Skip to content

Commit 25294c3

Browse files
gshenigsheni
committed
cleanup
1 parent 3b40e87 commit 25294c3

File tree

3 files changed

+184
-5
lines changed

3 files changed

+184
-5
lines changed

‎Makefile‎

Lines changed: 0 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -127,11 +127,6 @@ coverage: ## check code coverage quickly with the default Python
127127

128128

129129
# RELEASE TARGETS
130-
131-
.PHONY: git-push
132-
git-push: ## Simply push the repository to github
133-
git push
134-
135130
.PHONY: dist
136131
dist: clean ## builds source and wheel package
137132
python -m build --wheel --sdist

‎RELEASE.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,7 @@ git clone https://github.com/sdv-dev/DeepEcho.git
3131
cd DeepEcho
3232
git checkout main
3333
make install-develop
34+
make install-readme
3435
```
3536

3637
## Linting and tests

‎tests/readme_test/README.md‎

Lines changed: 183 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,183 @@
1+
<div align="center">
2+
<br/>
3+
<p align="center">
4+
<i>This repository is part of <a href="https://sdv.dev">The Synthetic Data Vault Project</a>, a project from <a href="https://datacebo.com">DataCebo</a>.</i>
5+
</p>
6+
7+
[![Development Status](https://img.shields.io/badge/Development%20Status-2%20--%20Pre--Alpha-yellow)](https://pypi.org/search/?c=Development+Status+%3A%3A+2+-+Pre-Alpha)
8+
[![PyPi Shield](https://img.shields.io/pypi/v/deepecho.svg)](https://pypi.python.org/pypi/deepecho)
9+
[![Tests](https://github.com/sdv-dev/DeepEcho/workflows/Run%20Tests/badge.svg)](https://github.com/sdv-dev/DeepEcho/actions?query=workflow%3A%22Run+Tests%22+branch%3Amain)
10+
[![Downloads](https://pepy.tech/badge/deepecho)](https://pepy.tech/project/deepecho)
11+
[![Coverage Status](https://codecov.io/gh/sdv-dev/DeepEcho/branch/main/graph/badge.svg)](https://codecov.io/gh/sdv-dev/DeepEcho)
12+
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/sdv-dev/DeepEcho/main?filepath=tutorials/timeseries_data)
13+
[![Slack](https://img.shields.io/badge/Slack%20Workspace-Join%20now!-36C5F0?logo=slack)](https://bit.ly/sdv-slack-invite)
14+
15+
<div align="left">
16+
<br/>
17+
<p align="center">
18+
<a href="https://github.com/sdv-dev/DeepEcho">
19+
<img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/DeepEcho-DataCebo.png"></img>
20+
</a>
21+
</p>
22+
</div>
23+
24+
</div>
25+
26+
# Overview
27+
28+
**DeepEcho** is a **Synthetic Data Generation** Python library for **mixed-type**, **multivariate
29+
time series**. It provides:
30+
31+
1. Multiple models based both on **classical statistical modeling** of time series and the latest
32+
in **Deep Learning** techniques.
33+
2. A robust [benchmarking framework](https://github.com/sdv-dev/SDGym) for evaluating these methods
34+
on multiple datasets and with multiple metrics.
35+
3. Ability for **Machine Learning researchers** to submit new methods following our `model` and
36+
`sample` API and get evaluated.
37+
38+
| Important Links | |
39+
| --------------------------------------------- | -------------------------------------------------------------------- |
40+
| :computer: **[Website]** | Check out the SDV Website for more information about the project. |
41+
| :orange_book: **[SDV Blog]** | Regular publshing of useful content about Synthetic Data Generation. |
42+
| :book: **[Documentation]** | Quickstarts, User and Development Guides, and API Reference. |
43+
| :octocat: **[Repository]** | The link to the Github Repository of this library. |
44+
| :keyboard: **[Development Status]** | This software is in its Pre-Alpha stage. |
45+
| [![][Slack Logo] **Community**][Community] | Join our Slack Workspace for announcements and discussions. |
46+
| [![][MyBinder Logo] **Tutorials**][Tutorials] | Run the SDV Tutorials in a Binder environment. |
47+
48+
[Website]: https://sdv.dev
49+
[SDV Blog]: https://sdv.dev/blog
50+
[Documentation]: https://sdv.dev/SDV
51+
[Repository]: https://github.com/sdv-dev/DeepEcho
52+
[License]: https://github.com/sdv-dev/DeepEcho/blob/main/LICENSE
53+
[Development Status]: https://pypi.org/search/?c=Development+Status+%3A%3A+2+-+Pre-Alpha
54+
[Slack Logo]: https://github.com/sdv-dev/SDV/blob/stable/docs/images/slack.png
55+
[Community]: https://bit.ly/sdv-slack-invite
56+
[MyBinder Logo]: https://github.com/sdv-dev/SDV/blob/stable/docs/images/mybinder.png
57+
[Tutorials]: https://mybinder.org/v2/gh/sdv-dev/DeepEcho/main?filepath=tutorials
58+
59+
# Install
60+
61+
**DeepEcho** is part of the **SDV** project and is automatically installed alongside it. For
62+
details about this process please visit the [SDV Installation Guide](
63+
https://sdv.dev/SDV/getting_started/install.html)
64+
65+
Optionally, **DeepEcho** can also be installed as a standalone library using the following commands:
66+
67+
**Using `pip`:**
68+
69+
```bash
70+
pip install deepecho
71+
```
72+
73+
**Using `conda`:**
74+
75+
```bash
76+
conda install -c pytorch -c conda-forge deepecho
77+
```
78+
79+
For more installation options please visit the [DeepEcho installation Guide](INSTALL.md)
80+
81+
# Quickstart
82+
83+
**DeepEcho** is included as part of [SDV](https://sdv.dev/SDV) to model and sample synthetic
84+
time series. In most cases, usage through SDV is recommeded, since it provides additional
85+
functionalities which are not available here. For more details about how to use DeepEcho
86+
whithin SDV, please visit the corresponding User Guide:
87+
88+
* [SDV TimeSeries User Guide](https://sdv.dev/SDV/user_guides/timeseries/par.html)
89+
90+
## Standalone usage
91+
92+
**DeepEcho** can also be used as a standalone library.
93+
94+
In this short quickstart, we show how to learn a mixed-type multivariate time series
95+
dataset and then generate synthetic data that resembles it.
96+
97+
We will start by loading the data and preparing the instance of our model.
98+
99+
```python3
100+
from deepecho import PARModel
101+
from deepecho.demo import load_demo
102+
103+
# Load demo data
104+
data = load_demo()
105+
106+
# Define data types for all the columns
107+
data_types = {
108+
'region': 'categorical',
109+
'day_of_week': 'categorical',
110+
'total_sales': 'continuous',
111+
'nb_customers': 'count',
112+
}
113+
114+
model = PARModel(cuda=False)
115+
```
116+
117+
If we want to use different settings for our model, like increasing the number
118+
of epochs or enabling CUDA, we can pass the arguments when creating the model:
119+
120+
```python # keep this as python (without the 3) to avoid using it in test-readme
121+
model = PARModel(epochs=1024, cuda=True)
122+
```
123+
124+
Notice that for smaller datasets like the one used on this demo, CUDA usage introduces
125+
more overhead than the gains it obtains from parallelization, so the process in this
126+
case is more efficient without CUDA, even if it is available.
127+
128+
Once we have created our instance, we are ready to learn the data and generate
129+
new synthetic data that resembles it:
130+
131+
```python3
132+
# Learn a model from the data
133+
model.fit(
134+
data=data,
135+
entity_columns=['store_id'],
136+
context_columns=['region'],
137+
data_types=data_types,
138+
sequence_index='date'
139+
)
140+
141+
# Sample new data
142+
model.sample(num_entities=5)
143+
```
144+
145+
The output will be a table with synthetic time series data with the same properties to
146+
the demo data that we used as input.
147+
148+
# What's next?
149+
150+
For more details about **DeepEcho** and all its possibilities and features, please check and
151+
run the [tutorials](tutorials).
152+
153+
If you want to see how we evaluate the performance and quality of our models, please have a
154+
look at the [SDGym Benchmarking framework](https://github.com/sdv-dev/SDGym).
155+
156+
Also, please feel welcome to visit [our contributing guide](CONTRIBUTING.rst) in order to help
157+
us developing new features or cool ideas!
158+
159+
---
160+
161+
162+
<div align="center">
163+
<a href="https://datacebo.com"><img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/DataCebo.png"></img></a>
164+
</div>
165+
<br/>
166+
<br/>
167+
168+
[The Synthetic Data Vault Project](https://sdv.dev) was first created at MIT's [Data to AI Lab](
169+
https://dai.lids.mit.edu/) in 2016. After 4 years of research and traction with enterprise, we
170+
created [DataCebo](https://datacebo.com) in 2020 with the goal of growing the project.
171+
Today, DataCebo is the proud developer of SDV, the largest ecosystem for
172+
synthetic data generation & evaluation. It is home to multiple libraries that support synthetic
173+
data, including:
174+
175+
* 🔄 Data discovery & transformation. Reverse the transforms to reproduce realistic data.
176+
* 🧠 Multiple machine learning models -- ranging from Copulas to Deep Learning -- to create tabular,
177+
multi table and time series data.
178+
* 📊 Measuring quality and privacy of synthetic data, and comparing different synthetic data
179+
generation models.
180+
181+
[Get started using the SDV package](https://sdv.dev/SDV/getting_started/install.html) -- a fully
182+
integrated solution and your one-stop shop for synthetic data. Or, use the standalone libraries
183+
for specific needs.

0 commit comments

Comments
 (0)