Our aim this week was to perform certain operations on the ‘style.csv’ file in our dataset and bring it to the format we wanted.
Procedures we apply:
1-) Deleting column containing Nan values
2-) Determining the column we will use (“articleType” and “baseColour”)
3-) See visually what contents these columns contain
4-) Deleting rows less than a certain amount (500) to reduce the size of the dataset and prevent complexity.
5-) Plot the amount of lines we have left after feature deletion.
The model will be trained with a CSV file with clothing images and labels of the features and clothing names corresponding to these images. Our aim in the trained model is to predict the features of the clothes in the externally provided image and then make suggestions based on other clothes with similar labels. The recommendation will be made based on the photographs in our dataset.
⭐Data Set in Use: https://bit.ly/49fdxf6
⭐ High Quality Data Source: https://bit.ly/40vUVUd
Machine Learning Project © 2023