diff options
| -rw-r--r-- | Doc/library/statistics.rst | 7 | ||||
| -rw-r--r-- | Lib/statistics.py | 4 | ||||
| -rw-r--r-- | Lib/test/test_statistics.py | 7 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2023-09-30-12-50-47.gh-issue-110150.9j0Ij5.rst | 2 |
4 files changed, 17 insertions, 3 deletions
diff --git a/Doc/library/statistics.rst b/Doc/library/statistics.rst index f3c1bf2..5c8ad3a 100644 --- a/Doc/library/statistics.rst +++ b/Doc/library/statistics.rst @@ -585,7 +585,7 @@ However, for reading convenience, most of the examples show sorted sequences. The *data* can be any iterable containing sample data. For meaningful results, the number of data points in *data* should be larger than *n*. - Raises :exc:`StatisticsError` if there are not at least two data points. + Raises :exc:`StatisticsError` if there is not at least one data point. The cut points are linearly interpolated from the two nearest data points. For example, if a cut point falls one-third @@ -625,6 +625,11 @@ However, for reading convenience, most of the examples show sorted sequences. .. versionadded:: 3.8 + .. versionchanged:: 3.13 + No longer raises an exception for an input with only a single data point. + This allows quantile estimates to be built up one sample point + at a time becoming gradually more refined with each new data point. + .. function:: covariance(x, y, /) Return the sample covariance of two inputs *x* and *y*. Covariance diff --git a/Lib/statistics.py b/Lib/statistics.py index 96c8034..4da0688 100644 --- a/Lib/statistics.py +++ b/Lib/statistics.py @@ -844,7 +844,9 @@ def quantiles(data, *, n=4, method='exclusive'): data = sorted(data) ld = len(data) if ld < 2: - raise StatisticsError('must have at least two data points') + if ld == 1: + return data * (n - 1) + raise StatisticsError('must have at least one data point') if method == 'inclusive': m = ld - 1 result = [] diff --git a/Lib/test/test_statistics.py b/Lib/test/test_statistics.py index f9b0ac2..b24fc3c 100644 --- a/Lib/test/test_statistics.py +++ b/Lib/test/test_statistics.py @@ -2454,6 +2454,11 @@ class TestQuantiles(unittest.TestCase): data = random.choices(range(100), k=k) q1, q2, q3 = quantiles(data, method='inclusive') self.assertEqual(q2, statistics.median(data)) + # Base case with a single data point: When estimating quantiles from + # a sample, we want to be able to add one sample point at a time, + # getting increasingly better estimates. + self.assertEqual(quantiles([10], n=4), [10.0, 10.0, 10.0]) + self.assertEqual(quantiles([10], n=4, method='exclusive'), [10.0, 10.0, 10.0]) def test_equal_inputs(self): quantiles = statistics.quantiles @@ -2504,7 +2509,7 @@ class TestQuantiles(unittest.TestCase): with self.assertRaises(ValueError): quantiles([10, 20, 30], method='X') # method is unknown with self.assertRaises(StatisticsError): - quantiles([10], n=4) # not enough data points + quantiles([], n=4) # not enough data points with self.assertRaises(TypeError): quantiles([10, None, 30], n=4) # data is non-numeric diff --git a/Misc/NEWS.d/next/Library/2023-09-30-12-50-47.gh-issue-110150.9j0Ij5.rst b/Misc/NEWS.d/next/Library/2023-09-30-12-50-47.gh-issue-110150.9j0Ij5.rst new file mode 100644 index 0000000..3c4dde5 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2023-09-30-12-50-47.gh-issue-110150.9j0Ij5.rst @@ -0,0 +1,2 @@ +Fix base case handling in statistics.quantiles. Now allows a single data +point. |