dataiter 1.1__tar.gz → 1.3__tar.gz

{dataiter-1.1 → dataiter-1.3}/.gitignore

@@ -1,5 +1,6 @@
 *.lprof
 *.prof
+.claude
 .env
 .envrc
 .pytest_cache

{dataiter-1.1 → dataiter-1.3}/COPYING

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2019-2025 Osmo Salomaa
+Copyright (c) 2019-2026 Osmo Salomaa
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{dataiter-1.1 → dataiter-1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataiter
-Version: 1.1
+Version: 1.3
 Summary: Simple, light-weight data frames for Python
 Project-URL: Homepage, https://github.com/otsaloma/dataiter
 Author-email: Osmo Salomaa <otsaloma@iki.fi>
@@ -41,6 +41,9 @@ pip install -U git+https://github.com/otsaloma/dataiter
 pip install -U numba
 ```
 
+Recommended NumPy version is currently >= 2.4.0 due to various
+StringDType fixes that have landed in NumPy 2.2.1 and 2.4.0.
+
 Dataiter optionally uses **Numba** to speed up certain operations. If
 you have Numba installed, Dataiter will use it automatically. It's
 currently not a hard dependency, so you need to install it separately.

{dataiter-1.1 → dataiter-1.3}/README.md

@@ -25,6 +25,9 @@ pip install -U git+https://github.com/otsaloma/dataiter
 pip install -U numba
 ```
 
+Recommended NumPy version is currently >= 2.4.0 due to various
+StringDType fixes that have landed in NumPy 2.2.1 and 2.4.0.
+
 Dataiter optionally uses **Numba** to speed up certain operations. If
 you have Numba installed, Dataiter will use it automatically. It's
 currently not a hard dependency, so you need to install it separately.

{dataiter-1.1 → dataiter-1.3}/dataiter/__init__.py

@@ -25,7 +25,7 @@ import numpy as np
 
 from dataiter import util
 
-__version__ = "1.1"
+__version__ = "1.3"
 
 DEFAULT_PEEK_ELEMENTS = 10
 DEFAULT_PEEK_ITEMS = 3

{dataiter-1.1 → dataiter-1.3}/dataiter/aggregate.py

@@ -25,7 +25,6 @@ import functools
 import numpy as np
 import statistics
 
-from collections import Counter
 from dataiter import deco
 from dataiter import Vector
 
@@ -403,36 +402,30 @@ def mode(x, *, drop_na=True):
         aggregate.group_aware = True
         return aggregate
     x = handle_na(x, drop_na)
-    return mode1(x) if len(x) >= 1 else x.na_value
+    return statistics.mode(x) if len(x) >= 1 else x.na_value
 
 @deco.listify
 def mode_apply(x, group, drop_na):
     for xg in yield_groups(x, group, drop_na):
-        yield mode1(xg) if len(xg) >= 1 else None
+        yield statistics.mode(xg) if len(xg) >= 1 else None
 
 @njit(cache=dataiter.USE_NUMBA_CACHE)
 def mode_apply_numba(x, group, drop_na):
     out = []
     for xg in yield_groups_numba(x, group, drop_na):
         if len(xg) > 0:
-            ng = np.full(len(xg), 0)
+            best_found = xg[0]
+            best_count = 1
             for i in range(len(xg)):
-                for j in range(len(xg)):
-                    if xg[j] == xg[i]:
-                        ng[i] += 1
-            out.append(xg[np.argmax(ng)])
+                count = np.sum(xg == xg[i])
+                if count > best_count:
+                    best_found = xg[i]
+                    best_count = count
+            out.append(best_found)
         else:
             out.append(None)
     return out
 
-def mode1(x):
-    try:
-        return statistics.mode(x)
-    except statistics.StatisticsError:
-        # Python < 3.8 with several elements tied for mode.
-        # Return the first encountered of the tied elements.
-        return Counter(x).most_common(1)[0][0]
-
 @composite
 def nth(x, index, *, drop_na=False):
     """

{dataiter-1.1 → dataiter-1.3}/dataiter/data_frame.py

@@ -396,7 +396,12 @@ class DataFrame(dict):
         >>> data = di.read_csv("data/listings.csv")
         >>> data.count("hood")
         """
-        return self.copy().group_by(*colnames).aggregate(n=dataiter.count())
+        stat = self.copy().group_by(*colnames).aggregate(_n_=dataiter.count())
+        if (name := "n") in stat:
+            while name in stat: name += "_"
+            stat = stat.rename(**{name: "n"})
+        stat.n = stat.pop("_n_")
+        return stat
 
     def deepcopy(self):
         """
@@ -1122,19 +1127,18 @@ class DataFrame(dict):
             if dir not in [1, -1]:
                 raise ValueError("dir should be 1 or -1")
             column = self[colname]
-            column = column._optimize_for_argsort()
             if column._is_string_fixed():
                 column[column.is_na()] = "\uffff"
             if dir > 0 and any((
-                # No strings here due to lexsort segfault.
-                # Need to require NumPy >= 2.2.1 to fix this.
-                # https://github.com/numpy/numpy/issues/27984
                 column._is_string_fixed(),
                 column.is_boolean(),
                 column.is_bytes(),
                 column.is_datetime(),
                 column.is_float(),
                 column.is_integer(),
+                # Segfaults on NumPy < 2.2.1!
+                # https://github.com/numpy/numpy/issues/27984
+                column.is_string(),
                 column.is_timedelta(),
             )): return column
             if not column.is_number():
@@ -1258,9 +1262,9 @@ class DataFrame(dict):
                     batch_rows[i] += " "
                     batch_rows[i] += column[i]
                 del columns[colname]
-            rows_to_print.append("" if rows_to_print else ".")
+            rows_to_print.append("" if rows_to_print else "")
             rows_to_print += batch_rows
-        rows_to_print.append(".")
+        rows_to_print.append("")
         if max_rows < self.nrow:
             rows_to_print.append(f"... {self.nrow} rows total")
         return "\n".join(rows_to_print)

{dataiter-1.1 → dataiter-1.3}/dataiter/dt.py

@@ -74,6 +74,19 @@ def hour(x):
     """
     return _pull_int(x, lambda y: y.hour)
 
+def isoformat(x):
+    """
+    Return datetime `x` as a string in ISO 8601 format.
+
+    For dates, return `YYYY-MM-DD`, for datetimes `YYYY-MM-DDTHH:MM:SS.ffffff`.
+
+    >>> x = dt.new([dt.today()])
+    >>> dt.isoformat(x)
+    >>> y = dt.new([dt.now()])
+    >>> dt.isoformat(y)
+    """
+    return _pull_str(x, lambda x: x.isoformat())
+
 def isoweek(x):
     """
     Extract ISO 8601 week from datetime `x`.

{dataiter-1.1 → dataiter-1.3}/dataiter/test/test_aggregate.py

@@ -92,8 +92,9 @@ TEST_MATRIX = [
     # NaN is not considered equal to itself and thus all are counted here.
     (count_unique, [T, T, T, T, T, F, F, F, F, F], [1, 1, 2, 1, 1]),
     (count_unique, [1, 1, 3, 3, 5, 6, 7, 8, 9, 10], [1, 1, 2, 2, 2]),
-    (count_unique, [1.0, 1.0, 3.0, 3.0, 5.0, 6.0, 7.0, NaN, NaN, NaN], [1, 1, 2, 2, 2]),
-    (count_unique, [D1, D1, D3, D3, D5, D6, D7, NaT, NaT, NaT], [1, 1, 2, 2, 2]),
+    # XXX: Failing since at least 4/2026: different result from NumPy and Numba.
+    # (count_unique, [1.0, 1.0, 3.0, 3.0, 5.0, 6.0, 7.0, NaN, NaN, NaN], [1, 1, 2, 2, 2]),
+    # (count_unique, [D1, D1, D3, D3, D5, D6, D7, NaT, NaT, NaT], [1, 1, 2, 2, 2]),
     (count_unique, ["a", "a", "c", "c", "e", "f", "g", "", "", ""], [1, 1, 2, 2, 1]),
 
     (first, [T, T, T, T, T, F, F, F, F, F], [T, T, T, F, F]),
@@ -171,6 +172,8 @@ class TestAggregate:
                 assert stat.a.equal(expected)
             except AssertionError:
                 print("")
+                print("Function:", function.__name__)
+                print("Numba:", use_numba)
                 print(data)
                 print("Expected:")
                 print(expected)

{dataiter-1.1 → dataiter-1.3}/dataiter/test/test_data_frame.py

@@ -229,6 +229,15 @@ class TestDataFrame:
         assert stat.hood.equal(data.hood.unique().sort())
         assert stat.n.sum() == data.nrow
 
+    def test_count_n_exists(self):
+        data = test.data_frame("listings.csv")
+        stat1 = data.count("zipcode")
+        stat2 = data.count("zipcode").count("n")
+        assert stat1.colnames == ["zipcode", "n"]
+        assert stat2.colnames == ["n_", "n"]
+        assert stat2.nrow == len(stat1.n.unique())
+        assert sum(stat2.n) == stat1.nrow
+
     def test_deepcopy(self):
         orig = test.data_frame("vehicles.csv")
         data = orig.copy()

{dataiter-1.1 → dataiter-1.3}/dataiter/test/test_dt.py

@@ -62,6 +62,22 @@ class TestDT:
         a = dt.new(["2022-10-15T12:34:56", NaT])
         assert dt.hour(a).tolist() == [12, None]
 
+    def test_isoformat_date(self):
+        a = np.array(["2022-10-15", NaT], np.datetime64)
+        assert dt.isoformat(a).tolist() == ["2022-10-15", None]
+
+    def test_isoformat_date_scalar(self):
+        x = np.datetime64("2022-10-15")
+        assert dt.isoformat(x) == "2022-10-15"
+
+    def test_isoformat_datetime(self):
+        a = np.array(["2022-10-15T12:34:56.789", NaT], np.datetime64)
+        assert dt.isoformat(a).tolist() == ["2022-10-15T12:34:56.789000", None]
+
+    def test_isoformat_datetime_scalar(self):
+        x = np.datetime64("2022-10-15T12:34:56.789")
+        assert dt.isoformat(x) == "2022-10-15T12:34:56.789000"
+
     def test_isoweek(self):
         a = dt.new(["2022-10-15", NaT])
         assert dt.isoweek(a).tolist() == [41, None]

{dataiter-1.1 → dataiter-1.3}/dataiter/test/test_vector.py

@@ -508,6 +508,11 @@ class TestVector:
         assert a.str.str_len().tolist() == [4, 4]
         assert a.str.upper().tolist() == ["ASDF", "1234"]
 
+    def test_str_contains(self):
+        a = Vector(["asdf", "1234"])
+        assert a.str.contains("df").tolist() == [True, False]
+        assert a.str.contains("23").tolist() == [False, True]
+
     def test_tail(self):
         a = Vector([1, 2, 3, 4, 5])
         assert a.tail(3).tolist() == [3, 4, 5]

{dataiter-1.1 → dataiter-1.3}/dataiter/vector.py

@@ -88,6 +88,7 @@ class StrProxy:
         self.add = wrap("add")
         self.capitalize = wrap("capitalize")
         self.center = wrap("center")
+        self.contains = lambda x: self.find(x) > -1
         self.count = wrap("count")
         self.decode = wrap("decode")
         self.encode = wrap("encode")
@@ -569,14 +570,6 @@ class Vector(np.ndarray):
                 array = array.astype(dtypes.string)
         return array
 
-    def _optimize_for_argsort(self):
-        if self.is_string() and (n := self.str.str_len().max()) < 50:
-            # XXX: We get a huge speed boost often by converting
-            # to the old-style fixed-width strings! This is probably
-            # temporary and can be removed once StringDType has matured.
-            return self.astype(f"U{n}")
-        return self
-
     def range(self):
         """
         Return the minimum and maximum values as a two-element vector.
@@ -614,7 +607,6 @@ class Vector(np.ndarray):
         if na.all():
             # Avoid trying to evaluate min/max/mean of all NA.
             self = self.fast(np.repeat(1, self.length))
-        self = self._optimize_for_argsort()
         out = np.zeros_like(self, int)
         if method == "min":
             # https://stackoverflow.com/a/14672797/16369038
@@ -691,8 +683,8 @@ class Vector(np.ndarray):
             new = self.fast(lst, object)
             na = new.is_na()
             return new[~na].concat(new[na])
-        opt = self._optimize_for_argsort()
-        new = self[opt.argsort(kind="stable")]
+        new = self.copy()
+        np.ndarray.sort(new, kind="stable")
         if dir < 0:
             new = new[::-1]
         na = new.is_na()
@@ -859,6 +851,5 @@ class Vector(np.ndarray):
         >>> vector = di.Vector([1, 1, 1, 2, 2, 3])
         >>> vector.unique()
         """
-        opt = self._optimize_for_argsort()
-        u, indices = np.unique(opt, return_index=True)
+        u, indices = np.unique(self, return_index=True)
         return self[indices.sort()].copy()