astype checks notnull Fixes: pandas-dev#8732 added benchmark,added nu…

…ll check

pandas/core/common.py

@@ -2580,14 +2580,14 @@ def _astype_nansafe(arr, dtype, copy=True):
         if np.isnan(arr).any():
             raise ValueError('Cannot convert NA to integer')
     elif arr.dtype == np.object_ and np.issubdtype(dtype.type, np.integer):
+        has_nulls = isnull(arr).any() or not is_numeric_dtype(arr.dtype)
         # work around NumPy brokenness, #1987
-        return lib.astype_intsafe(arr.ravel(), dtype).reshape(arr.shape)
+        return lib.astype_intsafe(arr.ravel(), dtype, has_nulls).reshape(arr.shape)
     elif issubclass(dtype.type, compat.text_type):
         # in Py3 that's str, in Py2 that's unicode
         return lib.astype_unicode(arr.ravel()).reshape(arr.shape)
     elif issubclass(dtype.type, compat.string_types):
         return lib.astype_str(arr.ravel()).reshape(arr.shape)
-
     if copy:
         return arr.astype(dtype)
     return arr.view(dtype)

pandas/lib.pyx

@@ -827,7 +827,7 @@ def vec_binop(ndarray[object] left, ndarray[object] right, object op):
     return maybe_convert_bool(result)
 
 
-def astype_intsafe(ndarray[object] arr, new_dtype):
+def astype_intsafe(ndarray[object] arr, new_dtype, has_nulls):
     cdef:
         Py_ssize_t i, n = len(arr)
         object v
@@ -837,6 +837,9 @@ def astype_intsafe(ndarray[object] arr, new_dtype):
     # on 32-bit, 1.6.2 numpy M8[ns] is a subdtype of integer, which is weird
     is_datelike = new_dtype in ['M8[ns]','m8[ns]']
 
+    if not is_datelike and not has_nulls:
+        return arr.astype(new_dtype)
+
     result = np.empty(n, dtype=new_dtype)
     for i in range(n):
         v = arr[i]

pandas/tests/test_frame.py

@@ -2141,6 +2141,45 @@ def setUp(self):
         self.simple = DataFrame(arr, columns=['one', 'two', 'three'],
                                 index=['a', 'b', 'c'])
 
+    def test_hasnulls(self):
+        # Github Issue 8732
+        df = tm.makeMissingDataframe()
+        df['A'][df.index[0]] = np.nan
+        self.assertEqual(df['A'].notnull().all(), False)
+        casted = df.astype(np.float64)
+        expected = DataFrame(df.values.astype(np.float64),
+                             index=df.index,
+                             columns=df.columns)
+        assert_frame_equal(casted, expected)
+
+        casted = df.astype(np.str)
+        expected = DataFrame(df.values.astype(np.str),
+                             index=df.index,
+                             columns=df.columns)
+        assert_frame_equal(casted, expected)
+
+        df = tm.makeMissingCustomDataframe(10, 5)
+        col = df.columns[0]
+        df[col][df.index[0]] = np.nan
+        self.assertEqual(df[col].notnull().all(), False)
+        casted = df.astype(np.str)
+        expected = DataFrame(df.values.astype(np.str),
+                             index=df.index,
+                             columns=df.columns)
+        assert_frame_equal(casted, expected)
+
+        df = tm.makeMixedDataFrameWithNaN()
+        self.assertEqual(df['A'].notnull().all(), False)
+        self.assertEqual(df['B'].notnull().all(), False)
+        self.assertEqual(df['C'].notnull().all(), False)
+        self.assertEqual(df['D'].notnull().all(), True)
+
+        casted = df.astype(np.object)
+        expected = DataFrame(df.values.astype(np.object),
+                             index=df.index,
+                             columns=df.columns)
+        assert_frame_equal(casted, expected)
+
     def test_get_axis(self):
         f = self.frame
         self.assertEqual(f._get_axis_number(0), 0)

pandas/tests/test_series.py

@@ -560,11 +560,18 @@ def test_scalar_conversion(self):
     def test_astype(self):
         s = Series(np.random.randn(5),name='foo')
 
-        for dtype in ['float32','float64','int64','int32']:
+        for dtype in ['float32','float64','int64','int32', 'object']:
             astyped = s.astype(dtype)
             self.assertEqual(astyped.dtype, dtype)
             self.assertEqual(astyped.name, s.name)
 
+    def test_astype_to(self):
+        arr = np.random.randint(1, 10, size=100)
+        s = Series(arr)
+        for dtype in ['float32', 'float64', 'int64', 'int32', 'object']:
+            astyped = s.astype(dtype)
+            self.assertEqual(astyped.dtype, dtype)
+
     def test_constructor(self):
         # Recognize TimeSeries
         self.assertTrue(self.ts.is_time_series)

pandas/util/testing.py

@@ -877,6 +877,20 @@ def getMixedTypeDict():
 
     return index, data
 
+
+def makeMixedDataFrameWithNaN():
+    index = Index(['a', 'b', 'c', 'd', 'e', 'f'])
+
+    data = {
+        'A': [0., 1., 2., 3., 4., np.nan],
+        'B': [0., 1., 0., 1., 0., np.nan],
+        'C': ['foo1', 'foo2', 'foo3', 'foo4', 'foo5', np.nan],
+        'D': bdate_range('1/1/2009', periods=6)
+    }
+
+    return DataFrame(data, index=index)
+
+
 def makeMixedDataFrame():
     return DataFrame(getMixedTypeDict()[1])
 

vb_suite/astype.py

@@ -0,0 +1,15 @@
+from vbench.api import Benchmark
+
+common_setup = """from pandas_vb_common import *
+from datetime import timedelta
+import pandas as pd
+import numpy as np
+
+N = 1000000
+arr = np.random.randint(1,10,size=1000000)
+s = pd.Series(arr)
+"""
+
+astype_test = Benchmark('s.astype(np.str)',
+                        common_setup,
+                        name='astype_test')

vb_suite/suite.py

@@ -13,6 +13,7 @@
            'indexing',
            'io_bench',
            'io_sql',
+           'astype',
            'inference',
            'hdfstore_bench',
            'join_merge',