Product Categorization into Categories with Machine Learning
Budget: $30 ā $250 USD
Hi, I have a dataset of 559.000 products (the data is in Spanish),
I need to categorize the products into different categories ideally according to Google taxonomy list (https://www.google.com/basepages/producttype/taxonomy-with-ids.es-ES.txt) or any other similar.
I don't have an already categorized training set data.
The product data structure is as follows:
base_url: https://24powersports.com
source_url (where the data was scraped from): https://24powersports.com/collections/accesorios-para-motos
url_metadata (metadata of source_url): accesorios motos 24powersports accesorios motos tienda creada pilotos pilotos productos ayudaran alcanzar maximo nivel motocicleta
product_description*: Cubre Caja filtro Honda
brand (not available for all products): Twin Air
texts (additional associated scraped text of product): cubre caja filtro honda twin air 29.900
href (final url of product): https://24powersports.com/collections/accesorios-para-motos/products/cubre-caja-filtro-honda
image (image url of product): http://cdn.shopify.com/s/files/1/0396/5884/8410/products/160112_installed_{width}x.jpg?v=1623724801
*product description is not 100% accurate in all cases since the scraping program sometimes takes the wrong description.
(sample data available at https://drive.google.com/file/d/1y-KXdHkATHDeyYYfdi58U6B2coTEJQpP/view?usp=sharing)
Iām looking for someone who classify products into categories using machine learning in python, and can deliver the categorized products, the training dataset utilized and the full functional python scripts model for further project development and classification of new products.
If you need any further information about the project please let me know and drop me a message in my inbox, thanks!
I need to categorize the products into different categories ideally according to Google taxonomy list (https://www.google.com/basepages/producttype/taxonomy-with-ids.es-ES.txt) or any other similar.
I don't have an already categorized training set data.
The product data structure is as follows:
base_url: https://24powersports.com
source_url (where the data was scraped from): https://24powersports.com/collections/accesorios-para-motos
url_metadata (metadata of source_url): accesorios motos 24powersports accesorios motos tienda creada pilotos pilotos productos ayudaran alcanzar maximo nivel motocicleta
product_description*: Cubre Caja filtro Honda
brand (not available for all products): Twin Air
texts (additional associated scraped text of product): cubre caja filtro honda twin air 29.900
href (final url of product): https://24powersports.com/collections/accesorios-para-motos/products/cubre-caja-filtro-honda
image (image url of product): http://cdn.shopify.com/s/files/1/0396/5884/8410/products/160112_installed_{width}x.jpg?v=1623724801
*product description is not 100% accurate in all cases since the scraping program sometimes takes the wrong description.
(sample data available at https://drive.google.com/file/d/1y-KXdHkATHDeyYYfdi58U6B2coTEJQpP/view?usp=sharing)
Iām looking for someone who classify products into categories using machine learning in python, and can deliver the categorized products, the training dataset utilized and the full functional python scripts model for further project development and classification of new products.
If you need any further information about the project please let me know and drop me a message in my inbox, thanks!