productner
productner copied to clipboard
etano
Algorithms to categorize products and do named entity recognition on words in product descriptions
- Update Readme.MD with clear instructions on requirements - Reformat code with Python guidelines - Fix and freeze dependencies so it would reliably work on Python 3.7 with old version...
Running from the terminal, I am getting the error "zsh: illegal hardware instruction python train_tokenizer.py" Running from Jupyter Notebook, the kernel simply dies, so not sure where the issue is....
Hello etano I was trying to execute the commands as you have provided. But after trimming and running the following all scripts give the index error. productner-master\data>python supplement.py products.normalized.trimmed.csv Traceback...
Bumps [pyyaml](https://github.com/yaml/pyyaml) from 5.1.2 to 5.4. Changelog Sourced from pyyaml's changelog. 5.4 (2021-01-19) yaml/pyyaml#407 -- Build modernization, remove distutils, fix metadata, build wheels, CI to GHA yaml/pyyaml#472 -- Fix for...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
After running python parse.py metadata.json (results: good: 1806933 , bad: 152) The next script fails : python normalize.py products.csv Traceback (most recent call last): File "normalize.py", line 33, in writer.writerow(row)...
Hi Ethan, First of all amazing project. Have been trying my hands on it and just wanted to understand that from json data of 9.4 mil rows after running the...
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 1.5.0 to 1.15.4. Release notes Sourced from tensorflow's releases. TensorFlow 1.15.4 Release 1.15.4 Bug Fixes and Other Changes Fixes an undefined behavior causing a segfault in tf.raw_ops.Switch...
Error when running: ` python train_classifier.py data/products.normalized.trimmed.supplemented.tagged.csv ` ValueError: You are passing a target array of shape (0, 1) while using as loss categorical_crossentropy. categorical_crossentropy expects targets to be binary...
I believe the line below must be replaced to ` outfile = open('.'.join(data_file.split('.')[:-1] + ['processed', 'csv']), 'wb') ` To the line below for python3 ` outfile = open('.'.join(data_file.split('.')[:-1] + ['processed',...
