Merge pull request #3333 from jreback/series_perf

PERF: series construction perf enhancements, use a fast path based on dt...

Author: jreback

pandas/core/common.py

@@ -42,6 +42,8 @@ class AmbiguousIndexError(PandasError, KeyError):
     pass
 
 
+_POSSIBLY_CAST_DTYPES = set([ np.dtype(t) for t in ['M8[ns]','m8[ns]','O','int8','uint8','int16','uint16','int32','uint32','int64','uint64'] ])
+
 def isnull(obj):
     '''
     Detect missing values (NaN in numeric arrays, None/NaN in object arrays)
@@ -1038,6 +1040,9 @@ def _possibly_convert_objects(values, convert_dates=True, convert_numeric=True):
 
     return values
 
+def _possibly_castable(arr):
+    return arr.dtype not in _POSSIBLY_CAST_DTYPES
+
 def _possibly_convert_platform(values):
     """ try to do platform conversion, allow ndarray or list here """
 

pandas/core/series.py

@@ -3196,7 +3196,6 @@ def remove_na(arr):
     """
     return arr[notnull(arr)]
 
-
 def _sanitize_array(data, index, dtype=None, copy=False,
                     raise_cast_failure=False):
 
@@ -3208,7 +3207,13 @@ def _sanitize_array(data, index, dtype=None, copy=False,
         else:
             data = data.copy()
 
-    def _try_cast(arr):
+    def _try_cast(arr, take_fast_path):
+
+        # perf shortcut as this is the most common case
+        if take_fast_path:
+            if com._possibly_castable(arr) and not copy and dtype is None:
+                return arr
+
         try:
             arr = com._possibly_cast_to_datetime(arr, dtype)
             subarr = pa.array(arr, dtype=dtype, copy=copy)
@@ -3227,7 +3232,7 @@ def _try_cast(arr):
             # possibility of nan -> garbage
             if com.is_float_dtype(data.dtype) and com.is_integer_dtype(dtype):
                 if not isnull(data).any():
-                    subarr = _try_cast(data)
+                    subarr = _try_cast(data, True)
                 elif copy:
                     subarr = data.copy()
             else:
@@ -3239,17 +3244,17 @@ def _try_cast(arr):
                     elif raise_cast_failure:
                         raise TypeError('Cannot cast datetime64 to %s' % dtype)
                 else:
-                    subarr = _try_cast(data)
+                    subarr = _try_cast(data, True)
         else:
-            subarr = _try_cast(data)
+            subarr = _try_cast(data, True)
 
         if copy:
             subarr = data.copy()
 
     elif isinstance(data, list) and len(data) > 0:
         if dtype is not None:
             try:
-                subarr = _try_cast(data)
+                subarr = _try_cast(data, False)
             except Exception:
                 if raise_cast_failure:  # pragma: no cover
                     raise
@@ -3262,7 +3267,7 @@ def _try_cast(arr):
         subarr = com._possibly_cast_to_datetime(subarr, dtype)
 
     else:
-        subarr = _try_cast(data)
+        subarr = _try_cast(data, False)
 
     # scalar like
     if subarr.ndim == 0: