgrs_indexers, self.new_axes, concat_axis=self.axis,
copy=self.copy)
if not self.copy:
new_data._consolidate_inplace()
cons = _concat._get_frame_result_type(new_data, self.objs)
return (cons._from_axes(new_data, self.new_axes)
.__finalize__(self, method='concat'))
def get_result(self):
# series only
if self._is_series:
# stack blocks
if self.axis == 0:
# concat Series with length to keep dtype as much
non_empties = [x for x in self.objs if len(x) > 0]
if len(non_empties) > 0:
values = [x._values for x in non_empties]
else:
values = [x._values for x in self.objs]
new_data = _concat._concat_compat(values)
name = com._consensus_name_attr(self.objs)
cons = _concat._get_series_result_type(new_data)
return (cons(new_data, index=self.new_axes[0],
name=name, dtype=new_data.dtype)
.__finalize__(self, method='concat'))
# combine as columns in a frame
else:
data = dict(zip(range(len(self.objs)), self.objs))
cons = _concat._get_series_result_type(data)
index, columns = self.new_axes
df = cons(data, index=index)
df.columns = columns
return df.__finalize__(self, method='concat')
# combine block managers
else:
mgrs_indexers = []
for obj in self.objs:
mgr = obj._data
indexers = {}
for ax, new_labels in enumerate(self.new_axes):
if ax == self.axis:
# Suppress reindexing on concat axis
continue
obj_labels = mgr.axes[ax]
if not new_labels.equals(obj_labels):
indexers[ax] = obj_labels.reindex(new_labels)[1]
mgrs_indexers.append((obj._data, indexers))
new_data = concatenate_block_managers(
mgrs_indexers, self.new_axes, concat_axis=self.axis,
copy=self.copy)
if not self.copy:
new_data._consolidate_inplace()
cons = _concat._get_frame_result_type(new_data, self.objs)
return (cons._from_axes(new_data, self.new_axes)
.__finalize__(self, method='concat'))
def _fast_union(self, other):
if len(other) == 0:
return self.view(type(self))
if len(self) == 0:
return other.view(type(self))
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
left_end = left[-1]
right_end = right[-1]
# concatenate
if left_end < right_end:
loc = right.searchsorted(left_end, side='right')
right_chunk = right.values[loc:]
dates = _concat._concat_compat((left.values, right_chunk))
return self._shallow_copy(dates)
else:
return left
def _fast_union(self, other):
if len(other) == 0:
return self.view(type(self))
if len(self) == 0:
return other.view(type(self))
# to make our life easier, "sort" the two ranges
if self[0] <= other[0]:
left, right = self, other
else:
left, right = other, self
left_end = left[-1]
right_end = right[-1]
# concatenate
if left_end < right_end:
loc = right.searchsorted(left_end, side='right')
right_chunk = right.values[loc:]
dates = _concat._concat_compat((left.values, right_chunk))
return self._shallow_copy(dates)
else:
return left
def lreshape(data, groups, dropna=True, label=None):
"""
Reshape long-format data to wide. Generalized inverse of DataFrame.pivot
Parameters
----------
data : DataFrame
groups : dict
{new_name : list_of_columns}
dropna : boolean, default True
Examples
--------
>>> data = pd.DataFrame({'hr1': [514, 573], 'hr2': [545, 526],
... 'team': ['Red Sox', 'Yankees'],
... 'year1': [2007, 2007], 'year2': [2008, 2008]})
>>> data
hr1 hr2 team year1 year2
0 514 545 Red Sox 2007 2008
1 573 526 Yankees 2007 2008
>>> pd.lreshape(data, {'year': ['year1', 'year2'], 'hr': ['hr1', 'hr2']})
team year hr
0 Red Sox 2007 514
1 Yankees 2007 573
2 Red Sox 2008 545
3 Yankees 2008 526
Returns
-------
reshaped : DataFrame
"""
if isinstance(groups, dict):
keys = list(groups.keys())
values = list(groups.values())
else:
keys, values = zip(*groups)
all_cols = list(set.union(*[set(x) for x in values]))
id_cols = list(data.columns.difference(all_cols))
K = len(values[0])
for seq in values:
if len(seq) != K:
raise ValueError('All column lists must be same length')
mdata = {}
pivot_cols = []
for target, names in zip(keys, values):
to_concat = [data[col].values for col in names]
import pandas.core.dtypes.concat as _concat
mdata[target] = _concat._concat_compat(to_concat)
pivot_cols.append(target)
for col in id_cols:
mdata[col] = np.tile(data[col].values, K)
if dropna:
mask = np.ones(len(mdata[pivot_cols[0]]), dtype=bool)
for c in pivot_cols:
mask &= notna(mdata[c])
if not mask.all():
mdata = {k: v[mask] for k, v in compat.iteritems(mdata)}
return data._constructor(mdata, columns=id_cols + pivot_cols)
def lreshape(data, groups, dropna=True, label=None):
"""
Reshape long-format data to wide. Generalized inverse of DataFrame.pivot
Parameters
----------
data : DataFrame
groups : dict
{new_name : list_of_columns}
dropna : boolean, default True
Examples
--------
>>> import pandas as pd
>>> data = pd.DataFrame({'hr1': [514, 573], 'hr2': [545, 526],
... 'team': ['Red Sox', 'Yankees'],
... 'year1': [2007, 2007], 'year2': [2008, 2008]})
>>> data
hr1 hr2 team year1 year2
0 514 545 Red Sox 2007 2008
1 573 526 Yankees 2007 2008
>>> pd.lreshape(data, {'year': ['year1', 'year2'], 'hr': ['hr1', 'hr2']})
team year hr
0 Red Sox 2007 514
1 Yankees 2007 573
2 Red Sox 2008 545
3 Yankees 2008 526
Returns
-------
reshaped : DataFrame
"""
if isinstance(groups, dict):
keys = list(groups.keys())
values = list(groups.values())
else:
keys, values = zip(*groups)
all_cols = list(set.union(*[set(x) for x in values]))
id_cols = list(data.columns.difference(all_cols))
K = len(values[0])
for seq in values:
if len(seq) != K:
raise ValueError('All column lists must be same length')
mdata = {}
pivot_cols = []
for target, names in zip(keys, values):
to_concat = [data[col].values for col in names]
mdata[target] = _concat._concat_compat(to_concat)
pivot_cols.append(target)
for col in id_cols:
mdata[col] = np.tile(data[col].values, K)
if dropna:
mask = np.ones(len(mdata[pivot_cols[0]]), dtype=bool)
for c in pivot_cols:
mask &= notna(mdata[c])
if not mask.all():
mdata = dict((k, v[mask]) for k, v in compat.iteritems(mdata))
return DataFrame(mdata, columns=id_cols + pivot_cols)
