|
a |
|
b/README.md |
|
|
1 |
# ML-Redefining-Cancer-Treatment :stethoscope: |
|
|
2 |
|
|
|
3 |
- Personalized Medicine: Redefining Cancer Treatment. |
|
|
4 |
- Predict the effect of Genetic Variants to enable Personalized Medicine. |
|
|
5 |
|
|
|
6 |
* Medical Domain AI Solution :pill: |
|
|
7 |
|
|
|
8 |
* Credit & thanks to teclov. |
|
|
9 |
|
|
|
10 |
* Kaggle link: https://www.kaggle.com/c/msk-redefining-cancer-treatment |
|
|
11 |
|
|
|
12 |
* Most exiting part is, real world problem statement and dataset availability. |
|
|
13 |
|
|
|
14 |
## Tech stack :point_down: |
|
|
15 |
Python | Machine Learning | NLP | VS Code :computer: |
|
|
16 |
|
|
|
17 |
## Dataset :point_down: |
|
|
18 |
1. In the project "training_text" file is missing under "training" directory (due to upload file size limit). Please find it in the kaggle link provided above. |
|
|
19 |
|
|
|
20 |
## How to run ? :point_down: |
|
|
21 |
1. Clone/Download the project from github. |
|
|
22 |
2. Open project in Pycharm/VS Code. |
|
|
23 |
3. Run "run.py" file or Run by highlighting snippets of code. |
|
|
24 |
|
|
|
25 |
## Application directory structure :point_down: |
|
|
26 |
 |
|
|
27 |
|
|
|
28 |
## Lessons learnt :open_book: |
|
|
29 |
* Important business metrics to consider before modelling such as Interpretability, Latency, Due to medical domain very less error etc. |
|
|
30 |
* Merge dataframes based on IDs. |
|
|
31 |
* EDA & Viz. |
|
|
32 |
* Log loss evaluation metrics. |
|
|
33 |
* Laplace smoothing. |
|
|
34 |
* Callibirated classifier. |
|
|
35 |
* Stochastic gradient descent. |
|
|
36 |
* Response encoding technique. |
|
|
37 |
* Feature importance. |
|
|
38 |
* Finally, python :smile: |
|
|
39 |
|
|
|
40 |
## License :point_down: |
|
|
41 |
[<img align="left" alt="" width="52px" src="https://icon-icons.com/icons2/2649/PNG/512/mit_license_icon_160873.png" />](https://spdx.org/licenses/MIT.html) |
|
|
42 |
|
|
|
43 |
<br/><br/> |
|
|
44 |
|
|
|
45 |
### Connect with me :point_down: |
|
|
46 |
|
|
|
47 |
[<img align="left" alt="" width="22px" src="https://simpleicons.org/icons/linkedin.svg" />](https://www.linkedin.com/in/akshay-kumar-c-p/) |
|
|
48 |
[<img align="left" alt="" width="22px" src="https://simpleicons.org/icons/youtube.svg" />](https://www.youtube.com/channel/UC3l8RTE3zBRzUrHbSXpx-qA) |
|
|
49 |
[<img align="left" alt="" width="22px" src="https://simpleicons.org/icons/github.svg" />](https://github.com/Akshaykumarcp) |
|
|
50 |
[<img align="left" alt="" width="22px" src="https://simpleicons.org/icons/medium.svg" />](https://medium.com/@akshai.148) |
|
|
51 |
|
|
|
52 |
|
|
|
53 |
|
|
|
54 |
|
|
|
55 |
|
|
|
56 |
|