Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/pandas/plotting/

1from __future__ import annotations

3from contextlib import contextmanager

4from typing import (

5 TYPE_CHECKING,

6 Generator,

9from pandas.plotting._core import _get_plot_backend

11if TYPE_CHECKING:

12 from matplotlib.axes import Axes

13 from matplotlib.figure import Figure

14 import numpy as np

16 from pandas import (

17 DataFrame,

18 Series,

19 )

22def table(ax, data, **kwargs):

23 """

24 Helper function to convert DataFrame and Series to matplotlib.table.

26 Parameters

27 ----------

28 ax : Matplotlib axes object

29 data : DataFrame or Series

30 Data for table contents.

31 **kwargs

32 Keyword arguments to be passed to matplotlib.table.table.

33 If `rowLabels` or `colLabels` is not specified, data index or column

34 name will be used.

36 Returns

37 -------

38 matplotlib table object

39 """

40 plot_backend = _get_plot_backend("matplotlib")

41 return plot_backend.table(

42 ax=ax, data=data, rowLabels=None, colLabels=None, **kwargs

43 )

46def register() -> None:

47 """

48 Register pandas formatters and converters with matplotlib.

50 This function modifies the global ``matplotlib.units.registry``

51 dictionary. pandas adds custom converters for

53 * pd.Timestamp

54 * pd.Period

55 * np.datetime64

56 * datetime.datetime

57 * datetime.date

58 * datetime.time

60 See Also

61 --------

62 deregister_matplotlib_converters : Remove pandas formatters and converters.

63 """

64 plot_backend = _get_plot_backend("matplotlib")

65 plot_backend.register()

68def deregister() -> None:

69 """

70 Remove pandas formatters and converters.

72 Removes the custom converters added by :func:`register`. This

73 attempts to set the state of the registry back to the state before

74 pandas registered its own units. Converters for pandas' own types like

75 Timestamp and Period are removed completely. Converters for types

76 pandas overwrites, like ``datetime.datetime``, are restored to their

77 original value.

79 See Also

80 --------

81 register_matplotlib_converters : Register pandas formatters and converters

82 with matplotlib.

83 """

84 plot_backend = _get_plot_backend("matplotlib")

85 plot_backend.deregister()

88def scatter_matrix(

89 frame: DataFrame,

90 alpha: float = 0.5,

91 figsize: tuple[float, float] | None = None,

92 ax: Axes | None = None,

93 grid: bool = False,

94 diagonal: str = "hist",

95 marker: str = ".",

96 density_kwds=None,

97 hist_kwds=None,

98 range_padding: float = 0.05,

99 **kwargs,

100) -> np.ndarray:

101 """

102 Draw a matrix of scatter plots.

103

104 Parameters

105 ----------

106 frame : DataFrame

107 alpha : float, optional

108 Amount of transparency applied.

109 figsize : (float,float), optional

110 A tuple (width, height) in inches.

111 ax : Matplotlib axis object, optional

112 grid : bool, optional

113 Setting this to True will show the grid.

114 diagonal : {'hist', 'kde'}

115 Pick between 'kde' and 'hist' for either Kernel Density Estimation or

116 Histogram plot in the diagonal.

117 marker : str, optional

118 Matplotlib marker type, default '.'.

119 density_kwds : keywords

120 Keyword arguments to be passed to kernel density estimate plot.

121 hist_kwds : keywords

122 Keyword arguments to be passed to hist function.

123 range_padding : float, default 0.05

124 Relative extension of axis range in x and y with respect to

125 (x_max - x_min) or (y_max - y_min).

126 **kwargs

127 Keyword arguments to be passed to scatter function.

128

129 Returns

130 -------

131 numpy.ndarray

132 A matrix of scatter plots.

133

134 Examples

135 --------

136

137 .. plot::

138 :context: close-figs

139

140 >>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])

141 >>> pd.plotting.scatter_matrix(df, alpha=0.2)

142 array([[<AxesSubplot: xlabel='A', ylabel='A'>,

143 <AxesSubplot: xlabel='B', ylabel='A'>,

144 <AxesSubplot: xlabel='C', ylabel='A'>,

145 <AxesSubplot: xlabel='D', ylabel='A'>],

146 [<AxesSubplot: xlabel='A', ylabel='B'>,

147 <AxesSubplot: xlabel='B', ylabel='B'>,

148 <AxesSubplot: xlabel='C', ylabel='B'>,

149 <AxesSubplot: xlabel='D', ylabel='B'>],

150 [<AxesSubplot: xlabel='A', ylabel='C'>,

151 <AxesSubplot: xlabel='B', ylabel='C'>,

152 <AxesSubplot: xlabel='C', ylabel='C'>,

153 <AxesSubplot: xlabel='D', ylabel='C'>],

154 [<AxesSubplot: xlabel='A', ylabel='D'>,

155 <AxesSubplot: xlabel='B', ylabel='D'>,

156 <AxesSubplot: xlabel='C', ylabel='D'>,

157 <AxesSubplot: xlabel='D', ylabel='D'>]], dtype=object)

158 """

159 plot_backend = _get_plot_backend("matplotlib")

160 return plot_backend.scatter_matrix(

161 frame=frame,

162 alpha=alpha,

163 figsize=figsize,

164 ax=ax,

165 grid=grid,

166 diagonal=diagonal,

167 marker=marker,

168 density_kwds=density_kwds,

169 hist_kwds=hist_kwds,

170 range_padding=range_padding,

171 **kwargs,

172 )

173

174

175def radviz(

176 frame: DataFrame,

177 class_column: str,

178 ax: Axes | None = None,

179 color: list[str] | tuple[str, ...] | None = None,

180 colormap=None,

181 **kwds,

182) -> Axes:

183 """

184 Plot a multidimensional dataset in 2D.

185

186 Each Series in the DataFrame is represented as a evenly distributed

187 slice on a circle. Each data point is rendered in the circle according to

188 the value on each Series. Highly correlated `Series` in the `DataFrame`

189 are placed closer on the unit circle.

190

191 RadViz allow to project a N-dimensional data set into a 2D space where the

192 influence of each dimension can be interpreted as a balance between the

193 influence of all dimensions.

194

195 More info available at the `original article

196 <https://doi.org/10.1145/331770.331775>`_

197 describing RadViz.

198

199 Parameters

200 ----------

201 frame : `DataFrame`

202 Object holding the data.

203 class_column : str

204 Column name containing the name of the data point category.

205 ax : :class:`matplotlib.axes.Axes`, optional

206 A plot instance to which to add the information.

207 color : list[str] or tuple[str], optional

208 Assign a color to each category. Example: ['blue', 'green'].

209 colormap : str or :class:`matplotlib.colors.Colormap`, default None

210 Colormap to select colors from. If string, load colormap with that

211 name from matplotlib.

212 **kwds

213 Options to pass to matplotlib scatter plotting method.

214

215 Returns

216 -------

217 :class:`matplotlib.axes.Axes`

218

219 See Also

220 --------

221 pandas.plotting.andrews_curves : Plot clustering visualization.

222

223 Examples

224 --------

225

226 .. plot::

227 :context: close-figs

228

229 >>> df = pd.DataFrame(

230 ... {

231 ... 'SepalLength': [6.5, 7.7, 5.1, 5.8, 7.6, 5.0, 5.4, 4.6, 6.7, 4.6],

232 ... 'SepalWidth': [3.0, 3.8, 3.8, 2.7, 3.0, 2.3, 3.0, 3.2, 3.3, 3.6],

233 ... 'PetalLength': [5.5, 6.7, 1.9, 5.1, 6.6, 3.3, 4.5, 1.4, 5.7, 1.0],

234 ... 'PetalWidth': [1.8, 2.2, 0.4, 1.9, 2.1, 1.0, 1.5, 0.2, 2.1, 0.2],

235 ... 'Category': [

236 ... 'virginica',

237 ... 'virginica',

238 ... 'setosa',

239 ... 'virginica',

240 ... 'virginica',

241 ... 'versicolor',

242 ... 'versicolor',

243 ... 'setosa',

244 ... 'virginica',

245 ... 'setosa'

246 ... ]

247 ... }

248 ... )

249 >>> pd.plotting.radviz(df, 'Category')

250 <AxesSubplot: xlabel='y(t)', ylabel='y(t + 1)'>

251 """

252 plot_backend = _get_plot_backend("matplotlib")

253 return plot_backend.radviz(

254 frame=frame,

255 class_column=class_column,

256 ax=ax,

257 color=color,

258 colormap=colormap,

259 **kwds,

260 )

261

262

263def andrews_curves(

264 frame: DataFrame,

265 class_column: str,

266 ax: Axes | None = None,

267 samples: int = 200,

268 color: list[str] | tuple[str, ...] | None = None,

269 colormap=None,

270 **kwargs,

271) -> Axes:

272 """

273 Generate a matplotlib plot for visualising clusters of multivariate data.

274

275 Andrews curves have the functional form:

276

277 .. math::

278 f(t) = \\frac{x_1}{\\sqrt{2}} + x_2 \\sin(t) + x_3 \\cos(t) +

279 x_4 \\sin(2t) + x_5 \\cos(2t) + \\cdots

280

281 Where :math:`x` coefficients correspond to the values of each dimension

282 and :math:`t` is linearly spaced between :math:`-\\pi` and :math:`+\\pi`.

283 Each row of frame then corresponds to a single curve.

284

285 Parameters

286 ----------

287 frame : DataFrame

288 Data to be plotted, preferably normalized to (0.0, 1.0).

289 class_column : label

290 Name of the column containing class names.

291 ax : axes object, default None

292 Axes to use.

293 samples : int

294 Number of points to plot in each curve.

295 color : str, list[str] or tuple[str], optional

296 Colors to use for the different classes. Colors can be strings

297 or 3-element floating point RGB values.

298 colormap : str or matplotlib colormap object, default None

299 Colormap to select colors from. If a string, load colormap with that

300 name from matplotlib.

301 **kwargs

302 Options to pass to matplotlib plotting method.

303

304 Returns

305 -------

306 :class:`matplotlib.axes.Axes`

307

308 Examples

309 --------

310

311 .. plot::

312 :context: close-figs

313

314 >>> df = pd.read_csv(

315 ... 'https://raw.githubusercontent.com/pandas-dev/'

316 ... 'pandas/main/pandas/tests/io/data/csv/iris.csv'

317 ... )

318 >>> pd.plotting.andrews_curves(df, 'Name')

319 <AxesSubplot: title={'center': 'width'}>

320 """

321 plot_backend = _get_plot_backend("matplotlib")

322 return plot_backend.andrews_curves(

323 frame=frame,

324 class_column=class_column,

325 ax=ax,

326 samples=samples,

327 color=color,

328 colormap=colormap,

329 **kwargs,

330 )

331

332

333def bootstrap_plot(

334 series: Series,

335 fig: Figure | None = None,

336 size: int = 50,

337 samples: int = 500,

338 **kwds,

339) -> Figure:

340 """

341 Bootstrap plot on mean, median and mid-range statistics.

342

343 The bootstrap plot is used to estimate the uncertainty of a statistic

344 by relying on random sampling with replacement [1]_. This function will

345 generate bootstrapping plots for mean, median and mid-range statistics

346 for the given number of samples of the given size.

347

348 .. [1] "Bootstrapping (statistics)" in \

349 https://en.wikipedia.org/wiki/Bootstrapping_%28statistics%29

350

351 Parameters

352 ----------

353 series : pandas.Series

354 Series from where to get the samplings for the bootstrapping.

355 fig : matplotlib.figure.Figure, default None

356 If given, it will use the `fig` reference for plotting instead of

357 creating a new one with default parameters.

358 size : int, default 50

359 Number of data points to consider during each sampling. It must be

360 less than or equal to the length of the `series`.

361 samples : int, default 500

362 Number of times the bootstrap procedure is performed.

363 **kwds

364 Options to pass to matplotlib plotting method.

365

366 Returns

367 -------

368 matplotlib.figure.Figure

369 Matplotlib figure.

370

371 See Also

372 --------

373 pandas.DataFrame.plot : Basic plotting for DataFrame objects.

374 pandas.Series.plot : Basic plotting for Series objects.

375

376 Examples

377 --------

378 This example draws a basic bootstrap plot for a Series.

379

380 .. plot::

381 :context: close-figs

382

383 >>> s = pd.Series(np.random.uniform(size=100))

384 >>> pd.plotting.bootstrap_plot(s)

385 <Figure size 640x480 with 6 Axes>

386 """

387 plot_backend = _get_plot_backend("matplotlib")

388 return plot_backend.bootstrap_plot(

389 series=series, fig=fig, size=size, samples=samples, **kwds

390 )

391

392

393def parallel_coordinates(

394 frame: DataFrame,

395 class_column: str,

396 cols: list[str] | None = None,

397 ax: Axes | None = None,

398 color: list[str] | tuple[str, ...] | None = None,

399 use_columns: bool = False,

400 xticks: list | tuple | None = None,

401 colormap=None,

402 axvlines: bool = True,

403 axvlines_kwds=None,

404 sort_labels: bool = False,

405 **kwargs,

406) -> Axes:

407 """

408 Parallel coordinates plotting.

409

410 Parameters

411 ----------

412 frame : DataFrame

413 class_column : str

414 Column name containing class names.

415 cols : list, optional

416 A list of column names to use.

417 ax : matplotlib.axis, optional

418 Matplotlib axis object.

419 color : list or tuple, optional

420 Colors to use for the different classes.

421 use_columns : bool, optional

422 If true, columns will be used as xticks.

423 xticks : list or tuple, optional

424 A list of values to use for xticks.

425 colormap : str or matplotlib colormap, default None

426 Colormap to use for line colors.

427 axvlines : bool, optional

428 If true, vertical lines will be added at each xtick.

429 axvlines_kwds : keywords, optional

430 Options to be passed to axvline method for vertical lines.

431 sort_labels : bool, default False

432 Sort class_column labels, useful when assigning colors.

433 **kwargs

434 Options to pass to matplotlib plotting method.

435

436 Returns

437 -------

438 matplotlib.axes.Axes

439

440 Examples

441 --------

442

443 .. plot::

444 :context: close-figs

445

446 >>> df = pd.read_csv(

447 ... 'https://raw.githubusercontent.com/pandas-dev/'

448 ... 'pandas/main/pandas/tests/io/data/csv/iris.csv'

449 ... )

450 >>> pd.plotting.parallel_coordinates(

451 ... df, 'Name', color=('#556270', '#4ECDC4', '#C7F464')

452 ... )

453 <AxesSubplot: xlabel='y(t)', ylabel='y(t + 1)'>

454 """

455 plot_backend = _get_plot_backend("matplotlib")

456 return plot_backend.parallel_coordinates(

457 frame=frame,

458 class_column=class_column,

459 cols=cols,

460 ax=ax,

461 color=color,

462 use_columns=use_columns,

463 xticks=xticks,

464 colormap=colormap,

465 axvlines=axvlines,

466 axvlines_kwds=axvlines_kwds,

467 sort_labels=sort_labels,

468 **kwargs,

469 )

470

471

472def lag_plot(series: Series, lag: int = 1, ax: Axes | None = None, **kwds) -> Axes:

473 """

474 Lag plot for time series.

475

476 Parameters

477 ----------

478 series : Series

479 The time series to visualize.

480 lag : int, default 1

481 Lag length of the scatter plot.

482 ax : Matplotlib axis object, optional

483 The matplotlib axis object to use.

484 **kwds

485 Matplotlib scatter method keyword arguments.

486

487 Returns

488 -------

489 matplotlib.axes.Axes

490

491 Examples

492 --------

493 Lag plots are most commonly used to look for patterns in time series data.

494

495 Given the following time series

496

497 .. plot::

498 :context: close-figs

499

500 >>> np.random.seed(5)

501 >>> x = np.cumsum(np.random.normal(loc=1, scale=5, size=50))

502 >>> s = pd.Series(x)

503 >>> s.plot()

504 <AxesSubplot: xlabel='Midrange'>

505

506 A lag plot with ``lag=1`` returns

507

508 .. plot::

509 :context: close-figs

510

511 >>> pd.plotting.lag_plot(s, lag=1)

512 <AxesSubplot: xlabel='y(t)', ylabel='y(t + 1)'>

513 """

514 plot_backend = _get_plot_backend("matplotlib")

515 return plot_backend.lag_plot(series=series, lag=lag, ax=ax, **kwds)

516

517

518def autocorrelation_plot(series: Series, ax: Axes | None = None, **kwargs) -> Axes:

519 """

520 Autocorrelation plot for time series.

521

522 Parameters

523 ----------

524 series : Series

525 The time series to visualize.

526 ax : Matplotlib axis object, optional

527 The matplotlib axis object to use.

528 **kwargs

529 Options to pass to matplotlib plotting method.

530

531 Returns

532 -------

533 matplotlib.axes.Axes

534

535 Examples

536 --------

537 The horizontal lines in the plot correspond to 95% and 99% confidence bands.

538

539 The dashed line is 99% confidence band.

540

541 .. plot::

542 :context: close-figs

543

544 >>> spacing = np.linspace(-9 * np.pi, 9 * np.pi, num=1000)

545 >>> s = pd.Series(0.7 * np.random.rand(1000) + 0.3 * np.sin(spacing))

546 >>> pd.plotting.autocorrelation_plot(s)

547 <AxesSubplot: title={'center': 'width'}, xlabel='Lag', ylabel='Autocorrelation'>

548 """

549 plot_backend = _get_plot_backend("matplotlib")

550 return plot_backend.autocorrelation_plot(series=series, ax=ax, **kwargs)

551

552

553class _Options(dict):

554 """

555 Stores pandas plotting options.

556

557 Allows for parameter aliasing so you can just use parameter names that are

558 the same as the plot function parameters, but is stored in a canonical

559 format that makes it easy to breakdown into groups later.

560 """

561

562 # alias so the names are same as plotting method parameter names

563 _ALIASES = {"x_compat": "xaxis.compat"}

564 _DEFAULT_KEYS = ["xaxis.compat"]

565

566 def __init__(self, deprecated: bool = False) -> None:

567 self._deprecated = deprecated

568 super().__setitem__("xaxis.compat", False)

569

570 def __getitem__(self, key):

571 key = self._get_canonical_key(key)

572 if key not in self:

573 raise ValueError(f"{key} is not a valid pandas plotting option")

574 return super().__getitem__(key)

575

576 def __setitem__(self, key, value) -> None:

577 key = self._get_canonical_key(key)

578 super().__setitem__(key, value)

579

580 def __delitem__(self, key) -> None:

581 key = self._get_canonical_key(key)

582 if key in self._DEFAULT_KEYS:

583 raise ValueError(f"Cannot remove default parameter {key}")

584 super().__delitem__(key)

585

586 def __contains__(self, key) -> bool:

587 key = self._get_canonical_key(key)

588 return super().__contains__(key)

589

590 def reset(self) -> None:

591 """

592 Reset the option store to its initial state

593

594 Returns

595 -------

596 None

597 """

598 # error: Cannot access "__init__" directly

599 self.__init__() # type: ignore[misc]

600

601 def _get_canonical_key(self, key):

602 return self._ALIASES.get(key, key)

603

604 @contextmanager

605 def use(self, key, value) -> Generator[_Options, None, None]:

606 """

607 Temporarily set a parameter value using the with statement.

608 Aliasing allowed.

609 """

610 old_value = self[key]

611 try:

612 self[key] = value

613 yield self

614 finally:

615 self[key] = old_value

616

617

618plot_params = _Options()

Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/pandas/plotting/_misc.py: 41%

73 statements