Convert all workload_type values to lowercase before comparision

RedHatInsights · Dec 13, 2024 · 0e884ac · 0e884ac
1 parent 8f3e347
commit 0e884ac
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 7 deletions.
diff --git a/.~lock.output.csv# b/.~lock.output.csv#
@@ -0,0 +1 @@
+,amit,fedora,13.12.2024 18:49,file:///home/amit/.config/libreoffice/4;
diff --git a/internal/utils/aggregator.go b/internal/utils/aggregator.go
@@ -31,7 +31,6 @@ func Aggregate_data(df dataframe.DataFrame) (dataframe.DataFrame, error) {
 	if df.Nrow() == 0 {
 		return df, fmt.Errorf("no valid records present in CSV to process further")
 	}
-
 	df = determine_k8s_object_type(df)
 
 	dfGroups := df.GroupBy(
@@ -82,8 +81,8 @@ func Aggregate_data(df dataframe.DataFrame) (dataframe.DataFrame, error) {
 	return df, nil
 }
 
-func filter_valid_csv_records(main_df dataframe.DataFrame) (dataframe.DataFrame, int) {
-	df := main_df.FilterAggregation(
+func filter_valid_csv_records(mainDf dataframe.DataFrame) (dataframe.DataFrame, int) {
+	df := mainDf.FilterAggregation(
 		dataframe.And,
 		dataframe.F{Colname: "memory_rss_usage_container_sum", Comparator: series.GreaterEq, Comparando: 0},
 		dataframe.F{Colname: "memory_rss_usage_container_max", Comparator: series.GreaterEq, Comparando: 0},
@@ -101,22 +100,43 @@ func filter_valid_csv_records(main_df dataframe.DataFrame) (dataframe.DataFrame,
 		dataframe.F{Colname: "owner_name", Comparator: series.Neq, Comparando: ""},
 		dataframe.F{Colname: "owner_kind", Comparator: series.Neq, Comparando: "<none>"},
 		dataframe.F{Colname: "owner_name", Comparator: series.Neq, Comparando: "<none>"},
+		dataframe.F{Colname: "workload_type", Comparator: series.Neq, Comparando: "<none>"},
+		dataframe.F{Colname: "workload_type", Comparator: series.Neq, Comparando: ""},
+	)
+
+	// Change the case of all workload_type to lowercase
+	lcaseWorkloadTypes := df.Rapply(func(s series.Series) series.Series {
+		columns := df.Names()
+		indexOfWorkloadType := findInStringSlice("workload_type", columns)
+		workloadType := s.Elem(indexOfWorkloadType).String()
+		lcaseWorkloadType := strings.ToLower(workloadType)
+		return series.Strings([]string{lcaseWorkloadType})
+	})
+
+	// Delete existing workload_type column
+	df = df.Mutate(df.Col("workload_type")).Drop("workload_type")
+
+	// Rename lowercase converted column to workload_type
+	df = df.Mutate(lcaseWorkloadTypes.Col("X0")).Rename("workload_type", "X0")
+
+	// The Replicaset and Replicationcontroller has been removed from filter
+	// as these types do not get populated in workload_type column
+	df = df.FilterAggregation(
+		dataframe.And,
 		dataframe.F{
 			Colname:    "workload_type",
 			Comparator: series.In,
 			Comparando: []string{
 				w.Daemonset.String(),
 				w.Deployment.String(),
 				w.Deploymentconfig.String(),
-				w.Replicaset.String(),
-				w.Replicationcontroller.String(),
 				w.Statefulset.String(),
 			}},
 	)
 
-	no_of_dropped_records := main_df.Nrow() - df.Nrow()
+	noOfDroppedRecords := mainDf.Nrow() - df.Nrow()
 
-	return df, no_of_dropped_records
+	return df, noOfDroppedRecords
 }
 
 func determine_k8s_object_type(df dataframe.DataFrame) dataframe.DataFrame {
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		,amit,fedora,13.12.2024 18:49,file:///home/amit/.config/libreoffice/4;