def test_autocorrelation_plot(self):
from pandas.tools.plotting import autocorrelation_plot
_check_plot_works(autocorrelation_plot, series=self.ts)
_check_plot_works(autocorrelation_plot, series=self.ts.values)
ax = autocorrelation_plot(self.ts, label='Test')
self._check_legend_labels(ax, labels=['Test'])
def test_scatter_matrix_axis(self):
tm._skip_if_no_scipy()
scatter_matrix = plotting.scatter_matrix
with tm.RNGContext(42):
df = DataFrame(randn(100, 3))
# we are plotting multiples on a sub-plot
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(scatter_matrix, filterwarnings='always',
frame=df, range_padding=.1)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
# GH 5662
expected = ['-2', '-1', '0', '1', '2']
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(
axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
df[0] = ((df[0] - 2) / 3)
# we are plotting multiples on a sub-plot
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(scatter_matrix, filterwarnings='always',
frame=df, range_padding=.1)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
expected = ['-1.2', '-1.0', '-0.8', '-0.6', '-0.4', '-0.2', '0.0']
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(
axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
def test_andrews_curves(self):
from pandas.tools.plotting import andrews_curves
from matplotlib import cm
df = self.iris
_check_plot_works(andrews_curves, df, 'Name')
rgba = ('#556270', '#4ECDC4', '#C7F464')
ax = _check_plot_works(andrews_curves, df, 'Name', color=rgba)
self._check_colors(ax.get_lines()[:10], linecolors=rgba, mapping=df['Name'][:10])
cnames = ['dodgerblue', 'aquamarine', 'seagreen']
ax = _check_plot_works(andrews_curves, df, 'Name', color=cnames)
self._check_colors(ax.get_lines()[:10], linecolors=cnames, mapping=df['Name'][:10])
ax = _check_plot_works(andrews_curves, df, 'Name', colormap=cm.jet)
cmaps = lmap(cm.jet, np.linspace(0, 1, df['Name'].nunique()))
self._check_colors(ax.get_lines()[:10], linecolors=cmaps, mapping=df['Name'][:10])
colors = ['b', 'g', 'r']
df = DataFrame({"A": [1, 2, 3],
"B": [1, 2, 3],
"C": [1, 2, 3],
"Name": colors})
ax = andrews_curves(df, 'Name', color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, linecolors=colors)
with tm.assert_produces_warning(FutureWarning):
andrews_curves(data=df, class_column='Name')
def test_grouped_hist_layout(self):
df = self.hist_df
self.assertRaises(ValueError, df.hist, column='weight', by=df.gender,
layout=(1, 1))
self.assertRaises(ValueError, df.hist, column='height', by=df.category,
layout=(1, 3))
self.assertRaises(ValueError, df.hist, column='height', by=df.category,
layout=(-1, -1))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.hist, column='height', by=df.gender,
layout=(2, 1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.hist, column='height', by=df.gender,
layout=(2, -1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
axes = df.hist(column='height', by=df.category, layout=(4, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
axes = df.hist(column='height', by=df.category, layout=(-1, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
axes = df.hist(column='height', by=df.category,
layout=(4, 2), figsize=(12, 8))
self._check_axes_shape(
axes, axes_num=4, layout=(4, 2), figsize=(12, 8))
tm.close()
# GH 6769
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
df.hist, column='height', by='classroom', layout=(2, 2))
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
# without column
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.hist, by='classroom')
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
axes = df.hist(by='gender', layout=(3, 5))
self._check_axes_shape(axes, axes_num=2, layout=(3, 5))
axes = df.hist(column=['height', 'weight', 'category'])
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
def test_radviz(self):
from pandas.tools.plotting import radviz
from matplotlib import cm
df = self.iris
_check_plot_works(radviz, df, 'Name')
rgba = ('#556270', '#4ECDC4', '#C7F464')
ax = _check_plot_works(radviz, df, 'Name', color=rgba)
# skip Circle drawn as ticks
patches = [p for p in ax.patches[:20] if p.get_label() != '']
self._check_colors(patches[:10], facecolors=rgba, mapping=df['Name'][:10])
cnames = ['dodgerblue', 'aquamarine', 'seagreen']
_check_plot_works(radviz, df, 'Name', color=cnames)
patches = [p for p in ax.patches[:20] if p.get_label() != '']
self._check_colors(patches, facecolors=cnames, mapping=df['Name'][:10])
_check_plot_works(radviz, df, 'Name', colormap=cm.jet)
cmaps = lmap(cm.jet, np.linspace(0, 1, df['Name'].nunique()))
patches = [p for p in ax.patches[:20] if p.get_label() != '']
self._check_colors(patches, facecolors=cmaps, mapping=df['Name'][:10])
colors = [[0., 0., 1., 1.],
[0., 0.5, 1., 1.],
[1., 0., 0., 1.]]
df = DataFrame({"A": [1, 2, 3],
"B": [2, 1, 3],
"C": [3, 2, 1],
"Name": ['b', 'g', 'r']})
ax = radviz(df, 'Name', color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, facecolors=colors)
def test_hist_layout_with_by(self):
df = self.hist_df
axes = _check_plot_works(df.height.hist, by=df.gender, layout=(2, 1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
axes = _check_plot_works(df.height.hist, by=df.gender, layout=(3, -1))
self._check_axes_shape(axes, axes_num=2, layout=(3, 1))
axes = _check_plot_works(df.height.hist, by=df.category, layout=(4, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(2, -1))
self._check_axes_shape(axes, axes_num=4, layout=(2, 2))
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(3, -1))
self._check_axes_shape(axes, axes_num=4, layout=(3, 2))
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(-1, 4))
self._check_axes_shape(axes, axes_num=4, layout=(1, 4))
axes = _check_plot_works(
df.height.hist, by=df.classroom, layout=(2, 2))
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
axes = df.height.hist(by=df.category, layout=(4, 2), figsize=(12, 7))
self._check_axes_shape(
axes, axes_num=4, layout=(4, 2), figsize=(12, 7))
def test_scatter_matrix_axis(self):
tm._skip_if_no_scipy()
scatter_matrix = plotting.scatter_matrix
with tm.RNGContext(42):
df = DataFrame(randn(100, 3))
axes = _check_plot_works(scatter_matrix, df, range_padding=.1)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
# GH 5662
expected = ['-2', '-1', '0', '1', '2']
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
df[0] = ((df[0] - 2) / 3)
axes = _check_plot_works(scatter_matrix, df, range_padding=.1)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
expected = ['-1.2', '-1.0', '-0.8', '-0.6', '-0.4', '-0.2', '0.0']
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
def test_boxplot_legacy(self):
grouped = self.hist_df.groupby(by='gender')
with warnings.catch_warnings():
warnings.simplefilter('ignore')
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=2, layout=(1, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
grouped = df.groupby(level=1)
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=10, layout=(4, 3))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
grouped = df.unstack(level=1).groupby(level=0, axis=1)
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=3, layout=(2, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
def test_hist_df_nan_and_weights(self):
d = {'category' : ['A', 'A', 'B', 'B', 'C'],
'items' : [4., 3., 2., np.nan, 1],
'val' : [10., 8., np.nan, 5, 7.]}
df = DataFrame(d)
orig_columns = df.columns
orig_rows = len(df)
_check_plot_works(df.hist, column='items', by='category',
weights='val', bins=range(0, 10))
_check_plot_works(df.hist, column='items', by='category',
weights=df.val.values, bins=range(0, 10))
# check without weights functionality
_check_plot_works(df.hist, column='items', by='category',
bins=range(0, 10))
_check_plot_works(df.hist, column='items', weights='val',
bins=range(0, 10))
_check_plot_works(df.hist, column='items', weights=df.val.values,
bins=range(0, 10))
# also check that we have not changed the original df that had
# nan values in it.
self.assertEqual(len(orig_columns), len(df.columns))
self.assertEqual(orig_rows, len(df))
def test_hist_layout_with_by(self):
df = self.hist_df
# _check_plot_works adds an `ax` kwarg to the method call
# so we get a warning about an axis being cleared, even
# though we don't explicing pass one, see GH #13188
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.height.hist, by=df.gender,
layout=(2, 1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.height.hist, by=df.gender,
layout=(3, -1))
self._check_axes_shape(axes, axes_num=2, layout=(3, 1))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(df.height.hist, by=df.category,
layout=(4, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(2, -1))
self._check_axes_shape(axes, axes_num=4, layout=(2, 2))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(3, -1))
self._check_axes_shape(axes, axes_num=4, layout=(3, 2))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
df.height.hist, by=df.category, layout=(-1, 4))
self._check_axes_shape(axes, axes_num=4, layout=(1, 4))
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
df.height.hist, by=df.classroom, layout=(2, 2))
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
axes = df.height.hist(by=df.category, layout=(4, 2), figsize=(12, 7))
self._check_axes_shape(
axes, axes_num=4, layout=(4, 2), figsize=(12, 7))
def test_scatter_plot_legacy(self):
tm._skip_if_no_scipy()
df = DataFrame(randn(100, 2))
def scat(**kwds):
return plotting.scatter_matrix(df, **kwds)
_check_plot_works(scat)
_check_plot_works(scat, marker='+')
_check_plot_works(scat, vmin=0)
if _ok_for_gaussian_kde('kde'):
_check_plot_works(scat, diagonal='kde')
if _ok_for_gaussian_kde('density'):
_check_plot_works(scat, diagonal='density')
_check_plot_works(scat, diagonal='hist')
_check_plot_works(scat, range_padding=.1)
def scat2(x, y, by=None, ax=None, figsize=None):
return plotting.scatter_plot(df, x, y, by, ax, figsize=None)
_check_plot_works(scat2, x=0, y=1)
grouper = Series(np.repeat([1, 2, 3, 4, 5], 20), df.index)
_check_plot_works(scat2, x=0, y=1, by=grouper)
def test_hist_df_legacy(self):
from matplotlib.patches import Rectangle
_check_plot_works(self.hist_df.hist)
# make sure layout is handled
df = DataFrame(randn(100, 3))
axes = _check_plot_works(df.hist, grid=False)
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
self.assertFalse(axes[1, 1].get_visible())
df = DataFrame(randn(100, 1))
_check_plot_works(df.hist)
# make sure layout is handled
df = DataFrame(randn(100, 6))
axes = _check_plot_works(df.hist, layout=(4, 2))
self._check_axes_shape(axes, axes_num=6, layout=(4, 2))
# make sure sharex, sharey is handled
_check_plot_works(df.hist, sharex=True, sharey=True)
# handle figsize arg
_check_plot_works(df.hist, figsize=(8, 10))
# check bins argument
_check_plot_works(df.hist, bins=5)
# make sure xlabelsize and xrot are handled
ser = df[0]
xf, yf = 20, 18
xrot, yrot = 30, 40
axes = ser.hist(xlabelsize=xf, xrot=xrot, ylabelsize=yf, yrot=yrot)
self._check_ticks_props(axes, xlabelsize=xf, xrot=xrot,
ylabelsize=yf, yrot=yrot)
xf, yf = 20, 18
xrot, yrot = 30, 40
axes = df.hist(xlabelsize=xf, xrot=xrot, ylabelsize=yf, yrot=yrot)
self._check_ticks_props(axes, xlabelsize=xf, xrot=xrot,
ylabelsize=yf, yrot=yrot)
tm.close()
# make sure kwargs to hist are handled
ax = ser.hist(normed=True, cumulative=True, bins=4)
# height of last bin (index 5) must be 1.0
rects = [x for x in ax.get_children() if isinstance(x, Rectangle)]
self.assertAlmostEqual(rects[-1].get_height(), 1.0)
tm.close()
ax = ser.hist(log=True)
# scale of y must be 'log'
self._check_ax_scales(ax, yaxis='log')
tm.close()
# propagate attr exception from matplotlib.Axes.hist
with tm.assertRaises(AttributeError):
ser.hist(foo='bar')
def test_scatter_plot_legacy(self):
tm._skip_if_no_scipy()
df = DataFrame(randn(100, 2))
def scat(**kwds):
return plotting.scatter_matrix(df, **kwds)
_check_plot_works(scat)
_check_plot_works(scat, marker='+')
_check_plot_works(scat, vmin=0)
if _ok_for_gaussian_kde('kde'):
_check_plot_works(scat, diagonal='kde')
if _ok_for_gaussian_kde('density'):
_check_plot_works(scat, diagonal='density')
_check_plot_works(scat, diagonal='hist')
_check_plot_works(scat, range_padding=.1)
def scat2(x, y, by=None, ax=None, figsize=None):
return plotting.scatter_plot(df, x, y, by, ax, figsize=None)
_check_plot_works(scat2, x=0, y=1)
grouper = Series(np.repeat([1, 2, 3, 4, 5], 20), df.index)
_check_plot_works(scat2, x=0, y=1, by=grouper)
def test_boxplot_legacy(self):
df = DataFrame(randn(6, 4),
index=list(string.ascii_letters[:6]),
columns=['one', 'two', 'three', 'four'])
df['indic'] = ['foo', 'bar'] * 3
df['indic2'] = ['foo', 'bar', 'foo'] * 2
_check_plot_works(df.boxplot, return_type='dict')
_check_plot_works(df.boxplot, column=[
'one', 'two'], return_type='dict')
_check_plot_works(df.boxplot, column=['one', 'two'], by='indic')
_check_plot_works(df.boxplot, column='one', by=['indic', 'indic2'])
_check_plot_works(df.boxplot, by='indic')
_check_plot_works(df.boxplot, by=['indic', 'indic2'])
_check_plot_works(plotting.boxplot, data=df['one'], return_type='dict')
_check_plot_works(df.boxplot, notch=1, return_type='dict')
_check_plot_works(df.boxplot, by='indic', notch=1)
df = DataFrame(np.random.rand(10, 2), columns=['Col1', 'Col2'])
df['X'] = Series(['A', 'A', 'A', 'A', 'A', 'B', 'B', 'B', 'B', 'B'])
df['Y'] = Series(['A'] * 10)
_check_plot_works(df.boxplot, by='X')
# When ax is supplied and required number of axes is 1,
# passed ax should be used:
fig, ax = self.plt.subplots()
axes = df.boxplot('Col1', by='X', ax=ax)
self.assertIs(ax.get_axes(), axes)
fig, ax = self.plt.subplots()
axes = df.groupby('Y').boxplot(ax=ax, return_type='axes')
self.assertIs(ax.get_axes(), axes['A'])
# Multiple columns with an ax argument should use same figure
fig, ax = self.plt.subplots()
axes = df.boxplot(column=['Col1', 'Col2'],
by='X', ax=ax, return_type='axes')
self.assertIs(axes['Col1'].get_figure(), fig)
# When by is None, check that all relevant lines are present in the
# dict
fig, ax = self.plt.subplots()
d = df.boxplot(ax=ax, return_type='dict')
lines = list(itertools.chain.from_iterable(d.values()))
self.assertEqual(len(ax.get_lines()), len(lines))
def test_boxplot_empty_column(self):
_skip_if_mpl_14_or_dev_boxplot()
df = DataFrame(np.random.randn(20, 4))
df.loc[:, 0] = np.nan
_check_plot_works(df.boxplot, return_type='axes')
def test_lag_plot(self):
from pandas.tools.plotting import lag_plot
_check_plot_works(lag_plot, series=self.ts)
_check_plot_works(lag_plot, series=self.ts, lag=5)
def test_bootstrap_plot(self):
from pandas.tools.plotting import bootstrap_plot
_check_plot_works(bootstrap_plot, series=self.ts, size=10)
def test_grouped_box_layout(self):
df = self.hist_df
self.assertRaises(ValueError, df.boxplot, column=['weight', 'height'],
by=df.gender, layout=(1, 1))
self.assertRaises(ValueError, df.boxplot,
column=['height', 'weight', 'category'],
layout=(2, 1), return_type='dict')
self.assertRaises(ValueError, df.boxplot, column=['weight', 'height'],
by=df.gender, layout=(-1, -1))
box = _check_plot_works(df.groupby('gender').boxplot, column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=2, layout=(1, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(2, 2))
# GH 6769
box = _check_plot_works(df.groupby('classroom').boxplot,
column='height', return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
# GH 5897
axes = df.boxplot(column=['height', 'weight', 'category'], by='gender',
return_type='axes')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
for ax in [axes['height']]:
self._check_visible(ax.get_xticklabels(), visible=False)
self._check_visible([ax.xaxis.get_label()], visible=False)
for ax in [axes['weight'], axes['category']]:
self._check_visible(ax.get_xticklabels())
self._check_visible([ax.xaxis.get_label()])
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'], return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, 2), return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, -1), return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
box = df.boxplot(column=['height', 'weight', 'category'], by='gender',
layout=(4, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(4, 1))
box = df.boxplot(column=['height', 'weight', 'category'], by='gender',
layout=(-1, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(3, 1))
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'], layout=(1, 4),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 4))
box = df.groupby('classroom').boxplot( # noqa
column=['height', 'weight', 'category'], layout=(1, -1),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 3))
def test_hist_legacy(self):
_check_plot_works(self.ts.hist)
_check_plot_works(self.ts.hist, grid=False)
_check_plot_works(self.ts.hist, figsize=(8, 10))
_check_plot_works(self.ts.hist, by=self.ts.index.month)
_check_plot_works(self.ts.hist, by=self.ts.index.month, bins=5)
fig, ax = self.plt.subplots(1, 1)
_check_plot_works(self.ts.hist, ax=ax)
_check_plot_works(self.ts.hist, ax=ax, figure=fig)
_check_plot_works(self.ts.hist, figure=fig)
tm.close()
fig, (ax1, ax2) = self.plt.subplots(1, 2)
_check_plot_works(self.ts.hist, figure=fig, ax=ax1)
_check_plot_works(self.ts.hist, figure=fig, ax=ax2)
with tm.assertRaises(ValueError):
self.ts.hist(by=self.ts.index, figure=fig)
def test_hist_legacy(self):
_check_plot_works(self.ts.hist)
_check_plot_works(self.ts.hist, grid=False)
_check_plot_works(self.ts.hist, figsize=(8, 10))
# _check_plot_works adds an ax so catch warning. see GH #13188
with tm.assert_produces_warning(UserWarning):
_check_plot_works(self.ts.hist, by=self.ts.index.month)
with tm.assert_produces_warning(UserWarning):
_check_plot_works(self.ts.hist, by=self.ts.index.month, bins=5)
fig, ax = self.plt.subplots(1, 1)
_check_plot_works(self.ts.hist, ax=ax)
_check_plot_works(self.ts.hist, ax=ax, figure=fig)
_check_plot_works(self.ts.hist, figure=fig)
tm.close()
fig, (ax1, ax2) = self.plt.subplots(1, 2)
_check_plot_works(self.ts.hist, figure=fig, ax=ax1)
_check_plot_works(self.ts.hist, figure=fig, ax=ax2)
with tm.assertRaises(ValueError):
self.ts.hist(by=self.ts.index, figure=fig)
def test_hist_legacy(self):
_check_plot_works(self.ts.hist)
_check_plot_works(self.ts.hist, grid=False)
_check_plot_works(self.ts.hist, figsize=(8, 10))
_check_plot_works(self.ts.hist, by=self.ts.index.month)
_check_plot_works(self.ts.hist, by=self.ts.index.month, bins=5)
fig, ax = self.plt.subplots(1, 1)
_check_plot_works(self.ts.hist, ax=ax)
_check_plot_works(self.ts.hist, ax=ax, figure=fig)
_check_plot_works(self.ts.hist, figure=fig)
tm.close()
fig, (ax1, ax2) = self.plt.subplots(1, 2)
_check_plot_works(self.ts.hist, figure=fig, ax=ax1)
_check_plot_works(self.ts.hist, figure=fig, ax=ax2)
with tm.assertRaises(ValueError):
self.ts.hist(by=self.ts.index, figure=fig)
def test_grouped_box_layout(self):
df = self.hist_df
self.assertRaises(ValueError,
df.boxplot,
column=['weight', 'height'],
by=df.gender,
layout=(1, 1))
self.assertRaises(ValueError,
df.boxplot,
column=['height', 'weight', 'category'],
layout=(2, 1),
return_type='dict')
self.assertRaises(ValueError,
df.boxplot,
column=['weight', 'height'],
by=df.gender,
layout=(-1, -1))
box = _check_plot_works(df.groupby('gender').boxplot,
column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=2, layout=(1, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(2, 2))
# GH 6769
box = _check_plot_works(df.groupby('classroom').boxplot,
column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
# GH 5897
axes = df.boxplot(column=['height', 'weight', 'category'],
by='gender',
return_type='axes')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
for ax in [axes['height']]:
self._check_visible(ax.get_xticklabels(), visible=False)
self._check_visible([ax.xaxis.get_label()], visible=False)
for ax in [axes['weight'], axes['category']]:
self._check_visible(ax.get_xticklabels())
self._check_visible([ax.xaxis.get_label()])
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'], return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, 2),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, -1),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
box = df.boxplot(column=['height', 'weight', 'category'],
by='gender',
layout=(4, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(4, 1))
box = df.boxplot(column=['height', 'weight', 'category'],
by='gender',
layout=(-1, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(3, 1))
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'],
layout=(1, 4),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 4))
box = df.groupby('classroom').boxplot( # noqa
column=['height', 'weight', 'category'],
layout=(1, -1),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 3))
def test_boxplot_empty_column(self):
_skip_if_mpl_14_or_dev_boxplot()
df = DataFrame(np.random.randn(20, 4))
df.loc[:, 0] = np.nan
_check_plot_works(df.boxplot, return_type='axes')
def test_boxplot_legacy(self):
df = DataFrame(randn(6, 4),
index=list(string.ascii_letters[:6]),
columns=['one', 'two', 'three', 'four'])
df['indic'] = ['foo', 'bar'] * 3
df['indic2'] = ['foo', 'bar', 'foo'] * 2
_check_plot_works(df.boxplot, return_type='dict')
_check_plot_works(df.boxplot, column=[
'one', 'two'], return_type='dict')
_check_plot_works(df.boxplot, column=['one', 'two'], by='indic')
_check_plot_works(df.boxplot, column='one', by=['indic', 'indic2'])
_check_plot_works(df.boxplot, by='indic')
_check_plot_works(df.boxplot, by=['indic', 'indic2'])
_check_plot_works(plotting.boxplot, data=df['one'], return_type='dict')
_check_plot_works(df.boxplot, notch=1, return_type='dict')
_check_plot_works(df.boxplot, by='indic', notch=1)
df = DataFrame(np.random.rand(10, 2), columns=['Col1', 'Col2'])
df['X'] = Series(['A', 'A', 'A', 'A', 'A', 'B', 'B', 'B', 'B', 'B'])
df['Y'] = Series(['A'] * 10)
_check_plot_works(df.boxplot, by='X')
# When ax is supplied and required number of axes is 1,
# passed ax should be used:
fig, ax = self.plt.subplots()
axes = df.boxplot('Col1', by='X', ax=ax)
self.assertIs(ax.get_axes(), axes)
fig, ax = self.plt.subplots()
axes = df.groupby('Y').boxplot(ax=ax, return_type='axes')
self.assertIs(ax.get_axes(), axes['A'])
# Multiple columns with an ax argument should use same figure
fig, ax = self.plt.subplots()
axes = df.boxplot(column=['Col1', 'Col2'],
by='X', ax=ax, return_type='axes')
self.assertIs(axes['Col1'].get_figure(), fig)
# When by is None, check that all relevant lines are present in the
# dict
fig, ax = self.plt.subplots()
d = df.boxplot(ax=ax, return_type='dict')
lines = list(itertools.chain.from_iterable(d.values()))
self.assertEqual(len(ax.get_lines()), len(lines))
def test_bootstrap_plot(self):
from pandas.tools.plotting import bootstrap_plot
_check_plot_works(bootstrap_plot, series=self.ts, size=10)
def test_lag_plot(self):
from pandas.tools.plotting import lag_plot
_check_plot_works(lag_plot, series=self.ts)
_check_plot_works(lag_plot, series=self.ts, lag=5)
def test_hist_df_legacy(self):
from matplotlib.patches import Rectangle
_check_plot_works(self.hist_df.hist)
# make sure layout is handled
df = DataFrame(randn(100, 3))
axes = _check_plot_works(df.hist, grid=False)
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
self.assertFalse(axes[1, 1].get_visible())
df = DataFrame(randn(100, 1))
_check_plot_works(df.hist)
# make sure layout is handled
df = DataFrame(randn(100, 6))
axes = _check_plot_works(df.hist, layout=(4, 2))
self._check_axes_shape(axes, axes_num=6, layout=(4, 2))
# make sure sharex, sharey is handled
_check_plot_works(df.hist, sharex=True, sharey=True)
# handle figsize arg
_check_plot_works(df.hist, figsize=(8, 10))
# check bins argument
_check_plot_works(df.hist, bins=5)
# make sure xlabelsize and xrot are handled
ser = df[0]
xf, yf = 20, 18
xrot, yrot = 30, 40
axes = ser.hist(xlabelsize=xf, xrot=xrot, ylabelsize=yf, yrot=yrot)
self._check_ticks_props(axes,
xlabelsize=xf,
xrot=xrot,
ylabelsize=yf,
yrot=yrot)
xf, yf = 20, 18
xrot, yrot = 30, 40
axes = df.hist(xlabelsize=xf, xrot=xrot, ylabelsize=yf, yrot=yrot)
self._check_ticks_props(axes,
xlabelsize=xf,
xrot=xrot,
ylabelsize=yf,
yrot=yrot)
tm.close()
# make sure kwargs to hist are handled
ax = ser.hist(normed=True, cumulative=True, bins=4)
# height of last bin (index 5) must be 1.0
rects = [x for x in ax.get_children() if isinstance(x, Rectangle)]
self.assertAlmostEqual(rects[-1].get_height(), 1.0)
tm.close()
ax = ser.hist(log=True)
# scale of y must be 'log'
self._check_ax_scales(ax, yaxis='log')
tm.close()
# propagate attr exception from matplotlib.Axes.hist
with tm.assertRaises(AttributeError):
ser.hist(foo='bar')
def test_grouped_hist_layout(self):
df = self.hist_df
self.assertRaises(ValueError,
df.hist,
column='weight',
by=df.gender,
layout=(1, 1))
self.assertRaises(ValueError,
df.hist,
column='height',
by=df.category,
layout=(1, 3))
self.assertRaises(ValueError,
df.hist,
column='height',
by=df.category,
layout=(-1, -1))
axes = _check_plot_works(df.hist,
column='height',
by=df.gender,
layout=(2, 1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
axes = _check_plot_works(df.hist,
column='height',
by=df.gender,
layout=(2, -1))
self._check_axes_shape(axes, axes_num=2, layout=(2, 1))
axes = df.hist(column='height', by=df.category, layout=(4, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
axes = df.hist(column='height', by=df.category, layout=(-1, 1))
self._check_axes_shape(axes, axes_num=4, layout=(4, 1))
axes = df.hist(column='height',
by=df.category,
layout=(4, 2),
figsize=(12, 8))
self._check_axes_shape(axes,
axes_num=4,
layout=(4, 2),
figsize=(12, 8))
tm.close()
# GH 6769
axes = _check_plot_works(df.hist,
column='height',
by='classroom',
layout=(2, 2))
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
# without column
axes = _check_plot_works(df.hist, by='classroom')
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
axes = df.hist(by='gender', layout=(3, 5))
self._check_axes_shape(axes, axes_num=2, layout=(3, 5))
axes = df.hist(column=['height', 'weight', 'category'])
self._check_axes_shape(axes, axes_num=3, layout=(2, 2))
def test_hist_legacy(self):
_check_plot_works(self.ts.hist)
_check_plot_works(self.ts.hist, grid=False)
_check_plot_works(self.ts.hist, figsize=(8, 10))
# _check_plot_works adds an ax so catch warning. see GH #13188
with tm.assert_produces_warning(UserWarning):
_check_plot_works(self.ts.hist, by=self.ts.index.month)
with tm.assert_produces_warning(UserWarning):
_check_plot_works(self.ts.hist, by=self.ts.index.month, bins=5)
fig, ax = self.plt.subplots(1, 1)
_check_plot_works(self.ts.hist, ax=ax)
_check_plot_works(self.ts.hist, ax=ax, figure=fig)
_check_plot_works(self.ts.hist, figure=fig)
tm.close()
fig, (ax1, ax2) = self.plt.subplots(1, 2)
_check_plot_works(self.ts.hist, figure=fig, ax=ax1)
_check_plot_works(self.ts.hist, figure=fig, ax=ax2)
with tm.assertRaises(ValueError):
self.ts.hist(by=self.ts.index, figure=fig)
def test_andrews_curves(self):
from pandas.tools.plotting import andrews_curves
from matplotlib import cm
df = self.iris
_check_plot_works(andrews_curves, frame=df, class_column='Name')
rgba = ('#556270', '#4ECDC4', '#C7F464')
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
color=rgba)
self._check_colors(ax.get_lines()[:10],
linecolors=rgba,
mapping=df['Name'][:10])
cnames = ['dodgerblue', 'aquamarine', 'seagreen']
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
color=cnames)
self._check_colors(ax.get_lines()[:10],
linecolors=cnames,
mapping=df['Name'][:10])
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
colormap=cm.jet)
cmaps = lmap(cm.jet, np.linspace(0, 1, df['Name'].nunique()))
self._check_colors(ax.get_lines()[:10],
linecolors=cmaps,
mapping=df['Name'][:10])
length = 10
df = DataFrame({
"A": random.rand(length),
"B": random.rand(length),
"C": random.rand(length),
"Name": ["A"] * length
})
_check_plot_works(andrews_curves, frame=df, class_column='Name')
rgba = ('#556270', '#4ECDC4', '#C7F464')
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
color=rgba)
self._check_colors(ax.get_lines()[:10],
linecolors=rgba,
mapping=df['Name'][:10])
cnames = ['dodgerblue', 'aquamarine', 'seagreen']
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
color=cnames)
self._check_colors(ax.get_lines()[:10],
linecolors=cnames,
mapping=df['Name'][:10])
ax = _check_plot_works(andrews_curves,
frame=df,
class_column='Name',
colormap=cm.jet)
cmaps = lmap(cm.jet, np.linspace(0, 1, df['Name'].nunique()))
self._check_colors(ax.get_lines()[:10],
linecolors=cmaps,
mapping=df['Name'][:10])
colors = ['b', 'g', 'r']
df = DataFrame({
"A": [1, 2, 3],
"B": [1, 2, 3],
"C": [1, 2, 3],
"Name": colors
})
ax = andrews_curves(df, 'Name', color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, linecolors=colors)
with tm.assert_produces_warning(FutureWarning):
andrews_curves(data=df, class_column='Name')
