legend-for-scatter

ImportanceOfBeingErnest · ImportanceOfBeingErnest · commit 3d85295fee28 · 2018-06-19T17:16:02.000+02:00
diff --git a/doc/users/next_whats_new/legend_for_scatter.rst b/doc/users/next_whats_new/legend_for_scatter.rst
@@ -0,0 +1,17 @@
+Legend for scatter
+------------------
+
+A new method for creating legends for scatter plots has been introduced.
+Previously, in order to obtain a legend for a :meth:`~.axes.Axes.scatter`
+plot, one could either plot several scatters, each with an individual label,
+or create proxy artists to show in the legend manually.
+Now, :class:`~.collections.PathCollection` provides a method
+:meth:`~.collections.PathCollection.legend_elements` to obtain the handles and labels
+for a scatter plot in an automated way. This makes creating a legend for a
+scatter plot as easy as::
+
+    scatter = plt.scatter([1,2,3], [4,5,6], c=[7,2,3])
+    plt.legend(*scatter.legend_elements())
+
+An example can be found in
+:ref:`automatedlegendcreation`.
diff --git a/examples/lines_bars_and_markers/scatter_with_legend.py b/examples/lines_bars_and_markers/scatter_with_legend.py
@@ -3,24 +3,113 @@
 Scatter plots with a legend
 ===========================
 
-Also demonstrates how transparency of the markers
-can be adjusted by giving ``alpha`` a value between
-0 and 1.
+To create a scatter plot with a legend one may use a loop and create one
+`~.Axes.scatter` plot per item to appear in the legend and set the ``label``
+accordingly.
+
+The following also demonstrates how transparency of the markers
+can be adjusted by giving ``alpha`` a value between 0 and 1.
 """
 
+import numpy as np
+np.random.seed(19680801)
 import matplotlib.pyplot as plt
-from numpy.random import rand
 
 
 fig, ax = plt.subplots()
 for color in ['red', 'green', 'blue']:
     n = 750
-    x, y = rand(2, n)
-    scale = 200.0 * rand(n)
+    x, y = np.random.rand(2, n)
+    scale = 200.0 * np.random.rand(n)
     ax.scatter(x, y, c=color, s=scale, label=color,
                alpha=0.3, edgecolors='none')
 
 ax.legend()
 ax.grid(True)
 
 plt.show()
+
+
+##############################################################################
+# .. _automatedlegendcreation:
+#
+# Automated legend creation
+# -------------------------
+#
+# Another option for creating a legend for a scatter is to use the
+# :class:`~matplotlib.collections.PathCollection`'s
+# :meth:`~.PathCollection.legend_elements` method.
+# It will automatically try to determine a useful number of legend entries
+# to be shown and return a tuple of handles and labels. Those can be passed
+# to the call to :meth:`~.axes.Axes.legend`.
+
+
+N = 45
+x, y = np.random.rand(2, N)
+c = np.random.randint(1, 5, size=N)
+s = np.random.randint(10, 220, size=N)
+
+fig, ax = plt.subplots()
+
+scatter = ax.scatter(x, y, c=c, s=s)
+
+# produce a legend with the unique colors from the scatter
+legend1 = ax.legend(*scatter.legend_elements(), loc=3, title="Classes")
+ax.add_artist(legend1)
+
+# produce a legend with a cross section of sizes from the scatter
+handles, labels = scatter.legend_elements(prop="sizes", alpha=0.6)
+legend2 = ax.legend(handles, labels, loc=1, title="Sizes")
+
+plt.show()
+
+
+##############################################################################
+# Further arguments to the :meth:`~.PathCollection.legend_elements` method
+# can be used to steer how many legend entries are to be created and how they
+# should be labeled. The following shows how to use some of them.
+#
+
+volume = np.random.rayleigh(27, size=40)
+amount = np.random.poisson(10, size=40)
+ranking = np.random.normal(size=40)
+price = np.random.uniform(1, 10, size=40)
+
+fig, ax = plt.subplots()
+
+# Because the price is much too small when being provided as size for ``s``,
+# we normalize it to some useful point sizes, s=0.3*(price*3)**2
+scatter = ax.scatter(volume, amount, c=ranking, s=0.3*(price*3)**2,
+                     vmin=-3, vmax=3, cmap="Spectral")
+
+# Produce a legend for the ranking (colors). Even though there are 40 different
+# rankings, we only want to show 5 of them in the legend.
+legend1 = ax.legend(*scatter.legend_elements(num=5), loc=2, title="Ranking")
+ax.add_artist(legend1)
+
+# Produce a legend for the price (sizes). Because we want to show the prices
+# in dollars, we use the *func* argument to supply the inverse of the function
+# used to calculate the sizes from above. The *fmt* ensures to show the price
+# in dollars. Note how we target at 5 elements here, but obtain only 4 in the
+# created legend due to the automatic round prices that are chosen for us.
+kw = dict(prop="sizes", num=5, color=scatter.cmap(0.7), fmt="\$ {x:.2f}",
+          func=lambda s: np.sqrt(s/.3)/3)
+legend2 = ax.legend(*scatter.legend_elements(**kw), loc=4, title="Price")
+
+plt.show()
+
+#############################################################################
+#
+# ------------
+#
+# References
+# """"""""""
+#
+# The usage of the following functions and methods is shown in this example:
+
+import matplotlib
+matplotlib.axes.Axes.scatter
+matplotlib.pyplot.scatter
+matplotlib.axes.Axes.legend
+matplotlib.pyplot.legend
+matplotlib.collections.PathCollection.legend_elements
diff --git a/lib/matplotlib/collections.py b/lib/matplotlib/collections.py
@@ -877,6 +877,7 @@ def draw(self, renderer):
 class PathCollection(_CollectionWithSizes):
     """
     This is the most basic :class:`Collection` subclass.
+    A :class:`PathCollection` is e.g. created by a :meth:`~.Axes.scatter` plot.
     """
     @docstring.dedent_interpd
     def __init__(self, paths, sizes=None, **kwargs):
@@ -899,6 +900,125 @@ def set_paths(self, paths):
     def get_paths(self):
         return self._paths
 
+    def legend_elements(self, prop="colors", num="auto",
+                     fmt=None, func=lambda x: x, **kwargs):
+        """
+        Creates legend handles and labels for a PathCollection. This is useful
+        for obtaining a legend for a :meth:`~.Axes.scatter` plot. E.g.::
+
+            scatter = plt.scatter([1,2,3], [4,5,6], c=[7,2,3])
+            plt.legend(*scatter.legend_elements())
+
+        Also see the :ref:`automatedlegendcreation` example.
+
+        Parameters
+        ----------
+        prop : string, optional, default *"colors"*
+            Can be *"colors"* or *"sizes"*. In case of *"colors"*, the legend
+            handles will show the different colors of the collection. In case
+            of "sizes", the legend will show the different sizes.
+        num : int, None, "auto" (default), or `~.ticker.Locator`, optional
+            Target number of elements to create.
+            If None, use all unique elements of the mappable array. If an
+            integer, target to use *num* elements in the normed range.
+            If *"auto"*, try to determine which option better suits the nature
+            of the data.
+            The number of created elements may slightly deviate from *num* due
+            to a `~.ticker.Locator` being used to find useful locations.
+            Finally, a `~.ticker.Locator` can be provided.
+        fmt : string, `~matplotlib.ticker.Formatter`, or None (default)
+            The format or formatter to use for the labels. If a string must be
+            a valid input for a `~.StrMethodFormatter`. If None (the default),
+            use a `~.ScalarFormatter`.
+        func : function, default *lambda x: x*
+            Function to calculate the labels. Often the size (or color)
+            argument to :meth:`~.Axes.scatter` will have been pre-processed
+            by the user using a function *s = f(x)* to make the markers
+            visible; e.g. *size = np.log10(x)*. Providing the inverse of this
+            function here allows that pre-processing to be inverted, so that
+            the legend labels have the correct values;
+            e.g. *func = np.exp(x, 10)*.
+        kwargs : further parameters
+            Allowed kwargs are *color* and *size*. E.g. it may be useful to
+            set the color of the markers if *prop="sizes"* is used; similarly
+            to set the size of the markers if *prop="colors"* is used.
+            Any further parameters are passed onto the `.Line2D` instance.
+            This may be useful to e.g. specify a different *markeredgecolor* or
+            *alpha* for the legend handles.
+
+        Returns
+        -------
+        tuple (handles, labels)
+            with *handles* being a list of `.Line2D`  objects
+            and *labels* a list of strings of the same length.
+        """
+        handles = []
+        labels = []
+        hasarray = self.get_array() is not None
+        if fmt is None:
+            fmt = mpl.ticker.ScalarFormatter(useOffset=False, useMathText=True)
+        elif isinstance(fmt, str):
+            fmt = mpl.ticker.StrMethodFormatter(fmt)
+        fmt.create_dummy_axis()
+
+        if prop == "colors" and hasarray:
+            u = np.unique(self.get_array())
+            size = kwargs.pop("size", mpl.rcParams["lines.markersize"])
+        elif prop == "sizes":
+            u = np.unique(self.get_sizes())
+            color = kwargs.pop("color", "k")
+        else:
+            warnings.warn("Invalid prop provided, or collection without "
+                          "array used.")
+            return handles, labels
+
+        fmt.set_bounds(func(u).min(), func(u).max())
+        if num == "auto":
+            num = 9
+            if len(u) <= num:
+                num = None
+        if num is None:
+            values = u
+            label_values = func(values)
+        else:
+            if prop == "colors" and hasarray:
+                arr = self.get_array()
+            elif prop == "sizes":
+                arr = self.get_sizes()
+            if isinstance(num, mpl.ticker.Locator):
+                loc = num
+            else:
+                num = int(num)
+                loc = mpl.ticker.MaxNLocator(nbins=num, min_n_ticks=num-1,
+                                             steps=[1, 2, 2.5, 3, 5, 6, 8, 10])
+            label_values = loc.tick_values(func(arr).min(), func(arr).max())
+            cond = (label_values >= func(arr).min()) & \
+                   (label_values <= func(arr).max())
+            label_values = label_values[cond]
+            xarr = np.linspace(arr.min(), arr.max(), 256)
+            values = np.interp(label_values, func(xarr), xarr)
+
+        kw = dict(markeredgewidth=self.get_linewidths()[0],
+                  alpha=self.get_alpha())
+        kw.update(kwargs)
+
+        for val, lab in zip(values, label_values):
+            if prop == "colors" and hasarray:
+                color = self.cmap(self.norm(val))
+            elif prop == "sizes":
+                size = np.sqrt(val)
+                if np.isclose(size, 0.0):
+                    continue
+            h = mlines.Line2D([0], [0], ls="", color=color, ms=size,
+                              marker=self.get_paths()[0], **kw)
+            handles.append(h)
+            if hasattr(fmt, "set_locs"):
+                fmt.set_locs(label_values)
+            l = fmt(lab)
+            labels.append(l)
+
+        return handles, labels
+
 
 class PolyCollection(_CollectionWithSizes):
     @docstring.dedent_interpd
diff --git a/lib/matplotlib/tests/test_collections.py b/lib/matplotlib/tests/test_collections.py
@@ -669,3 +669,51 @@ def test_scatter_post_alpha():
     # this needs to be here to update internal state
     fig.canvas.draw()
     sc.set_alpha(.1)
+
+
+def test_pathcollection_legend_elements():
+    np.random.seed(19680801)
+    x, y = np.random.rand(2, 10)
+    y = np.random.rand(10)
+    c = np.random.randint(0, 5, size=10)
+    s = np.random.randint(10, 300, size=10)
+
+    fig, ax = plt.subplots()
+    sc = ax.scatter(x, y, c=c, s=s, cmap="jet", marker="o", linewidths=0)
+
+    h, l = sc.legend_elements(fmt="{x:g}")
+    assert len(h) == 5
+    assert_array_equal(np.array(l).astype(float), np.arange(5))
+    colors = np.array([line.get_color() for line in h])
+    colors2 = sc.cmap(np.arange(5)/4)
+    assert_array_equal(colors, colors2)
+    l1 = ax.legend(h, l, loc=1)
+
+    h2, lab2 = sc.legend_elements(num=9)
+    assert len(h2) == 9
+    l2 = ax.legend(h2, lab2, loc=2)
+
+    h, l = sc.legend_elements(prop="sizes", alpha=0.5, color="red")
+    alpha = np.array([line.get_alpha() for line in h])
+    assert_array_equal(alpha, 0.5)
+    color = np.array([line.get_markerfacecolor() for line in h])
+    assert_array_equal(color, "red")
+    l3 = ax.legend(h, l, loc=4)
+
+    h, l = sc.legend_elements(prop="sizes", num=4, fmt="{x:.2f}",
+                           func=lambda x: 2*x)
+    actsizes = [line.get_markersize() for line in h]
+    labeledsizes = np.sqrt(np.array(l).astype(float)/2)
+    assert_array_almost_equal(actsizes, labeledsizes)
+    l4 = ax.legend(h, l, loc=3)
+
+    import matplotlib.ticker as mticker
+    loc = mticker.MaxNLocator(nbins=9, min_n_ticks=9-1,
+                              steps=[1, 2, 2.5, 3, 5, 6, 8, 10])
+    h5, lab5 = sc.legend_elements(num=loc)
+    assert len(h2) == len(h5)
+
+    for l in [l1, l2, l3, l4]:
+        ax.add_artist(l)
+
+    fig.canvas.draw()
