adding few changes

rh-pre-commit.version: 2.2.0 rh-pre-commit.check-secrets: ENABLED
cloud-bulldozer · Aug 26, 2024 · 666e714 · 666e714
1 parent 3352126
commit 666e714
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 11 deletions.
diff --git a/pkg/algorithms/algorithm.py b/pkg/algorithms/algorithm.py
@@ -113,10 +113,10 @@ def group_change_points_by_time(
         changes: List[ChangePoint] = []
         for metric in change_points.keys():
             changes += change_points[metric]
+
         changes.sort(key=lambda c: c.index)
         points = []
         for k, g in groupby(changes, key=lambda c: c.index):
-
             cp = ChangePointGroup(
                 index=k,
                 time=series.time[k],
@@ -126,6 +126,7 @@ def group_change_points_by_time(
                 changes=list(g),
             )
             points.append(cp)
+
         return points
 
     def setup_series(self) -> Series:
@@ -173,5 +174,4 @@ def output(self, output_format) -> Union[Any,None]:
             return self.output_text()
         if output_format == cnsts.JUNIT:
             return self.output_junit()
-
         raise ValueError("Unsupported output format {output_format} selected")
diff --git a/pkg/algorithms/cmr/cmr.py b/pkg/algorithms/cmr/cmr.py
@@ -1,4 +1,4 @@
-"""EDivisive Algorithm from hunter"""
+"""CMR Algorithm"""
 
 # pylint: disable = line-too-long
 from typing import List
@@ -27,24 +27,22 @@ def _analyze(self):
             change_points_by_metric: list of ChangePoints
         """
         logger_instance = SingletonLogger.getLogger("Orion")
-        logger_instance.info("Starting analysis using Isolation Forest")
+        logger_instance.info("Starting analysis using CMR")
         self.dataframe["timestamp"] = pd.to_datetime(self.dataframe["timestamp"])
         self.dataframe["timestamp"] = self.dataframe["timestamp"].astype(int) // 10**9
 
-        logger_instance.info('data frame ' + str(self.dataframe))
-
         # if larger than 2 rows, need to get the mean of 0 through -2
-        self.dataframe = self.combine_data_frames( self.dataframe)
+        self.dataframe = self.combine_and_average_runs( self.dataframe)
 
         series= self.setup_series()
         tolerancy = 20
-        metric_columns = self.metrics_config.keys()
-        df, change_points_by_metric = self.run_cmr(tolerancy, metric_columns, self.dataframe)
+
+        df, change_points_by_metric = self.run_cmr(tolerancy, self.dataframe)
         series.data= df
         return series, change_points_by_metric
 
 
-    def run_cmr(self, tolerancy: int,metric_columns: List[str],  dataframe_list: pd.DataFrame):
+    def run_cmr(self, tolerancy: int, dataframe_list: pd.DataFrame):
         """
         Generate the percent difference in a 2 row dataframe
 
@@ -56,6 +54,7 @@ def run_cmr(self, tolerancy: int,metric_columns: List[str],  dataframe_list: pd.
         Returns:
             pd.Dataframe, dict[metric_name, ChangePoint]: Returned data frame and change points
         """
+        metric_columns = self.metrics_config.keys()
         change_points_by_metric={ k:[] for k in metric_columns }
         max_date_time = pd.Timestamp.max.to_pydatetime()
         max_time = max_date_time.timestamp()
@@ -90,7 +89,7 @@ def run_cmr(self, tolerancy: int,metric_columns: List[str],  dataframe_list: pd.
         # based on change point generate pass/fail
         return dataframe_list, change_points_by_metric
 
-    def combine_data_frames(self, dataFrame: pd.DataFrame):
+    def combine_and_average_runs(self, dataFrame: pd.DataFrame):
         """
         If more than 1 previous run, mean data together into 1 single row
         Combine with current run into 1 data frame (current run being -1 index)