From bad59b245785e2ae21653990dcaa933cf5e697fe Mon Sep 17 00:00:00 2001
From: Alexander Nikitin <1243786+AlexanderVNikitin@users.noreply.github.com>
Date: Mon, 23 Oct 2023 12:56:28 +0300
Subject: [PATCH] update docs

---
 CONTRIBUTING.md | 10 +++++-----
 docs/index.rst  | 40 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index ee117ef..5d9fa78 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -17,24 +17,24 @@ The easiest way to make a pull request is to fork the repo, see [GitHub document
 
 ## Development
 To install TSGM in development mode, first install prerequisites:
-```
+```bash
 pip install -r requirements/requirements.txt
 pip install -r requirements/tests_requirements.txt
 pip install -r requirements/docs_requirements.txt
 ```
 
 and then, install TSGM in development mode:
-```
+```bash
 python setup.py develop
 ```
 
 To run tests, use pytest, for example:
-```
+```bash
 pytest tests/test_cgan.py::test_temporal_cgan
 ```
 
 To run linters, use:
-```
+```bash
 flake8 tsgm/
 ```
 
@@ -42,7 +42,7 @@ flake8 tsgm/
 We aim to produce high-quality documentation to help our users to use the library. In your contribution, please edit corresponding documentation pages in [./docs](https://github.com/AlexanderVNikitin/tsgm/tree/main/docs).
 
 To build the documentation, use:
-```
+```bash
 cd docs
 make html
 ```
diff --git a/docs/index.rst b/docs/index.rst
index 272a6f7..baa6c54 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -6,7 +6,45 @@ Time Series Simulator (TSGM) Official Documentation
 Time Series Generative Modeling (TSGM) is a Python framework for time series data generation. It include data-driven and model-based approaches to synthetic time-series generation. It uses both generative
 
 
-The package is built on top of `Tensorflow <https://www.tensorflow.org/>`_ that allows training the models on CPUs, or GPUs. 
+The package is built on top of `Tensorflow <https://www.tensorflow.org/>`_ that allows training the models on CPUs, GPUs, or TPUs.
+
+Quick start:
+
+.. code-block:: bash
+
+    pip install tsgm
+
+
+.. code-block:: python
+
+    import tsgm
+
+    # ... Define hyperparameters ...
+    # dataset is a tensor of shape n_samples x seq_len x feature_dim
+
+    # Zoo contains several prebuilt architectures: we choose a conditional GAN architecture
+    architecture = tsgm.models.architectures.zoo["cgan_base_c4_l1"](
+        seq_len=seq_len, feat_dim=feature_dim,
+        latent_dim=latent_dim, output_dim=0)
+    discriminator, generator = architecture.discriminator, architecture.generator
+
+    # Initialize GAN object with selected discriminator and generator
+    gan = tsgm.models.cgan.GAN(
+        discriminator=discriminator, generator=generator, latent_dim=latent_dim
+    )
+    gan.compile(
+        d_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
+        g_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
+        loss_fn=keras.losses.BinaryCrossentropy(from_logits=True),
+    )
+    gan.fit(dataset, epochs=1)
+
+    # Generate 10 synthetic samples
+    result = gan.generate(10)
+
+For more examples, see `our tutorials <https://github.com/AlexanderVNikitin/tsgm/tree/main/tutorials>`_.
+
+If you find this repo useful, please consider citing our paper:
 
 .. code-block:: latex