ENH: add get_value, set_value to Panel per #437, more perf tweaks

pandas/core/panel.py

@@ -447,6 +447,40 @@ def _get_values(self):
 
     values = property(fget=_get_values)
 
+    #----------------------------------------------------------------------
+    # Getting and setting elements
+
+    def get_value(self, item, major, minor):
+        """
+        Quickly retrieve single value at (item, major, minor) location
+
+        Parameters
+        ----------
+        item : item label (panel item)
+        major : major axis label (panel item row)
+        minor : minor axis label (panel item column)
+
+        Returns
+        -------
+        element : scalar value
+        """
+        # hm, two layers to the onion
+        frame = self._get_item_cache(item)
+        return frame.get_value(major, minor)
+
+    def set_value(self, item, major, minor, value):
+        """
+        Quickly set single value at (item, major, minor) location
+
+        Parameters
+        ----------
+        index : row label
+        col : column label
+        value : scalar value
+        """
+        frame = self._get_item_cache(item)
+        return frame.set_value(major, minor, value)
+
     def _box_item_values(self, key, values):
         return DataFrame(values, index=self.major_axis, columns=self.minor_axis)
 

pandas/core/series.py

@@ -24,6 +24,7 @@
 import pandas.core.datetools as datetools
 import pandas.core.nanops as nanops
 import pandas._tseries as lib
+import pandas._engines as _gin
 
 __all__ = ['Series', 'TimeSeries']
 
@@ -253,12 +254,11 @@ def __getitem__(self, key):
                 return self._multilevel_index(key)
             else:
                 hash(key)
-                values = self.values
                 try:
-                    return values[self.index.get_loc(key)]
+                    return self.get_value(key)
                 except KeyError, e1:
                     try:
-                        return values[key]
+                        return _gin.get_value_at(self, key)
                     except Exception, _:
                         pass
                     raise e1
@@ -305,12 +305,25 @@ def get(self, label, default=None):
         y : scalar
         """
         try:
-            return self.index._engine.get_value(self, label)
+            return self.get_value(label)
         except KeyError:
             return default
-    get_value = get
 
-    def put_value(self, label, value):
+    def get_value(self, label):
+        """
+        Quickly retrieve single value at passed index label
+
+        Parameters
+        ----------
+        index : label
+
+        Returns
+        -------
+        value : scalar value
+        """
+        return self.index._engine.get_value(self, label)
+
+    def set_value(self, label, value):
         """
         Quickly set single value at passed label
 
@@ -323,7 +336,7 @@ def put_value(self, label, value):
         -------
         element : scalar value
         """
-        self.index._engine.put_value(self, label, value)
+        self.index._engine.set_value(self, label, value)
 
     def _multilevel_index(self, key):
         values = self.values

pandas/src/engines.pyx

@@ -1,8 +1,9 @@
 from numpy cimport ndarray
 cimport numpy as cnp
 
-cdef extern from "numpy_helper.h":
-    inline int is_integer_object(object)
+cnp.import_array()
+
+cimport util
 
 cdef class IndexEngine:
 
@@ -15,9 +16,7 @@ cdef class IndexEngine:
             void* data_ptr
 
         loc = self.get_loc(key)
-        assert(is_integer_object(loc))
-        data_ptr = cnp.PyArray_GETPTR1(arr, loc)
-        return cnp.PyArray_GETITEM(arr, data_ptr)
+        return get_value_at(arr, loc)
 
     cpdef set_value(self, ndarray arr, object key, object value):
         '''
@@ -28,21 +27,34 @@ cdef class IndexEngine:
             void* data_ptr
 
         loc = self.get_loc(key)
-        assert(is_integer_object(loc))
-        data_ptr = cnp.PyArray_GETPTR1(arr, loc)
-        cnp.PyArray_SETITEM(arr, data_ptr, value)
+        set_value_at(arr, loc, value)
 
-cpdef get_value_at(ndarray arr, object loc):
-    assert(is_integer_object(loc))
-    data_ptr = cnp.PyArray_GETPTR1(arr, loc)
+cpdef inline object get_value_at(ndarray arr, object loc):
+    cdef:
+        Py_ssize_t i
+    if util.is_float_object(loc):
+        casted = int(loc)
+        if casted == loc:
+            loc = casted
+    i = <Py_ssize_t> loc
+    if i < 0:
+        i += cnp.PyArray_SIZE(arr)
+    data_ptr = cnp.PyArray_GETPTR1(arr, i)
     return cnp.PyArray_GETITEM(arr, data_ptr)
 
-cpdef set_value_at(ndarray arr, object loc, object value):
-    assert(is_integer_object(loc))
+cpdef inline set_value_at(ndarray arr, object loc, object value):
+    cdef:
+        Py_ssize_t i
+    if util.is_float_object(loc):
+        casted = int(loc)
+        if casted == loc:
+            loc = casted
+    i = <Py_ssize_t> loc
+    if i < 0:
+        i += cnp.PyArray_SIZE(arr)
     data_ptr = cnp.PyArray_GETPTR1(arr, loc)
     cnp.PyArray_SETITEM(arr, data_ptr, value)
 
-
 cdef class DictIndexEngine(IndexEngine):
     '''
     For accelerating low-level internal details of indexing

pandas/src/numpy_helper.h

@@ -4,3 +4,9 @@ inline int
 is_integer_object(PyObject* obj) {
   return PyArray_IsIntegerScalar(obj);
 }
+
+inline int
+is_float_object(PyObject* obj) {
+  return (PyFloat_Check(obj)
+          || PyObject_TypeCheck(obj, &PyFloatingArrType_Type));
+}

pandas/src/tseries.pyx

@@ -49,8 +49,7 @@ cdef double_t *get_double_ptr(ndarray arr):
 
     return <double_t *> arr.data
 
-cdef extern from "numpy_helper.h":
-    inline int is_integer_object(object)
+from util cimport is_integer_object
 
 cdef extern from "math.h":
     double sqrt(double x)
@@ -479,3 +478,4 @@ include "reindex.pyx"
 include "generated.pyx"
 include "parsing.pyx"
 include "reduce.pyx"
+

pandas/tests/test_frame.py

@@ -666,16 +666,20 @@ def test_get_value(self):
             for col in self.frame.columns:
                 result = self.frame.get_value(idx, col)
                 expected = self.frame[col][idx]
-                self.assertEqual(result, expected)
-
-        # partial w/ MultiIndex raise exception
-        index = MultiIndex.from_tuples([(0, 1), (0, 2), (1, 1), (1, 2)])
+                assert_almost_equal(result, expected)
 
     def test_set_value(self):
         for idx in self.frame.index:
             for col in self.frame.columns:
                 self.frame.set_value(idx, col, 1)
-                self.assertEqual(self.frame[col][idx], 1)
+                assert_almost_equal(self.frame[col][idx], 1)
+
+    def test_get_set_value_no_partial_indexing(self):
+        # partial w/ MultiIndex raise exception
+        index = MultiIndex.from_tuples([(0, 1), (0, 2), (1, 1), (1, 2)])
+        df = DataFrame(index=index, columns=range(4))
+        self.assertRaises(KeyError, df.get_value, 0, 1)
+        self.assertRaises(KeyError, df.set_value, 0, 1, 0)
 
     def test_single_element_ix_dont_upcast(self):
         self.frame['E'] = 1

pandas/tests/test_panel.py

@@ -528,6 +528,21 @@ def _check_view(self, indexer, comp):
         self.assert_((obj.values == 0).all())
         comp(cp.ix[indexer].reindex_like(obj), obj)
 
+    def test_get_value(self):
+        for item in self.panel.items:
+            for mjr in self.panel.major_axis[::2]:
+                for mnr in self.panel.minor_axis:
+                    result = self.panel.get_value(item, mjr, mnr)
+                    expected = self.panel[item][mnr][mjr]
+                    assert_almost_equal(result, expected)
+
+    def test_set_value(self):
+        for item in self.panel.items:
+            for mjr in self.panel.major_axis[::2]:
+                for mnr in self.panel.minor_axis:
+                    self.panel.set_value(item, mjr, mnr, 1.)
+                    assert_almost_equal(self.panel[item][mnr][mjr], 1.)
+
 class TestPanel(unittest.TestCase, PanelTests, CheckIndexing,
                 SafeForLongAndSparse,
                 SafeForSparse):

setup.py

@@ -289,7 +289,7 @@ def srcpath(name=None, suffix='.pyx', subdir='src'):
     tseries_depends = None
 
 tseries_ext = Extension('pandas._tseries',
-                        depends=tseries_depends,
+                        depends=tseries_depends + ['pandas/src/numpy_helper.h'],
                         sources=[srcpath('tseries', suffix=suffix)],
                         include_dirs=[np.get_include()])
 
@@ -298,8 +298,9 @@ def srcpath(name=None, suffix='.pyx', subdir='src'):
                        include_dirs=[np.get_include()])
 
 engines_ext = Extension('pandas._engines',
-                       sources=[srcpath('engines', suffix=suffix)],
-                       include_dirs=[np.get_include()])
+                        depends=['pandas/src/numpy_helper.h'],
+                        sources=[srcpath('engines', suffix=suffix)],
+                        include_dirs=[np.get_include()])
 
 sandbox_ext = Extension('pandas._sandbox',
                         sources=[srcpath('sandbox', suffix=suffix)],