Skip to content

Commit dc36e28

Browse files
katxiaokatxiao
committed
make release-tag: Merge branch 'master' into stable
2 parents 74bfda8 + f4ba53c commit dc36e28

File tree

74 files changed

+3321
-236
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

74 files changed

+3321
-236
lines changed

‎.github/ISSUE_TEMPLATE/feature_request.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
name: Feature request
33
about: Request a new feature that you would like to see implemented in SDMetrics
44
title: ''
5-
labels: new feature, pending review
5+
labels: feature request, pending review
66
assignees: ''
77

88
---

‎.github/workflows/integration.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ jobs:
1010
strategy:
1111
matrix:
1212
python-version: [3.6, 3.7, 3.8, 3.9]
13-
os: [ubuntu-latest, macos-10.15, windows-latest]
13+
os: [ubuntu-latest, macos-latest, windows-latest]
1414
steps:
1515
- uses: actions/checkout@v1
1616
- name: Set up Python ${{ matrix.python-version }}

‎.github/workflows/minimum.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ jobs:
1010
strategy:
1111
matrix:
1212
python-version: [3.6, 3.7, 3.8, 3.9]
13-
os: [ubuntu-latest, macos-10.15, windows-latest]
13+
os: [ubuntu-latest, macos-latest, windows-latest]
1414
steps:
1515
- uses: actions/checkout@v1
1616
- name: Set up Python ${{ matrix.python-version }}

‎.github/workflows/readme.yml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,11 +10,11 @@ jobs:
1010
strategy:
1111
matrix:
1212
python-version: [3.6, 3.7, 3.8, 3.9]
13-
os: [ubuntu-latest, macos-10.15] # skip windows bc rundoc fails
13+
os: [ubuntu-latest, macos-latest] # skip windows bc rundoc fails
1414
steps:
1515
- uses: actions/checkout@v1
1616
- name: Set up Python ${{ matrix.python-version }}
17-
uses: actions/setup-python@v1
17+
uses: actions/setup-python@v2
1818
with:
1919
python-version: ${{ matrix.python-version }}
2020
- name: Install dependencies

‎.github/workflows/unit.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ jobs:
1010
strategy:
1111
matrix:
1212
python-version: [3.6, 3.7, 3.8, 3.9]
13-
os: [ubuntu-latest, macos-10.15, windows-latest]
13+
os: [ubuntu-latest, macos-latest, windows-latest]
1414
steps:
1515
- uses: actions/checkout@v1
1616
- name: Set up Python ${{ matrix.python-version }}

‎HISTORY.md‎

Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,39 @@
11
# History
22

3+
## v0.6.0 - 2022-08-12
4+
5+
This release removes SDMetric's dependency on the RDT library, and also introduces new quality and diagnostic metrics. Additionally, we introduce a new `compute_breakdown` method that returns a breakdown of metric results.
6+
7+
### New Features
8+
* Handle null values correctly - Issue [#194](https://github.com/sdv-dev/SDMetrics/issues/194) by @katxiao
9+
* Add wrapper classes for new single and multi table metrics - Issue [#169](https://github.com/sdv-dev/SDMetrics/issues/169) by @katxiao
10+
* Add CorrelationSimilarity metric - Issue [#143](https://github.com/sdv-dev/SDMetrics/issues/143) by @katxiao
11+
* Add CardinalityShapeSimilarity metric - Issue [#160](https://github.com/sdv-dev/SDMetrics/issues/160) by @katxiao
12+
* Add CardinalityStatisticSimilarity metric - Issue [#145](https://github.com/sdv-dev/SDMetrics/issues/145) by @katxiao
13+
* Add ContingencySimilarity Metric - Issue [#159](https://github.com/sdv-dev/SDMetrics/issues/159) by @katxiao
14+
* Add TVComplement metric - Issue [#142](https://github.com/sdv-dev/SDMetrics/issues/142) by @katxiao
15+
* Add MissingValueSimilarity metric - Issue [#139](https://github.com/sdv-dev/SDMetrics/issues/139) by @katxiao
16+
* Add CategoryCoverage metric - Issue [#140](https://github.com/sdv-dev/SDMetrics/issues/140) by @katxiao
17+
* Add compute breakdown column for single column - Issue [#152](https://github.com/sdv-dev/SDMetrics/issues/152) by @katxiao
18+
* Add BoundaryAdherence metric - Issue [#138](https://github.com/sdv-dev/SDMetrics/issues/138) by @katxiao
19+
* Get KSComplement Score Breakdown - Issue [#130](https://github.com/sdv-dev/SDMetrics/issues/130) by @katxiao
20+
* Add StatisticSimilarity Metric - Issue [#137](https://github.com/sdv-dev/SDMetrics/issues/130) by @katxiao
21+
* New features for KSTest.compute - Issue [#129](https://github.com/sdv-dev/SDMetrics/issues/129) by @amontanez24
22+
23+
### Internal Improvements
24+
* Add integration tests and fixes - Issue [#183](https://github.com/sdv-dev/SDMetrics/issues/183) by @katxiao
25+
* Remove rdt hypertransformer dependency in timeseries metrics - Issue [#176](https://github.com/sdv-dev/SDMetrics/issues/178) by @katxiao
26+
* Replace rdt LabelEncoder with sklearn - Issue [#178](https://github.com/sdv-dev/SDMetrics/issues/178) by @katxiao
27+
* Remove rdt as a dependency - Issue [#182](https://github.com/sdv-dev/SDMetrics/issues/182) by @katxiao
28+
* Use sklearn's OneHotEncoder instead of rdt - Issue [#170](https://github.com/sdv-dev/SDMetrics/issues/170) by @katxiao
29+
* Remove KSTestExtended - Issue [#180](https://github.com/sdv-dev/SDMetrics/issues/180) by @katxiao
30+
* Remove TSFClassifierEfficacy and TSFCDetection metrics - Issue [#171](https://github.com/sdv-dev/SDMetrics/issues/171) by @katxiao
31+
* Update the default tags for a feature request - Issue [#172](https://github.com/sdv-dev/SDMetrics/issues/172) by @katxiao
32+
* Bump github macos version - Issue [#174](https://github.com/sdv-dev/SDMetrics/issues/174) by @katxiao
33+
* Fix pydocstyle to check sdmetrics - Issue [#153](https://github.com/sdv-dev/SDMetrics/issues/153) by @pvk-developer
34+
* Update the RDT version to 1.0 - Issue [#150](https://github.com/sdv-dev/SDMetrics/issues/150) by @pvk-developer
35+
* Update slack invite link - Issue [#132](https://github.com/sdv-dev/SDMetrics/issues/132) by @pvk-developer
36+
337
## v0.5.0 - 2022-05-11
438

539
This release fixes an error where the relational `KSTest` crashes if a table doesn't have numerical columns.

‎README.md‎

Lines changed: 11 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ of a synthetic database** by comparing it to the real database that it is modele
4444
[License]: https://github.com/sdv-dev/SDMetrics/blob/master/LICENSE
4545
[Development Status]: https://pypi.org/search/?c=Development+Status+%3A%3A+2+-+Pre-Alpha
4646
[Slack Logo]: https://github.com/sdv-dev/SDV/blob/master/docs/images/slack.png
47-
[Community]: https://join.slack.com/t/sdv-space/shared_invite/zt-gdsfcb5w-0QQpFMVoyB2Yd6SRiMplcw
47+
[Community]: https://bit.ly/sdv-slack-invite
4848
[MyBinder Logo]: https://github.com/sdv-dev/SDV/blob/master/docs/images/mybinder.png
4949
[Tutorials]: https://mybinder.org/v2/gh/sdv-dev/SDV/master?filepath=tutorials
5050

@@ -125,17 +125,16 @@ sdmetrics.compute_metrics(metrics, real_data, synthetic_data, metadata=metadata)
125125

126126
The output will be a table with all the details about the executed metrics and their score:
127127

128-
| metric | name | score | min_value | max_value | goal |
129-
|------------------------------|-----------------------------------------|------------|-------------|-------------|----------|
130-
| CSTest | Chi-Squared | 0.76651 | 0 | 1 | MAXIMIZE |
131-
| KSTest | Inverted Kolmogorov-Smirnov D statistic | 0.75 | 0 | 1 | MAXIMIZE |
132-
| KSTestExtended | Inverted Kolmogorov-Smirnov D statistic | 0.777778 | 0 | 1 | MAXIMIZE |
133-
| LogisticDetection | LogisticRegression Detection | 0.882716 | 0 | 1 | MAXIMIZE |
134-
| SVCDetection | SVC Detection | 0.833333 | 0 | 1 | MAXIMIZE |
135-
| BNLikelihood | BayesianNetwork Likelihood | nan | 0 | 1 | MAXIMIZE |
136-
| BNLogLikelihood | BayesianNetwork Log Likelihood | nan | -inf | 0 | MAXIMIZE |
137-
| LogisticParentChildDetection | LogisticRegression Detection | 0.619444 | 0 | 1 | MAXIMIZE |
138-
| SVCParentChildDetection | SVC Detection | 0.916667 | 0 | 1 | MAXIMIZE |
128+
| metric | name | score | min_value | max_value | goal |
129+
|------------------------------|----------------------------------------------|------------|-------------|-------------|----------|
130+
| CSTest | Chi-Squared | 0.76651 | 0 | 1 | MAXIMIZE |
131+
| KSComplement | Complement to Kolmogorov-Smirnov D statistic | 0.75 | 0 | 1 | MAXIMIZE |
132+
| LogisticDetection | LogisticRegression Detection | 0.882716 | 0 | 1 | MAXIMIZE |
133+
| SVCDetection | SVC Detection | 0.833333 | 0 | 1 | MAXIMIZE |
134+
| BNLikelihood | BayesianNetwork Likelihood | nan | 0 | 1 | MAXIMIZE |
135+
| BNLogLikelihood | BayesianNetwork Log Likelihood | nan | -inf | 0 | MAXIMIZE |
136+
| LogisticParentChildDetection | LogisticRegression Detection | 0.619444 | 0 | 1 | MAXIMIZE |
137+
| SVCParentChildDetection | SVC Detection | 0.916667 | 0 | 1 | MAXIMIZE |
139138

140139
# What's next?
141140

‎conda/meta.yaml‎

Lines changed: 1 addition & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
{% set name = 'sdmetrics' %}
2-
{% set version = '0.5.0' %}
2+
{% set version = '0.6.0.dev2' %}
33

44
package:
55
name: "{{ name|lower }}"
@@ -23,19 +23,15 @@ requirements:
2323
- numpy >=1.18.0,<2
2424
- pandas >=1.1.3,<2
2525
- pytorch >=1.8.0,<2
26-
- pyts >=0.12.0,<0.13.0
2726
- copulas>=0.6.0,<0.7
28-
- rdt >=0.6.1,<0.7
2927
run:
3028
- python >=3.6,<3.10
3129
- scikit-learn >=0.24,<2
3230
- scipy >=1.5.4,<2
3331
- numpy >=1.18.0,<2
3432
- pandas >=1.1.3,<2
3533
- pytorch >=1.8.0,<2
36-
- pyts >=0.12.0,<0.13.0
3734
- copulas>=0.6.0,<0.7
38-
- rdt >=0.6.1,<0.7
3935

4036
about:
4137
home: "https://github.com/sdv-dev/SDMetrics"

‎sdmetrics/__init__.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44

55
__author__ = 'MIT Data To AI Lab'
66
__email__ = 'dailabmit@gmail.com'
7-
__version__ = '0.5.0'
7+
__version__ = '0.6.0.dev2'
88

99
import pandas as pd
1010

‎sdmetrics/column_pairs/__init__.py‎

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,15 @@
11
"""Metrics to compare column pairs."""
22

3-
from sdmetrics.column_pairs import statistical
43
from sdmetrics.column_pairs.base import ColumnPairsMetric
4+
from sdmetrics.column_pairs.statistical.contingency_similarity import ContingencySimilarity
5+
from sdmetrics.column_pairs.statistical.correlation_similarity import CorrelationSimilarity
56
from sdmetrics.column_pairs.statistical.kl_divergence import (
67
ContinuousKLDivergence, DiscreteKLDivergence)
78

89
__all__ = [
9-
'statistical',
1010
'ColumnPairsMetric',
11+
'ContingencySimilarity',
1112
'ContinuousKLDivergence',
13+
'CorrelationSimilarity',
1214
'DiscreteKLDivergence',
1315
]

0 commit comments

Comments
 (0)