MAINT: Temporarily ignore pandas warnings in categoricals.

Pandas 0.18 doesn't like having null-ish values in categoricals.  Fixing
this properly requires re-thinking the semantics for missing_value on
pipeline terms, so we're punting on that until after we've upgraded to
0.18.

tests/pipeline/test_blaze.py

@@ -41,6 +41,7 @@ from zipline.testing import (
 from zipline.testing.fixtures import WithAssetFinder
 from zipline.testing.predicates import assert_equal, assert_isidentical
 from zipline.utils.numpy_utils import float64_dtype, int64_dtype
+from zipline.utils.pandas_utils import ignore_pandas_nan_categorical_warning
 
 
 nameof = op.attrgetter('name')

tests/pipeline/test_column.py

@@ -11,6 +11,7 @@ from zipline.lib.labelarray import LabelArray
 from zipline.pipeline import Pipeline
 from zipline.pipeline.data.testing import TestingDataSet as TDS
 from zipline.testing import chrange, temp_pipeline_engine
+from zipline.utils.pandas_utils import ignore_pandas_nan_categorical_warning
 
 
 class LatestTestCase(TestCase):
@@ -71,6 +72,8 @@ class LatestTestCase(TestCase):
             dates_to_test[-1],
         )
         for column in columns:
-            col_result = result[column.name].unstack()
+            with ignore_pandas_nan_categorical_warning():
+                col_result = result[column.name].unstack()
+
             expected_col_result = self.expected_latest(column, cal_slice)
             assert_frame_equal(col_result, expected_col_result)

zipline/lib/labelarray.py

@@ -24,6 +24,7 @@ from zipline.utils.numpy_utils import (
     int_dtype_with_size_in_bytes,
     is_object,
 )
+from zipline.utils.pandas_utils import ignore_pandas_nan_categorical_warning
 
 from ._factorize import (
     factorize_strings,
@@ -284,14 +285,16 @@ class LabelArray(ndarray):
         """
         if len(self.shape) > 1:
             raise ValueError("Can't convert a 2D array to a categorical.")
-        return pd.Categorical.from_codes(
-            self.as_int_array(),
-            # We need to make a copy because pandas >= 0.17 fails if this
-            # buffer isn't writeable.
-            self.categories.copy(),
-            ordered=False,
-            name=name,
-        )
+
+        with ignore_pandas_nan_categorical_warning():
+            return pd.Categorical.from_codes(
+                self.as_int_array(),
+                # We need to make a copy because pandas >= 0.17 fails if this
+                # buffer isn't writeable.
+                self.categories.copy(),
+                ordered=False,
+                name=name,
+            )
 
     def as_categorical_frame(self, index, columns, name=None):
         """

zipline/utils/pandas_utils.py

@@ -1,8 +1,10 @@
 """
 Utilities for working with pandas objects.
 """
+from contextlib import contextmanager
 from itertools import product
 import operator as op
+import warnings
 
 import pandas as pd
 from distutils.version import StrictVersion
@@ -162,6 +164,19 @@ def timedelta_to_integral_minutes(delta):
     return timedelta_to_integral_seconds(delta) // 60
 
 
+@contextmanager
+def ignore_pandas_nan_categorical_warning():
+    with warnings.catch_warnings():
+        # Pandas >= 0.18 doesn't like null-ish values in catgories, but
+        # avoiding that requires a broader change to how missing values are
+        # handled in pipeline, so for now just silence the warning.
+        warnings.filterwarnings(
+            'ignore',
+            category=FutureWarning,
+        )
+        yield
+
+
 # Remove when we drop support for 0.17
 if pandas_version >= StrictVersion('0.18'):
     def rolling_mean(arg,