From a7a48d3593f414581cd87275c70031be88e3daa4 Mon Sep 17 00:00:00 2001
From: Kyle Brandt <kyle@kbrandt.com>
Date: Wed, 17 Feb 2016 10:08:56 -0500
Subject: [PATCH] cmd/bosun: Add linelr func

for visualizing a linear regression line
---
 cmd/bosun/expr/funcs.go | 42 +++++++++++++++++++++++++++++++++++++++++
 docs/expressions.md     | 12 ++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/cmd/bosun/expr/funcs.go b/cmd/bosun/expr/funcs.go
index 43ae37fde7..89d0a0af6a 100644
--- a/cmd/bosun/expr/funcs.go
+++ b/cmd/bosun/expr/funcs.go
@@ -178,6 +178,12 @@ var builtins = map[string]parse.Func{
 		Tags:   tagFirst,
 		F:      Forecast_lr,
 	},
+	"linelr": {
+		Args:   []models.FuncType{models.TypeSeriesSet, models.TypeString},
+		Return: models.TypeSeriesSet,
+		Tags:   tagFirst,
+		F:      Line_lr,
+	},
 	"last": {
 		Args:   []models.FuncType{models.TypeSeriesSet},
 		Return: models.TypeNumberSet,
@@ -1331,6 +1337,42 @@ func (e *State) forecast_lr(dps Series, args ...float64) float64 {
 	return s.Seconds()
 }
 
+func Line_lr(e *State, T miniprofiler.Timer, series *Results, d string) (*Results, error) {
+	dur, err := opentsdb.ParseDuration(d)
+	if err != nil {
+		return series, err
+	}
+	for _, res := range series.Results {
+		res.Value = line_lr(res.Value.(Series), time.Duration(dur))
+		res.Group.Merge(opentsdb.TagSet{"regression": "line"})
+	}
+	return series, nil
+}
+
+// line_lr generates a series representing the line up to duration in the future.
+func line_lr(dps Series, d time.Duration) Series {
+	var x []float64
+	var y []float64
+	sortedDPS := NewSortedSeries(dps)
+	var maxT time.Time
+	if len(sortedDPS) > 1 {
+		maxT = sortedDPS[len(sortedDPS)-1].T
+	}
+	for _, v := range sortedDPS {
+		xv := float64(v.T.Unix())
+		x = append(x, xv)
+		y = append(y, v.V)
+	}
+	var slope, intercept, _, _, _, _ = stats.LinearRegression(x, y)
+	s := make(Series)
+	// First point in the regression line
+	s[maxT] = float64(maxT.Unix())*slope + intercept
+	// Last point
+	last := maxT.Add(d)
+	s[last] = float64(last.Unix())*slope + intercept
+	return s
+}
+
 func Percentile(e *State, T miniprofiler.Timer, series *Results, p *Results) (r *Results, err error) {
 	return reduce(e, T, series, percentile, p)
 }
diff --git a/docs/expressions.md b/docs/expressions.md
index c5e90f1c7f..c5ec718ee6 100644
--- a/docs/expressions.md
+++ b/docs/expressions.md
@@ -311,6 +311,18 @@ Returns the first (least recent) data point in each series.
 
 Returns the number of seconds until a linear regression of each series will reach y_val.
 
+## linelr(seriesSet, d Duration) seriesSet
+
+Linelr return the linear regression line from the end of each series to end+duration (an [OpenTSDB duration string](http://opentsdb.net/docs/build/html/user_guide/query/dates.html)). It adds `regression=line` to the group / tagset. It is meant for graphing with expressions, for example:
+
+```
+$d = "1w"
+$q = q("avg:1h-avg:os.disk.fs.percent_free{}{host=ny-tsdb*,disk=/mnt*}", "2w", "")
+$line = linelr($q, "3n")
+$m = merge($q, $line)
+$m
+```
+
 ## last(seriesSet) numberSet
 
 Returns the last (most recent) data point in each series.