diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py index 79b51ef57cd37..17bd60fb9d152 100644 --- a/pandas/core/groupby/ops.py +++ b/pandas/core/groupby/ops.py @@ -53,59 +53,6 @@ ) -def generate_bins_generic(values, binner, closed): - """ - Generate bin edge offsets and bin labels for one array using another array - which has bin edge values. Both arrays must be sorted. - - Parameters - ---------- - values : array of values - binner : a comparable array of values representing bins into which to bin - the first array. Note, 'values' end-points must fall within 'binner' - end-points. - closed : which end of bin is closed; left (default), right - - Returns - ------- - bins : array of offsets (into 'values' argument) of bins. - Zero and last edge are excluded in result, so for instance the first - bin is values[0:bin[0]] and the last is values[bin[-1]:] - """ - lenidx = len(values) - lenbin = len(binner) - - if lenidx <= 0 or lenbin <= 0: - raise ValueError("Invalid length for values or for binner") - - # check binner fits data - if values[0] < binner[0]: - raise ValueError("Values falls before first bin") - - if values[lenidx - 1] > binner[lenbin - 1]: - raise ValueError("Values falls after last bin") - - bins = np.empty(lenbin - 1, dtype=np.int64) - - j = 0 # index into values - bc = 0 # bin count - - # linear scan, presume nothing about values/binner except that it fits ok - for i in range(0, lenbin - 1): - r_bin = binner[i + 1] - - # count values in current bin, advance to next bin - while j < lenidx and ( - values[j] < r_bin or (closed == "right" and values[j] == r_bin) - ): - j += 1 - - bins[bc] = j - bc += 1 - - return bins - - class BaseGrouper: """ This is an internal Grouper class, which actually holds diff --git a/pandas/tests/groupby/test_bin_groupby.py b/pandas/tests/groupby/test_bin_groupby.py index 8da03a7f61029..0e7a66769d2d4 100644 --- a/pandas/tests/groupby/test_bin_groupby.py +++ b/pandas/tests/groupby/test_bin_groupby.py @@ -6,9 +6,7 @@ from pandas.core.dtypes.common import ensure_int64 from pandas import Index, Series, isna -from pandas.core.groupby.ops import generate_bins_generic import pandas.util.testing as tm -from pandas.util.testing import assert_almost_equal def test_series_grouper(): @@ -21,10 +19,10 @@ def test_series_grouper(): result, counts = grouper.get_result() expected = np.array([obj[3:6].mean(), obj[6:].mean()]) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) exp_counts = np.array([3, 4], dtype=np.int64) - assert_almost_equal(counts, exp_counts) + tm.assert_almost_equal(counts, exp_counts) def test_series_bin_grouper(): @@ -37,48 +35,37 @@ def test_series_bin_grouper(): result, counts = grouper.get_result() expected = np.array([obj[:3].mean(), obj[3:6].mean(), obj[6:].mean()]) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) exp_counts = np.array([3, 3, 4], dtype=np.int64) - assert_almost_equal(counts, exp_counts) - - -class TestBinGroupers: - def setup_method(self, method): - self.obj = np.random.randn(10, 1) - self.labels = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2, 2], dtype=np.int64) - self.bins = np.array([3, 6], dtype=np.int64) - - def test_generate_bins(self): - values = np.array([1, 2, 3, 4, 5, 6], dtype=np.int64) - binner = np.array([0, 3, 6, 9], dtype=np.int64) - - for func in [lib.generate_bins_dt64, generate_bins_generic]: - bins = func(values, binner, closed="left") - assert (bins == np.array([2, 5, 6])).all() - - bins = func(values, binner, closed="right") - assert (bins == np.array([3, 6, 6])).all() - - for func in [lib.generate_bins_dt64, generate_bins_generic]: - values = np.array([1, 2, 3, 4, 5, 6], dtype=np.int64) - binner = np.array([0, 3, 6], dtype=np.int64) - - bins = func(values, binner, closed="right") - assert (bins == np.array([3, 6])).all() - - msg = "Invalid length for values or for binner" - with pytest.raises(ValueError, match=msg): - generate_bins_generic(values, [], "right") - with pytest.raises(ValueError, match=msg): - generate_bins_generic(values[:0], binner, "right") - - msg = "Values falls before first bin" - with pytest.raises(ValueError, match=msg): - generate_bins_generic(values, [4], "right") - msg = "Values falls after last bin" - with pytest.raises(ValueError, match=msg): - generate_bins_generic(values, [-3, -1], "right") + tm.assert_almost_equal(counts, exp_counts) + + +@pytest.mark.parametrize( + "binner,closed,expected", + [ + ( + np.array([0, 3, 6, 9], dtype=np.int64), + "left", + np.array([2, 5, 6], dtype=np.int64), + ), + ( + np.array([0, 3, 6, 9], dtype=np.int64), + "right", + np.array([3, 6, 6], dtype=np.int64), + ), + (np.array([0, 3, 6], dtype=np.int64), "left", np.array([2, 5], dtype=np.int64)), + ( + np.array([0, 3, 6], dtype=np.int64), + "right", + np.array([3, 6], dtype=np.int64), + ), + ], +) +def test_generate_bins(binner, closed, expected): + values = np.array([1, 2, 3, 4, 5, 6], dtype=np.int64) + result = lib.generate_bins_dt64(values, binner, closed=closed) + tm.assert_numpy_array_equal(result, expected) def test_group_ohlc(): @@ -100,13 +87,13 @@ def _ohlc(group): expected = np.array([_ohlc(obj[:6]), _ohlc(obj[6:12]), _ohlc(obj[12:])]) - assert_almost_equal(out, expected) + tm.assert_almost_equal(out, expected) tm.assert_numpy_array_equal(counts, np.array([6, 6, 8], dtype=np.int64)) obj[:6] = np.nan func(out, counts, obj[:, None], labels) expected[0] = np.nan - assert_almost_equal(out, expected) + tm.assert_almost_equal(out, expected) _check("float32") _check("float64") @@ -121,29 +108,29 @@ def test_int_index(self): arr = np.random.randn(100, 4) result = libreduction.compute_reduction(arr, np.sum, labels=Index(np.arange(4))) expected = arr.sum(0) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) result = libreduction.compute_reduction( arr, np.sum, axis=1, labels=Index(np.arange(100)) ) expected = arr.sum(1) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) dummy = Series(0.0, index=np.arange(100)) result = libreduction.compute_reduction( arr, np.sum, dummy=dummy, labels=Index(np.arange(4)) ) expected = arr.sum(0) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) dummy = Series(0.0, index=np.arange(4)) result = libreduction.compute_reduction( arr, np.sum, axis=1, dummy=dummy, labels=Index(np.arange(100)) ) expected = arr.sum(1) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected) result = libreduction.compute_reduction( arr, np.sum, axis=1, dummy=dummy, labels=Index(np.arange(100)) ) - assert_almost_equal(result, expected) + tm.assert_almost_equal(result, expected)