Revert skipna=True where it was added

pandas-dev · jreback · Jan 4, 2019 · Dec 2, 2018 · Dec 5, 2018 · Dec 6, 2018
commit fd8c0101f5ec07a302326f7c9bc2b29ddf5644cf
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
@@ -165,7 +165,7 @@ def _ensure_arraylike(values):
     ensure that we are arraylike if not already
     """
     if not is_array_like(values):
-        inferred = lib.infer_dtype(values, skipna=True)
+        inferred = lib.infer_dtype(values, skipna=False)
         if inferred in ['mixed', 'string', 'unicode']:
             if isinstance(values, tuple):
                 values = list(values)

diff --git a/pandas/core/arrays/array_.py b/pandas/core/arrays/array_.py
@@ -209,7 +209,7 @@ def array(data,         # type: Sequence[object]
         return cls._from_sequence(data, dtype=dtype, copy=copy)
 
     if dtype is None:
-        inferred_dtype = lib.infer_dtype(data, skipna=True)
+        inferred_dtype = lib.infer_dtype(data, skipna=False)
         if inferred_dtype == 'period':
             try:
                 return period_array(data, copy=copy)

diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
@@ -1678,7 +1678,7 @@ def sequence_to_dt64ns(data, dtype=None, copy=False,
         # TODO: We do not have tests specific to string-dtypes,
         #  also complex or categorical or other extension
         copy = False
-        if lib.infer_dtype(data, skipna=True) == 'integer':
+        if lib.infer_dtype(data, skipna=False) == 'integer':
             data = data.astype(np.int64)
         else:
             # data comes back here as either i8 to denote UTC timestamps

diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py
@@ -580,7 +580,7 @@ def __floordiv__(self, other):
         elif is_object_dtype(other):
             result = [self[n] // other[n] for n in range(len(self))]
             result = np.array(result)
-            if lib.infer_dtype(result, skipna=True) == 'timedelta':
+            if lib.infer_dtype(result, skipna=False) == 'timedelta':
                 result, _ = sequence_to_td64ns(result)
                 return type(self)(result)
             return result

diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
@@ -76,7 +76,7 @@ def trans(x):
     if isinstance(dtype, string_types):
         if dtype == 'infer':
             inferred_type = lib.infer_dtype(ensure_object(result.ravel()),
-                                            skipna=True)
+                                            skipna=False)
             if inferred_type == 'boolean':
                 dtype = 'bool'
             elif inferred_type == 'integer':
@@ -461,7 +461,7 @@ def infer_dtype_from_array(arr, pandas_dtype=False):
         return arr.dtype, np.asarray(arr)
 
     # don't force numpy coerce with nan's
-    inferred = lib.infer_dtype(arr, skipna=True)
+    inferred = lib.infer_dtype(arr, skipna=False)
     if inferred in ['string', 'bytes', 'unicode',
                     'mixed', 'mixed-integer']:
         return (np.object_, arr)

diff --git a/pandas/core/dtypes/common.py b/pandas/core/dtypes/common.py
@@ -704,7 +704,7 @@ def is_datetime_arraylike(arr):
         return True
     elif isinstance(arr, (np.ndarray, ABCSeries)):
         return (is_object_dtype(arr.dtype)
-                and lib.infer_dtype(arr, skipna=True) == 'datetime')
+                and lib.infer_dtype(arr, skipna=False) == 'datetime')
     return getattr(arr, 'inferred_type', None) == 'datetime'
 
 

diff --git a/pandas/core/dtypes/missing.py b/pandas/core/dtypes/missing.py
@@ -474,7 +474,7 @@ def _infer_fill_value(val):
     if is_datetimelike(val):
         return np.array('NaT', dtype=val.dtype)
     elif is_object_dtype(val.dtype):
-        dtype = lib.infer_dtype(ensure_object(val), skipna=True)
+        dtype = lib.infer_dtype(ensure_object(val), skipna=False)
         if dtype in ['datetime', 'datetime64']:
             return np.array('NaT', dtype=_NS_DTYPE)
         elif dtype in ['timedelta', 'timedelta64']:

diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
@@ -346,7 +346,7 @@ def __new__(cls, data=None, dtype=None, copy=False, name=None,
                     # should not be coerced
                     # GH 11836
                     if is_integer_dtype(dtype):
-                        inferred = lib.infer_dtype(data, skipna=True)
+                        inferred = lib.infer_dtype(data, skipna=False)
                         if inferred == 'integer':
                             data = maybe_cast_to_integer_array(data, dtype,
                                                                copy=copy)
@@ -376,7 +376,7 @@ def __new__(cls, data=None, dtype=None, copy=False, name=None,
                         else:
                             data = data.astype(dtype)
                     elif is_float_dtype(dtype):
-                        inferred = lib.infer_dtype(data, skipna=True)
+                        inferred = lib.infer_dtype(data, skipna=False)
                         if inferred == 'string':
                             pass
                         else:
@@ -1718,7 +1718,7 @@ def inferred_type(self):
         """
         Return a string of the type inferred from the values.
         """
-        return lib.infer_dtype(self, skipna=True)
+        return lib.infer_dtype(self, skipna=False)
 
     @cache_readonly
     def is_all_dates(self):

diff --git a/pandas/core/indexes/multi.py b/pandas/core/indexes/multi.py
@@ -2319,7 +2319,7 @@ def _partial_tup_index(self, tup, side='left'):
 
             if lab not in lev:
                 if not lev.is_type_compatible(lib.infer_dtype([lab],
-                                                              skipna=True)):
+                                                              skipna=False)):
                     raise TypeError('Level type mismatch: %s' % lab)
 
                 # short circuit

diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py
@@ -667,7 +667,7 @@ def sanitize_array(data, index, dtype=None, copy=False,
             subarr = np.array(data, dtype=object, copy=copy)
 
     if is_object_dtype(subarr.dtype) and dtype != 'object':
-        inferred = lib.infer_dtype(subarr, skipna=True)
+        inferred = lib.infer_dtype(subarr, skipna=False)
         if inferred == 'period':
             try:
                 subarr = period_array(subarr)

diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
@@ -947,8 +947,8 @@ def _maybe_coerce_merge_keys(self):
                     continue
 
                 # let's infer and see if we are ok
-                elif (lib.infer_dtype(lk, skipna=True)
-                      == lib.infer_dtype(rk, skipna=True)):
+                elif (lib.infer_dtype(lk, skipna=False)
+                      == lib.infer_dtype(rk, skipna=False)):
                     continue
 
             # Check if we are trying to merge on obviously
@@ -962,8 +962,8 @@ def _maybe_coerce_merge_keys(self):
             # object values are allowed to be merged
             elif ((lk_is_object and is_numeric_dtype(rk)) or
                   (is_numeric_dtype(lk) and rk_is_object)):
-                inferred_left = lib.infer_dtype(lk, skipna=True)
-                inferred_right = lib.infer_dtype(rk, skipna=True)
+                inferred_left = lib.infer_dtype(lk, skipna=False)
+                inferred_right = lib.infer_dtype(rk, skipna=False)
                 bool_types = ['integer', 'mixed-integer', 'boolean', 'empty']
                 string_types = ['string', 'unicode', 'mixed', 'bytes', 'empty']
 

diff --git a/pandas/core/reshape/tile.py b/pandas/core/reshape/tile.py
@@ -416,7 +416,7 @@ def _convert_bin_to_numeric_type(bins, dtype):
     ------
     ValueError if bins are not of a compat dtype to dtype
     """
-    bins_dtype = infer_dtype(bins, skipna=True)
+    bins_dtype = infer_dtype(bins, skipna=False)
     if is_timedelta64_dtype(dtype):
         if bins_dtype in ['timedelta', 'timedelta64']:
             bins = to_timedelta(bins).view(np.int64)

diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -875,7 +875,7 @@ def _get_with(self, key):
         if isinstance(key, Index):
             key_type = key.inferred_type
         else:
-            key_type = lib.infer_dtype(key, skipna=True)
+            key_type = lib.infer_dtype(key, skipna=False)
 
         if key_type == 'integer':
             if self.index.is_integer() or self.index.is_floating():
@@ -1012,7 +1012,7 @@ def _set_with(self, key, value):
             if isinstance(key, Index):
                 key_type = key.inferred_type
             else:
-                key_type = lib.infer_dtype(key, skipna=True)
+                key_type = lib.infer_dtype(key, skipna=False)
 
             if key_type == 'integer':
                 if self.index.inferred_type == 'integer':

diff --git a/pandas/core/sorting.py b/pandas/core/sorting.py
@@ -454,7 +454,7 @@ def sort_mixed(values):
         return np.concatenate([nums, np.asarray(strs, dtype=object)])
 
     sorter = None
-    if PY3 and lib.infer_dtype(values, skipna=True) == 'mixed-integer':
+    if PY3 and lib.infer_dtype(values, skipna=False) == 'mixed-integer':
         # unorderable in py3 if mixed str/int
         ordered = sort_mixed(values)
     else:

diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
@@ -1300,7 +1300,7 @@ def _validate_usecols_arg(usecols):
         elif not is_list_like(usecols):
             raise ValueError(msg)
         else:
-            usecols_dtype = lib.infer_dtype(usecols, skipna=True)
+            usecols_dtype = lib.infer_dtype(usecols, skipna=False)
             if usecols_dtype not in ('empty', 'integer',
                                      'string', 'unicode'):
                 raise ValueError(msg)

diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
@@ -1952,7 +1952,7 @@ def set_atom(self, block, block_items, existing_col, min_itemsize,
             return self.set_atom_complex(block)
 
         dtype = block.dtype.name
-        inferred_type = lib.infer_dtype(block.values, skipna=True)
+        inferred_type = lib.infer_dtype(block.values, skipna=False)
 
         if inferred_type == 'date':
             raise TypeError(
@@ -1998,15 +1998,15 @@ def set_atom_string(self, block, block_items, existing_col, min_itemsize,
         data = block.values
 
         # see if we have a valid string type
-        inferred_type = lib.infer_dtype(data.ravel(), skipna=True)
+        inferred_type = lib.infer_dtype(data.ravel(), skipna=False)
         if inferred_type != 'string':
 
             # we cannot serialize this data, so report an exception on a column
             # by column basis
             for i, item in enumerate(block_items):
 
                 col = block.iget(i)
-                inferred_type = lib.infer_dtype(col.ravel(), skipna=True)
+                inferred_type = lib.infer_dtype(col.ravel(), skipna=False)
                 if inferred_type != 'string':
                     raise TypeError(
                         "Cannot serialize the column [%s] because\n"
@@ -2745,7 +2745,7 @@ def write_array(self, key, value, items=None):
 
             # infer the type, warn if we have a non-string type here (for
             # performance)
-            inferred_type = lib.infer_dtype(value.ravel(), skipna=True)
+            inferred_type = lib.infer_dtype(value.ravel(), skipna=False)
             if empty_array:
                 pass
             elif inferred_type == 'string':
@@ -4512,7 +4512,7 @@ def _convert_index(index, encoding=None, errors='strict', format_type=None):
     if isinstance(index, MultiIndex):
         raise TypeError('MultiIndex not supported here!')
 
-    inferred_type = lib.infer_dtype(index, skipna=True)
+    inferred_type = lib.infer_dtype(index, skipna=False)
 
     values = np.asarray(index)
 
@@ -4745,7 +4745,7 @@ def __init__(self, table, where=None, start=None, stop=None):
 
             # see if we have a passed coordinate like
             try:
-                inferred = lib.infer_dtype(where, skipna=True)
+                inferred = lib.infer_dtype(where, skipna=False)
                 if inferred == 'integer' or inferred == 'boolean':
                     where = np.asarray(where)
                     if where.dtype == np.bool_:

diff --git a/pandas/io/stata.py b/pandas/io/stata.py
@@ -396,7 +396,7 @@ def parse_dates_safe(dates, delta=False, year=False, days=False):
                         to_datetime(d['year'], format='%Y').astype(np.int64))
                 d['days'] = days // NS_PER_DAY
 
-        elif infer_dtype(dates, skipna=True) == 'datetime':
+        elif infer_dtype(dates, skipna=False) == 'datetime':
             if delta:
                 delta = dates.values - stata_epoch
                 f = lambda x: \