https://github.com/sanji515/abhikalpan-hackathon
https://github.com/sanji515/abhikalpan-hackathon
aws bootstrap4 django elasticbeanstalk html-css-javascript ibm natural-language-understanding python
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/sanji515/abhikalpan-hackathon
- Owner: Sanji515
- Created: 2019-02-28T20:27:24.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T01:39:28.000Z (over 2 years ago)
- Last Synced: 2025-01-04T04:16:42.160Z (5 months ago)
- Topics: aws, bootstrap4, django, elasticbeanstalk, html-css-javascript, ibm, natural-language-understanding, python
- Language: JavaScript
- Size: 11.5 MB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Abhikalpan-Hackathon
Setting up this project on your local machine is really easy.
## Installation instructions:
* Download and install python 3.6 and git
* Clone using `$ git clone https://github.com/Sanji515/Abhikalpan-Hackathon.git && cd Abhikalpan-Hackathon`
### Run
* Install virtualenv
- on Ubuntu: `$ sudo apt install python-virtualenv`
- on Windows: `$ pip install virtualenv`
* Create a virtual environment
- on Ubuntu: `$ virtualenv venv -p python3.6`
- on Windows: `$ virtualenv venv`
* Activate the environment:
- on Ubuntu: `$ source venv/bin/activate`
- on Windows: `$ ./venv/Scripts/activate`
* Install the requirements: `$ pip install -r requirements.txt`
* Make migrations `$ python manage.py makemigrations`
* Migrate the changes to the database `$ python manage.py migrate`
* Run the server `$ python manage.py runserver`
That's it. Open web browser and hit the url http://127.0.0.1:8000
## Steps for training model:
### 1. Prerequisites:
- IBM Cloud account: If you do not have an IBM Cloud account, you can create an account [Click Here](https://cloud.ibm.com/) .
- Watson Knowledge Studio account: User must have a WKS account. If you do not have an account, you can create a free account [click Here](https://www.ibm.com/account/us-en/signup/register.html?a=IBMWatsonKnowledgeStudio). Make a note of the login URL since it is unique to every login id
- Basic knowledge of building models in WKS: The user must possess basic knowledge of building model in WKS in order to build a custom model. Check getting started documentation [Click Here](https://cloud.ibm.com/docs/services/knowledge-studio/tutorials-create-project.html#wks_tutintro)
### 2. Create NLU service instance:
- Step1: [Click here](https://cloud.ibm.com/catalog/services/natural-language-understanding) to create NLU service and enter the service name
- Step2: Once you click on Create NLU service instance should get created.
### 3. Training Your Model:
- Click Create Workspace in Watson Knowledge Studio
- In the Create Workspace pop up window, enter the name of the new project. Click Create
- Click on the workspace you created and on Entity Type Click on Upload and add json file Abhikalpan-Hackathon/Watson_knowlege_Studio/Entities/types-de2a5c20-3cc6-11e9-9a38-235c4e7dcc32.json
- On Documents Click Upload and select Abhikalpan-Hackathon/Watson_knowlege_Studio/dataset/corpus-de2a5c20-3cc6-11e9-9a38-235c4e7dcc32.zip
- Click on Annotation Task under Machine Learning model and click on task available
- Click on Task which is in Not Complete and make each task Complete
- Click on Versions under Machine learning model and create new version and deploy it to Natural Language Understanding services
- Click on Performance under Machine learning model and click on Train and Evaluate button which will train the model against the annotations
### 4. Analyze Results:
- Run the Abhikalpan-Hackathon/try.py and enter any piece of secret text and the function will analyze the text
