TST: Fail on warning (#22699)

Author: TomAugspurger

.travis.yml

@@ -64,7 +64,7 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+        - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
       addons:
         apt:
           packages:
@@ -79,7 +79,7 @@ matrix:
           - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
       - dist: trusty
         env:
-          - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+          - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
         addons:
           apt:
             packages:

ci/travis-36-numpydev.yaml renamed to ci/travis-37-numpydev.yaml

@@ -2,7 +2,7 @@ name: pandas
 channels:
   - defaults
 dependencies:
-  - python=3.6*
+  - python=3.7*
   - pytz
   - Cython>=0.28.2
   # universal

doc/source/contributing.rst

@@ -632,6 +632,14 @@ Otherwise, you need to do it manually:
         warnings.warn('Use new_func instead.', FutureWarning, stacklevel=2)
         new_func()
 
+You'll also need to
+
+1. write a new test that asserts a warning is issued when calling with the deprecated argument
+2. Update all of pandas existing tests and code to use the new argument
+
+See :ref:`contributing.warnings` for more.
+
+
 .. _contributing.ci:
 
 Testing With Continuous Integration
@@ -859,6 +867,55 @@ preferred if the inputs or logic are simple, with Hypothesis tests reserved
 for cases with complex logic or where there are too many combinations of
 options or subtle interactions to test (or think of!) all of them.
 
+.. _contributing.warnings:
+
+Testing Warnings
+~~~~~~~~~~~~~~~~
+
+By default, one of pandas CI workers will fail if any unhandled warnings are emitted.
+
+If your change involves checking that a warning is actually emitted, use
+``tm.assert_produces_warning(ExpectedWarning)``.
+
+
+.. code-block:: python
+
+   with tm.assert_prodcues_warning(FutureWarning):
+       df.some_operation()
+
+We prefer this to the ``pytest.warns`` context manager because ours checks that the warning's
+stacklevel is set correctly. The stacklevel is what ensure the *user's* file name and line number
+is printed in the warning, rather than something internal to pandas. It represents the number of
+function calls from user code (e.g. ``df.some_operation()``) to the function that actually emits
+the warning. Our linter will fail the build if you use ``pytest.warns`` in a test.
+
+If you have a test that would emit a warning, but you aren't actually testing the
+warning itself (say because it's going to be removed in the future, or because we're
+matching a 3rd-party library's behavior), then use ``pytest.mark.filterwarnings`` to
+ignore the error.
+
+.. code-block:: python
+
+   @pytest.mark.filterwarnings("ignore:msg:category")
+   def test_thing(self):
+       ...
+
+If the test generates a warning of class ``category`` whose message starts
+with ``msg``, the warning will be ignored and the test will pass.
+
+If you need finer-grained control, you can use Python's usual
+`warnings module <https://docs.python.org/3/library/warnings.html>`__
+to control whether a warning is ignored / raised at different places within
+a single test.
+
+.. code-block:: python
+
+   with warch.catch_warnings():
+       warnings.simplefilter("ignore", FutureWarning)
+       # Or use warnings.filterwarnings(...)
+
+Alternatively, consider breaking up the unit test.
+
 
 Running the test suite
 ----------------------

pandas/compat/__init__.py

@@ -38,6 +38,7 @@
 import struct
 import inspect
 from collections import namedtuple
+import collections
 
 PY2 = sys.version_info[0] == 2
 PY3 = sys.version_info[0] >= 3
@@ -135,6 +136,11 @@ def lfilter(*args, **kwargs):
 
     from importlib import reload
     reload = reload
+    Hashable = collections.abc.Hashable
+    Iterable = collections.abc.Iterable
+    Mapping = collections.abc.Mapping
+    Sequence = collections.abc.Sequence
+    Sized = collections.abc.Sized
 
 else:
     # Python 2
@@ -190,6 +196,12 @@ def get_range_parameters(data):
 
     reload = builtins.reload
 
+    Hashable = collections.Hashable
+    Iterable = collections.Iterable
+    Mapping = collections.Mapping
+    Sequence = collections.Sequence
+    Sized = collections.Sized
+
 if PY2:
     def iteritems(obj, **kw):
         return obj.iteritems(**kw)

pandas/compat/chainmap_impl.py

@@ -1,4 +1,11 @@
-from collections import MutableMapping
+import sys
+
+PY3 = sys.version_info[0] >= 3
+
+if PY3:
+    from collections.abc import MutableMapping
+else:
+    from collections import MutableMapping
 
 try:
     from thread import get_ident

pandas/core/algorithms.py

@@ -3,7 +3,7 @@
 intended for public consumption
 """
 from __future__ import division
-from warnings import warn, catch_warnings
+from warnings import warn, catch_warnings, simplefilter
 from textwrap import dedent
 
 import numpy as np
@@ -91,7 +91,8 @@ def _ensure_data(values, dtype=None):
 
             # ignore the fact that we are casting to float
             # which discards complex parts
-            with catch_warnings(record=True):
+            with catch_warnings():
+                simplefilter("ignore", np.ComplexWarning)
                 values = ensure_float64(values)
             return values, 'float64', 'float64'
 

pandas/core/arrays/datetimelike.py

@@ -59,6 +59,7 @@ def cmp_method(self, other):
         # numpy will show a DeprecationWarning on invalid elementwise
         # comparisons, this will raise in the future
         with warnings.catch_warnings(record=True):
+            warnings.filterwarnings("ignore", "elementwise", FutureWarning)
             with np.errstate(all='ignore'):
                 result = op(self.values, np.asarray(other))
 

pandas/core/arrays/integer.py

@@ -5,7 +5,7 @@
 
 from pandas._libs.lib import infer_dtype
 from pandas.util._decorators import cache_readonly
-from pandas.compat import u, range
+from pandas.compat import u, range, string_types
 from pandas.compat import set_function_name
 
 from pandas.core.dtypes.cast import astype_nansafe
@@ -147,6 +147,11 @@ def coerce_to_array(values, dtype, mask=None, copy=False):
             dtype = values.dtype
 
     if dtype is not None:
+        if (isinstance(dtype, string_types) and
+                (dtype.startswith("Int") or dtype.startswith("UInt"))):
+            # Avoid DeprecationWarning from NumPy about np.dtype("Int64")
+            # https://github.com/numpy/numpy/pull/7476
+            dtype = dtype.lower()
         if not issubclass(type(dtype), _IntegerDtype):
             try:
                 dtype = _dtypes[str(np.dtype(dtype))]
@@ -507,7 +512,8 @@ def cmp_method(self, other):
 
             # numpy will show a DeprecationWarning on invalid elementwise
             # comparisons, this will raise in the future
-            with warnings.catch_warnings(record=True):
+            with warnings.catch_warnings():
+                warnings.filterwarnings("ignore", "elementwise", FutureWarning)
                 with np.errstate(all='ignore'):
                     result = op(self._data, other)
 

pandas/core/common.py

@@ -356,7 +356,7 @@ def standardize_mapping(into):
             return partial(
                 collections.defaultdict, into.default_factory)
         into = type(into)
-    if not issubclass(into, collections.Mapping):
+    if not issubclass(into, compat.Mapping):
         raise TypeError('unsupported type: {into}'.format(into=into))
     elif into == collections.defaultdict:
         raise TypeError(

pandas/core/computation/eval.py

@@ -323,6 +323,7 @@ def eval(expr, parser='pandas', engine=None, truediv=True,
             # to use a non-numeric indexer
             try:
                 with warnings.catch_warnings(record=True):
+                    # TODO: Filter the warnings we actually care about here.
                     target[assigner] = ret
             except (TypeError, IndexError):
                 raise ValueError("Cannot assign expression output to target")

pandas/core/dtypes/inference.py

@@ -1,10 +1,9 @@
 """ basic inference routines """
 
-import collections
 import re
 import numpy as np
-from collections import Iterable
 from numbers import Number
+from pandas import compat
 from pandas.compat import (PY2, string_types, text_type,
                            string_and_binary_types, re_type)
 from pandas._libs import lib
@@ -112,7 +111,7 @@ def _iterable_not_string(obj):
     False
     """
 
-    return (isinstance(obj, collections.Iterable) and
+    return (isinstance(obj, compat.Iterable) and
             not isinstance(obj, string_types))
 
 
@@ -284,7 +283,7 @@ def is_list_like(obj):
     False
     """
 
-    return (isinstance(obj, Iterable) and
+    return (isinstance(obj, compat.Iterable) and
             # we do not count strings/unicode/bytes as list-like
             not isinstance(obj, string_and_binary_types) and
             # exclude zero-dimensional numpy arrays, effectively scalars

pandas/core/frame.py

@@ -417,9 +417,9 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                                          copy=copy)
 
         # For data is list-like, or Iterable (will consume into list)
-        elif (isinstance(data, collections.Iterable)
+        elif (isinstance(data, compat.Iterable)
               and not isinstance(data, string_and_binary_types)):
-            if not isinstance(data, collections.Sequence):
+            if not isinstance(data, compat.Sequence):
                 data = list(data)
             if len(data) > 0:
                 if is_list_like(data[0]) and getattr(data[0], 'ndim', 1) == 1:
@@ -7654,7 +7654,7 @@ def _to_arrays(data, columns, coerce_float=False, dtype=None):
     if isinstance(data[0], (list, tuple)):
         return _list_to_arrays(data, columns, coerce_float=coerce_float,
                                dtype=dtype)
-    elif isinstance(data[0], collections.Mapping):
+    elif isinstance(data[0], compat.Mapping):
         return _list_of_dict_to_arrays(data, columns,
                                        coerce_float=coerce_float, dtype=dtype)
     elif isinstance(data[0], Series):

pandas/core/groupby/generic.py

@@ -758,7 +758,7 @@ def aggregate(self, func_or_funcs, *args, **kwargs):
         if isinstance(func_or_funcs, compat.string_types):
             return getattr(self, func_or_funcs)(*args, **kwargs)
 
-        if isinstance(func_or_funcs, collections.Iterable):
+        if isinstance(func_or_funcs, compat.Iterable):
             # Catch instances of lists / tuples
             # but not the class list / tuple itself.
             ret = self._aggregate_multiple_funcs(func_or_funcs,

pandas/core/indexes/base.py

@@ -98,6 +98,7 @@ def cmp_method(self, other):
             # numpy will show a DeprecationWarning on invalid elementwise
             # comparisons, this will raise in the future
             with warnings.catch_warnings(record=True):
+                warnings.filterwarnings("ignore", "elementwise", FutureWarning)
                 with np.errstate(all='ignore'):
                     result = op(self.values, np.asarray(other))
 

pandas/core/internals/blocks.py

@@ -3490,6 +3490,7 @@ def _putmask_smart(v, m, n):
 
         # we ignore ComplexWarning here
         with warnings.catch_warnings(record=True):
+            warnings.simplefilter("ignore", np.ComplexWarning)
             nn_at = nn.astype(v.dtype)
 
         # avoid invalid dtype comparisons

pandas/core/series.py

@@ -6,7 +6,6 @@
 # pylint: disable=E1101,E1103
 # pylint: disable=W0703,W0622,W0613,W0201
 
-import collections
 import warnings
 from textwrap import dedent
 
@@ -240,8 +239,8 @@ def __init__(self, data=None, index=None, dtype=None, name=None,
                 raise TypeError("{0!r} type is unordered"
                                 "".format(data.__class__.__name__))
             # If data is Iterable but not list-like, consume into list.
-            elif (isinstance(data, collections.Iterable)
-                  and not isinstance(data, collections.Sized)):
+            elif (isinstance(data, compat.Iterable)
+                  and not isinstance(data, compat.Sized)):
                 data = list(data)
             else:
 

pandas/core/window.py

@@ -2387,11 +2387,13 @@ def dataframe_from_int_dict(data, frame_template):
                     if not arg2.columns.is_unique:
                         raise ValueError("'arg2' columns are not unique")
                     with warnings.catch_warnings(record=True):
+                        warnings.simplefilter("ignore", RuntimeWarning)
                         X, Y = arg1.align(arg2, join='outer')
                     X = X + 0 * Y
                     Y = Y + 0 * X
 
                     with warnings.catch_warnings(record=True):
+                        warnings.simplefilter("ignore", RuntimeWarning)
                         res_columns = arg1.columns.union(arg2.columns)
                     for col in res_columns:
                         if col in X and col in Y:

pandas/io/common.py

@@ -386,6 +386,8 @@ def _get_handle(path_or_buf, mode, encoding=None, compression=None,
         # ZIP Compression
         elif compression == 'zip':
             zf = BytesZipFile(path_or_buf, mode)
+            # Ensure the container is closed as well.
+            handles.append(zf)
             if zf.mode == 'w':
                 f = zf
             elif zf.mode == 'r':

pandas/io/html.py

@@ -6,14 +6,14 @@
 import os
 import re
 import numbers
-import collections
 
 from distutils.version import LooseVersion
 
 from pandas.core.dtypes.common import is_list_like
 from pandas.errors import EmptyDataError
 from pandas.io.common import _is_url, urlopen, _validate_header_arg
 from pandas.io.parsers import TextParser
+from pandas import compat
 from pandas.compat import (lrange, lmap, u, string_types, iteritems,
                            raise_with_traceback, binary_type)
 from pandas import Series
@@ -859,7 +859,7 @@ def _validate_flavor(flavor):
         flavor = 'lxml', 'bs4'
     elif isinstance(flavor, string_types):
         flavor = flavor,
-    elif isinstance(flavor, collections.Iterable):
+    elif isinstance(flavor, compat.Iterable):
         if not all(isinstance(flav, string_types) for flav in flavor):
             raise TypeError('Object of type {typ!r} is not an iterable of '
                             'strings'

pandas/io/pickle.py

@@ -160,7 +160,8 @@ def try_read(path, encoding=None):
         # GH 6899
         try:
             with warnings.catch_warnings(record=True):
-                # We want to silencce any warnings about, e.g. moved modules.
+                # We want to silence any warnings about, e.g. moved modules.
+                warnings.simplefilter("ignore", Warning)
                 return read_wrapper(lambda f: pkl.load(f))
         except Exception:
             # reg/patched pickle