https://github.com/henrixapp/text_analytics
Final project for text analytics class Fall '20
https://github.com/henrixapp/text_analytics
clustering machine-learning recipes
Last synced: over 1 year ago
JSON representation
Final project for text analytics class Fall '20
- Host: GitHub
- URL: https://github.com/henrixapp/text_analytics
- Owner: henrixapp
- License: gpl-3.0
- Created: 2021-11-07T22:38:05.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-11-07T22:38:39.000Z (over 4 years ago)
- Last Synced: 2025-01-09T07:25:02.820Z (over 1 year ago)
- Topics: clustering, machine-learning, recipes
- Language: Jupyter Notebook
- Homepage:
- Size: 33.9 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ITA: Text Analytics
**Lecturer:** Prof. Dr. Michael Gertz
**Term:** Winter Semester 20/21
## Assignments
The assignments 1 to 4 can be found in the respective folders.
## [Project](src/)
To get started with running the example pipelines [read more here](src/). Our project implementation is found in the [src folder](src/) together with a [README](src/), where all important steps are desrcibed.
In our project we are clustering and augmenting recipes. A detailed description of the project idea can be found in the [proposal](proposal/project-proposal.pdf). An overview over the progress and an analysis of the dataset in particular can be found in our report for the [first milestone](milestone-1/README.md). Our issue tracking and meetings are documented in the folder [meetings](meetings/).
### Appetizer
Just to give a taste, here is a clustering visualization using [UMAP](https://umap-learn.readthedocs.io/en/latest/), k-Means clustering and baseline approach (TF-IDF, TruncatedSVD).
[](https://www.youtube.com/watch?v=SewE9nil0Nc)