FIX: Use rolling window for outlier detection

+ Rename find_outliers to split_outliers.
+ Make remove_ouliers call split_outliers internally.
+ Add "window" argument to both functions.
+ Add TODOs to call sites not setting window size explicitly.
+ Improve docstrings.

Change-Id: I24961e2859ddbfa62b543031284517c7389a2abb
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit 4f5872c1bb23873b3a93cb471aae8700d5ca029d)

1 files changed, 11 insertions, 6 deletions

diff --git a/resources/tools/presentation/generator_tables.py b/resources/tools/presentation/generator_tables.py
index 74579b0a9d..9b9f09f4be 100644
--- a/resources/tools/presentation/generator_tables.py
+++ b/resources/tools/presentation/generator_tables.py
@@ -25,7 +25,7 @@ from math import isnan
 from xml.etree import ElementTree as ET
 
 from errors import PresentationError
-from utils import mean, stdev, relative_change, remove_outliers, find_outliers
+from utils import mean, stdev, relative_change, remove_outliers, split_outliers
 
 
 def generate_tables(spec, data):
@@ -405,14 +405,16 @@ def table_performance_comparison(table, input_data):
         item = [tbl_dict[tst_name]["name"], ]
         if tbl_dict[tst_name]["ref-data"]:
             data_t = remove_outliers(tbl_dict[tst_name]["ref-data"],
-                                     table["outlier-const"])
+                                     outlier_constant=table["outlier-const"])
+            # TODO: Specify window size.
             item.append(round(mean(data_t) / 1000000, 2))
             item.append(round(stdev(data_t) / 1000000, 2))
         else:
             item.extend([None, None])
         if tbl_dict[tst_name]["cmp-data"]:
             data_t = remove_outliers(tbl_dict[tst_name]["cmp-data"],
-                                     table["outlier-const"])
+                                     outlier_constant=table["outlier-const"])
+            # TODO: Specify window size.
             item.append(round(mean(data_t) / 1000000, 2))
             item.append(round(stdev(data_t) / 1000000, 2))
         else:
@@ -594,14 +596,16 @@ def table_performance_comparison_mrr(table, input_data):
         item = [tbl_dict[tst_name]["name"], ]
         if tbl_dict[tst_name]["ref-data"]:
             data_t = remove_outliers(tbl_dict[tst_name]["ref-data"],
-                                     table["outlier-const"])
+                                     outlier_const=table["outlier-const"])
+            # TODO: Specify window size.
             item.append(round(mean(data_t) / 1000000, 2))
             item.append(round(stdev(data_t) / 1000000, 2))
         else:
             item.extend([None, None])
         if tbl_dict[tst_name]["cmp-data"]:
             data_t = remove_outliers(tbl_dict[tst_name]["cmp-data"],
-                                     table["outlier-const"])
+                                     outlier_const=table["outlier-const"])
+            # TODO: Specify window size.
             item.append(round(mean(data_t) / 1000000, 2))
             item.append(round(stdev(data_t) / 1000000, 2))
         else:
@@ -708,7 +712,8 @@ def table_performance_trending_dashboard(table, input_data):
             name = tbl_dict[tst_name]["name"]
 
             median = pd_data.rolling(window=win_size, min_periods=2).median()
-            trimmed_data, _ = find_outliers(pd_data, outlier_const=1.5)
+            trimmed_data, _ = split_outliers(pd_data, outlier_const=1.5,
+                                             window=win_size)
             stdev_t = pd_data.rolling(window=win_size, min_periods=2).std()
 
             rel_change_lst = [None, ]