s444409/ium_444409
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Zadania realizowane w ramach zajęć Inżynieria Uczenia Maszynowego
64 Commits 2 Branches 0 Tags 76 KiB
Jupyter Notebook 77.8%
Python 17.6%
Shell 4.1%
Dockerfile 0.5%
8a967075c4
Go to file
Marcin Kostrzewski 8a967075c4 Change model path
2022-05-11 19:12:25 +02:00
.gitignore Add MLproject for MLFlow 2022-05-09 17:14:37 +02:00
Dockerfile Improved caching layers 2022-05-09 17:04:58 +02:00
download_dataset.sh Save artifacts 2022-03-27 23:29:37 +02:00
eval_model.py Move common methods and functions to model.py 2022-05-06 21:51:49 +02:00
Jenkinsfile-build Revert "Do not use string interpolation" 2022-05-07 10:34:33 +02:00
Jenkinsfile-eval Revert "Add model build selector" 2022-05-06 18:45:04 +02:00
Jenkinsfile-predict-s444356 Add scripts to use someones model 2022-05-11 18:33:30 +02:00
Jenkinsfile-stats Cleanup Jenkinsfiles 2022-05-06 20:16:15 +02:00
Jenkinsfile-train Fix mountpoint 2022-05-11 17:56:50 +02:00
MLproject Add MLproject for MLFlow 2022-05-09 17:14:37 +02:00
model.py Floatify 2022-05-11 19:10:26 +02:00
power_plant_data_stats.ipynb Added first solution 2022-03-20 18:07:34 +01:00
power_plant_data_stats.py Dockerization 2022-04-01 22:25:05 +02:00
predict_s444356.py Change model path 2022-05-11 19:12:25 +02:00
README.md Added first solution 2022-03-20 18:07:34 +01:00
requirements.txt Initial MLFlow setup 2022-05-09 13:57:15 +02:00
stats.sh Added statistics script 2022-03-27 23:46:51 +02:00
train_model.py Add tracking to MLFlow Models 2022-05-09 18:36:44 +02:00

README.md

ium_444409

Zadania realizowane w ramach zajęć Inżynieria Uczenia Maszynowego.

Zbiór

Solar Power Generation Data https://www.kaggle.com/datasets/anikannal/solar-power-generation-data?select=Plant_1_Generation_Data.csv

Wymagania

  • python3
  • pip
  • API token z kaggle.com

Uruchamianie

  • Instalujemy potrzebne pakiety:
$ pip install -r requirements.txt
  • Pobieramy zbiór danych z Kaggle. Skorzystamy ze skryptu w repo, który pobierze i podzieli dane na podzbiory:
$ ./download_dataset.sh