def make_axis_dummies(frame, axis='minor', transform=None):
"""
Construct 1-0 dummy variables corresponding to designated axis
labels
Parameters
----------
frame : DataFrame
axis : {'major', 'minor'}, default 'minor'
transform : function, default None
Function to apply to axis labels first. For example, to
get "day of week" dummies in a time series regression
you might call::
make_axis_dummies(panel, axis='major',
transform=lambda d: d.weekday())
Returns
-------
dummies : DataFrame
Column names taken from chosen axis
"""
numbers = {'major': 0, 'minor': 1}
num = numbers.get(axis, axis)
items = frame.index.levels[num]
codes = frame.index.codes[num]
if transform is not None:
mapped_items = items.map(transform)
codes, items = _factorize_from_iterable(mapped_items.take(codes))
values = np.eye(len(items), dtype=float)
values = values.take(codes, axis=0)
return DataFrame(values, columns=items, index=frame.index)
def make_axis_dummies(frame, axis="minor", transform=None):
"""
Construct 1-0 dummy variables corresponding to designated axis
labels
Parameters
----------
frame : DataFrame
axis : {'major', 'minor'}, default 'minor'
transform : function, default None
Function to apply to axis labels first. For example, to
get "day of week" dummies in a time series regression
you might call::
make_axis_dummies(panel, axis='major',
transform=lambda d: d.weekday())
Returns
-------
dummies : DataFrame
Column names taken from chosen axis
"""
numbers = {"major": 0, "minor": 1}
num = numbers.get(axis, axis)
items = frame.index.levels[num]
codes = frame.index.codes[num]
if transform is not None:
mapped_items = items.map(transform)
codes, items = _factorize_from_iterable(mapped_items.take(codes))
values = np.eye(len(items), dtype=float)
values = values.take(codes, axis=0)
return DataFrame(values, columns=items, index=frame.index)
def _get_dummies_1d(
data,
prefix,
prefix_sep="_",
dummy_na=False,
sparse=False,
drop_first=False,
dtype=None,
):
from pandas.core.reshape.concat import concat
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_frame(data):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
return DataFrame(index=index)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_frame(data)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_frame(data)
number_of_cols = len(levels)
if prefix is None:
dummy_cols = levels
else:
# PY2 embedded unicode, gh-22084
def _make_col_name(prefix, prefix_sep, level):
fstr = "{prefix}{prefix_sep}{level}"
return fstr.format(prefix=prefix,
prefix_sep=prefix_sep,
level=level)
dummy_cols = [
_make_col_name(prefix, prefix_sep, level) for level in levels
]
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
if is_integer_dtype(dtype):
fill_value = 0
elif dtype == bool:
fill_value = False
else:
fill_value = 0.0
sparse_series = []
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
mask = codes != -1
codes = codes[mask]
n_idx = np.arange(N)[mask]
for ndx, code in zip(n_idx, codes):
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(
np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs),
fill_value=fill_value,
dtype=dtype,
)
sparse_series.append(Series(data=sarr, index=index, name=col))
out = concat(sparse_series, axis=1, copy=False)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
def _stack_multi_columns(frame, level_num=-1, dropna=True):
def _convert_level_number(level_num, columns):
"""
Logic for converting the level number to something we can safely pass
to swaplevel:
We generally want to convert the level number into a level name, except
when columns do not have names, in which case we must leave as a level
number
"""
if level_num in columns.names:
return columns.names[level_num]
else:
if columns.names[level_num] is None:
return level_num
else:
return columns.names[level_num]
this = frame.copy()
# this makes life much simpler
if level_num != frame.columns.nlevels - 1:
# roll levels to put selected level at end
roll_columns = this.columns
for i in range(level_num, frame.columns.nlevels - 1):
# Need to check if the ints conflict with level names
lev1 = _convert_level_number(i, roll_columns)
lev2 = _convert_level_number(i + 1, roll_columns)
roll_columns = roll_columns.swaplevel(lev1, lev2)
this.columns = roll_columns
if not this.columns.is_lexsorted():
# Workaround the edge case where 0 is one of the column names,
# which interferes with trying to sort based on the first
# level
level_to_sort = _convert_level_number(0, this.columns)
this = this.sort_index(level=level_to_sort, axis=1)
# tuple list excluding level for grouping columns
if len(frame.columns.levels) > 2:
tuples = list(
zip(*[
lev.take(level_codes) for lev, level_codes in zip(
this.columns.levels[:-1], this.columns.codes[:-1])
]))
unique_groups = [key for key, _ in itertools.groupby(tuples)]
new_names = this.columns.names[:-1]
new_columns = MultiIndex.from_tuples(unique_groups, names=new_names)
else:
new_columns = this.columns.levels[0]._shallow_copy(
name=this.columns.names[0])
unique_groups = new_columns
# time to ravel the values
new_data = {}
level_vals = this.columns.levels[-1]
level_codes = sorted(set(this.columns.codes[-1]))
level_vals_used = level_vals[level_codes]
levsize = len(level_codes)
drop_cols = []
for key in unique_groups:
try:
loc = this.columns.get_loc(key)
except KeyError:
drop_cols.append(key)
continue
# can make more efficient?
# we almost always return a slice
# but if unsorted can get a boolean
# indexer
if not isinstance(loc, slice):
slice_len = len(loc)
else:
slice_len = loc.stop - loc.start
if slice_len != levsize:
chunk = this.loc[:, this.columns[loc]]
chunk.columns = level_vals.take(chunk.columns.codes[-1])
value_slice = chunk.reindex(columns=level_vals_used).values
else:
if frame._is_homogeneous_type and is_extension_array_dtype(
frame.dtypes.iloc[0]):
dtype = this[this.columns[loc]].dtypes.iloc[0]
subset = this[this.columns[loc]]
value_slice = dtype.construct_array_type()._concat_same_type(
[x._values for _, x in subset.items()])
N, K = this.shape
idx = np.arange(N * K).reshape(K, N).T.ravel()
value_slice = value_slice.take(idx)
elif frame._is_mixed_type:
value_slice = this[this.columns[loc]].values
else:
value_slice = this.values[:, loc]
if value_slice.ndim > 1:
# i.e. not extension
value_slice = value_slice.ravel()
new_data[key] = value_slice
if len(drop_cols) > 0:
new_columns = new_columns.difference(drop_cols)
N = len(this)
if isinstance(this.index, MultiIndex):
new_levels = list(this.index.levels)
new_names = list(this.index.names)
new_codes = [lab.repeat(levsize) for lab in this.index.codes]
else:
old_codes, old_levels = _factorize_from_iterable(this.index)
new_levels = [old_levels]
new_codes = [old_codes.repeat(levsize)]
new_names = [this.index.name] # something better?
new_levels.append(level_vals)
new_codes.append(np.tile(level_codes, N))
new_names.append(frame.columns.names[level_num])
new_index = MultiIndex(levels=new_levels,
codes=new_codes,
names=new_names,
verify_integrity=False)
result = frame._constructor(new_data, index=new_index, columns=new_columns)
# more efficient way to go about this? can do the whole masking biz but
# will only save a small amount of time...
if dropna:
result = result.dropna(axis=0, how="all")
return result
def factorize(index):
if index.is_unique:
return index, np.arange(len(index))
codes, categories = _factorize_from_iterable(index)
return categories, codes
def _get_dummies_1d(data, prefix, prefix_sep='_', dummy_na=False,
sparse=False, drop_first=False, dtype=None):
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_Frame(data, sparse):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
if not sparse:
return DataFrame(index=index)
else:
return SparseDataFrame(index=index, default_fill_value=0)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_Frame(data, sparse)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_Frame(data, sparse)
number_of_cols = len(levels)
if prefix is not None:
dummy_strs = [u'{prefix}{sep}{level}' if isinstance(v, text_type)
else '{prefix}{sep}{level}' for v in levels]
dummy_cols = [dummy_str.format(prefix=prefix, sep=prefix_sep, level=v)
for dummy_str, v in zip(dummy_strs, levels)]
else:
dummy_cols = levels
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
sparse_series = {}
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
mask = codes != -1
codes = codes[mask]
n_idx = np.arange(N)[mask]
for ndx, code in zip(n_idx, codes):
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs), fill_value=0,
dtype=dtype)
sparse_series[col] = SparseSeries(data=sarr, index=index)
out = SparseDataFrame(sparse_series, index=index, columns=dummy_cols,
default_fill_value=0,
dtype=dtype)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
def _make_concat_multiindex(indexes, keys, levels=None, names=None):
if (levels is None
and isinstance(keys[0], tuple)) or (levels is not None
and len(levels) > 1):
zipped = list(zip(*keys))
if names is None:
names = [None] * len(zipped)
if levels is None:
_, levels = _factorize_from_iterables(zipped)
else:
levels = [ensure_index(x) for x in levels]
else:
zipped = [keys]
if names is None:
names = [None]
if levels is None:
levels = [ensure_index(keys)]
else:
levels = [ensure_index(x) for x in levels]
if not _all_indexes_same(indexes):
codes_list = []
# things are potentially different sizes, so compute the exact codes
# for each level and pass those to MultiIndex.from_arrays
for hlevel, level in zip(zipped, levels):
to_concat = []
for key, index in zip(hlevel, indexes):
try:
i = level.get_loc(key)
except KeyError:
raise ValueError(
"Key {key!s} not in level {level!s}".format(
key=key, level=level))
to_concat.append(np.repeat(i, len(index)))
codes_list.append(np.concatenate(to_concat))
concat_index = _concat_indexes(indexes)
# these go at the end
if isinstance(concat_index, MultiIndex):
levels.extend(concat_index.levels)
codes_list.extend(concat_index.codes)
else:
codes, categories = _factorize_from_iterable(concat_index)
levels.append(categories)
codes_list.append(codes)
if len(names) == len(levels):
names = list(names)
else:
# make sure that all of the passed indices have the same nlevels
if not len({idx.nlevels for idx in indexes}) == 1:
raise AssertionError("Cannot concat indices that do"
" not have the same number of levels")
# also copies
names = names + _get_consensus_names(indexes)
return MultiIndex(levels=levels,
codes=codes_list,
names=names,
verify_integrity=False)
new_index = indexes[0]
n = len(new_index)
kpieces = len(indexes)
# also copies
new_names = list(names)
new_levels = list(levels)
# construct codes
new_codes = []
# do something a bit more speedy
for hlevel, level in zip(zipped, levels):
hlevel = ensure_index(hlevel)
mapped = level.get_indexer(hlevel)
mask = mapped == -1
if mask.any():
raise ValueError(
"Values not found in passed level: {hlevel!s}".format(
hlevel=hlevel[mask]))
new_codes.append(np.repeat(mapped, n))
if isinstance(new_index, MultiIndex):
new_levels.extend(new_index.levels)
new_codes.extend([np.tile(lab, kpieces) for lab in new_index.codes])
else:
new_levels.append(new_index)
new_codes.append(np.tile(np.arange(n), kpieces))
if len(new_names) < len(new_levels):
new_names.extend(new_index.names)
return MultiIndex(levels=new_levels,
codes=new_codes,
names=new_names,
verify_integrity=False)
def _get_dummies_1d(data, prefix, prefix_sep='_', dummy_na=False,
sparse=False, drop_first=False, dtype=None):
from pandas.core.reshape.concat import concat
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_frame(data):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
return DataFrame(index=index)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_frame(data)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_frame(data)
number_of_cols = len(levels)
if prefix is None:
dummy_cols = levels
else:
# PY2 embedded unicode, gh-22084
def _make_col_name(prefix, prefix_sep, level):
fstr = '{prefix}{prefix_sep}{level}'
return fstr.format(prefix=prefix,
prefix_sep=prefix_sep,
level=level)
dummy_cols = [_make_col_name(prefix, prefix_sep, level)
for level in levels]
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
if is_integer_dtype(dtype):
fill_value = 0
elif dtype == bool:
fill_value = False
else:
fill_value = 0.0
sparse_series = []
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
mask = codes != -1
codes = codes[mask]
n_idx = np.arange(N)[mask]
for ndx, code in zip(n_idx, codes):
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs),
fill_value=fill_value,
dtype=dtype)
sparse_series.append(Series(data=sarr, index=index, name=col))
out = concat(sparse_series, axis=1, copy=False)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
def factorize(index):
if index.is_unique:
return index, np.arange(len(index))
codes, categories = _factorize_from_iterable(index)
return categories, codes
def _get_dummies_1d(data, prefix, prefix_sep='_', dummy_na=False,
sparse=False, drop_first=False, dtype=None):
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_Frame(data, sparse):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
if not sparse:
return DataFrame(index=index)
else:
return SparseDataFrame(index=index, default_fill_value=0)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_Frame(data, sparse)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_Frame(data, sparse)
number_of_cols = len(levels)
if prefix is not None:
dummy_strs = [u'{prefix}{sep}{level}' if isinstance(v, text_type)
else '{prefix}{sep}{level}' for v in levels]
dummy_cols = [dummy_str.format(prefix=prefix, sep=prefix_sep, level=v)
for dummy_str, v in zip(dummy_strs, levels)]
else:
dummy_cols = levels
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
sparse_series = {}
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
for ndx, code in enumerate(codes):
if code == -1:
# Blank entries if not dummy_na and code == -1, #GH4446
continue
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs), fill_value=0,
dtype=dtype)
sparse_series[col] = SparseSeries(data=sarr, index=index)
out = SparseDataFrame(sparse_series, index=index, columns=dummy_cols,
default_fill_value=0,
dtype=dtype)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
def _make_concat_multiindex(indexes, keys, levels=None, names=None):
if ((levels is None and isinstance(keys[0], tuple)) or
(levels is not None and len(levels) > 1)):
zipped = compat.lzip(*keys)
if names is None:
names = [None] * len(zipped)
if levels is None:
_, levels = _factorize_from_iterables(zipped)
else:
levels = [ensure_index(x) for x in levels]
else:
zipped = [keys]
if names is None:
names = [None]
if levels is None:
levels = [ensure_index(keys)]
else:
levels = [ensure_index(x) for x in levels]
if not _all_indexes_same(indexes):
codes_list = []
# things are potentially different sizes, so compute the exact codes
# for each level and pass those to MultiIndex.from_arrays
for hlevel, level in zip(zipped, levels):
to_concat = []
for key, index in zip(hlevel, indexes):
try:
i = level.get_loc(key)
except KeyError:
raise ValueError('Key {key!s} not in level {level!s}'
.format(key=key, level=level))
to_concat.append(np.repeat(i, len(index)))
codes_list.append(np.concatenate(to_concat))
concat_index = _concat_indexes(indexes)
# these go at the end
if isinstance(concat_index, MultiIndex):
levels.extend(concat_index.levels)
codes_list.extend(concat_index.codes)
else:
codes, categories = _factorize_from_iterable(concat_index)
levels.append(categories)
codes_list.append(codes)
if len(names) == len(levels):
names = list(names)
else:
# make sure that all of the passed indices have the same nlevels
if not len({idx.nlevels for idx in indexes}) == 1:
raise AssertionError("Cannot concat indices that do"
" not have the same number of levels")
# also copies
names = names + _get_consensus_names(indexes)
return MultiIndex(levels=levels, codes=codes_list, names=names,
verify_integrity=False)
new_index = indexes[0]
n = len(new_index)
kpieces = len(indexes)
# also copies
new_names = list(names)
new_levels = list(levels)
# construct codes
new_codes = []
# do something a bit more speedy
for hlevel, level in zip(zipped, levels):
hlevel = ensure_index(hlevel)
mapped = level.get_indexer(hlevel)
mask = mapped == -1
if mask.any():
raise ValueError('Values not found in passed level: {hlevel!s}'
.format(hlevel=hlevel[mask]))
new_codes.append(np.repeat(mapped, n))
if isinstance(new_index, MultiIndex):
new_levels.extend(new_index.levels)
new_codes.extend([np.tile(lab, kpieces) for lab in new_index.codes])
else:
new_levels.append(new_index)
new_codes.append(np.tile(np.arange(n), kpieces))
if len(new_names) < len(new_levels):
new_names.extend(new_index.names)
return MultiIndex(levels=new_levels, codes=new_codes, names=new_names,
verify_integrity=False)
def _get_dummies_1d(self,
data,
prefix,
prefix_sep='_',
dummy_na=False,
sparse=False,
drop_first=False):
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
def get_empty_Frame(data, sparse):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
if not sparse:
return DataFrame(index=index)
else:
return SparseDataFrame(index=index, default_fill_value=0)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_Frame(data, sparse)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_Frame(data, sparse)
number_of_cols = len(levels)
if prefix is not None:
dummy_cols = ['%s%s%s' % (prefix, prefix_sep, v) for v in levels]
else:
dummy_cols = levels
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
sparse_series = {}
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
for ndx, code in enumerate(codes):
if code == -1:
# Blank entries if not dummy_na and code == -1, #GH4446
continue
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(np.ones(len(ixs), dtype=np.uint8),
sparse_index=IntIndex(N, ixs),
fill_value=0,
dtype=np.uint8)
sparse_series[col] = SparseSeries(data=sarr, index=index)
out = SparseDataFrame(sparse_series,
index=index,
columns=dummy_cols,
default_fill_value=0,
dtype=np.uint8)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=np.uint8).take(codes,
axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
