add tests for engines and add is_monotonic_uint(32|16)

Author: topper-123

asv_bench/benchmarks/indexing_engines.py

@@ -1,6 +1,6 @@
 import numpy as np
 
-from pandas._libs import index as li
+from pandas._libs import index as libindex
 
 
 def _get_numeric_engines():
@@ -11,8 +11,9 @@ def _get_numeric_engines():
         ('UInt16engine', np.uint16), ('UInt8Engine', np.uint8),
         ('Float64Engine', np.float64), ('Float32Engine', np.float32),
     ]
-    return [(getattr(li, engine_name), dtype)
-            for engine_name, dtype in engine_names if hasattr(li, engine_name)]
+    return [(getattr(libindex, engine_name), dtype)
+            for engine_name, dtype in engine_names
+            if hasattr(libindex, engine_name)]
 
 
 class NumericEngineIndexing(object):
@@ -58,7 +59,7 @@ def setup(self, index_type):
             'non_monotonic': np.array(list('abc') * N, dtype=object),
         }[index_type]
 
-        self.data = li.ObjectEngine(lambda: arr, len(arr))
+        self.data = libindex.ObjectEngine(lambda: arr, len(arr))
         # code belows avoids populating the mapping etc. while timing.
         self.data.get_loc('b')
 

pandas/_libs/algos.pyx

@@ -365,6 +365,8 @@ ctypedef fused algos_t:
     int16_t
     int8_t
     uint64_t
+    uint32_t
+    uint16_t
     uint8_t
 
 
@@ -872,6 +874,9 @@ is_monotonic_int32 = is_monotonic["int32_t"]
 is_monotonic_int16 = is_monotonic["int16_t"]
 is_monotonic_int8 = is_monotonic["int8_t"]
 is_monotonic_uint64 = is_monotonic["uint64_t"]
+is_monotonic_uint32 = is_monotonic["uint32_t"]
+is_monotonic_uint16 = is_monotonic["uint16_t"]
+is_monotonic_uint8 = is_monotonic["uint8_t"]
 is_monotonic_bool = is_monotonic["uint8_t"]
 
 

pandas/tests/indexing/conftest.py

@@ -0,0 +1,20 @@
+import numpy as np
+import pytest
+
+from pandas._libs import index as libindex
+
+
+@pytest.fixture(params=[
+    (libindex.Int64Engine, np.int64),
+    (libindex.Int32Engine, np.int32),
+    (libindex.Int16Engine, np.int16),
+    (libindex.Int8Engine, np.int8),
+    (libindex.UInt64Engine, np.uint64),
+    (libindex.UInt32Engine, np.uint32),
+    (libindex.UInt16Engine, np.uint16),
+    (libindex.UInt8Engine, np.uint8),
+    (libindex.Float64Engine, np.float64),
+    (libindex.Float32Engine, np.float32),
+], ids=lambda x: x[0].__name__)
+def numeric_indexing_engine_type_and_dtype(request):
+    return request.param

pandas/tests/indexing/test_indexing_engines.py

@@ -0,0 +1,120 @@
+import numpy as np
+
+from pandas._libs import index as libindex
+
+
+class TestNumericEngine(object):
+    def test_is_monotonic(self, numeric_indexing_engine_type_and_dtype):
+        engine_type, dtype = numeric_indexing_engine_type_and_dtype
+
+        num = 1000
+        arr = np.array([1] * num + [2] * num + [3] * num, dtype=dtype)
+
+        # monotonic increasing
+        engine = engine_type(lambda: arr, len(arr))
+        assert engine.is_monotonic_increasing
+        assert not engine.is_monotonic_decreasing
+
+        # monotonic decreasing
+        engine = engine_type(lambda: arr[::-1], len(arr))
+        assert not engine.is_monotonic_increasing
+        assert engine.is_monotonic_decreasing
+
+        # neither monotonic increasing or decreasing
+        arr = np.array([1] * num + [2] * num + [1] * num, dtype=dtype)
+        engine = engine_type(lambda: arr[::-1], len(arr))
+        assert not engine.is_monotonic_increasing
+        assert not engine.is_monotonic_decreasing
+
+    def test_is_unique(self, numeric_indexing_engine_type_and_dtype):
+        engine_type, dtype = numeric_indexing_engine_type_and_dtype
+
+        # unique
+        arr = np.array([1, 2, 4, 3], dtype=dtype)
+        engine = engine_type(lambda: arr, len(arr))
+        assert engine.is_unique
+
+        # not unique
+        arr = np.array([1, 2, 1], dtype=dtype)
+        engine = engine_type(lambda: arr, len(arr))
+        assert not engine.is_unique
+
+    def test_get_loc(self, numeric_indexing_engine_type_and_dtype):
+        engine_type, dtype = numeric_indexing_engine_type_and_dtype
+
+        # unique
+        arr = np.array([1, 2, 3], dtype=dtype)
+        engine = engine_type(lambda: arr, len(arr))
+        assert engine.get_loc(2) == 1
+
+        # monotonic
+        num = 1000
+        arr = np.array([1] * num + [2] * num + [3] * num, dtype=dtype)
+        engine = engine_type(lambda: arr, len(arr))
+        assert engine.get_loc(2) == slice(1000, 2000)
+
+        # not monotonic
+        arr = np.array([1, 2, 3] * num, dtype=dtype)
+        engine = engine_type(lambda: arr, len(arr))
+        expected = np.array([False, True, False] * num, dtype=bool)
+        result = engine.get_loc(2)
+        assert (result == expected).all()
+
+
+class TestObjectEngine(object):
+    engine_type = libindex.ObjectEngine
+    dtype = np.object_
+
+    def test_is_monotonic(self):
+
+        num = 1000
+        arr = np.array(['a'] * num + ['a'] * num + ['c'] * num,
+                       dtype=self.dtype)
+
+        # monotonic increasing
+        engine = self.engine_type(lambda: arr, len(arr))
+        assert engine.is_monotonic_increasing
+        assert not engine.is_monotonic_decreasing
+
+        # monotonic decreasing
+        engine = self.engine_type(lambda: arr[::-1], len(arr))
+        assert not engine.is_monotonic_increasing
+        assert engine.is_monotonic_decreasing
+
+        # neither monotonic increasing or decreasing
+        arr = np.array(['a'] * num + ['b'] * num + ['a'] * num,
+                       dtype=self.dtype)
+        engine = self.engine_type(lambda: arr[::-1], len(arr))
+        assert not engine.is_monotonic_increasing
+        assert not engine.is_monotonic_decreasing
+
+    def test_is_unique(self):
+        # unique
+        arr = np.array(['a', 'b', 'c', 'd'], dtype=self.dtype)
+        engine = self.engine_type(lambda: arr, len(arr))
+        assert engine.is_unique
+
+        # not unique
+        arr = np.array(['a', 'b', 'a'], dtype=self.dtype)
+        engine = self.engine_type(lambda: arr, len(arr))
+        assert not engine.is_unique
+
+    def test_get_loc(self):
+        # unique
+        arr = np.array(['a', 'b', 'c'], dtype=self.dtype)
+        engine = self.engine_type(lambda: arr, len(arr))
+        assert engine.get_loc('b') == 1
+
+        # monotonic
+        num = 1000
+        arr = np.array(['a'] * num + ['b'] * num + ['c'] * num,
+                       dtype=self.dtype)
+        engine = self.engine_type(lambda: arr, len(arr))
+        assert engine.get_loc('b') == slice(1000, 2000)
+
+        # not monotonic
+        arr = np.array(['a', 'b', 'c'] * num, dtype=self.dtype)
+        engine = self.engine_type(lambda: arr, len(arr))
+        expected = np.array([False, True, False] * num, dtype=bool)
+        result = engine.get_loc('b')
+        assert (result == expected).all()