Add benchmarks for object deduplication

Change-Id: I834e91d6a2474bfc67c504dc1bd0497c08869563

python/benchmarks/convert_pandas.py

@@ -17,6 +17,8 @@
 
 import numpy as np
 import pandas as pd
+import pandas.util.testing as tm
+
 import pyarrow as pa
 
 
@@ -50,6 +52,25 @@ class PandasConversionsFromArrow(PandasConversionsBase):
         self.arrow_data.to_pandas()
 
 
+class ToPandasStrings(object):
+
+    params = ((100, 10000, 100000, 500000),)
+    string_length = 25
+    num_elements = 1000 * 1000
+
+    def setup(self, nunique):
+        unique_values = [tm.rands(self.string_length) for i in range(nunique)]
+        values = unique_values * (self.num_elements // nunique)
+        self.arr = pa.array(values, type=pa.string())
+        self.table = pa.Table.from_arrays([self.arr], ['f0'])
+
+    def time_to_pandas_dedup(self, nunique):
+        self.arr.to_pandas()
+
+    def time_to_pandas_no_dedup(self, nunique):
+        self.arr.to_pandas(deduplicate_objects=False)
+
+
 class ZeroCopyPandasRead(object):
 
     def setup(self):

python/pyarrow/compat.py

@@ -192,11 +192,15 @@ def _iterate_python_module_paths(package_name):
             for finder in sys.meta_path:
                 try:
                     spec = finder.find_spec(absolute_name, None)
-                except AttributeError:
+                except (AttributeError, TypeError):
                     # On Travis (Python 3.5) the above produced:
                     # AttributeError: 'VendorImporter' object has no
                     # attribute 'find_spec'
+                    #
+                    # ARROW-4117: When running "asv dev", TypeError is raised
+                    # due to the meta-importer
                     spec = None
+
                 if spec is not None:
                     break