{ "__type": "IngestedDoc", "__tag": 4010, "_content": { "Notes": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "All but the last (righthand-most) bin is half-open. In other words, if " }, { "__type": "ParamRef", "__tag": 4071, "name": "bins" }, { "__type": "Text", "__tag": 4046, "value": " is " }, { "__type": "InlineCode", "__tag": 4051, "value": "[1, 2, 3, 4]" }, { "__type": "Text", "__tag": 4046, "value": ", then the first bin is " }, { "__type": "InlineCode", "__tag": 4051, "value": "[1, 2)" }, { "__type": "Text", "__tag": 4046, "value": " (including 1, but excluding 2) and the second " }, { "__type": "InlineCode", "__tag": 4051, "value": "[2, 3)" }, { "__type": "Text", "__tag": 4046, "value": ". The last bin, however, is " }, { "__type": "InlineCode", "__tag": 4051, "value": "[3, 4]" }, { "__type": "Text", "__tag": 4046, "value": ", which " }, { "__type": "Emphasis", "__tag": 4047, "children": [ { "__type": "Text", "__tag": 4046, "value": "includes" } ] }, { "__type": "Text", "__tag": 4046, "value": " 4." } ] }, { "__type": "Admonition", "__tag": 4056, "kind": "versionadded", "base_type": "neutral", "children": [ { "__type": "AdmonitionTitle", "__tag": 4055, "children": [ { "__type": "Text", "__tag": 4046, "value": "versionadded 0.11.0" } ] } ] }, { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Strong", "__tag": 4048, "children": [ { "__type": "Text", "__tag": 4046, "value": "Array API Standard Support" } ] } ] }, { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "CrossRef", "__tag": 4002, "value": "binned_statistic", "reference": { "__type": "LocalRef", "__tag": 4022, "kind": "module", "path": "scipy.stats._binned_statistic:binned_statistic" }, "kind": "module" }, { "__type": "Text", "__tag": 4046, "value": " has experimental support for Python Array API Standard compatible backends in addition to NumPy. Please consider testing these features by setting an environment variable " }, { "__type": "InlineCode", "__tag": 4051, "value": "SCIPY_ARRAY_API=1" }, { "__type": "Text", "__tag": 4046, "value": " and providing CuPy, PyTorch, JAX, or Dask arrays as array arguments. The following combinations of backend and device (or other capability) are supported." } ] }, { "__type": "Code", "__tag": 4050, "value": "==================== ==================== ====================\nLibrary CPU GPU\n==================== ==================== ====================\nNumPy ✅ n/a \nCuPy n/a ⛔ \nPyTorch ⛔ ⛔ \nJAX ⛔ ⛔ \nDask ⛔ n/a \n==================== ==================== ====================", "execution_status": null }, { "__type": "Blockquote", "__tag": 4059, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "See " }, { "__type": "InlineRole", "__tag": 4003, "value": "dev-arrayapi", "domain": null, "role": "ref", "inventory": null }, { "__type": "Text", "__tag": 4046, "value": " for more information." } ] } ] } ], "title": [], "level": 0, "target": null }, "Warns": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Raises": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Yields": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Methods": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Returns": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Parameters", "__tag": 4026, "children": [ { "__type": "DocParam", "__tag": 4016, "name": "statistic", "annotation": "array", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The values of the selected statistic in each bin." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "bin_edges", "annotation": "array of dtype float", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Return the bin edges " }, { "__type": "InlineCode", "__tag": 4051, "value": "(length(statistic)+1)" }, { "__type": "Text", "__tag": 4046, "value": "." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "", "annotation": "binnumber: 1-D ndarray of ints", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Indices of the bins (corresponding to " }, { "__type": "CrossRef", "__tag": 4002, "value": "bin_edges", "reference": { "__type": "RefInfo", "__tag": 4000, "module": null, "version": null, "kind": "local", "path": "bin_edges" }, "kind": "local" }, { "__type": "Text", "__tag": 4046, "value": ") in which each value of " }, { "__type": "ParamRef", "__tag": 4071, "name": "x" }, { "__type": "Text", "__tag": 4046, "value": " belongs. Same length as " }, { "__type": "ParamRef", "__tag": 4071, "name": "values" }, { "__type": "Text", "__tag": 4046, "value": ". A binnumber of " }, { "__type": "InlineRole", "__tag": 4003, "value": "i", "domain": null, "role": null, "inventory": null }, { "__type": "Text", "__tag": 4046, "value": " means the corresponding value is between (bin_edges[i-1], bin_edges[i])." } ] } ] } ] } ], "title": [], "level": 0, "target": null }, "Summary": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Compute a binned statistic for one or more sets of data." } ] } ], "title": [], "level": 0, "target": null }, "Receives": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Warnings": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Attributes": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Parameters": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Parameters", "__tag": 4026, "children": [ { "__type": "DocParam", "__tag": 4016, "name": "x", "annotation": "(N,) array_like", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "A sequence of values to be binned." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "values", "annotation": "(N,) array_like or list of (N,) array_like", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The data on which the statistic will be computed. This must be the same shape as " }, { "__type": "ParamRef", "__tag": 4071, "name": "x" }, { "__type": "Text", "__tag": 4046, "value": ", or a set of sequences - each the same shape as " }, { "__type": "ParamRef", "__tag": 4071, "name": "x" }, { "__type": "Text", "__tag": 4046, "value": ". If " }, { "__type": "ParamRef", "__tag": 4071, "name": "values" }, { "__type": "Text", "__tag": 4046, "value": " is a set of sequences, the statistic will be computed on each independently." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "statistic", "annotation": "string or callable, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The statistic to compute (default is 'mean'). The following statistics are available:" } ] }, { "__type": "Blockquote", "__tag": 4059, "children": [ { "__type": "BulletList", "__tag": 4053, "ordered": false, "start": 1, "children": [ { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'mean'compute the mean of values for points within each bin. Empty bins will be represented by NaN." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'std'compute the standard deviation within each bin. This is implicitly calculated with ddof=0." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'median'compute the median of values for points within each bin. Empty bins will be represented by NaN." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'count'compute the count of points within each bin. This is identical to an unweighted histogram. " }, { "__type": "ParamRef", "__tag": 4071, "name": "values" }, { "__type": "Text", "__tag": 4046, "value": " array is not referenced." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'sum'compute the sum of values for points within each bin. This is identical to a weighted histogram." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'min'compute the minimum of values for points within each bin. Empty bins will be represented by NaN." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "'max'compute the maximum of values for point within each bin. Empty bins will be represented by NaN." } ] } ] }, { "__type": "ListItem", "__tag": 4054, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "functiona user-defined function which takes a 1D array of values, and outputs a single numerical statistic. This function will be called on the values in each bin. Empty bins will be represented by function([]), or NaN if this returns an error." } ] } ] } ] } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "bins", "annotation": "int or sequence of scalars, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "If " }, { "__type": "ParamRef", "__tag": 4071, "name": "bins" }, { "__type": "Text", "__tag": 4046, "value": " is an int, it defines the number of equal-width bins in the given range (10 by default). If " }, { "__type": "ParamRef", "__tag": 4071, "name": "bins" }, { "__type": "Text", "__tag": 4046, "value": " is a sequence, it defines the bin edges, including the rightmost edge, allowing for non-uniform bin widths. Values in " }, { "__type": "ParamRef", "__tag": 4071, "name": "x" }, { "__type": "Text", "__tag": 4046, "value": " that are smaller than lowest bin edge are assigned to bin number 0, values beyond the highest bin are assigned to " }, { "__type": "InlineCode", "__tag": 4051, "value": "bins[-1]" }, { "__type": "Text", "__tag": 4046, "value": ". If the bin edges are specified, the number of bins will be, (nx = len(bins)-1)." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "range", "annotation": "(float, float) or [(float, float)], optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The lower and upper range of the bins. If not provided, range is simply " }, { "__type": "InlineCode", "__tag": 4051, "value": "(x.min(), x.max())" }, { "__type": "Text", "__tag": 4046, "value": ". Values outside the range are ignored." } ] } ] } ] } ], "title": [], "level": 0, "target": null }, "Extended Summary": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "This is a generalization of a histogram function. A histogram divides the space into bins, and returns the count of the number of points in each bin. This function allows the computation of the sum, mean, median, or other statistic of the values (or set of values) within each bin." } ] } ], "title": [], "level": 0, "target": null }, "Other Parameters": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null } }, "_ordered_sections": [ "Summary", "Extended Summary", "Parameters", "Attributes", "Methods", "Returns", "Yields", "Receives", "Other Parameters", "Raises", "Warns", "Warnings", "Notes" ], "item_file": "/scipy/stats/_binned_statistic.py", "item_line": 18, "item_type": "function", "aliases": [ "scipy.stats.binned_statistic" ], "example_section_data": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Code", "__tag": 4050, "value": "import numpy as np\nfrom scipy import stats\nimport matplotlib.pyplot as plt\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\nFirst some basic examples:\n\nCreate two evenly spaced bins in the range of the given sample, and sum the\ncorresponding values in each of those bins:\n\n" }, { "__type": "Code", "__tag": 4050, "value": "values = [1.0, 1.0, 2.0, 1.5, 3.0]\n", "execution_status": "success" }, { "__type": "Code", "__tag": 4050, "value": "stats.binned_statistic([1, 1, 2, 5, 7], values, 'sum', bins=2)\n", "execution_status": "failure" }, { "__type": "Text", "__tag": 4046, "value": "\nMultiple arrays of values can also be passed. The statistic is calculated\non each set independently:\n\n" }, { "__type": "Code", "__tag": 4050, "value": "values = [[1.0, 1.0, 2.0, 1.5, 3.0], [2.0, 2.0, 4.0, 3.0, 6.0]]\n", "execution_status": "success" }, { "__type": "Code", "__tag": 4050, "value": "stats.binned_statistic([1, 1, 2, 5, 7], values, 'sum', bins=2)\n", "execution_status": "failure" }, { "__type": "Text", "__tag": 4046, "value": "\n" }, { "__type": "Code", "__tag": 4050, "value": "stats.binned_statistic([1, 2, 1, 2, 4], np.arange(5), statistic='mean',\n bins=3)\n", "execution_status": "failure" }, { "__type": "Text", "__tag": 4046, "value": "\nAs a second example, we now generate some random data of sailing boat speed\nas a function of wind speed, and then determine how fast our boat is for\ncertain wind speeds:\n\n" }, { "__type": "Code", "__tag": 4050, "value": "rng = np.random.default_rng()\nwindspeed = 8 * rng.random(500)\nboatspeed = .3 * windspeed**.5 + .2 * rng.random(500)\nbin_means, bin_edges, binnumber = stats.binned_statistic(windspeed,\n boatspeed, statistic='median', bins=[1,2,3,4,5,6,7])\n", "execution_status": "success" }, { "__type": "Code", "__tag": 4050, "value": "plt.figure()\nplt.plot(windspeed, boatspeed, 'b.', label='raw data')\nplt.hlines(bin_means, bin_edges[:-1], bin_edges[1:], colors='g', lw=5,\n label='binned statistic of data')\nplt.legend()\n", "execution_status": "failure" }, { "__type": "Text", "__tag": 4046, "value": "\nNow we can use ``binnumber`` to select all datapoints with a windspeed\nbelow 1:\n\n" }, { "__type": "Code", "__tag": 4050, "value": "low_boatspeed = boatspeed[binnumber == 0]\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\nAs a final example, we will use ``bin_edges`` and ``binnumber`` to make a\nplot of a distribution that shows the mean and distribution around that\nmean per bin, on top of a regular histogram and the probability\ndistribution function:\n\n" }, { "__type": "Code", "__tag": 4050, "value": "x = np.linspace(0, 5, num=500)\nx_pdf = stats.maxwell.pdf(x)\nsamples = stats.maxwell.rvs(size=10000)\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\n" }, { "__type": "Code", "__tag": 4050, "value": "bin_means, bin_edges, binnumber = stats.binned_statistic(x, x_pdf,\n statistic='mean', bins=25)\nbin_width = (bin_edges[1] - bin_edges[0])\nbin_centers = bin_edges[1:] - bin_width/2\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\n" }, { "__type": "Code", "__tag": 4050, "value": "plt.figure()\nplt.hist(samples, bins=50, density=True, histtype='stepfilled',\n alpha=0.2, label='histogram of data')\nplt.plot(x, x_pdf, 'r-', label='analytical pdf')\nplt.hlines(bin_means, bin_edges[:-1], bin_edges[1:], colors='g', lw=2,\n label='binned statistic of data')\nplt.plot((binnumber - 0.5) * bin_width, x_pdf, 'g.', alpha=0.5)\nplt.legend(fontsize=10)\n", "execution_status": "failure" }, { "__type": "Code", "__tag": 4050, "value": "plt.show()\n", "execution_status": "success" }, { "__type": "Figure", "__tag": 4024, "value": { "__type": "RefInfo", "__tag": 4000, "module": "scipy", "version": "1.17.1", "kind": "assets", "path": "fig-53ea8ff3da2b2c22.png" } }, { "__type": "Figure", "__tag": 4024, "value": { "__type": "RefInfo", "__tag": 4000, "module": "scipy", "version": "1.17.1", "kind": "assets", "path": "fig-4c2d23cd7719f8ac.png" } } ], "title": [], "level": 0, "target": null }, "see_also": [ { "__type": "SeeAlsoItem", "__tag": 4028, "name": { "__type": "CrossRef", "__tag": 4002, "value": "binned_statistic_2d", "reference": { "__type": "LocalRef", "__tag": 4022, "kind": "module", "path": "scipy.stats._binned_statistic:binned_statistic_2d" }, "kind": "module" }, "descriptions": [], "type": "func" }, { "__type": "SeeAlsoItem", "__tag": 4028, "name": { "__type": "CrossRef", "__tag": 4002, "value": "binned_statistic_dd", "reference": { "__type": "LocalRef", "__tag": 4022, "kind": "module", "path": "scipy.stats._binned_statistic:binned_statistic_dd" }, "kind": "module" }, "descriptions": [], "type": "func" }, { "__type": "SeeAlsoItem", "__tag": 4028, "name": { "__type": "CrossRef", "__tag": 4002, "value": "numpy.digitize", "reference": { "__type": "RefInfo", "__tag": 4000, "module": "current-module", "version": "current-version", "kind": "to-resolve", "path": "numpy.digitize" }, "kind": "module" }, "descriptions": [], "type": "func" }, { "__type": "SeeAlsoItem", "__tag": 4028, "name": { "__type": "CrossRef", "__tag": 4002, "value": "numpy.histogram", "reference": { "__type": "RefInfo", "__tag": 4000, "module": "current-module", "version": "current-version", "kind": "to-resolve", "path": "numpy.histogram" }, "kind": "module" }, "descriptions": [], "type": "func" } ], "signature": { "__type": "SignatureNode", "__tag": 4029, "kind": "function", "parameters": [ { "__type": "SigParam", "__tag": 4030, "name": "x", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": { "__type": "Empty", "__tag": 4031 } }, { "__type": "SigParam", "__tag": 4030, "name": "values", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": { "__type": "Empty", "__tag": 4031 } }, { "__type": "SigParam", "__tag": 4030, "name": "statistic", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "mean" }, { "__type": "SigParam", "__tag": 4030, "name": "bins", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "10" }, { "__type": "SigParam", "__tag": 4030, "name": "range", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "None" } ], "return_annotation": { "__type": "Empty", "__tag": 4031 }, "target_name": "binned_statistic" }, "references": null, "qa": "scipy.stats._binned_statistic:binned_statistic", "arbitrary": [], "local_refs": [ "bin_edges", "bins", "range", "statistic", "values", "x" ] }