ENH: missingdata: Change default to create NA-mask when NAs are in lists

Also adjust the repr to drop maskna=True when this rule will enable it
automatically.

4 files changed, 30 insertions, 12 deletions

diff --git a/numpy/core/numeric.py b/numpy/core/numeric.py
index f1e6b2da9..9b7c20d76 100644
--- a/numpy/core/numeric.py
+++ b/numpy/core/numeric.py
@@ -1336,9 +1336,12 @@ def array_repr(arr, max_line_width=None, precision=None, suppress_small=None):
     skipdtype = (arr.dtype.type in _typelessdata) and arr.size > 0
 
     if arr.flags.maskna:
-        lst += ", maskna=True"
-        # If everything is NA, can't skip the type
-        if skipdtype and all(isna(arr)):
+        whichna = isna(arr)
+        # If nothing is NA, explicitly signal the NA-mask
+        if not any(whichna):
+            lst += ", maskna=True"
+        # If everything is NA, can't skip the dtype
+        if skipdtype and all(whichna):
             skipdtype = False
 
     if skipdtype:
diff --git a/numpy/core/src/multiarray/common.c b/numpy/core/src/multiarray/common.c
index 98d86f38a..45c7558de 100644
--- a/numpy/core/src/multiarray/common.c
+++ b/numpy/core/src/multiarray/common.c
@@ -100,6 +100,10 @@ PyArray_DTypeFromObject(PyObject *obj, int maxdims, int *out_contains_na,
 
     /* Check if it's an ndarray */
     if (PyArray_Check(obj)) {
+        /* Check for any NAs in the array */
+        if (PyArray_ContainsNA((PyArrayObject *)obj)) {
+            *out_contains_na = 1;
+        }
         dtype = PyArray_DESCR((PyArrayObject *)obj);
         Py_INCREF(dtype);
         goto promote_types;
diff --git a/numpy/core/src/multiarray/ctors.c b/numpy/core/src/multiarray/ctors.c
index bcd33afd8..894e3fd22 100644
--- a/numpy/core/src/multiarray/ctors.c
+++ b/numpy/core/src/multiarray/ctors.c
@@ -1723,11 +1723,10 @@ PyArray_FromAny(PyObject *op, PyArray_Descr *newtype, int min_depth,
     /* If we got dimensions and dtype instead of an array */
     if (arr == NULL) {
         /*
-         * If the input data is an NA object, and the ALLOWNA flag is
+         * If the input data contains any NAs, and the ALLOWNA flag is
          * enabled, produce an array with an NA mask.
          */
-        if (contains_na && (flags & NPY_ARRAY_ALLOWNA) != 0 &&
-                                    NpyNA_Check(op)) {
+        if (contains_na && (flags & NPY_ARRAY_ALLOWNA) != 0) {
             flags |= NPY_ARRAY_MASKNA;
         }
 
diff --git a/numpy/core/tests/test_maskna.py b/numpy/core/tests/test_maskna.py
index 4dd2b13e5..ff1db7603 100644
--- a/numpy/core/tests/test_maskna.py
+++ b/numpy/core/tests/test_maskna.py
@@ -29,11 +29,15 @@ def test_array_maskna_construction():
     assert_equal(a.dtype, np.dtype('f8'))
     assert_(a.flags.maskna)
     assert_equal(type(a[2]), np.NAType)
-    # Without the 'maskna=True', produces an object array
+    # Without the 'maskna=True', still produces an NA mask if NA is there
     a = np.array([1.0, 2.0, np.NA, 7.0])
-    assert_equal(a.dtype, np.dtype('O'))
-    assert_(not a.flags.maskna)
+    assert_equal(a.dtype, np.dtype('f8'))
+    assert_(a.flags.maskna)
     assert_equal(type(a[2]), np.NAType)
+    # Without any NAs, does not produce an NA mask
+    a = np.array([1.0, 2.0, 4.0, 7.0])
+    assert_equal(a.dtype, np.dtype('f8'))
+    assert_(not a.flags.maskna)
 
     # From np.NA as a straight scalar
     a = np.array(np.NA, maskna=True)
@@ -76,11 +80,19 @@ def test_array_maskna_construction():
 def test_array_maskna_repr():
     # Test some simple reprs with NA in them
     a = np.array(np.NA, maskna=True)
-    assert_equal(repr(a), 'array(NA, maskna=True, dtype=float64)')
+    assert_equal(repr(a), 'array(NA, dtype=float64)')
+    a = np.array(3, maskna=True)
+    assert_equal(repr(a), 'array(3, maskna=True)')
     a = np.array([np.NA, 3], maskna=True)
-    assert_equal(repr(a), 'array([NA, 3], maskna=True)')
+    assert_equal(repr(a), 'array([NA, 3])')
+    a = np.array([np.NA, np.NA])
+    assert_equal(repr(a), 'array([NA, NA], dtype=float64)')
     a = np.array([3.5, np.NA], maskna=True)
-    assert_equal(repr(a), 'array([ 3.5, NA], maskna=True)')
+    assert_equal(repr(a), 'array([ 3.5, NA])')
+    a = np.array([3.75, 6.25], maskna=True)
+    assert_equal(repr(a), 'array([ 3.75,  6.25], maskna=True)')
+    a = np.array([3.75, 6.25], maskna=True, dtype='f4')
+    assert_equal(repr(a), 'array([ 3.75,  6.25], maskna=True, dtype=float32)')
 
 def test_isna():
     # Objects which are not np.NA or ndarray all return False