This is an automated email from the ASF dual-hosted git repository.
myui pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/incubator-hivemall-site.git
commit 13e887a89eb23fb824abc1a11ec07a0c1df9f482
Author: Makoto Yui <m...@apache.org>
AuthorDate: Wed Oct 23 18:12:27 2019 +0900
Updated function docs
---
userguide/misc/funcs.html | 129 ++++++++++++-------------------------
userguide/misc/generic_funcs.html | 131 ++++++++++++--------------------------
2 files changed, 82 insertions(+), 178 deletions(-)
diff --git a/userguide/misc/funcs.html b/userguide/misc/funcs.html
index 9673640..ff974bf 100644
--- a/userguide/misc/funcs.html
+++ b/userguide/misc/funcs.html
@@ -2077,13 +2077,13 @@
- <li class="header">Part XIII - Hivemall on Spark</li>
+ <li class="header">Part XIII - Hivemall on SparkSQL</li>
- <li class="chapter " data-level="13.1"
data-path="../spark/getting_started/">
+ <li class="chapter " data-level="13.1"
data-path="../spark/getting_started/README.md">
- <a href="../spark/getting_started/">
+ <span>
<b>13.1.</b>
@@ -2133,27 +2133,12 @@
<ul class="articles">
- <li class="chapter " data-level="13.2.1"
data-path="../spark/binaryclass/a9a_df.html">
-
- <a href="../spark/binaryclass/a9a_df.html">
-
-
- <b>13.2.1.</b>
-
- a9a Tutorial for DataFrame
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.2.2"
data-path="../spark/binaryclass/a9a_sql.html">
+ <li class="chapter " data-level="13.2.1"
data-path="../spark/binaryclass/a9a_sql.html">
<a href="../spark/binaryclass/a9a_sql.html">
- <b>13.2.2.</b>
+ <b>13.2.1.</b>
a9a Tutorial for SQL
@@ -2184,27 +2169,12 @@
<ul class="articles">
- <li class="chapter " data-level="13.3.1"
data-path="../spark/regression/e2006_df.html">
-
- <a href="../spark/regression/e2006_df.html">
-
-
- <b>13.3.1.</b>
-
- E2006-tfidf Regression Tutorial for DataFrame
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.3.2"
data-path="../spark/regression/e2006_sql.html">
+ <li class="chapter " data-level="13.3.1"
data-path="../spark/regression/e2006_sql.html">
<a href="../spark/regression/e2006_sql.html">
- <b>13.3.2.</b>
+ <b>13.3.1.</b>
E2006-tfidf Regression Tutorial for SQL
@@ -2219,57 +2189,6 @@
</li>
- <li class="chapter " data-level="13.4"
data-path="../spark/misc/misc.html">
-
- <a href="../spark/misc/misc.html">
-
-
- <b>13.4.</b>
-
- Generic Features
-
- </a>
-
-
-
- <ul class="articles">
-
-
- <li class="chapter " data-level="13.4.1"
data-path="../spark/misc/topk_join.html">
-
- <a href="../spark/misc/topk_join.html">
-
-
- <b>13.4.1.</b>
-
- Top-k Join Processing
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.4.2"
data-path="../spark/misc/functions.html">
-
- <a href="../spark/misc/functions.html">
-
-
- <b>13.4.2.</b>
-
- Other Utility Functions
-
- </a>
-
-
-
- </li>
-
-
- </ul>
-
- </li>
-
@@ -2955,6 +2874,38 @@ bloom <span class="hljs-keyword">as</span> (
</li>
<li><p><code>train_randomforest_regressor(array<double|string> features,
double target [, string options])</code> - Returns a relation consists of
<int model_id, int model_type, string model, array<double>
var_importance, double oob_errors, int oob_tests></p>
</li>
+<li><p><code>decision_path(string modelId, string model,
array<double|string> features [, const string options] [, optional
array<string> featureNames=null, optional array<string>
classNames=null])</code> - Returns a decision path for each prediction in
array<string></p>
+<pre><code class="lang-sql">SELECT
+ t.passengerid,
+ decision_path(m.model_id, m.model, t.features, '-classification')
+FROM
+ model_rf m
+ LEFT OUTER JOIN
+ test_rf t;
+> | 892 | ["2 [0.0] = 0.0","0 [3.0] = 3.0","1
[696.0] != 107.0","7 [7.8292] <= 7.9104","1 [696.0] !=
828.0","1 [696.0] != 391.0","0 [0.961038961038961,
0.03896103896103896]"] |
+
+-- Show 100 frequent branches
+WITH tmp as (
+ SELECT
+ decision_path(m.model_id, m.model, t.features, '-classification
-no_verbose -no_leaf',
array('pclass','name','sex','age','sibsp','parch','ticket','fare','cabin','embarked'),
array('no','yes')) as path
+ FROM
+ model_rf m
+ LEFT OUTER JOIN -- CROSS JOIN
+ test_rf t
+)
+select
+ r.branch,
+ count(1) as cnt
+from
+ tmp l
+ LATERAL VIEW explode(l.path) r as branch
+group by
+ r.branch
+order by
+ cnt desc
+limit 100;
+</code></pre>
+</li>
<li><p><code>guess_attribute_types(ANY, ...)</code> - Returns attribute
types</p>
<pre><code class="lang-sql">select guess_attribute_types(*) from train limit 1;
> Q,Q,C,C,C,C,Q,C,C,C,Q,C,Q,Q,Q,Q,C,Q
@@ -3057,7 +3008,7 @@ Apache Hivemall is an effort undergoing incubation at The
Apache Software Founda
<script>
var gitbook = gitbook || [];
gitbook.push(function() {
- gitbook.page.hasChanged({"page":{"title":"List of
Functions","level":"1.3","depth":1,"next":{"title":"Tips for Effective
Hivemall","level":"1.4","depth":1,"path":"tips/README.md","ref":"tips/README.md","articles":[{"title":"Explicit
add_bias() for better
prediction","level":"1.4.1","depth":2,"path":"tips/addbias.md","ref":"tips/addbias.md","articles":[]},{"title":"Use
rand_amplify() to better prediction
results","level":"1.4.2","depth":2,"path":"tips/rand_amplify.md","ref":"t [...]
+ gitbook.page.hasChanged({"page":{"title":"List of
Functions","level":"1.3","depth":1,"next":{"title":"Tips for Effective
Hivemall","level":"1.4","depth":1,"path":"tips/README.md","ref":"tips/README.md","articles":[{"title":"Explicit
add_bias() for better
prediction","level":"1.4.1","depth":2,"path":"tips/addbias.md","ref":"tips/addbias.md","articles":[]},{"title":"Use
rand_amplify() to better prediction
results","level":"1.4.2","depth":2,"path":"tips/rand_amplify.md","ref":"t [...]
});
</script>
</div>
diff --git a/userguide/misc/generic_funcs.html
b/userguide/misc/generic_funcs.html
index 592458e..9ff13d8 100644
--- a/userguide/misc/generic_funcs.html
+++ b/userguide/misc/generic_funcs.html
@@ -2077,13 +2077,13 @@
- <li class="header">Part XIII - Hivemall on Spark</li>
+ <li class="header">Part XIII - Hivemall on SparkSQL</li>
- <li class="chapter " data-level="13.1"
data-path="../spark/getting_started/">
+ <li class="chapter " data-level="13.1"
data-path="../spark/getting_started/README.md">
- <a href="../spark/getting_started/">
+ <span>
<b>13.1.</b>
@@ -2133,27 +2133,12 @@
<ul class="articles">
- <li class="chapter " data-level="13.2.1"
data-path="../spark/binaryclass/a9a_df.html">
-
- <a href="../spark/binaryclass/a9a_df.html">
-
-
- <b>13.2.1.</b>
-
- a9a Tutorial for DataFrame
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.2.2"
data-path="../spark/binaryclass/a9a_sql.html">
+ <li class="chapter " data-level="13.2.1"
data-path="../spark/binaryclass/a9a_sql.html">
<a href="../spark/binaryclass/a9a_sql.html">
- <b>13.2.2.</b>
+ <b>13.2.1.</b>
a9a Tutorial for SQL
@@ -2184,27 +2169,12 @@
<ul class="articles">
- <li class="chapter " data-level="13.3.1"
data-path="../spark/regression/e2006_df.html">
-
- <a href="../spark/regression/e2006_df.html">
-
-
- <b>13.3.1.</b>
-
- E2006-tfidf Regression Tutorial for DataFrame
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.3.2"
data-path="../spark/regression/e2006_sql.html">
+ <li class="chapter " data-level="13.3.1"
data-path="../spark/regression/e2006_sql.html">
<a href="../spark/regression/e2006_sql.html">
- <b>13.3.2.</b>
+ <b>13.3.1.</b>
E2006-tfidf Regression Tutorial for SQL
@@ -2219,57 +2189,6 @@
</li>
- <li class="chapter " data-level="13.4"
data-path="../spark/misc/misc.html">
-
- <a href="../spark/misc/misc.html">
-
-
- <b>13.4.</b>
-
- Generic Features
-
- </a>
-
-
-
- <ul class="articles">
-
-
- <li class="chapter " data-level="13.4.1"
data-path="../spark/misc/topk_join.html">
-
- <a href="../spark/misc/topk_join.html">
-
-
- <b>13.4.1.</b>
-
- Top-k Join Processing
-
- </a>
-
-
-
- </li>
-
- <li class="chapter " data-level="13.4.2"
data-path="../spark/misc/functions.html">
-
- <a href="../spark/misc/functions.html">
-
-
- <b>13.4.2.</b>
-
- Other Utility Functions
-
- </a>
-
-
-
- </li>
-
-
- </ul>
-
- </li>
-
@@ -2399,6 +2318,40 @@
</div><!-- tocstop -->
<h1 id="array">Array</h1>
<ul>
+<li><p><code>arange([int start=0, ] int stop, [int step=1])</code> - Return
evenly spaced values within a given interval</p>
+<pre><code class="lang-sql">SELECT arange(5), arange(1, 5), arange(1, 5, 1),
arange(0, 5, 1);
+> [0,1,2,3,4] [1,2,3,4] [1,2,3,4] [0,1,2,3,4]
+
+SELECT arange(1, 6, 2);
+> 1, 3, 5
+
+SELECT arange(-1, -6, 2);
+> -1, -3, -5
+</code></pre>
+</li>
+<li><p><code>argmax(array<T> a)</code> - Returns the first index of the
maximum value</p>
+<pre><code class="lang-sql">SELECT argmax(array(5,2,0,1));
+> 0
+</code></pre>
+</li>
+<li><p><code>argmin(array<T> a)</code> - Returns the first index of the
minimum value</p>
+<pre><code class="lang-sql">SELECT argmin(array(5,2,0,1));
+> 2
+</code></pre>
+</li>
+<li><p><code>argrank(array<ANY> a)</code> - Returns the indices that
would sort an array.</p>
+<pre><code class="lang-sql">SELECT argrank(array(5,2,0,1)),
argsort(argsort(array(5,2,0,1)));
+> [3, 2, 0, 1] [3, 2, 0, 1]
+</code></pre>
+</li>
+<li><p><code>argsort(array<ANY> a)</code> - Returns the indices that
would sort an array.</p>
+<pre><code class="lang-sql">SELECT argsort(array(5,2,0,1));
+> 2, 3, 1, 0
+
+SELECT array_slice(array(5,2,0,1), argsort(array(5,2,0,1)));
+> 0, 1, 2, 5
+</code></pre>
+</li>
<li><p><code>array_append(array<T> arr, T elem)</code> - Append an
element to the end of an array</p>
<pre><code class="lang-sql"><span class="hljs-keyword">SELECT</span>
array_append(<span class="hljs-built_in">array</span>(<span
class="hljs-number">1</span>,<span class="hljs-number">2</span>),<span
class="hljs-number">3</span>);
1,2,3
@@ -3183,7 +3136,7 @@ Apache Hivemall is an effort undergoing incubation at The
Apache Software Founda
<script>
var gitbook = gitbook || [];
gitbook.push(function() {
- gitbook.page.hasChanged({"page":{"title":"List of Generic Hivemall
Functions","level":"2.1","depth":1,"next":{"title":"Efficient Top-K Query
Processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"previous":{"title":"Map-side
join causes ClassCastException on
Tez","level":"1.6.5","depth":2,"path":"troubleshooting/mapjoin_classcastex.md","ref":"troubleshooting/mapjoin_classcastex.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme
[...]
+ gitbook.page.hasChanged({"page":{"title":"List of Generic Hivemall
Functions","level":"2.1","depth":1,"next":{"title":"Efficient Top-K Query
Processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"previous":{"title":"Map-side
join causes ClassCastException on
Tez","level":"1.6.5","depth":2,"path":"troubleshooting/mapjoin_classcastex.md","ref":"troubleshooting/mapjoin_classcastex.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme
[...]
});
</script>
</div>
