Merge pull request #10676 from jorisvandenbossche/stacklevel

DEPR: add stacklevel to FutureWarnings (GH9584)

pandas/computation/align.py

@@ -101,7 +101,8 @@ def _align_core(terms):
                                   'than an order of magnitude on term {1!r}, '
                                   'by more than {2:.4g}; performance may '
                                   'suffer'.format(axis, terms[i].name, ordm),
-                                  category=pd.io.common.PerformanceWarning)
+                                  category=pd.io.common.PerformanceWarning,
+                                  stacklevel=6)
 
                 if transpose:
                     f = partial(ti.reindex, index=reindexer, copy=False)

pandas/computation/pytables.py

@@ -535,7 +535,7 @@ def parse_back_compat(self, w, op=None, value=None):
                 w, op, value = w
             warnings.warn("passing a tuple into Expr is deprecated, "
                           "pass the where as a single string",
-                          DeprecationWarning)
+                          DeprecationWarning, stacklevel=10)
 
         if op is not None:
             if not isinstance(w, string_types):

pandas/core/algorithms.py

@@ -125,8 +125,8 @@ def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
     note: an array of Periods will ignore sort as it returns an always sorted PeriodIndex
     """
     if order is not None:
-        warn("order is deprecated."
-             "See https://github.com/pydata/pandas/issues/6926", FutureWarning)
+        msg = "order is deprecated. See https://github.com/pydata/pandas/issues/6926"
+        warn(msg, FutureWarning, stacklevel=2)
 
     from pandas.core.index import Index
     from pandas.core.series import Series

pandas/core/categorical.py

@@ -414,7 +414,7 @@ def _get_labels(self):
 
         Deprecated, use .codes!
         """
-        warn("'labels' is deprecated. Use 'codes' instead", FutureWarning, stacklevel=3)
+        warn("'labels' is deprecated. Use 'codes' instead", FutureWarning, stacklevel=2)
         return self.codes
 
     labels = property(fget=_get_labels, fset=_set_codes)
@@ -456,7 +456,7 @@ def _validate_categories(cls, categories, fastpath=False):
                 # NaNs in cats deprecated in 0.17, remove in 0.18 or 0.19 GH 10748
                 msg = ('\nSetting NaNs in `categories` is deprecated and '
                        'will be removed in a future version of pandas.')
-                warn(msg, FutureWarning, stacklevel=5)
+                warn(msg, FutureWarning, stacklevel=3)
 
             # categories must be unique
 
@@ -491,12 +491,12 @@ def _get_categories(self):
 
     def _set_levels(self, levels):
         """ set new levels (deprecated, use "categories") """
-        warn("Assigning to 'levels' is deprecated, use 'categories'", FutureWarning, stacklevel=3)
+        warn("Assigning to 'levels' is deprecated, use 'categories'", FutureWarning, stacklevel=2)
         self.categories = levels
 
     def _get_levels(self):
         """ Gets the levels (deprecated, use "categories") """
-        warn("Accessing 'levels' is deprecated, use 'categories'", FutureWarning, stacklevel=3)
+        warn("Accessing 'levels' is deprecated, use 'categories'", FutureWarning, stacklevel=2)
         return self.categories
 
     # TODO: Remove after deprecation period in 2017/ after 0.18
@@ -507,7 +507,7 @@ def _get_levels(self):
     def _set_ordered(self, value):
         """ Sets the ordered attribute to the boolean value """
         warn("Setting 'ordered' directly is deprecated, use 'set_ordered'", FutureWarning,
-             stacklevel=3)
+             stacklevel=2)
         self.set_ordered(value, inplace=True)
 
     def set_ordered(self, value, inplace=False):
@@ -1200,7 +1200,7 @@ def order(self, inplace=False, ascending=True, na_position='last'):
         Category.sort
         """
         warn("order is deprecated, use sort_values(...)",
-             FutureWarning, stacklevel=3)
+             FutureWarning, stacklevel=2)
         return self.sort_values(inplace=inplace, ascending=ascending, na_position=na_position)
 
     def sort(self, inplace=True, ascending=True, na_position='last'):

pandas/core/frame.py

@@ -1468,7 +1468,7 @@ def to_html(self, buf=None, columns=None, col_space=None, colSpace=None,
 
         if colSpace is not None:  # pragma: no cover
             warnings.warn("colSpace is deprecated, use col_space",
-                          FutureWarning)
+                          FutureWarning, stacklevel=2)
             col_space = colSpace
 
         formatter = fmt.DataFrameFormatter(self, buf=buf, columns=columns,
@@ -1517,7 +1517,7 @@ def to_latex(self, buf=None, columns=None, col_space=None, colSpace=None,
 
         if colSpace is not None:  # pragma: no cover
             warnings.warn("colSpace is deprecated, use col_space",
-                          FutureWarning)
+                          FutureWarning, stacklevel=2)
             col_space = colSpace
 
         formatter = fmt.DataFrameFormatter(self, buf=buf, columns=columns,
@@ -2919,7 +2919,7 @@ def dropna(self, axis=0, how='any', thresh=None, subset=None,
             return result
 
     @deprecate_kwarg('take_last', 'keep', mapping={True: 'last', False: 'first'})
-    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset')
+    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset', stacklevel=3)
     def drop_duplicates(self, subset=None, keep='first', inplace=False):
         """
         Return DataFrame with duplicate rows removed, optionally only
@@ -2953,7 +2953,7 @@ def drop_duplicates(self, subset=None, keep='first', inplace=False):
             return self[-duplicated]
 
     @deprecate_kwarg('take_last', 'keep', mapping={True: 'last', False: 'first'})
-    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset')
+    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset', stacklevel=3)
     def duplicated(self, subset=None, keep='first'):
         """
         Return boolean Series denoting duplicate rows, optionally only

pandas/core/generic.py

@@ -706,7 +706,7 @@ def iterkv(self, *args, **kwargs):
         "iteritems alias used to get around 2to3. Deprecated"
         warnings.warn("iterkv is deprecated and will be removed in a future "
                       "release, use ``iteritems`` instead.",
-                      FutureWarning)
+                      FutureWarning, stacklevel=2)
         return self.iteritems(*args, **kwargs)
 
     def __len__(self):
@@ -3376,11 +3376,11 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
             For frequencies that evenly subdivide 1 day, the "origin" of the
             aggregated intervals. For example, for '5min' frequency, base could
             range from 0 through 4. Defaults to 0
-        
+
 
         Examples
         --------
-        
+
         Start by creating a series with 9 one minute timestamps.
 
         >>> index = pd.date_range('1/1/2000', periods=9, freq='T')
@@ -3409,11 +3409,11 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
         Downsample the series into 3 minute bins as above, but label each
         bin using the right edge instead of the left. Please note that the
         value in the bucket used as the label is not included in the bucket,
-        which it labels. For example, in the original series the 
+        which it labels. For example, in the original series the
         bucket ``2000-01-01 00:03:00`` contains the value 3, but the summed
-        value in the resampled bucket with the label``2000-01-01 00:03:00`` 
+        value in the resampled bucket with the label``2000-01-01 00:03:00``
         does not include 3 (if it did, the summed value would be 6, not 3).
-        To include this value close the right side of the bin interval as 
+        To include this value close the right side of the bin interval as
         illustrated in the example below this one.
 
         >>> series.resample('3T', how='sum', label='right')
@@ -3424,7 +3424,7 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
 
         Downsample the series into 3 minute bins as above, but close the right
         side of the bin interval.
-        
+
         >>> series.resample('3T', how='sum', label='right', closed='right')
         2000-01-01 00:00:00     0
         2000-01-01 00:03:00     6
@@ -3453,7 +3453,7 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
         2000-01-01 00:02:00    2
         Freq: 30S, dtype: int64
 
-        Upsample the series into 30 second bins and fill the 
+        Upsample the series into 30 second bins and fill the
         ``NaN`` values using the ``bfill`` method.
 
         >>> series.resample('30S', fill_method='bfill')[0:5]
@@ -3468,7 +3468,7 @@ def resample(self, rule, how=None, axis=0, fill_method=None,
 
         >>> def custom_resampler(array_like):
         ...     return np.sum(array_like)+5
-        
+
         >>> series.resample('3T', how=custom_resampler)
         2000-01-01 00:00:00     8
         2000-01-01 00:03:00    17

pandas/core/index.py

@@ -842,14 +842,14 @@ def to_int():
             elif is_float(key):
                 key = to_int()
                 warnings.warn("scalar indexers for index type {0} should be integers and not floating point".format(
-                    type(self).__name__),FutureWarning, stacklevel=8)
+                    type(self).__name__), FutureWarning, stacklevel=5)
                 return key
             return self._invalid_indexer('label', key)
 
         if is_float(key):
             if not self.is_floating():
                 warnings.warn("scalar indexers for index type {0} should be integers and not floating point".format(
-                    type(self).__name__),FutureWarning, stacklevel=8)
+                    type(self).__name__), FutureWarning, stacklevel=3)
             return to_int()
 
         return key
@@ -887,7 +887,7 @@ def f(c):
                 # warn if it's a convertible float
                 if v == int(v):
                     warnings.warn("slice indexers when using iloc should be integers "
-                                  "and not floating point",FutureWarning)
+                                  "and not floating point", FutureWarning, stacklevel=7)
                     return int(v)
 
                 self._invalid_indexer('slice {0} value'.format(c), v)
@@ -1415,22 +1415,22 @@ def argsort(self, *args, **kwargs):
     def __add__(self, other):
         if com.is_list_like(other):
             warnings.warn("using '+' to provide set union with Indexes is deprecated, "
-                          "use '|' or .union()", FutureWarning)
+                          "use '|' or .union()", FutureWarning, stacklevel=2)
         if isinstance(other, Index):
             return self.union(other)
         return Index(np.array(self) + other)
 
     def __radd__(self, other):
         if com.is_list_like(other):
             warnings.warn("using '+' to provide set union with Indexes is deprecated, "
-                          "use '|' or .union()", FutureWarning)
+                          "use '|' or .union()", FutureWarning, stacklevel=2)
         return Index(other + np.array(self))
 
     __iadd__ = __add__
 
     def __sub__(self, other):
         warnings.warn("using '-' to provide set differences with Indexes is deprecated, "
-                      "use .difference()",FutureWarning)
+                      "use .difference()",FutureWarning, stacklevel=2)
         return self.difference(other)
 
     def __and__(self, other):

pandas/core/strings.py

@@ -204,7 +204,7 @@ def str_contains(arr, pat, case=True, flags=0, na=np.nan, regex=True):
 
         if regex.groups > 0:
             warnings.warn("This pattern has match groups. To actually get the"
-                          " groups, use str.extract.", UserWarning)
+                          " groups, use str.extract.", UserWarning, stacklevel=3)
 
         f = lambda x: bool(regex.search(x))
     else:
@@ -377,11 +377,12 @@ def str_match(arr, pat, case=True, flags=0, na=np.nan, as_indexer=False):
         # Do this first, to make sure it happens even if the re.compile
         # raises below.
         warnings.warn("In future versions of pandas, match will change to"
-                      " always return a bool indexer.", UserWarning)
+                      " always return a bool indexer.", FutureWarning,
+                      stacklevel=3)
 
     if as_indexer and regex.groups > 0:
         warnings.warn("This pattern has match groups. To actually get the"
-                      " groups, use str.extract.", UserWarning)
+                      " groups, use str.extract.", UserWarning, stacklevel=3)
 
     # If not as_indexer and regex.groups == 0, this returns empty lists
     # and is basically useless, so we will not warn.

pandas/io/data.py

@@ -608,7 +608,7 @@ def __init__(self, symbol, data_source=None):
         self.symbol = symbol.upper()
         if data_source is None:
             warnings.warn("Options(symbol) is deprecated, use Options(symbol,"
-                          " data_source) instead", FutureWarning)
+                          " data_source) instead", FutureWarning, stacklevel=2)
             data_source = "yahoo"
         if data_source != "yahoo":
             raise NotImplementedError("currently only yahoo supported")
@@ -1072,7 +1072,8 @@ def get_forward_data(self, months, call=True, put=False, near=False,
                 Note: Format of returned data frame is dependent on Yahoo and may change.
 
         """
-        warnings.warn("get_forward_data() is deprecated", FutureWarning)
+        warnings.warn("get_forward_data() is deprecated", FutureWarning,
+                      stacklevel=2)
         end_date = dt.date.today() + MonthEnd(months)
         dates = (date for date in self.expiry_dates if date <= end_date.date())
         data = self._get_data_in_date_range(dates, call=call, put=put)

pandas/io/parsers.py

@@ -647,7 +647,7 @@ def _clean_options(self, options, engine):
             warnings.warn(("Falling back to the 'python' engine because"
                            " {0}; you can avoid this warning by specifying"
                            " engine='python'.").format(fallback_reason),
-                          ParserWarning)
+                          ParserWarning, stacklevel=5)
 
         index_col = options['index_col']
         names = options['names']

pandas/io/pytables.py

@@ -1596,7 +1596,7 @@ def update_info(self, info):
                 # frequency/name just warn
                 if key in ['freq', 'index_name']:
                     ws = attribute_conflict_doc % (key, existing_value, value)
-                    warnings.warn(ws, AttributeConflictWarning)
+                    warnings.warn(ws, AttributeConflictWarning, stacklevel=6)
 
                     # reset
                     idx[key] = None
@@ -2581,7 +2581,7 @@ def write_array(self, key, value, items=None):
                 except:
                     pass
                 ws = performance_doc % (inferred_type, key, items)
-                warnings.warn(ws, PerformanceWarning)
+                warnings.warn(ws, PerformanceWarning, stacklevel=7)
 
             vlarr = self._handle.create_vlarray(self.group, key,
                                                _tables().ObjectAtom())
@@ -3716,7 +3716,7 @@ def read(self, where=None, columns=None, **kwargs):
                 objs.append(obj)
 
         else:
-            warnings.warn(duplicate_doc, DuplicateWarning)
+            warnings.warn(duplicate_doc, DuplicateWarning, stacklevel=5)
 
             # reconstruct
             long_index = MultiIndex.from_arrays(