opendp/smartnoise-sdk
GitHub: opendp/smartnoise-sdk
为表格和关系型数据提供差分隐私保护的 SQL 查询执行与合成数据生成工具包
Stars: 292 | Forks: 79
[](https://opensource.org/licenses/MIT)
# SmartNoise SDK：表格数据差分隐私工具
SmartNoise SDK 包含 2 个包：
* [smartnoise-sql](sql/)：执行差分隐私 SQL 查询
* [smartnoise-synth](synth/)：生成差分隐私合成数据
入门请参考下方示例。点击进入各项目以查看更详细的示例。
## SQL
[](https://www.python.org/)
### 安装
```
pip install smartnoise-sql
```
### 查询
```
import snsql
from snsql import Privacy
import pandas as pd
csv_path = 'PUMS.csv'
meta_path = 'PUMS.yaml'
data = pd.read_csv(csv_path)
privacy = Privacy(epsilon=1.0, delta=0.01)
reader = snsql.from_connection(data, privacy=privacy, metadata=meta_path)
result = reader.execute('SELECT sex, AVG(age) AS age FROM PUMS.PUMS GROUP BY sex')
print(result)
```
`PUMS.csv` 和 `PUMS.yaml` 可在 [datasets](datasets/) 文件夹中找到。
请参阅 [SQL 项目](sql/README.md)
## Synthesizers
[](https://www.python.org/)
### 安装
```
pip install smartnoise-synth
```
### MWEM
```
import pandas as pd
import numpy as np
pums = pd.read_csv(pums_csv_path, index_col=None) # in datasets/
pums = pums.drop(['income'], axis=1)
nf = pums.to_numpy().astype(int)
synth = snsynth.MWEMSynthesizer(epsilon=1.0, split_factor=nf.shape[1])
synth.fit(nf)
sample = synth.sample(10) # get 10 synthetic rows
print(sample)
```
### PATE-CTGAN
```
import pandas as pd
import numpy as np
from snsynth.pytorch.nn import PATECTGAN
from snsynth.pytorch import PytorchDPSynthesizer
pums = pd.read_csv(pums_csv_path, index_col=None) # in datasets/
pums = pums.drop(['income'], axis=1)
synth = PytorchDPSynthesizer(1.0, PATECTGAN(regularization='dragan'), None)
synth.fit(pums, categorical_columns=pums.columns.values.tolist())
sample = synth.sample(10) # synthesize 10 rows
print(sample)
```
请参阅 [Synthesizers 项目](synth/README.md)
## 发布与贡献
如果您遇到 Bug，请通过[创建 issue](https://github.com/opendp/smartnoise-sdk/issues) 告知我们。
我们感谢所有的贡献。请查阅[贡献者指南](contributing.rst)。我们欢迎提交包含 Bug 修复的 Pull Request，无需事先讨论。
如果您计划为此系统贡献新功能、实用函数或扩展，请先开启一个 issue 并与我们讨论该功能。
# SmartNoise SDK：表格数据差分隐私工具
SmartNoise SDK 包含 2 个包：
* [smartnoise-sql](sql/)：执行差分隐私 SQL 查询
* [smartnoise-synth](synth/)：生成差分隐私合成数据
入门请参考下方示例。点击进入各项目以查看更详细的示例。
## SQL
[](https://www.python.org/)
### 安装
```
pip install smartnoise-sql
```
### 查询
```
import snsql
from snsql import Privacy
import pandas as pd
csv_path = 'PUMS.csv'
meta_path = 'PUMS.yaml'
data = pd.read_csv(csv_path)
privacy = Privacy(epsilon=1.0, delta=0.01)
reader = snsql.from_connection(data, privacy=privacy, metadata=meta_path)
result = reader.execute('SELECT sex, AVG(age) AS age FROM PUMS.PUMS GROUP BY sex')
print(result)
```
`PUMS.csv` 和 `PUMS.yaml` 可在 [datasets](datasets/) 文件夹中找到。
请参阅 [SQL 项目](sql/README.md)
## Synthesizers
[](https://www.python.org/)
### 安装
```
pip install smartnoise-synth
```
### MWEM
```
import pandas as pd
import numpy as np
pums = pd.read_csv(pums_csv_path, index_col=None) # in datasets/
pums = pums.drop(['income'], axis=1)
nf = pums.to_numpy().astype(int)
synth = snsynth.MWEMSynthesizer(epsilon=1.0, split_factor=nf.shape[1])
synth.fit(nf)
sample = synth.sample(10) # get 10 synthetic rows
print(sample)
```
### PATE-CTGAN
```
import pandas as pd
import numpy as np
from snsynth.pytorch.nn import PATECTGAN
from snsynth.pytorch import PytorchDPSynthesizer
pums = pd.read_csv(pums_csv_path, index_col=None) # in datasets/
pums = pums.drop(['income'], axis=1)
synth = PytorchDPSynthesizer(1.0, PATECTGAN(regularization='dragan'), None)
synth.fit(pums, categorical_columns=pums.columns.values.tolist())
sample = synth.sample(10) # synthesize 10 rows
print(sample)
```
请参阅 [Synthesizers 项目](synth/README.md)
## 发布与贡献
如果您遇到 Bug，请通过[创建 issue](https://github.com/opendp/smartnoise-sdk/issues) 告知我们。
我们感谢所有的贡献。请查阅[贡献者指南](contributing.rst)。我们欢迎提交包含 Bug 修复的 Pull Request，无需事先讨论。
如果您计划为此系统贡献新功能、实用函数或扩展，请先开启一个 issue 并与我们讨论该功能。标签：Apex, GAN, MWEM, PATE-CTGAN, Python, PyTorch, SmartNoise, 代码示例, 关系型数据, 凭据扫描, 匿名化, 合成数据, 多线程, 差分隐私, 开源库, 搜索引擎爬虫, 数据分析, 数据发布, 数据脱敏, 无后门, 机器学习, 深度学习, 统计噪声, 网络安全, 联邦学习, 表格数据, 逆向工具, 隐私保护, 隐私计算