The Kernel density estimate (`kde`) plot shows the distribution of the data. The KDE works by placing a Gaussian kernel at each sample with the supplied bandwidth, which are then summed to produce the density estimate. By default the bandwidth is determined using th
(self, y=None, by=None, **kwds)
| 1105 | ) |
| 1106 | |
| 1107 | def kde(self, y=None, by=None, **kwds): |
| 1108 | """ |
| 1109 | The Kernel density estimate (`kde`) plot shows the distribution of the data. |
| 1110 | |
| 1111 | The KDE works by placing a Gaussian kernel at each sample with the supplied |
| 1112 | bandwidth, which are then summed to produce the density estimate. By default |
| 1113 | the bandwidth is determined using the Scott's method, which usually produces |
| 1114 | good results, but it may be overridden by an explicit value. |
| 1115 | |
| 1116 | ``density`` is an alias of ``kde``. |
| 1117 | |
| 1118 | Reference: https://hvplot.holoviz.org/ref/api/manual/hvplot.hvPlot.kde.html |
| 1119 | |
| 1120 | Plotting options: https://hvplot.holoviz.org/ref/plotting_options/index.html |
| 1121 | |
| 1122 | Parameters |
| 1123 | ---------- |
| 1124 | y : string or sequence |
| 1125 | Field(s) in the data to compute distribution on. If not specified all numerical fields |
| 1126 | are used. |
| 1127 | by : string or sequence |
| 1128 | Field(s) in the data to group by. |
| 1129 | bandwidth : float, optional |
| 1130 | Allows supplying explicit bandwidth value of the kernel for the |
| 1131 | density estimate, rather than relying on Scott. Higher value |
| 1132 | yields smoother contours. Default is None. |
| 1133 | cut : float, optional |
| 1134 | Draw the estimate to cut * bw from the extreme data points. Default is 3. |
| 1135 | filled : |
| 1136 | Whether the bivariate contours should be filled. Default is True. |
| 1137 | bw_method : optional |
| 1138 | Not supported. |
| 1139 | ind : optional |
| 1140 | Not supported. |
| 1141 | kwds : optional |
| 1142 | Additional keywords arguments are documented in :ref:`plot-options`. |
| 1143 | Run ``hvplot.help('kde')`` for the full method documentation. |
| 1144 | |
| 1145 | Returns |
| 1146 | ------- |
| 1147 | :class:`holoviews:holoviews.element.Distribution` / Panel object |
| 1148 | You can `print` the object to study its composition and run: |
| 1149 | |
| 1150 | .. code-block:: |
| 1151 | |
| 1152 | import holoviews as hv |
| 1153 | hv.help(the_holoviews_object) |
| 1154 | |
| 1155 | to learn more about its parameters and options. |
| 1156 | |
| 1157 | See Also |
| 1158 | -------- |
| 1159 | hist : Histogram plot. |
| 1160 | bivariate : 2D KDE plot. |
| 1161 | contour : Isolines plot for gridded data. |
| 1162 | |
| 1163 | References |
| 1164 | ---------- |