Spaces:
Running
Running
File size: 18,221 Bytes
b9a0f21 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 |
If hvplot and pandas are both installed, then we can use the pandas.options.plotting.backend to control the output of `pd.DataFrame.plot` and `pd.Series.plot`. This notebook is meant to recreate the [pandas visualization docs](https://pandas.pydata.org/pandas-docs/stable/user_guide/visualization.html).
```python
import numpy as np
import pandas as pd
pd.options.plotting.backend = 'holoviews'
```
## Basic Plotting: `plot`
The plot method on Series and DataFrame is just a simple wrapper around `hvplot()`:
```python
ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
ts = ts.cumsum()
ts.plot()
```
If the index consists of dates, they will be sorted (as long as `sort_date=True`) and formatted the x-axis nicely as per above.
On DataFrame, `plot()` is a convenience to plot all of the columns with labels:
```python
df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index, columns=list('ABCD'))
df = df.cumsum()
df.plot()
```
You can plot one column versus another using the *x* and *y* keywords in `plot()`:
```python
df3 = pd.DataFrame(np.random.randn(1000, 2), columns=['B', 'C']).cumsum()
df3['A'] = pd.Series(list(range(len(df))))
df3.plot(x='A', y='B')
```
**Note** For more formatting and styling options, see [formatting](#plot-formatting) below.
## Other Plots
Plotting methods allow for a handful of plot styles other than the default `line` plot. These methods can be provided as the `kind` keyword argument to `plot()`. These include:
* `bar` or `barh` for bar plots
* `hist` for histogram
* `box` for boxplot
* `kde` or `density` for density plots
* `area` for area plots
* `scatter` for scatter plots
* `hexbin` for hexagonal bin plots
* ~~`pie` for pie plots~~
For example, a bar plot can be created the following way:
```python
df.iloc[5].plot(kind='bar')
```
You can also create these other plots using the methods DataFrame.plot.<kind> instead of providing the kind keyword argument. This makes it easier to discover plot methods and the specific arguments they use:
In addition to these `kind`s, there are the `DataFrame.hist()`, and `DataFrame.boxplot()` methods, which use a separate interface.
Finally, there are several plotting functions in `hvplot.plotting` that take a `Series` or `DataFrame` as an argument. These include:
* `Scatter Matrix`
* `Andrews Curves`
* `Parallel Coordinates`
* `Lag Plot`
* ~~`Autocorrelation Plot`~~
* ~~`Bootstrap Plot`~~
* ~~`RadViz`~~
Plots may also be adorned with errorbars or tables.
### Bar plots
For labeled, non-time series data, you may wish to produce a bar plot:
```python
import holoviews as hv
```
```python
df.iloc[5].plot.bar() * hv.HLine(0).opts(color='k')
```
Calling a DataFrame’s `plot.bar()` method produces a multiple bar plot:
```python
df2 = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df2.plot.bar()
```
To produce a stacked bar plot, pass `stacked=True`:
```python
df2.plot.bar(stacked=True)
```
To get horizontal bar plots, use the `barh` method:
```python
df2.plot.barh(stacked=True)
```
### Histograms
Histogram can be drawn by using the `DataFrame.plot.hist()` and `Series.plot.hist()` methods.
```python
df4 = pd.DataFrame({'a': np.random.randn(1000) + 1, 'b': np.random.randn(1000),
'c': np.random.randn(1000) - 1}, columns=['a', 'b', 'c'])
df4.plot.hist(alpha=0.5)
```
Using the matplotlib backend, histograms can be stacked using `stacked=True`; **stacking is not yet supported in the holoviews backend**. Bin size can be changed by `bins` keyword.
```python
# Stacked not supported
df4.plot.hist(stacked=True, bins=20)
```
You can pass other keywords supported by matplotlib hist. For example, horizontal and cumulative histogram can be drawn by `invert=True` and `cumulative=True`.
```python
df4['a'].plot.hist(invert=True, cumulative=True)
```
The existing interface `DataFrame.hist` to plot histogram still can be used.
```python
df['A'].diff().hist()
```
`DataFrame.hist()` plots the histograms of the columns on multiple subplots:
```python
df.diff().hist(color='k', alpha=0.5, bins=50, subplots=True, width=300).cols(2)
```
The by keyword can be specified to plot grouped histograms:
```python
# by does not support arrays, instead the array should be added as a column
data = pd.Series(np.random.randn(1000))
data = pd.DataFrame({'data': data, 'by_column': np.random.randint(0, 4, 1000)})
data.hist(by='by_column', width=300, subplots=True).cols(2)
```
### Box Plots
Boxplot can be drawn calling `Series.plot.box()` and `DataFrame.plot.box()`, or `DataFrame.boxplot()` to visualize the distribution of values within each column.
For instance, here is a boxplot representing five trials of 10 observations of a uniform random variable on [0,1).
```python
df = pd.DataFrame(np.random.rand(10, 5), columns=['A', 'B', 'C', 'D', 'E'])
df.plot.box()
```
Using the matplotlib backend, boxplot can be colorized by passing `color` keyword. You can pass a `dict` whose keys are `boxes`, `whiskers`, `medians` and `caps`.
**This behavior is not supported in the holoviews backend.**
You can pass other keywords supported by holoviews boxplot. For example, horizontal and custom-positioned boxplot can be drawn by `invert=True` and positions keywords.
```python
# positions not supported
df.plot.box(invert=True, positions=[1, 4, 5, 6, 8])
```
See the boxplot method and the matplotlib boxplot documentation for more.
The existing interface `DataFrame.boxplot` to plot boxplot still can be used.
```python
df = pd.DataFrame(np.random.rand(10, 5))
df.boxplot()
```
You can create a stratified boxplot using the `groupby` keyword argument to create groupings. For instance,
```python
df = pd.DataFrame(np.random.rand(10,2), columns=['Col1', 'Col2'])
df['X'] = pd.Series(['A','A','A','A','A','B','B','B','B','B'])
df.boxplot(col='X')
```
You can also pass a subset of columns to plot, as well as group by multiple columns:
```python
df = pd.DataFrame(np.random.rand(10,3), columns=['Col1', 'Col2', 'Col3'])
df['X'] = pd.Series(['A','A','A','A','A','B','B','B','B','B'])
df['Y'] = pd.Series(['A','B','A','B','A','B','A','B','A','B'])
df.boxplot(y=['Col1','Col2'], col='X', row='Y')
```
```python
df_box = pd.DataFrame(np.random.randn(50, 2))
df_box['g'] = np.random.choice(['A', 'B'], size=50)
df_box.loc[df_box['g'] == 'B', 1] += 3
df_box.boxplot(row='g')
```
For more control over the ordering of the levels, we can perform a groupby on the data before plotting.
```python
df_box.groupby('g').boxplot()
```
### Area Plot
You can create area plots with `Series.plot.area()` and `DataFrame.plot.area()`. Area plots are *not* stacked by default. To produce stacked area plot, each column must be either all positive or all negative values.
When input data contains *NaN*, it will be automatically filled by 0. If you want to drop or fill by different values, use `dataframe.dropna()` or `dataframe.fillna()` before calling plot.
```python
df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df.plot.area(alpha=0.5)
```
To produce an stacked plot, pass `stacked=True`.
```python
df.plot.area(stacked=True)
```
### Scatter Plot
Scatter plot can be drawn by using the `DataFrame.plot.scatter()` method. Scatter plot require that x and y be specified using the `x` and `y` keywords.
```python
df = pd.DataFrame(np.random.rand(50, 4), columns=['a', 'b', 'c', 'd'])
df.plot.scatter(x='a', y='b')
```
To plot multiple column groups in a single axes, repeat `plot` method and then use the overlay operator (`*`) to combine the plots. It is recommended to specify color and label keywords to distinguish each groups.
```python
plot_1 = df.plot.scatter(x='a', y='b', color='DarkBlue', label='Group 1')
plot_2 = df.plot.scatter(x='c', y='d', color='DarkGreen', label='Group 2')
plot_1 * plot_2
```
The keyword `c` may be given as the name of a column to provide colors for each point:
```python
df.plot.scatter(x='a', y='b', c='c', s=50)
```
You can pass other keywords supported by matplotlib `scatter`. The example below shows a bubble chart using a column of the `DataFrame` as the bubble size.
```python
df.plot.scatter(x='a', y='b', s=df['c']*500)
```
The same effect can be accomplished using the `scale` option.
```python
df.plot.scatter(x='a', y='b', s='c', scale=25)
```
### Hexagonal Bin Plot
You can create hexagonal bin plots with `DataFrame.plot.hexbin()`. Hexbin plots can be a useful alternative to scatter plots if your data are too dense to plot each point individually.
```python
df = pd.DataFrame(np.random.randn(1000, 2), columns=['a', 'b'])
df['b'] = df['b'] + np.arange(1000)
df.plot.hexbin(x='a', y='b', gridsize=25, width=500, height=400)
```
A useful keyword argument is `gridsize`; it controls the number of hexagons in the x-direction, and defaults to 100. A larger `gridsize` means more, smaller bins.
By default, a histogram of the counts around each `(x, y)` point is computed. You can specify alternative aggregations by passing values to the `C` and `reduce_C_function` arguments. `C` specifies the value at each `(x, y)` point and `reduce_C_function` is a function of one argument that reduces all the values in a bin to a single number (e.g. `mean`, `max`, `sum`, `std`). In this example the positions are given by columns `a` and `b`, while the value is given by column z. The bins are aggregated with numpy’s `max` function.
```python
df = pd.DataFrame(np.random.randn(1000, 2), columns=['a', 'b'])
df['b'] = df['b'] = df['b'] + np.arange(1000)
df['z'] = np.random.uniform(0, 3, 1000)
df.plot.hexbin(x='a', y='b', C='z', reduce_function=np.max, gridsize=25, width=500, height=400)
```
### Density Plot
You can create density plots using the `Series.plot.kde()` and `DataFrame.plot.kde()` methods.
```python
ser = pd.Series(np.random.randn(1000))
ser.plot.kde()
```
### Pie plot
**NOT SUPPORTED**
## Plotting Tools
These functions can be imported from `hvplot.plotting` and take a `Series` or `DataFrame` as an argument.
### Scatter Matrix Plot
You can create a scatter plot matrix using the `scatter_matrix` function:
```python
import pandas as pd, numpy as np
```
```python
from hvplot import scatter_matrix
df = pd.DataFrame(np.random.randn(1000, 4), columns=['a', 'b', 'c', 'd'])
scatter_matrix(df, alpha=0.2, diagonal='kde')
```
Since scatter matrix plots may generate a large number of points (the one above renders 120,000 points!), you may want to take advantage of the power provided by [Datashader](https://datashader.org/) to rasterize the off-diagonal plots into a fixed-resolution representation:
```python
df = pd.DataFrame(np.random.randn(10000, 4), columns=['a', 'b', 'c', 'd'])
scatter_matrix(df, rasterize=True, dynspread=True)
```
### Andrews Curves
Andrews curves allow one to plot multivariate data as a large number of curves that are created using the attributes of samples as coefficients for Fourier series. By coloring these curves differently for each class it is possible to visualize data clustering. Curves belonging to samples of the same class will usually be closer together and form larger structures.
```python
from bokeh.sampledata import iris
from hvplot import andrews_curves
data = iris.flowers
andrews_curves(data, 'species')
```
### Parallel Coordinates
Parallel coordinates is a plotting technique for plotting multivariate data. It allows one to see clusters in data and to estimate other statistics visually. Using parallel coordinates points are represented as connected line segments. Each vertical line represents one attribute. One set of connected line segments represents one data point. Points that tend to cluster will appear closer together.
```python
from hvplot import parallel_coordinates
parallel_coordinates(data, 'species')
```
### Lag Plot
Lag plots are used to check if a data set or time series is random. Random data should not exhibit any structure in the lag plot. Non-random structure implies that the underlying data are not random.
```python
from hvplot import lag_plot
data = pd.Series(0.1 * np.random.rand(1000) +
0.9 * np.sin(np.linspace(-99 * np.pi, 99 * np.pi, num=1000)))
lag_plot(data, width=400, height=400)
```
### Autocorrelation Plot
**NOT SUPPORTED**
### Bootstrap Plot
**NOT SUPPORTED**
### RadViz
**NOT SUPPORTED**
## Plot Formatting
### General plot style arguments
Most plotting methods have a set of keyword arguments that control the layout and formatting of the returned plot:
```python
ts.plot(c='k', line_dash='dashed', label='Series')
```
For each kind of plot (e.g. *line*, *bar*, *scatter*) any additional arguments keywords are passed along to the corresponding holoviews object (`hv.Curve`, `hv.Bar`, `hv.Scatter`). These can be used to control additional styling, beyond what pandas provides.
### Controlling the Legend
You may set the `legend` argument to `False` to hide the legend, which is shown by default. You can also control the placement of the legend using the same `legend` argument set to one of: 'top_right', 'top_left', 'bottom_left', 'bottom_right', 'right', 'left', 'top', or 'bottom'.
```python
df = pd.DataFrame(np.random.randn(1000, 4),
index=ts.index, columns=list('ABCD'))
df = df.cumsum()
df.plot(legend=False)
```
```python
df.plot(legend='top_left')
```
### Scales
You may pass `logy` to get a log-scale Y axis, similarly use `logx` to get a log-scale on the X axis or `logz` to get a log-scale on the color axis.
```python
ts = pd.Series(np.random.randn(1000),
index=pd.date_range('1/1/2000', periods=1000))
ts = np.exp(ts.cumsum())
ts.plot(logy=True)
```
```python
df = pd.DataFrame(np.random.randn(1000, 2), columns=['a', 'b'])
df['b'] = df['b'] + np.arange(1000)
df.plot.hexbin(x='a', y='b', gridsize=25, width=500, height=400, logz=True)
```
### Plotting on a Secondary Y-axis
**NOT SUPPORTED**
### Suppressing tick resolution adjustment
pandas includes automatic tick resolution adjustment for regular frequency time-series data. For limited cases where pandas cannot infer the frequency information (e.g., in an externally created twinx), you can choose to suppress this behavior for alignment purposes.
Here is the default behavior, notice how the x-axis tick labeling is performed:
```python
df = pd.DataFrame(np.random.randn(1000, 4),
index=ts.index, columns=list('ABCD'))
df = df.cumsum()
df.A.plot()
```
Formatters can be set using format strings, by declaring bokeh TickFormatters, or using custom functions. See [HoloViews Tick Docs](https://holoviews.org/user_guide/Customizing_Plots.html#Axis-ticks) for more information.
```python
from bokeh.models.formatters import DatetimeTickFormatter
formatter = DatetimeTickFormatter(months='%b %Y')
```
```python
df.A.plot(yformatter='$%.2f', xformatter=formatter)
```
### Subplots
Each `Series` in a `DataFrame` can be plotted on a different axis with the `subplots` keyword:
```python
df = pd.DataFrame(np.random.randn(1000, 4),
index=ts.index, columns=list('ABCD'))
df = df.cumsum()
df.plot(subplots=True, height=150).cols(1)
```
### Controlling layout and targeting multiple axes
The layout of subplots can be specified using `.cols(n)`.
```python
df.plot(subplots=True, shared_axes=False, width=150).cols(3)
```
### Plotting with error bars
Plotting with error bars is *not* supported in `DataFrame.plot()` and `Series.plot()`. To add errorbars, users should fall back to using hvplot directly.
```python
import hvplot.pandas # noqa
```
```python
df3 = pd.DataFrame({'data1': [3, 2, 4, 3, 2, 4, 3, 2],
'data2': [6, 5, 7, 5, 4, 5, 6, 5]})
mean_std = pd.DataFrame({'mean': df3.mean(), 'std': df3.std()})
mean_std
```
```python
(mean_std.plot.bar(y='mean', alpha=0.7) * \
mean_std.hvplot.errorbars(x='index', y='mean', yerr1='std')
).opts(show_legend=False).redim.range(mean=(0, 6.5))
```
### Plotting tables
The matplotlib backend includes support for the `table` keyword in `DataFrame.plot()` and `Series.plot()`. This same effect can be accomplished with holoviews by using `hvplot.table` and creating a layout of the resulting plots.
```python
df = pd.DataFrame(np.random.rand(5, 3), columns=['a', 'b', 'c'])
(df.plot(xaxis=False, legend='top_right') + \
df.T.hvplot.table()).cols(1)
```
### Colormaps
A potential issue when plotting a large number of columns is that it can be difficult to distinguish some series due to repetition in the default colors. To remedy this, DataFrame plotting supports the use of the `colormap` argument, which accepts either a colormap or a string that is a name of a colormap.
To use the cubehelix colormap, we can pass `colormap='cubehelix'`.
```python
df = pd.DataFrame(np.random.randn(1000, 10), index=ts.index)
df = df.cumsum()
df.plot(colormap='cubehelix')
```
Colormaps can also be used with other plot types, like bar charts:
```python
dd = pd.DataFrame(np.random.randn(10, 10)).applymap(abs)
dd = dd.cumsum()
dd.plot.bar(colormap='Greens')
```
Parallel coordinates charts:
```python
from bokeh.sampledata import iris
from hvplot import parallel_coordinates, andrews_curves
data = iris.flowers
parallel_coordinates(data, 'species', colormap='gist_rainbow')
```
Andrews curves charts:
```python
andrews_curves(data, 'species', colormap='winter')
```
## Plotting directly with holoviews
In some situations it may still be preferable or necessary to prepare plots directly with hvplot or holoviews, for instance when a certain type of plot or customization is not (yet) supported by pandas. `Series` and `DataFrame` objects behave like arrays and can therefore be passed directly to holoviews functions without explicit casts.
```python
import holoviews as hv
price = pd.Series(np.random.randn(150).cumsum(),
index=pd.date_range('2000-1-1', periods=150, freq='B'), name='price')
ma = price.rolling(20).mean()
mstd = price.rolling(20).std()
price.plot(c='k') * ma.plot(c='b', label='mean') * \
hv.Area((mstd.index, ma - 2 * mstd, ma + 2 * mstd),
vdims=['y', 'y2']).opts(color='b', alpha=0.2)
```
|