You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by jb...@apache.org on 2019/09/30 18:16:32 UTC
[lucene-solr] branch SOLR-13105-visual updated: SOLR-13105: Update
regression docs
This is an automated email from the ASF dual-hosted git repository.
jbernste pushed a commit to branch SOLR-13105-visual
in repository https://gitbox.apache.org/repos/asf/lucene-solr.git
The following commit(s) were added to refs/heads/SOLR-13105-visual by this push:
new f7c51f4 SOLR-13105: Update regression docs
f7c51f4 is described below
commit f7c51f4c63f83ec5fbf8f90c55f52c1f1384e951
Author: Joel Bernstein <jb...@apache.org>
AuthorDate: Mon Sep 30 14:16:09 2019 -0400
SOLR-13105: Update regression docs
---
.../src/images/math-expressions/knnRegress.png | Bin 265283 -> 245974 bytes
.../src/images/math-expressions/linear.png | Bin 253504 -> 250920 bytes
.../src/images/math-expressions/residual-plot.png | Bin 288454 -> 276638 bytes
.../src/images/math-expressions/residual-plot2.png | Bin 285505 -> 289663 bytes
solr/solr-ref-guide/src/machine-learning.adoc | 6 ++
solr/solr-ref-guide/src/regression.adoc | 66 ++++++++++-----------
6 files changed, 39 insertions(+), 33 deletions(-)
diff --git a/solr/solr-ref-guide/src/images/math-expressions/knnRegress.png b/solr/solr-ref-guide/src/images/math-expressions/knnRegress.png
index eb1719f..ddc85de 100644
Binary files a/solr/solr-ref-guide/src/images/math-expressions/knnRegress.png and b/solr/solr-ref-guide/src/images/math-expressions/knnRegress.png differ
diff --git a/solr/solr-ref-guide/src/images/math-expressions/linear.png b/solr/solr-ref-guide/src/images/math-expressions/linear.png
index fcf5d80..007d0d6 100644
Binary files a/solr/solr-ref-guide/src/images/math-expressions/linear.png and b/solr/solr-ref-guide/src/images/math-expressions/linear.png differ
diff --git a/solr/solr-ref-guide/src/images/math-expressions/residual-plot.png b/solr/solr-ref-guide/src/images/math-expressions/residual-plot.png
index 490f83e..d39d1cc 100644
Binary files a/solr/solr-ref-guide/src/images/math-expressions/residual-plot.png and b/solr/solr-ref-guide/src/images/math-expressions/residual-plot.png differ
diff --git a/solr/solr-ref-guide/src/images/math-expressions/residual-plot2.png b/solr/solr-ref-guide/src/images/math-expressions/residual-plot2.png
index c42aa83..97b6cb1 100644
Binary files a/solr/solr-ref-guide/src/images/math-expressions/residual-plot2.png and b/solr/solr-ref-guide/src/images/math-expressions/residual-plot2.png differ
diff --git a/solr/solr-ref-guide/src/machine-learning.adoc b/solr/solr-ref-guide/src/machine-learning.adoc
index ecd0221..11fc388 100644
--- a/solr/solr-ref-guide/src/machine-learning.adoc
+++ b/solr/solr-ref-guide/src/machine-learning.adoc
@@ -360,6 +360,12 @@ Below is an example of the `knnRegress` function. In this example 10,000 random
are taken, each containing the variables `filesize_d`, `service_d` and `response_d`. The pairs of
`filesize_d` and `service_d` will be used to predict the value of `response_d`.
+
+image::images/math-expressions/knnRegress.png[]
+
+
+
+
[source,text]
----
let(samples=random(collection1, q="*:*", rows="10000", fl="filesize_d, service_d, response_d"),
diff --git a/solr/solr-ref-guide/src/regression.adoc b/solr/solr-ref-guide/src/regression.adoc
index 08d193b..5b73935 100644
--- a/solr/solr-ref-guide/src/regression.adoc
+++ b/solr/solr-ref-guide/src/regression.adoc
@@ -39,7 +39,7 @@ analysis.
[source,text]
----
-let(a=random(testapp, q="*:*", rows="50000", fl="filesize_d, response_d"),
+let(a=random(logs, q="*:*", rows="50000", fl="filesize_d, response_d"),
x=col(a, filesize_d),
y=col(a, response_d),
r=regress(x, y))
@@ -91,7 +91,7 @@ the value of `response_d` for the `filesize_d` value of `40000`.
[source,text]
----
-let(a=random(testapp, q="*:*", rows="5000", fl="filesize_d, response_d"),
+let(a=random(logs, q="*:*", rows="5000", fl="filesize_d, response_d"),
x=col(a, filesize_d),
y=col(a, response_d),
r=regress(x, y),
@@ -126,7 +126,7 @@ In this case 5000 predictions are returned.
[source,text]
----
-let(a=random(testapp, q="*:*", rows="5000", fl="filesize_d, response_d"),
+let(a=random(logs, q="*:*", rows="5000", fl="filesize_d, response_d"),
x=col(a, filesize_d),
y=col(a, response_d),
r=regress(x, y),
@@ -171,7 +171,7 @@ Using *zplot* and the Zeppelin-Solr interpreter we can visualize both the observ
the same scatter plot. In the example below zplot is plotting the filesize_d observations on the
*x* axis, the response_d observations on the *y* access and the predictions on the *y1* access.
-image::images/math-expressions/regression-plot.png[]
+image::images/math-expressions/linear.png[]
=== Residuals
@@ -186,7 +186,7 @@ the array of residuals.
[source,text]
----
-let(a=random(testapp, q="*:*", rows="500", fl="filesize_d, response_d"),
+let(a=random(logs, q="*:*", rows="500", fl="filesize_d, response_d"),
x=col(a, filesize_d),
y=col(a, response_d),
r=regress(x, y),
@@ -196,7 +196,7 @@ let(a=random(testapp, q="*:*", rows="500", fl="filesize_d, response_d"),
When this expression is sent to the `/stream` handler it responds with:
-[source,json]
+[source,text]
----
{
"result-set": {
@@ -338,13 +338,13 @@ the first value represents a `filesize_d` of `40000` and the second value repres
[source,text]
----
-let(a=random(testapp, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
- b=col(a, filesize_d),
- c=col(a, load_d),
- d=col(a, response_d),
- e=transpose(matrix(b, c)),
- f=olsRegress(e, d),
- g=predict(f, array(40000, 4)))
+let(a=random(logs, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
+ x=col(a, filesize_d),
+ y=col(a, load_d),
+ z=col(a, response_d),
+ m=transpose(matrix(x, y)),
+ r=olsRegress(m, z),
+ p=predict(r, array(40000, 4)))
----
When this expression is sent to the `/stream` handler it responds with:
@@ -355,7 +355,7 @@ When this expression is sent to the `/stream` handler it responds with:
"result-set": {
"docs": [
{
- "g": 801.7725344814675
+ "p": 801.7725344814675
},
{
"EOF": true,
@@ -374,24 +374,24 @@ is passed to the `predict` function and it returns an array of predictions.
[source,text]
----
-let(a=random(testapp, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
- b=col(a, filesize_d),
- c=col(a, load_d),
- d=col(a, response_d),
- e=transpose(matrix(b, c)),
- f=olsRegress(e, d),
- g=predict(f, e))
+let(a=random(logs, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
+ x=col(a, filesize_d),
+ y=col(a, load_d),
+ z=col(a, response_d),
+ m=transpose(matrix(x, y)),
+ r=olsRegress(m, z),
+ p=predict(r, m))
----
When this expression is sent to the `/stream` handler it responds with:
-[source,json]
+[source,text]
----
{
"result-set": {
"docs": [
{
- "g": [
+ "p": [
917.7122088913725,
900.5418518783401,
871.7805676516689,
@@ -426,25 +426,25 @@ the predictions stored variable *`g`* are subtracted from observed values stored
[source,text]
----
-let(a=random(testapp, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
- b=col(a, filesize_d),
- c=col(a, load_d),
- d=col(a, response_d),
- e=transpose(matrix(b, c)),
- f=olsRegress(e, d),
- g=predict(f, e),
- r=ebeSubtract(d, g))
+let(a=random(logs, q="*:*", rows="5000", fl="filesize_d, load_d, response_d"),
+ x=col(a, filesize_d),
+ y=col(a, load_d),
+ z=col(a, response_d),
+ m=transpose(matrix(x, y)),
+ r=olsRegress(m, z),
+ p=predict(r, m),
+ e=ebeSubtract(z, p))
----
When this expression is sent to the `/stream` handler it responds with:
-[source,json]
+[source,text]
----
{
"result-set": {
"docs": [
{
- "r": [
+ "e": [
21.452271655340496,
9.647947283595727,
-23.02328008866334,