Fix profiler

eapframework · Dec 6, 2019 · c44bc33 · c44bc33
1 parent 2dbf018
commit c44bc33
Show file tree

Hide file tree

Showing 6 changed files with 5,875 additions and 604 deletions.
diff --git a/optimus/profiler/profiler.py b/optimus/profiler/profiler.py
@@ -396,7 +396,7 @@ def columns_stats(self, df, columns, buckets=10, infer=False, relative_error=REL
         logger.print("Processing Stats For columns...")
 
         # Get columns data types. This is necessary to make the pertinent histogram calculations.
-        count_by_data_type = df.cols.count_by_dtypes(columns, infer=infer, mismatch=mismatch)
+        count_by_data_type = df.cols.count_by_dtypes(columns, infer=infer)
 
         count_by_data_type_no_mismatch = copy.deepcopy(count_by_data_type)
 

diff --git a/tests/creator/creator-profiler.ipynb b/tests/creator/creator-profiler.ipynb
diff --git a/tests/creator/creator-profiler.py b/tests/creator/creator-profiler.py
@@ -151,4 +151,10 @@ def func(col_name, attrs):
 import json
 json.dumps("{'name'=a'a}")
 
+from optimus.profiler.profiler import Profiler
+
+op.profiler.run(source_df, "*")
+
+source_df.cols.range("height(ft)")
+