obsei-demo / README.md
obsei's picture
Update README.md
caec54a
---
title: Obsei Demo by Oraika
emoji: πŸš€
colorFrom: purple
colorTo: yellow
sdk: streamlit
sdk_version: 1.15.2
app_file: app.py
pinned: true
license: apache-2.0
---
<p align="center">
<img src="https://raw.githubusercontent.com/obsei/obsei-resources/master/images/obsei-flyer.png" />
</p>
<p align="center">
<a href="https://www.oraika.com">
<img src="https://static.wixstatic.com/media/59bc4e_971f153f107e48c7912b9b2d4cd1b1a4~mv2.png/v1/fill/w_177,h_49,al_c,q_85,usm_0.66_1.00_0.01,enc_auto/3_edited.png" />
</a>
<a href="https://github.com/obsei/obsei/blob/master/LICENSE">
<img alt="License" src="https://img.shields.io/pypi/l/obsei">
</a>
<a href="https://github.com/obsei/obsei">
<img alt="Github stars" src="https://img.shields.io/github/stars/obsei/obsei?style=social">
</a>
</p>
[**Obsei**](https://obsei.com) by [Oraika](https://www.oraika.com) is an open-source low-code AI powered automation tool. *Obsei* consist of -
- **Observer**, observes platform like Twitter, Facebook, App Stores, Google reviews, Amazon reviews, News, Website etc and feed that information to,
- **Analyzer**, which perform text analysis like classification, sentiment, translation, PII etc and feed that information to,
- **Informer**, which send it to ticketing system, data store, dataframe etc for further action and analysis.
![](https://raw.githubusercontent.com/obsei/obsei-resources/master/gifs/obsei_flow.gif)
## Documentation
For detailed installation instructions, usages and example refer [documentation](https://obsei.com).
## Tutorials
<table>
<thead>
<tr class="header">
<th>Sr. No.</th>
<th>Workflow</th>
<th>Colab</th>
<th>Binder</th>
</tr>
</thead>
<tbody>
<tr>
<td rowspan="2">1</td>
<td colspan="3">Observe app reviews from Google play store, Analyze them via performing text classification and then Inform them on console via logger</td>
</tr>
<tr>
<td>PlayStore Reviews β†’ Classification β†’ Logger</td>
<td>
<a href="https://colab.research.google.com/github/obsei/obsei/blob/master/tutorials/01_PlayStore_Classification_Logger.ipynb">
<img alt="Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</td>
<td>
<a href="https://mybinder.org/v2/gh/obsei/obsei/HEAD?filepath=tutorials%2F01_PlayStore_Classification_Logger.ipynb">
<img alt="Colab" src="https://mybinder.org/badge_logo.svg">
</a>
</td>
</tr>
<tr>
<td rowspan="2">2</td>
<td colspan="3">Observe app reviews from Google play store, PreProcess text via various text cleaning function, Analyze them via performing text classification, Inform them to Pandas DataFrame and store resultant CSV to Google Drive</td>
</tr>
<tr>
<td>PlayStore Reviews β†’ PreProcessing β†’ Classification β†’ Pandas DataFrame β†’ CSV in Google Drive</td>
<td>
<a href="https://colab.research.google.com/github/obsei/obsei/blob/master/tutorials/02_PlayStore_PreProc_Classification_Pandas.ipynb">
<img alt="Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</td>
<td>
<a href="https://mybinder.org/v2/gh/obsei/obsei/HEAD?filepath=tutorials%2F02_PlayStore_PreProc_Classification_Pandas.ipynb">
<img alt="Colab" src="https://mybinder.org/badge_logo.svg">
</a>
</td>
</tr>
<tr>
<td rowspan="2">3</td>
<td colspan="3">Observe app reviews from Apple app store, PreProcess text via various text cleaning function, Analyze them via performing text classification, Inform them to Pandas DataFrame and store resultant CSV to Google Drive</td>
</tr>
<tr>
<td>AppStore Reviews β†’ PreProcessing β†’ Classification β†’ Pandas DataFrame β†’ CSV in Google Drive</td>
<td>
<a href="https://colab.research.google.com/github/obsei/obsei/blob/master/tutorials/03_AppStore_PreProc_Classification_Pandas.ipynb">
<img alt="Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</td>
<td>
<a href="https://mybinder.org/v2/gh/obsei/obsei/HEAD?filepath=tutorials%2F03_AppStore_PreProc_Classification_Pandas.ipynb">
<img alt="Colab" src="https://mybinder.org/badge_logo.svg">
</a>
</td>
</tr>
<tr>
<td rowspan="2">4</td>
<td colspan="3">Observe news article from Google news, PreProcess text via various text cleaning function, Analyze them via performing text classification while splitting text in small chunks and later computing final inference using given formula</td>
</tr>
<tr>
<td>Google News β†’ Text Cleaner β†’ Text Splitter β†’ Classification β†’ Inference Aggregator</td>
<td>
<a href="https://colab.research.google.com/github/obsei/obsei/blob/master/tutorials/04_GoogleNews_Cleaner_Splitter_Classification_Aggregator.ipynb">
<img alt="Colab" src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</td>
<td>
<a href="https://mybinder.org/v2/gh/obsei/obsei/HEAD?filepath=tutorials%2F04_GoogleNews_Cleaner_Splitter_Classification_Aggregator.ipynb">
<img alt="Colab" src="https://mybinder.org/badge_logo.svg">
</a>
</td>
</tr>
</tbody>
</table>