Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commita8d8218

Browse files
authored
fix and test preprocessing examples (#1520)
1 parentc3a8514 commita8d8218

File tree

14 files changed

+70
-26
lines changed

14 files changed

+70
-26
lines changed

‎.github/workflows/ubuntu-packages-and-docker-image.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ on:
44
workflow_dispatch:
55
inputs:
66
packageVersion:
7-
default:"2.8.2"
7+
default:"2.9.1"
88
jobs:
99
#
1010
# PostgresML extension.

‎pgml-cms/docs/resources/developer-docs/contributing.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -127,7 +127,7 @@ SELECT pgml.version();
127127
postgres=# select pgml.version();
128128
version
129129
-------------------
130-
2.7.4
130+
2.9.1
131131
(1 row)
132132
```
133133
{% endtab %}

‎pgml-cms/docs/resources/developer-docs/installation.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -132,7 +132,7 @@ CREATE EXTENSION
132132
pgml_test=# SELECT pgml.version();
133133
version
134134
---------
135-
2.7.4
135+
2.9.1
136136
(1 row)
137137
```
138138

‎pgml-cms/docs/resources/developer-docs/quick-start-with-docker.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -80,7 +80,7 @@ Time: 41.520 ms
8080
postgresml=# SELECT pgml.version();
8181
version
8282
---------
83-
2.7.13
83+
2.9.1
8484
(1 row)
8585
```
8686

‎pgml-cms/docs/resources/developer-docs/self-hosting/pooler.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -115,6 +115,6 @@ Type "help" for help.
115115
postgresml=> SELECT pgml.version();
116116
version
117117
---------
118-
2.7.9
118+
2.9.1
119119
(1 row)
120120
```

‎pgml-extension/Cargo.lock

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more aboutcustomizing how changed files appear on GitHub.

‎pgml-extension/Cargo.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[package]
22
name ="pgml"
3-
version ="2.9.0"
3+
version ="2.9.1"
44
edition ="2021"
55

66
[lib]
Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
-- load the diamonds dataset, that contains text categorical variables
2+
SELECTpgml.load_dataset('jdxcosta/diamonds');
3+
4+
-- view the data
5+
SELECT*FROM pgml."jdxcosta/diamonds"LIMIT10;
6+
7+
-- drop the Unamed column, since it's not useful for training (you could create a view instead)
8+
ALTERTABLE pgml."jdxcosta/diamonds" DROP COLUMN"Unnamed: 0";
9+
10+
-- train a model using preprocessors to scale the numeric variables, and target encode the categoricals
11+
SELECTpgml.train(
12+
project_name=>'Diamond prices',
13+
task=>'regression',
14+
relation_name=>'pgml.jdxcosta/diamonds',
15+
y_column_name=>'price',
16+
algorithm=>'lightgbm',
17+
preprocess=>'{
18+
"carat": {"scale": "standard"},
19+
"depth": {"scale": "standard"},
20+
"table": {"scale": "standard"},
21+
"cut": {"encode": "target", "scale": "standard"},
22+
"color": {"encode": "target", "scale": "standard"},
23+
"clarity": {"encode": "target", "scale": "standard"}
24+
}'
25+
);
26+
27+
-- run some predictions, notice we're passing a heterogeneous row (tuple) as input, rather than a homogenous ARRAY[].
28+
SELECT price,pgml.predict('Diamond prices', (carat, cut, color, clarity, depth,"table", x, y, z))AS prediction
29+
FROM pgml."jdxcosta/diamonds"
30+
LIMIT10;
31+
32+
-- This is a difficult dataset for more algorithms, which makes it a good challenge for preprocessing, and additional
33+
-- feature engineering. What's next?

‎pgml-extension/sql/pgml--2.9.0--2.9.1.sql

Whitespace-only changes.

‎pgml-extension/src/bindings/transformers/mod.rs

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -380,7 +380,7 @@ pub fn load_dataset(
380380
.ok_or(anyhow!("dataset `data` key is not an object"))?;
381381
let column_names = types
382382
.iter()
383-
.map(|(name, _type)|name.clone())
383+
.map(|(name, _type)|format!("\"{}\"", name))
384384
.collect::<Vec<String>>()
385385
.join(", ");
386386
let column_types = types
@@ -393,13 +393,14 @@ pub fn load_dataset(
393393
"int64" =>"INT8",
394394
"int32" =>"INT4",
395395
"int16" =>"INT2",
396+
"int8" =>"INT2",
396397
"float64" =>"FLOAT8",
397398
"float32" =>"FLOAT4",
398399
"float16" =>"FLOAT4",
399400
"bool" =>"BOOLEAN",
400401
_ =>bail!("unhandled dataset feature while reading dataset: {type_}"),
401402
};
402-
Ok(format!("{name} {type_}"))
403+
Ok(format!("\"{name}\" {type_}"))
403404
})
404405
.collect::<Result<Vec<String>>>()?
405406
.join(", ");
@@ -455,7 +456,7 @@ pub fn load_dataset(
455456
.into_datum(),
456457
)),
457458
"dict" |"list" => row.push((PgBuiltInOids::JSONBOID.oid(),JsonB(value.clone()).into_datum())),
458-
"int64" |"int32" |"int16" => row.push((
459+
"int64" |"int32" |"int16"|"int8"=> row.push((
459460
PgBuiltInOids::INT8OID.oid(),
460461
value
461462
.as_i64()

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp