Skip to content

This my Data Science portfolio! This repository showcases my projects.

Notifications You must be signed in to change notification settings

kkowenn/DataSciencePortfilo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

86 Commits
 
 
 
 
 
 

Repository files navigation

Data Science Portfolio

Welcome to My Data Science World!

All machine learning notebook & MLOps Projects:

🦆 Kaggle:

https://www.kaggle.com/kritsadakruapat

🐶 DagsHub:

https://dagshub.com/kkowenn

🤗 HuggingFace:

https://huggingface.co/kritsadaK

Machine learning Projects:

Project 1: Machine learning without any library:

https://github.com/kkowenn/ManualMachineLearning

Project 2: The Feature Importance score from a decision tree model:

https://github.com/kkowenn/FastworkAnalysisProject

Project 3: Manual algorithm cosin similarity:

https://www.kaggle.com/code/kritsadakruapat/cosin

Deep learning Projects:

Project 1: Optimizing Performance Metrics to find the best possible combination of hyperparameters to achieve the highest performance. (before tuning vs after tuning)

https://github.com/kkowenn/DataSciencePortfilo/blob/main/Schooltask(WineQuality)/Wine_Quality.ipynb

Project 2: Data Augmentation to Fix Overfitting (nlp and computer vision)

https://github.com/yamerooo123/Political-Fake-News-Detector-NLP

https://www.kaggle.com/code/kritsadakruapat/cnnchangedatacolor-notjustred

Project 3: Comparing Regression Models + Exploratory Data Analysis(EDA)

https://www.kaggle.com/code/kritsadakruapat/comparing-regression-models

Project 4: Transfer Learning with ResNet-50 & MobileNetV2 and etc.

https://www.kaggle.com/code/kritsadakruapat/simpletransferlearning-resnet50-unsatisfied

https://www.kaggle.com/code/kritsadakruapat/mobilenetv2-image-classification

Project 5: RNN model (Vanilla RNN, LSTM, GRU, and Bidirectional RNN) converted text to numbers, and tried different model types (RNN) to see which performed best.

https://www.kaggle.com/code/kritsadakruapat/rnnmodelcomparison?scriptVersionId=182686891

Project 6: Applying model on web, draw digits on a canvas and classify them using a pre-trained convolutional neural network (CNN) model by using the MNIST dataset.

https://github.com/kkowenn/DigitRecognitionWeb

Computer Vision Projects:

Project 1: using 3D pose to detect arm to overlay tattoo filter:

https://huggingface.co/spaces/kritsadaK/TattooPoseOverlay

https://github.com/kkowenn/ComputerVisionProject

Project 2: simple yolov (object detection)

https://github.com/kkowenn/SimpleYolov

fall detection capture when detect fall

https://github.com/kkowenn/Fall-Detection

MLflow Projects:

Project 1: Deployment model on Amazon Bucket(s3):

Machine learning model -> Mlflow -> Amazon Web Services

https://dagshub.com/dashboard

https://dagshub.com/kkowenn/DeploymentOnAWSProject1.mlflow/#/experiments/0?searchFilter=&orderByKey=attributes.start_time&orderByAsc=false&startTime=ALL&lifecycleFilter=Active&modelVersionFilter=All+Runs&datasetsFilter=W10%3D

Project 2: Dogecoin Minutely Prediction:

Data Collection (API binance) & Preprocessing -> Model Training & Experiment Tracking (MLFlow) -> Version Control & Pipeline Management (DVC)

https://dagshub.com/kkowenn/End-to-endDogecoinMinutelyPrediction

Project 3: Thailand PM10 Prediction App (stream lit track Log experiments by mlflow )

url(Open Government Data of Thailand) -> mini ETL -> basic ARIMA model -> streamlit display & choose location to predict-> Experiment Tracking -> Version Control & Pipeline Management (DVC)

https://dagshub.com/kkowenn/OpendatathaiMLflow

https://huggingface.co/spaces/kritsadaK/ThailandPM10PredictionApp2022

Big data analysis:

Scala Projects:

https://github.com/kkowenn/Basic_Scala_ForBigData

Hadoop Projects:

https://github.com/kkowenn/Simple-Hadoop-Recommendation

ETC:

Web Scraping with Python Project:

https://github.com/kkowenn/MyScrapingProject

About

This my Data Science portfolio! This repository showcases my projects.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published