def run_binary(self, df, other, assert_func, test_flex=False,
numexpr_ops={'gt', 'lt', 'ge', 'le', 'eq', 'ne'}):
"""
tests solely that the result is the same whether or not numexpr is
enabled. Need to test whether the function does the correct thing
elsewhere.
"""
expr._MIN_ELEMENTS = 0
expr.set_test_mode(True)
operations = ['gt', 'lt', 'ge', 'le', 'eq', 'ne']
for arith in operations:
if test_flex:
op = lambda x, y: getattr(df, arith)(y)
op.__name__ = arith
else:
op = getattr(operator, arith)
expr.set_use_numexpr(False)
expected = op(df, other)
expr.set_use_numexpr(True)
expr.get_test_result()
result = op(df, other)
used_numexpr = expr.get_test_result()
try:
if arith in numexpr_ops:
assert used_numexpr, "Did not use numexpr as expected."
else:
assert not used_numexpr, "Used numexpr unexpectedly."
assert_func(expected, result)
except Exception:
pprint_thing("Failed test with operation %r" % arith)
pprint_thing("test_flex was %r" % test_flex)
raise
def run_arithmetic(self, df, other, assert_func, check_dtype=False,
test_flex=True):
expr._MIN_ELEMENTS = 0
operations = ['add', 'sub', 'mul', 'mod', 'truediv', 'floordiv']
for arith in operations:
operator_name = arith
if arith == 'div':
operator_name = 'truediv'
if test_flex:
op = lambda x, y: getattr(df, arith)(y)
op.__name__ = arith
else:
op = getattr(operator, operator_name)
expr.set_use_numexpr(False)
expected = op(df, other)
expr.set_use_numexpr(True)
result = op(df, other)
try:
if check_dtype:
if arith == 'truediv':
assert expected.dtype.kind == 'f'
assert_func(expected, result)
except Exception:
pprint_thing("Failed test with operator %r" % op.__name__)
raise
def _write_cell(self, s, kind='td', indent=0, tags=None):
if tags is not None:
start_tag = '<{kind} {tags}>'.format(kind=kind, tags=tags)
else:
start_tag = '<{kind}>'.format(kind=kind)
if self.escape:
# escape & first to prevent double escaping of &
esc = OrderedDict([('&', r'&'), ('<', r'<'),
('>', r'>')])
else:
esc = {}
rs = pprint_thing(s, escape_chars=esc).strip()
if self.render_links and _is_url(rs):
rs_unescaped = pprint_thing(s, escape_chars={}).strip()
start_tag += '<a href="{url}" target="_blank">'.format(
url=rs_unescaped)
end_a = '</a>'
else:
end_a = ''
self.write(u'{start}{rs}{end_a}</{kind}>'.format(
start=start_tag, rs=rs, end_a=end_a, kind=kind), indent)
def __unicode__(self):
"""Print a generic n-ary operator and its operands using infix
notation"""
# recurse over the operands
parened = ('({0})'.format(pprint_thing(opr))
for opr in self.operands)
return pprint_thing(' {0} '.format(self.op).join(parened))
def _print(result, error=None):
if error is not None:
error = str(error)
v = ("%-16.16s [%-16.16s]: [typ->%-8.8s,obj->%-8.8s,"
"key1->(%-4.4s),key2->(%-4.4s),axis->%s] %s" %
(name, result, t, o, method1, method2, a, error or ''))
if _verbose:
pprint_thing(v)
def test_copy_index_name_checking(self):
# don't want to be able to modify the index stored elsewhere after
# making a copy
self.ts.index.name = None
assert self.ts.index.name is None
assert self.ts is self.ts
cp = self.ts.copy()
cp.index.name = 'foo'
printing.pprint_thing(self.ts.index.name)
assert self.ts.index.name is None
def test_repr_binary_type():
import string
letters = string.ascii_letters
try:
raw = bytes(letters, encoding=cf.get_option('display.encoding'))
except TypeError:
raw = bytes(letters)
b = str(compat.bytes_to_str(raw))
res = printing.pprint_thing(b, quote_strings=True)
assert res == repr(b)
res = printing.pprint_thing(b, quote_strings=False)
assert res == b
def check_extension(cls, ext):
"""checks that path's extension against the Writer's supported
extensions. If it isn't supported, raises UnsupportedFiletypeError."""
if ext.startswith('.'):
ext = ext[1:]
if not any(ext in extension for extension in cls.supported_extensions):
msg = (u("Invalid extension for engine '{engine}': '{ext}'")
.format(engine=pprint_thing(cls.engine),
ext=pprint_thing(ext)))
raise ValueError(msg)
else:
return True
def _replot_ax(ax, freq, kwargs):
data = getattr(ax, '_plot_data', None)
# clear current axes and data
ax._plot_data = []
ax.clear()
_decorate_axes(ax, freq, kwargs)
lines = []
labels = []
if data is not None:
for series, plotf, kwds in data:
series = series.copy()
idx = series.index.asfreq(freq, how='S')
series.index = idx
ax._plot_data.append((series, plotf, kwds))
# for tsplot
if isinstance(plotf, str):
# XXX _plot_classes is private and shouldn't be imported
# here. But as tsplot is deprecated, and we'll remove this
# code soon, it's probably better to not overcomplicate
# things, and just leave this the way it was implemented
from pandas.plotting._core import _plot_classes
plotf = _plot_classes()[plotf]._plot
lines.append(plotf(ax, series.index._mpl_repr(),
series.values, **kwds)[0])
labels.append(pprint_thing(series.name))
return lines, labels
def _summary(self, name=None):
"""
Return a summarized representation.
Parameters
----------
name : str
name to use in the summary representation
Returns
-------
String with a summarized representation of the index
"""
formatter = self._formatter_func
if len(self) > 0:
index_summary = ', %s to %s' % (formatter(self[0]),
formatter(self[-1]))
else:
index_summary = ''
if name is None:
name = type(self).__name__
result = '%s: %s entries%s' % (printing.pprint_thing(name),
len(self), index_summary)
if self.freq:
result += '\nFreq: %s' % self.freqstr
# display as values, not quoted
result = result.replace("'", "")
return result
def _convert_expression(expr):
"""Convert an object to an expression.
Thus function converts an object to an expression (a unicode string) and
checks to make sure it isn't empty after conversion. This is used to
convert operators to their string representation for recursive calls to
:func:`~pandas.eval`.
Parameters
----------
expr : object
The object to be converted to a string.
Returns
-------
s : unicode
The string representation of an object.
Raises
------
ValueError
* If the expression is empty.
"""
s = pprint_thing(expr)
_check_expression(s)
return s
def check_keys_split(self, decoded):
"checks that dict has only the appropriate keys for orient='split'"
bad_keys = set(decoded.keys()).difference(set(self._split_keys))
if bad_keys:
bad_keys = ", ".join(bad_keys)
raise ValueError(u("JSON data had unexpected key(s): {bad_keys}")
.format(bad_keys=pprint_thing(bad_keys)))
def _replot_ax(ax, freq, kwargs):
data = getattr(ax, '_plot_data', None)
# clear current axes and data
ax._plot_data = []
ax.clear()
_decorate_axes(ax, freq, kwargs)
lines = []
labels = []
if data is not None:
for series, plotf, kwds in data:
series = series.copy()
idx = series.index.asfreq(freq, how='S')
series.index = idx
ax._plot_data.append((series, plotf, kwds))
# for tsplot
if isinstance(plotf, compat.string_types):
from pandas.plotting._core import _plot_klass
plotf = _plot_klass[plotf]._plot
lines.append(plotf(ax, series.index._mpl_repr(),
series.values, **kwds)[0])
labels.append(pprint_thing(series.name))
return lines, labels
def __repr__(self):
"""
Return a string representation for this object.
"""
prepr = pprint_thing(self, escape_chars=('\t', '\r', '\n'),
quote_strings=True)
return "%s(%s, dtype='%s')" % (type(self).__name__, prepr, self.dtype)
def _grouped_plot(plotf, data, column=None, by=None, numeric_only=True,
figsize=None, sharex=True, sharey=True, layout=None,
rot=0, ax=None, **kwargs):
if figsize == 'default':
# allowed to specify mpl default with 'default'
warnings.warn("figsize='default' is deprecated. Specify figure "
"size by tuple instead", FutureWarning, stacklevel=5)
figsize = None
grouped = data.groupby(by)
if column is not None:
grouped = grouped[column]
naxes = len(grouped)
fig, axes = _subplots(naxes=naxes, figsize=figsize,
sharex=sharex, sharey=sharey, ax=ax,
layout=layout)
_axes = _flatten(axes)
for i, (key, group) in enumerate(grouped):
ax = _axes[i]
if numeric_only and isinstance(group, ABCDataFrame):
group = group._get_numeric_data()
plotf(group, ax, **kwargs)
ax.set_title(pprint_thing(key))
return fig, axes
def parameter_mismatches(self):
errs = []
signature_params = self.signature_parameters
doc_params = tuple(self.doc_parameters)
missing = set(signature_params) - set(doc_params)
if missing:
errs.append(error('PR01', missing_params=pprint_thing(missing)))
extra = set(doc_params) - set(signature_params)
if extra:
errs.append(error('PR02', unknown_params=pprint_thing(extra)))
if (not missing and not extra and signature_params != doc_params
and not (not signature_params and not doc_params)):
errs.append(error('PR03',
actual_params=signature_params,
documented_params=doc_params))
return errs
def parameter_mismatches(self):
errs = []
signature_params = self.signature_parameters
doc_params = tuple(self.doc_parameters)
missing = set(signature_params) - set(doc_params)
if missing:
errs.append(
'Parameters {} not documented'.format(pprint_thing(missing)))
extra = set(doc_params) - set(signature_params)
if extra:
errs.append('Unknown parameters {}'.format(pprint_thing(extra)))
if (not missing and not extra and signature_params != doc_params
and not (not signature_params and not doc_params)):
errs.append('Wrong parameters order. ' +
'Actual: {!r}. '.format(signature_params) +
'Documented: {!r}'.format(doc_params))
return errs
def __unicode__(self):
"""
Return a string representation for this object.
Invoked by unicode(df) in py2 only. Yields a Unicode String in both
py2/py3.
"""
prepr = pprint_thing(self, escape_chars=('\t', '\r', '\n'),
quote_strings=True)
return "%s(%s, dtype='%s')" % (type(self).__name__, prepr, self.dtype)
def andrews_curves(frame, class_column, ax=None, samples=200, color=None,
colormap=None, **kwds):
from math import sqrt, pi
def function(amplitudes):
def f(t):
x1 = amplitudes[0]
result = x1 / sqrt(2.0)
# Take the rest of the coefficients and resize them
# appropriately. Take a copy of amplitudes as otherwise numpy
# deletes the element from amplitudes itself.
coeffs = np.delete(np.copy(amplitudes), 0)
coeffs.resize(int((coeffs.size + 1) / 2), 2)
# Generate the harmonics and arguments for the sin and cos
# functions.
harmonics = np.arange(0, coeffs.shape[0]) + 1
trig_args = np.outer(harmonics, t)
result += np.sum(coeffs[:, 0, np.newaxis] * np.sin(trig_args) +
coeffs[:, 1, np.newaxis] * np.cos(trig_args),
axis=0)
return result
return f
n = len(frame)
class_col = frame[class_column]
classes = frame[class_column].drop_duplicates()
df = frame.drop(class_column, axis=1)
t = np.linspace(-pi, pi, samples)
used_legends = set()
color_values = _get_standard_colors(num_colors=len(classes),
colormap=colormap, color_type='random',
color=color)
colors = dict(zip(classes, color_values))
if ax is None:
ax = plt.gca(xlim=(-pi, pi))
for i in range(n):
row = df.iloc[i].values
f = function(row)
y = f(t)
kls = class_col.iat[i]
label = pprint_thing(kls)
if label not in used_legends:
used_legends.add(label)
ax.plot(t, y, color=colors[kls], label=label, **kwds)
else:
ax.plot(t, y, color=colors[kls], **kwds)
ax.legend(loc='upper right')
ax.grid()
return ax
def _write_cell(self, s, kind='td', indent=0, tags=None):
if tags is not None:
start_tag = '<{kind} {tags}>'.format(kind=kind, tags=tags)
else:
start_tag = '<{kind}>'.format(kind=kind)
if self.escape:
# escape & first to prevent double escaping of &
esc = OrderedDict([('&', r'&'), ('<', r'<'),
('>', r'>')])
else:
esc = {}
rs = pprint_thing(s, escape_chars=esc).strip()
self.write(u'{start}{rs}</{kind}>'
.format(start=start_tag, rs=rs, kind=kind), indent)
def run_arithmetic(self, df, other, assert_func, check_dtype=False,
test_flex=True):
expr._MIN_ELEMENTS = 0
operations = ['add', 'sub', 'mul', 'mod', 'truediv', 'floordiv', 'pow']
if not compat.PY3:
operations.append('div')
for arith in operations:
# numpy >= 1.11 doesn't handle integers
# raised to integer powers
# https://github.com/pandas-dev/pandas/issues/15363
if arith == 'pow' and not _np_version_under1p11:
continue
operator_name = arith
if arith == 'div':
operator_name = 'truediv'
if test_flex:
op = lambda x, y: getattr(df, arith)(y)
op.__name__ = arith
else:
op = getattr(operator, operator_name)
expr.set_use_numexpr(False)
expected = op(df, other)
expr.set_use_numexpr(True)
result = op(df, other)
try:
if check_dtype:
if arith == 'truediv':
assert expected.dtype.kind == 'f'
assert_func(expected, result)
except Exception:
pprint_thing("Failed test with operator %r" % op.__name__)
raise
def writerow(self, row):
def _check_as_is(x):
return (self.quoting == csv.QUOTE_NONNUMERIC and
is_number(x)) or isinstance(x, str)
row = [x if _check_as_is(x)
else pprint_thing(x).encode("utf-8") for x in row]
self.writer.writerow([s for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and re-encode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def _make_plot(self):
colors = self._get_colors()
stacking_id = self._get_stacking_id()
for i, (label, y) in enumerate(self._iter_data()):
ax = self._get_ax(i)
kwds = self.kwds.copy()
label = pprint_thing(label)
kwds['label'] = label
style, kwds = self._apply_style_colors(colors, kwds, i, label)
if style is not None:
kwds['style'] = style
kwds = self._make_plot_keywords(kwds, y)
artists = self._plot(ax, y, column_num=i,
stacking_id=stacking_id, **kwds)
self._add_legend_handle(artists[0], label, index=i)
def apply_series_generator(self):
series_gen = self.series_generator
res_index = self.result_index
i = None
keys = []
results = {}
if self.ignore_failures:
successes = []
for i, v in enumerate(series_gen):
try:
results[i] = self.f(v)
keys.append(v.name)
successes.append(i)
except Exception:
pass
# so will work with MultiIndex
if len(successes) < len(res_index):
res_index = res_index.take(successes)
else:
try:
for i, v in enumerate(series_gen):
results[i] = self.f(v)
keys.append(v.name)
except Exception as e:
if hasattr(e, 'args'):
# make sure i is defined
if i is not None:
k = res_index[i]
e.args = e.args + ('occurred at index %s' %
pprint_thing(k), )
raise
self.results = results
self.res_index = res_index
self.res_columns = self.result_columns
def _gen_dtypes(self) -> Iterator[str]:
"""Iterator with string representation of column dtypes."""
for dtype in self.dtypes:
yield pprint_thing(dtype)
def __str__(self):
return printing.pprint_thing(self.terms)
def _print_as_set(s):
return '{%s}' % ', '.join([pprint_thing(el) for el in s])
def _make_plot(self):
import matplotlib as mpl
colors = self._get_colors()
ncolors = len(colors)
pos_prior = neg_prior = np.zeros(len(self.data))
K = self.nseries
for i, (label, y) in enumerate(self._iter_data(fillna=0)):
ax = self._get_ax(i)
kwds = self.kwds.copy()
if self._is_series:
kwds["color"] = colors
else:
kwds["color"] = colors[i % ncolors]
errors = self._get_errorbars(label=label, index=i)
kwds = dict(kwds, **errors)
label = pprint_thing(label)
if (("yerr" in kwds) or
("xerr" in kwds)) and (kwds.get("ecolor") is None):
kwds["ecolor"] = mpl.rcParams["xtick.color"]
start = 0
if self.log and (y >= 1).all():
start = 1
start = start + self._start_base
if self.subplots:
w = self.bar_width / 2
rect = self._plot(ax,
self.ax_pos + w,
y,
self.bar_width,
start=start,
label=label,
log=self.log,
**kwds)
ax.set_title(label)
elif self.stacked:
mask = y > 0
start = np.where(mask, pos_prior, neg_prior) + self._start_base
w = self.bar_width / 2
rect = self._plot(ax,
self.ax_pos + w,
y,
self.bar_width,
start=start,
label=label,
log=self.log,
**kwds)
pos_prior = pos_prior + np.where(mask, y, 0)
neg_prior = neg_prior + np.where(mask, 0, y)
else:
w = self.bar_width / K
rect = self._plot(ax,
self.ax_pos + (i + 0.5) * w,
y,
w,
start=start,
label=label,
log=self.log,
**kwds)
self._add_legend_handle(rect, label, index=i)
def get_label(i):
try:
return pprint_thing(data.index[i])
except Exception:
return ""
def write(self, s: Any, indent: int = 0) -> None:
rs = pprint_thing(s)
self.elements.append(" " * indent + rs)
def _post_plot_logic(self, ax, data):
x, y = self.x, self.y
ax.set_ylabel(pprint_thing(y))
ax.set_xlabel(pprint_thing(x))
def __init__(
self,
index: Index,
grouper=None,
obj: NDFrame | None = None,
level=None,
sort: bool = True,
observed: bool = False,
in_axis: bool = False,
dropna: bool = True,
) -> None:
self.level = level
self._orig_grouper = grouper
self.grouping_vector = _convert_grouper(index, grouper)
self._all_grouper = None
self._index = index
self._sort = sort
self.obj = obj
self._observed = observed
self.in_axis = in_axis
self._dropna = dropna
self._passed_categorical = False
# we have a single grouper which may be a myriad of things,
# some of which are dependent on the passing in level
ilevel = self._ilevel
if ilevel is not None:
mapper = self.grouping_vector
# In extant tests, the new self.grouping_vector matches
# `index.get_level_values(ilevel)` whenever
# mapper is None and isinstance(index, MultiIndex)
(
self.grouping_vector, # Index
self._codes,
self._group_index,
) = index._get_grouper_for_level(mapper, level=ilevel)
# a passed Grouper like, directly get the grouper in the same way
# as single grouper groupby, use the group_info to get codes
elif isinstance(self.grouping_vector, Grouper):
# get the new grouper; we already have disambiguated
# what key/level refer to exactly, don't need to
# check again as we have by this point converted these
# to an actual value (rather than a pd.Grouper)
assert self.obj is not None # for mypy
_, newgrouper, newobj = self.grouping_vector._get_grouper(
self.obj, validate=False)
self.obj = newobj
ng = newgrouper._get_grouper()
if isinstance(newgrouper, ops.BinGrouper):
# in this case we have `ng is newgrouper`
self.grouping_vector = ng
else:
# ops.BaseGrouper
# use Index instead of ndarray so we can recover the name
self.grouping_vector = Index(ng,
name=newgrouper.result_index.name)
elif is_categorical_dtype(self.grouping_vector):
# a passed Categorical
self._passed_categorical = True
self.grouping_vector, self._all_grouper = recode_for_groupby(
self.grouping_vector, sort, observed)
elif not isinstance(self.grouping_vector,
(Series, Index, ExtensionArray, np.ndarray)):
# no level passed
if getattr(self.grouping_vector, "ndim", 1) != 1:
t = self.name or str(type(self.grouping_vector))
raise ValueError(f"Grouper for '{t}' not 1-dimensional")
self.grouping_vector = index.map(self.grouping_vector)
if not (hasattr(self.grouping_vector, "__len__")
and len(self.grouping_vector) == len(index)):
grper = pprint_thing(self.grouping_vector)
errmsg = ("Grouper result violates len(labels) == "
f"len(data)\nresult: {grper}")
self.grouping_vector = None # Try for sanity
raise AssertionError(errmsg)
if isinstance(self.grouping_vector, np.ndarray):
# if we have a date/time-like grouper, make sure that we have
# Timestamps like
self.grouping_vector = sanitize_to_nanoseconds(
self.grouping_vector)
def test_arith_flex_frame(self):
ops = ['add', 'sub', 'mul', 'div', 'truediv', 'pow', 'floordiv', 'mod']
if not compat.PY3:
aliases = {}
else:
aliases = {'div': 'truediv'}
for op in ops:
try:
alias = aliases.get(op, op)
f = getattr(operator, alias)
result = getattr(self.frame, op)(2 * self.frame)
exp = f(self.frame, 2 * self.frame)
assert_frame_equal(result, exp)
# vs mix float
result = getattr(self.mixed_float, op)(2 * self.mixed_float)
exp = f(self.mixed_float, 2 * self.mixed_float)
assert_frame_equal(result, exp)
_check_mixed_float(result, dtype=dict(C=None))
# vs mix int
if op in ['add', 'sub', 'mul']:
result = getattr(self.mixed_int, op)(2 + self.mixed_int)
exp = f(self.mixed_int, 2 + self.mixed_int)
# no overflow in the uint
dtype = None
if op in ['sub']:
dtype = dict(B='uint64', C=None)
elif op in ['add', 'mul']:
dtype = dict(C=None)
assert_frame_equal(result, exp)
_check_mixed_int(result, dtype=dtype)
# rops
r_f = lambda x, y: f(y, x)
result = getattr(self.frame, 'r' + op)(2 * self.frame)
exp = r_f(self.frame, 2 * self.frame)
assert_frame_equal(result, exp)
# vs mix float
result = getattr(self.mixed_float,
op)(2 * self.mixed_float)
exp = f(self.mixed_float, 2 * self.mixed_float)
assert_frame_equal(result, exp)
_check_mixed_float(result, dtype=dict(C=None))
result = getattr(self.intframe, op)(2 * self.intframe)
exp = f(self.intframe, 2 * self.intframe)
assert_frame_equal(result, exp)
# vs mix int
if op in ['add', 'sub', 'mul']:
result = getattr(self.mixed_int,
op)(2 + self.mixed_int)
exp = f(self.mixed_int, 2 + self.mixed_int)
# no overflow in the uint
dtype = None
if op in ['sub']:
dtype = dict(B='uint64', C=None)
elif op in ['add', 'mul']:
dtype = dict(C=None)
assert_frame_equal(result, exp)
_check_mixed_int(result, dtype=dtype)
except:
printing.pprint_thing("Failing operation %r" % op)
raise
# ndim >= 3
ndim_5 = np.ones(self.frame.shape + (3, 4, 5))
msg = "Unable to coerce to Series/DataFrame"
with tm.assert_raises_regex(ValueError, msg):
f(self.frame, ndim_5)
with tm.assert_raises_regex(ValueError, msg):
getattr(self.frame, op)(ndim_5)
# res_add = self.frame.add(self.frame)
# res_sub = self.frame.sub(self.frame)
# res_mul = self.frame.mul(self.frame)
# res_div = self.frame.div(2 * self.frame)
# assert_frame_equal(res_add, self.frame + self.frame)
# assert_frame_equal(res_sub, self.frame - self.frame)
# assert_frame_equal(res_mul, self.frame * self.frame)
# assert_frame_equal(res_div, self.frame / (2 * self.frame))
const_add = self.frame.add(1)
assert_frame_equal(const_add, self.frame + 1)
# corner cases
result = self.frame.add(self.frame[:0])
assert_frame_equal(result, self.frame * np.nan)
result = self.frame[:0].add(self.frame)
assert_frame_equal(result, self.frame * np.nan)
with tm.assert_raises_regex(NotImplementedError, 'fill_value'):
self.frame.add(self.frame.iloc[0], fill_value=3)
with tm.assert_raises_regex(NotImplementedError, 'fill_value'):
self.frame.add(self.frame.iloc[0], axis='index', fill_value=3)
def __init__(
self,
index: Index,
grouper=None,
obj: Optional[FrameOrSeries] = None,
name=None,
level=None,
sort: bool = True,
observed: bool = False,
in_axis: bool = False,
dropna: bool = True,
):
self.name = name
self.level = level
self.grouper = _convert_grouper(index, grouper)
self.all_grouper = None
self.index = index
self.sort = sort
self.obj = obj
self.observed = observed
self.in_axis = in_axis
self.dropna = dropna
# right place for this?
if isinstance(grouper, (Series, Index)) and name is None:
self.name = grouper.name
if isinstance(grouper, MultiIndex):
self.grouper = grouper._values
# we have a single grouper which may be a myriad of things,
# some of which are dependent on the passing in level
if level is not None:
if not isinstance(level, int):
if level not in index.names:
raise AssertionError(f"Level {level} not in index")
level = index.names.index(level)
if self.name is None:
self.name = index.names[level]
(
self.grouper,
self._codes,
self._group_index,
) = index._get_grouper_for_level(self.grouper, level)
# a passed Grouper like, directly get the grouper in the same way
# as single grouper groupby, use the group_info to get codes
elif isinstance(self.grouper, Grouper):
# get the new grouper; we already have disambiguated
# what key/level refer to exactly, don't need to
# check again as we have by this point converted these
# to an actual value (rather than a pd.Grouper)
_, grouper, _ = self.grouper._get_grouper(self.obj, validate=False)
if self.name is None:
self.name = grouper.result_index.name
self.obj = self.grouper.obj
self.grouper = grouper._get_grouper()
else:
if self.grouper is None and self.name is not None and self.obj is not None:
self.grouper = self.obj[self.name]
elif isinstance(self.grouper, (list, tuple)):
self.grouper = com.asarray_tuplesafe(self.grouper)
# a passed Categorical
elif is_categorical_dtype(self.grouper):
self.grouper, self.all_grouper = recode_for_groupby(
self.grouper, self.sort, observed
)
categories = self.grouper.categories
# we make a CategoricalIndex out of the cat grouper
# preserving the categories / ordered attributes
self._codes = self.grouper.codes
if observed:
codes = algorithms.unique1d(self.grouper.codes)
codes = codes[codes != -1]
if sort or self.grouper.ordered:
codes = np.sort(codes)
else:
codes = np.arange(len(categories))
self._group_index = CategoricalIndex(
Categorical.from_codes(
codes=codes, categories=categories, ordered=self.grouper.ordered
),
name=self.name,
)
# we are done
if isinstance(self.grouper, Grouping):
self.grouper = self.grouper.grouper
# no level passed
elif not isinstance(
self.grouper, (Series, Index, ExtensionArray, np.ndarray)
):
if getattr(self.grouper, "ndim", 1) != 1:
t = self.name or str(type(self.grouper))
raise ValueError(f"Grouper for '{t}' not 1-dimensional")
self.grouper = self.index.map(self.grouper)
if not (
hasattr(self.grouper, "__len__")
and len(self.grouper) == len(self.index)
):
grper = pprint_thing(self.grouper)
errmsg = (
"Grouper result violates len(labels) == "
f"len(data)\nresult: {grper}"
)
self.grouper = None # Try for sanity
raise AssertionError(errmsg)
# if we have a date/time-like grouper, make sure that we have
# Timestamps like
if getattr(self.grouper, "dtype", None) is not None:
if is_datetime64_dtype(self.grouper):
self.grouper = self.grouper.astype("datetime64[ns]")
elif is_timedelta64_dtype(self.grouper):
self.grouper = self.grouper.astype("timedelta64[ns]")
def _print_as_set(s):
return '{%s}' % ', '.join([pprint_thing(el) for el in s])
def parallel_coordinates(
frame: DataFrame,
class_column,
cols=None,
ax: Optional[Axes] = None,
color=None,
use_columns=False,
xticks=None,
colormap=None,
axvlines: bool = True,
axvlines_kwds=None,
sort_labels: bool = False,
**kwds,
) -> Axes:
import matplotlib.pyplot as plt
if axvlines_kwds is None:
axvlines_kwds = {"linewidth": 1, "color": "black"}
n = len(frame)
classes = frame[class_column].drop_duplicates()
class_col = frame[class_column]
if cols is None:
df = frame.drop(class_column, axis=1)
else:
df = frame[cols]
used_legends: Set[str] = set()
ncols = len(df.columns)
# determine values to use for xticks
if use_columns is True:
if not np.all(np.isreal(list(df.columns))):
raise ValueError("Columns must be numeric to be used as xticks")
x = df.columns
elif xticks is not None:
if not np.all(np.isreal(xticks)):
raise ValueError("xticks specified must be numeric")
elif len(xticks) != ncols:
raise ValueError("Length of xticks must match number of columns")
x = xticks
else:
x = list(range(ncols))
if ax is None:
ax = plt.gca()
color_values = get_standard_colors(num_colors=len(classes),
colormap=colormap,
color_type="random",
color=color)
if sort_labels:
classes = sorted(classes)
color_values = sorted(color_values)
colors = dict(zip(classes, color_values))
for i in range(n):
y = df.iloc[i].values
kls = class_col.iat[i]
label = pprint_thing(kls)
if label not in used_legends:
used_legends.add(label)
ax.plot(x, y, color=colors[kls], label=label, **kwds)
else:
ax.plot(x, y, color=colors[kls], **kwds)
if axvlines:
for i in x:
ax.axvline(i, **axvlines_kwds)
ax.set_xticks(x)
ax.set_xticklabels(df.columns)
ax.set_xlim(x[0], x[-1])
ax.legend(loc="upper right")
ax.grid()
return ax
def andrews_curves(
frame: DataFrame,
class_column,
ax: Optional[Axes] = None,
samples: int = 200,
color=None,
colormap=None,
**kwds,
) -> Axes:
import matplotlib.pyplot as plt
def function(amplitudes):
def f(t):
x1 = amplitudes[0]
result = x1 / np.sqrt(2.0)
# Take the rest of the coefficients and resize them
# appropriately. Take a copy of amplitudes as otherwise numpy
# deletes the element from amplitudes itself.
coeffs = np.delete(np.copy(amplitudes), 0)
coeffs.resize(int((coeffs.size + 1) / 2), 2)
# Generate the harmonics and arguments for the sin and cos
# functions.
harmonics = np.arange(0, coeffs.shape[0]) + 1
trig_args = np.outer(harmonics, t)
result += np.sum(
coeffs[:, 0, np.newaxis] * np.sin(trig_args) +
coeffs[:, 1, np.newaxis] * np.cos(trig_args),
axis=0,
)
return result
return f
n = len(frame)
class_col = frame[class_column]
classes = frame[class_column].drop_duplicates()
df = frame.drop(class_column, axis=1)
t = np.linspace(-np.pi, np.pi, samples)
used_legends: Set[str] = set()
color_values = get_standard_colors(num_colors=len(classes),
colormap=colormap,
color_type="random",
color=color)
colors = dict(zip(classes, color_values))
if ax is None:
ax = plt.gca()
ax.set_xlim(-np.pi, np.pi)
for i in range(n):
row = df.iloc[i].values
f = function(row)
y = f(t)
kls = class_col.iat[i]
label = pprint_thing(kls)
if label not in used_legends:
used_legends.add(label)
ax.plot(t, y, color=colors[kls], label=label, **kwds)
else:
ax.plot(t, y, color=colors[kls], **kwds)
ax.legend(loc="upper right")
ax.grid()
return ax
def radviz(
frame: DataFrame,
class_column,
ax: Optional[Axes] = None,
color=None,
colormap=None,
**kwds,
) -> Axes:
import matplotlib.pyplot as plt
def normalize(series):
a = min(series)
b = max(series)
return (series - a) / (b - a)
n = len(frame)
classes = frame[class_column].drop_duplicates()
class_col = frame[class_column]
df = frame.drop(class_column, axis=1).apply(normalize)
if ax is None:
ax = plt.gca()
ax.set_xlim(-1, 1)
ax.set_ylim(-1, 1)
to_plot: Dict[Hashable, List[List]] = {}
colors = get_standard_colors(num_colors=len(classes),
colormap=colormap,
color_type="random",
color=color)
for kls in classes:
to_plot[kls] = [[], []]
m = len(frame.columns) - 1
s = np.array([(np.cos(t), np.sin(t))
for t in [2 * np.pi * (i / m) for i in range(m)]])
for i in range(n):
row = df.iloc[i].values
row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
y = (s * row_).sum(axis=0) / row.sum()
kls = class_col.iat[i]
to_plot[kls][0].append(y[0])
to_plot[kls][1].append(y[1])
for i, kls in enumerate(classes):
ax.scatter(
to_plot[kls][0],
to_plot[kls][1],
color=colors[i],
label=pprint_thing(kls),
**kwds,
)
ax.legend()
ax.add_patch(patches.Circle((0.0, 0.0), radius=1.0, facecolor="none"))
for xy, name in zip(s, df.columns):
ax.add_patch(patches.Circle(xy, radius=0.025, facecolor="gray"))
if xy[0] < 0.0 and xy[1] < 0.0:
ax.text(xy[0] - 0.025,
xy[1] - 0.025,
name,
ha="right",
va="top",
size="small")
elif xy[0] < 0.0 and xy[1] >= 0.0:
ax.text(
xy[0] - 0.025,
xy[1] + 0.025,
name,
ha="right",
va="bottom",
size="small",
)
elif xy[0] >= 0.0 and xy[1] < 0.0:
ax.text(xy[0] + 0.025,
xy[1] - 0.025,
name,
ha="left",
va="top",
size="small")
elif xy[0] >= 0.0 and xy[1] >= 0.0:
ax.text(xy[0] + 0.025,
xy[1] + 0.025,
name,
ha="left",
va="bottom",
size="small")
ax.axis("equal")
return ax
def raiseException(df):
pprint_thing("----------------------------------------")
pprint_thing(df.to_string())
raise TypeError("test")
def __unicode__(self):
return '%s\nFill: %s\n%s' % (printing.pprint_thing(self),
printing.pprint_thing(self.fill_value),
printing.pprint_thing(self.sp_index))
def _print_as_set(s) -> str:
arg = ", ".join(pprint_thing(el) for el in s)
return f"{{{arg}}}"
def __repr__(self):
if self.terms is not None:
return pprint_thing(self.terms)
return pprint_thing(self.expr)
def _print_as_set(s):
return ('{' + '{arg}'.format(arg=', '.join(
pprint_thing(el) for el in s)) + '}')
def __repr__(self):
return pprint_thing(
"[Condition : [{cond}]]".format(cond=self.condition))
def __repr__(self) -> str:
operands = map(str, self.operands)
return pprint_thing("{0}({1})".format(self.op, ",".join(operands)))
def andrews_curves(frame, class_column, ax=None, samples=200, color=None,
colormap=None, **kwds):
"""
Generates a matplotlib plot of Andrews curves, for visualising clusters of
multivariate data.
Andrews curves have the functional form:
f(t) = x_1/sqrt(2) + x_2 sin(t) + x_3 cos(t) +
x_4 sin(2t) + x_5 cos(2t) + ...
Where x coefficients correspond to the values of each dimension and t is
linearly spaced between -pi and +pi. Each row of frame then corresponds to
a single curve.
Parameters
----------
frame : DataFrame
Data to be plotted, preferably normalized to (0.0, 1.0)
class_column : Name of the column containing class names
ax : matplotlib axes object, default None
samples : Number of points to plot in each curve
color: list or tuple, optional
Colors to use for the different classes
colormap : str or matplotlib colormap object, default None
Colormap to select colors from. If string, load colormap with that name
from matplotlib.
kwds: keywords
Options to pass to matplotlib plotting method
Returns
-------
ax: Matplotlib axis object
"""
from math import sqrt, pi
import matplotlib.pyplot as plt
def function(amplitudes):
def f(t):
x1 = amplitudes[0]
result = x1 / sqrt(2.0)
# Take the rest of the coefficients and resize them
# appropriately. Take a copy of amplitudes as otherwise numpy
# deletes the element from amplitudes itself.
coeffs = np.delete(np.copy(amplitudes), 0)
coeffs.resize(int((coeffs.size + 1) / 2), 2)
# Generate the harmonics and arguments for the sin and cos
# functions.
harmonics = np.arange(0, coeffs.shape[0]) + 1
trig_args = np.outer(harmonics, t)
result += np.sum(coeffs[:, 0, np.newaxis] * np.sin(trig_args) +
coeffs[:, 1, np.newaxis] * np.cos(trig_args),
axis=0)
return result
return f
n = len(frame)
class_col = frame[class_column]
classes = frame[class_column].drop_duplicates()
df = frame.drop(class_column, axis=1)
t = np.linspace(-pi, pi, samples)
used_legends = set([])
color_values = _get_standard_colors(num_colors=len(classes),
colormap=colormap, color_type='random',
color=color)
colors = dict(zip(classes, color_values))
if ax is None:
ax = plt.gca(xlim=(-pi, pi))
for i in range(n):
row = df.iloc[i].values
f = function(row)
y = f(t)
kls = class_col.iat[i]
label = pprint_thing(kls)
if label not in used_legends:
used_legends.add(label)
ax.plot(t, y, color=colors[kls], label=label, **kwds)
else:
ax.plot(t, y, color=colors[kls], **kwds)
ax.legend(loc='upper right')
ax.grid()
return ax
def __repr__(self) -> str:
return pprint_thing("{0}({1})".format(self.op, self.operand))
def __repr__(self) -> str:
return pprint_thing(self.name)
def __unicode__(self):
return '{self}\nFill: {fill}\n{index}'.format(
self=printing.pprint_thing(self),
fill=printing.pprint_thing(self.fill_value),
index=printing.pprint_thing(self.sp_index))
def __unicode__(self):
return pprint_thing(self, quote_strings=True,
escape_chars=('\t', '\r', '\n'))
def raiseException(df):
pprint_thing('----------------------------------------')
pprint_thing(df.to_string())
raise TypeError('test')
def raw(self) -> str:
return pprint_thing("{0}(name={1!r}, type={2})"
"".format(self.__class__.__name__, self.name,
self.type))
def radviz(frame, class_column, ax=None, color=None, colormap=None, **kwds):
"""
Plot a multidimensional dataset in 2D.
Each Series in the DataFrame is represented as a evenly distributed
slice on a circle. Each data point is rendered in the circle according to
the value on each Series. Highly correlated `Series` in the `DataFrame`
are placed closer on the unit circle.
RadViz allow to project a N-dimensional data set into a 2D space where the
influence of each dimension can be interpreted as a balance between the
influence of all dimensions.
More info available at the `original article
<http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.889>`_
describing RadViz.
Parameters
----------
frame : `DataFrame`
Pandas object holding the data.
class_column : str
Column name containing the name of the data point category.
ax : :class:`matplotlib.axes.Axes`, optional
A plot instance to which to add the information.
color : list[str] or tuple[str], optional
Assign a color to each category. Example: ['blue', 'green'].
colormap : str or :class:`matplotlib.colors.Colormap`, default None
Colormap to select colors from. If string, load colormap with that
name from matplotlib.
kwds : optional
Options to pass to matplotlib scatter plotting method.
Returns
-------
axes : :class:`matplotlib.axes.Axes`
See Also
--------
pandas.plotting.andrews_curves : Plot clustering visualization
Examples
--------
.. plot::
:context: close-figs
>>> df = pd.DataFrame({
... 'SepalLength': [6.5, 7.7, 5.1, 5.8, 7.6, 5.0, 5.4, 4.6,
... 6.7, 4.6],
... 'SepalWidth': [3.0, 3.8, 3.8, 2.7, 3.0, 2.3, 3.0, 3.2,
... 3.3, 3.6],
... 'PetalLength': [5.5, 6.7, 1.9, 5.1, 6.6, 3.3, 4.5, 1.4,
... 5.7, 1.0],
... 'PetalWidth': [1.8, 2.2, 0.4, 1.9, 2.1, 1.0, 1.5, 0.2,
... 2.1, 0.2],
... 'Category': ['virginica', 'virginica', 'setosa',
... 'virginica', 'virginica', 'versicolor',
... 'versicolor', 'setosa', 'virginica',
... 'setosa']
... })
>>> rad_viz = pd.plotting.radviz(df, 'Category')
"""
import matplotlib.pyplot as plt
import matplotlib.patches as patches
def normalize(series):
a = min(series)
b = max(series)
return (series - a) / (b - a)
n = len(frame)
classes = frame[class_column].drop_duplicates()
class_col = frame[class_column]
df = frame.drop(class_column, axis=1).apply(normalize)
if ax is None:
ax = plt.gca(xlim=[-1, 1], ylim=[-1, 1])
to_plot = {}
colors = _get_standard_colors(num_colors=len(classes), colormap=colormap,
color_type='random', color=color)
for kls in classes:
to_plot[kls] = [[], []]
m = len(frame.columns) - 1
s = np.array([(np.cos(t), np.sin(t))
for t in [2.0 * np.pi * (i / float(m))
for i in range(m)]])
for i in range(n):
row = df.iloc[i].values
row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
y = (s * row_).sum(axis=0) / row.sum()
kls = class_col.iat[i]
to_plot[kls][0].append(y[0])
to_plot[kls][1].append(y[1])
for i, kls in enumerate(classes):
ax.scatter(to_plot[kls][0], to_plot[kls][1], color=colors[i],
label=pprint_thing(kls), **kwds)
ax.legend()
ax.add_patch(patches.Circle((0.0, 0.0), radius=1.0, facecolor='none'))
for xy, name in zip(s, df.columns):
ax.add_patch(patches.Circle(xy, radius=0.025, facecolor='gray'))
if xy[0] < 0.0 and xy[1] < 0.0:
ax.text(xy[0] - 0.025, xy[1] - 0.025, name,
ha='right', va='top', size='small')
elif xy[0] < 0.0 and xy[1] >= 0.0:
ax.text(xy[0] - 0.025, xy[1] + 0.025, name,
ha='right', va='bottom', size='small')
elif xy[0] >= 0.0 and xy[1] < 0.0:
ax.text(xy[0] + 0.025, xy[1] - 0.025, name,
ha='left', va='top', size='small')
elif xy[0] >= 0.0 and xy[1] >= 0.0:
ax.text(xy[0] + 0.025, xy[1] + 0.025, name,
ha='left', va='bottom', size='small')
ax.axis('equal')
return ax
def _gen_columns(self) -> Iterator[str]:
"""Iterator with string representation of column names."""
for col in self.ids:
yield pprint_thing(col)
def parallel_coordinates(frame, class_column, cols=None, ax=None, color=None,
use_columns=False, xticks=None, colormap=None,
axvlines=True, axvlines_kwds=None, sort_labels=False,
**kwds):
"""Parallel coordinates plotting.
Parameters
----------
frame: DataFrame
class_column: str
Column name containing class names
cols: list, optional
A list of column names to use
ax: matplotlib.axis, optional
matplotlib axis object
color: list or tuple, optional
Colors to use for the different classes
use_columns: bool, optional
If true, columns will be used as xticks
xticks: list or tuple, optional
A list of values to use for xticks
colormap: str or matplotlib colormap, default None
Colormap to use for line colors.
axvlines: bool, optional
If true, vertical lines will be added at each xtick
axvlines_kwds: keywords, optional
Options to be passed to axvline method for vertical lines
sort_labels: bool, False
Sort class_column labels, useful when assigning colors
.. versionadded:: 0.20.0
kwds: keywords
Options to pass to matplotlib plotting method
Returns
-------
ax: matplotlib axis object
Examples
--------
>>> from matplotlib import pyplot as plt
>>> df = pd.read_csv('https://raw.github.com/pandas-dev/pandas/master'
'/pandas/tests/data/iris.csv')
>>> pd.plotting.parallel_coordinates(
df, 'Name',
color=('#556270', '#4ECDC4', '#C7F464'))
>>> plt.show()
"""
if axvlines_kwds is None:
axvlines_kwds = {'linewidth': 1, 'color': 'black'}
import matplotlib.pyplot as plt
n = len(frame)
classes = frame[class_column].drop_duplicates()
class_col = frame[class_column]
if cols is None:
df = frame.drop(class_column, axis=1)
else:
df = frame[cols]
used_legends = set([])
ncols = len(df.columns)
# determine values to use for xticks
if use_columns is True:
if not np.all(np.isreal(list(df.columns))):
raise ValueError('Columns must be numeric to be used as xticks')
x = df.columns
elif xticks is not None:
if not np.all(np.isreal(xticks)):
raise ValueError('xticks specified must be numeric')
elif len(xticks) != ncols:
raise ValueError('Length of xticks must match number of columns')
x = xticks
else:
x = lrange(ncols)
if ax is None:
ax = plt.gca()
color_values = _get_standard_colors(num_colors=len(classes),
colormap=colormap, color_type='random',
color=color)
if sort_labels:
classes = sorted(classes)
color_values = sorted(color_values)
colors = dict(zip(classes, color_values))
for i in range(n):
y = df.iloc[i].values
kls = class_col.iat[i]
label = pprint_thing(kls)
if label not in used_legends:
used_legends.add(label)
ax.plot(x, y, color=colors[kls], label=label, **kwds)
else:
ax.plot(x, y, color=colors[kls], **kwds)
if axvlines:
for i in x:
ax.axvline(i, **axvlines_kwds)
ax.set_xticks(x)
ax.set_xticklabels(df.columns)
ax.set_xlim(x[0], x[-1])
ax.legend(loc='upper right')
ax.grid()
return ax
def __repr__(self):
return pprint_thing("[Filter : [{lhs}] -> [{op}]".format(
lhs=self.filter[0], op=self.filter[1]))
def f():
if obj1:
printing.pprint_thing("this works and shouldn't")
def __repr__(self) -> str:
return printing.pprint_thing(self.terms)
def _write_col_header(self, indent: int) -> None:
is_truncated_horizontally = self.fmt.is_truncated_horizontally
if isinstance(self.columns, MultiIndex):
template = 'colspan="{span:d}" halign="left"'
if self.fmt.sparsify:
# GH3547
sentinel = lib.no_default
else:
sentinel = False
levels = self.columns.format(sparsify=sentinel,
adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
for lnum, (records,
values) in enumerate(zip(level_lengths, levels)):
if is_truncated_horizontally:
# modify the header lines
ins_col = self.fmt.tr_col_num
if self.fmt.sparsify:
recs_new = {}
# Increment tags after ... col.
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
elif tag + span > ins_col:
recs_new[tag] = span + 1
if lnum == inner_lvl:
values = (values[:ins_col] + ("...", ) +
values[ins_col:])
else:
# sparse col headers do not receive a ...
values = (values[:ins_col] +
(values[ins_col - 1], ) +
values[ins_col:])
else:
recs_new[tag] = span
# if ins_col lies between tags, all col headers
# get ...
if tag + span == ins_col:
recs_new[ins_col] = 1
values = values[:ins_col] + (
"...", ) + values[ins_col:]
records = recs_new
inner_lvl = len(level_lengths) - 1
if lnum == inner_lvl:
records[ins_col] = 1
else:
recs_new = {}
for tag, span in list(records.items()):
if tag >= ins_col:
recs_new[tag + 1] = span
else:
recs_new[tag] = span
recs_new[ins_col] = 1
records = recs_new
values = values[:ins_col] + ["..."] + values[ins_col:]
# see gh-22579
# Column Offset Bug with to_html(index=False) with
# MultiIndex Columns and Index.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code
# block below for standard columns index.
row = [""] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class and create a
# _get_formatted_column_labels function for code
# parity with DataFrameFormatter class.
if self.fmt.show_index_names:
name = self.columns.names[lnum]
row.append(pprint_thing(name or ""))
else:
row.append("")
tags = {}
j = len(row)
for i, v in enumerate(values):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
continue
j += 1
row.append(v)
self.write_tr(row,
indent,
self.indent_delta,
tags=tags,
header=True)
else:
# see gh-22579
# Column misalignment also occurs for
# a standard index when the columns index is named.
# Initially fill row with blank cells before column names.
# TODO: Refactor to remove code duplication with code block
# above for columns MultiIndex.
row = [""] * (self.row_levels - 1)
if self.fmt.index or self.show_col_idx_names:
# see gh-22747
# If to_html(index_names=False) do not show columns
# index names.
# TODO: Refactor to use _get_column_name_list from
# DataFrameFormatter class.
if self.fmt.show_index_names:
row.append(self.columns.name or "")
else:
row.append("")
row.extend(self._get_columns_formatted_values())
align = self.fmt.justify
if is_truncated_horizontally:
ins_col = self.row_levels + self.fmt.tr_col_num
row.insert(ins_col, "...")
self.write_tr(row,
indent,
self.indent_delta,
header=True,
align=align)
def test_arith_flex_frame(self):
seriesd = tm.getSeriesData()
frame = pd.DataFrame(seriesd).copy()
mixed_float = pd.DataFrame({'A': frame['A'].copy().astype('float32'),
'B': frame['B'].copy().astype('float32'),
'C': frame['C'].copy().astype('float16'),
'D': frame['D'].copy().astype('float64')})
intframe = pd.DataFrame({k: v.astype(int)
for k, v in seriesd.items()})
mixed_int = pd.DataFrame({'A': intframe['A'].copy().astype('int32'),
'B': np.ones(len(intframe), dtype='uint64'),
'C': intframe['C'].copy().astype('uint8'),
'D': intframe['D'].copy().astype('int64')})
# force these all to int64 to avoid platform testing issues
intframe = pd.DataFrame({c: s for c, s in intframe.items()},
dtype=np.int64)
ops = ['add', 'sub', 'mul', 'div', 'truediv', 'pow', 'floordiv', 'mod']
if not PY3:
aliases = {}
else:
aliases = {'div': 'truediv'}
for op in ops:
try:
alias = aliases.get(op, op)
f = getattr(operator, alias)
result = getattr(frame, op)(2 * frame)
exp = f(frame, 2 * frame)
tm.assert_frame_equal(result, exp)
# vs mix float
result = getattr(mixed_float, op)(2 * mixed_float)
exp = f(mixed_float, 2 * mixed_float)
tm.assert_frame_equal(result, exp)
_check_mixed_float(result, dtype=dict(C=None))
# vs mix int
if op in ['add', 'sub', 'mul']:
result = getattr(mixed_int, op)(2 + mixed_int)
exp = f(mixed_int, 2 + mixed_int)
# no overflow in the uint
dtype = None
if op in ['sub']:
dtype = dict(B='uint64', C=None)
elif op in ['add', 'mul']:
dtype = dict(C=None)
tm.assert_frame_equal(result, exp)
_check_mixed_int(result, dtype=dtype)
# rops
r_f = lambda x, y: f(y, x)
result = getattr(frame, 'r' + op)(2 * frame)
exp = r_f(frame, 2 * frame)
tm.assert_frame_equal(result, exp)
# vs mix float
result = getattr(mixed_float, op)(2 * mixed_float)
exp = f(mixed_float, 2 * mixed_float)
tm.assert_frame_equal(result, exp)
_check_mixed_float(result, dtype=dict(C=None))
result = getattr(intframe, op)(2 * intframe)
exp = f(intframe, 2 * intframe)
tm.assert_frame_equal(result, exp)
# vs mix int
if op in ['add', 'sub', 'mul']:
result = getattr(mixed_int, op)(2 + mixed_int)
exp = f(mixed_int, 2 + mixed_int)
# no overflow in the uint
dtype = None
if op in ['sub']:
dtype = dict(B='uint64', C=None)
elif op in ['add', 'mul']:
dtype = dict(C=None)
tm.assert_frame_equal(result, exp)
_check_mixed_int(result, dtype=dtype)
except:
printing.pprint_thing("Failing operation %r" % op)
raise
# ndim >= 3
ndim_5 = np.ones(frame.shape + (3, 4, 5))
msg = "Unable to coerce to Series/DataFrame"
with tm.assert_raises_regex(ValueError, msg):
f(frame, ndim_5)
with tm.assert_raises_regex(ValueError, msg):
getattr(frame, op)(ndim_5)
# res_add = frame.add(frame)
# res_sub = frame.sub(frame)
# res_mul = frame.mul(frame)
# res_div = frame.div(2 * frame)
# tm.assert_frame_equal(res_add, frame + frame)
# tm.assert_frame_equal(res_sub, frame - frame)
# tm.assert_frame_equal(res_mul, frame * frame)
# tm.assert_frame_equal(res_div, frame / (2 * frame))
const_add = frame.add(1)
tm.assert_frame_equal(const_add, frame + 1)
# corner cases
result = frame.add(frame[:0])
tm.assert_frame_equal(result, frame * np.nan)
result = frame[:0].add(frame)
tm.assert_frame_equal(result, frame * np.nan)
with tm.assert_raises_regex(NotImplementedError, 'fill_value'):
frame.add(frame.iloc[0], fill_value=3)
with tm.assert_raises_regex(NotImplementedError, 'fill_value'):
frame.add(frame.iloc[0], axis='index', fill_value=3)
