HenryWoodOTC / multi-class-text-classification-cnn-rnn

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

Home Page:https://www.kaggle.com/c/sf-crime/data

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Project: Classify Kaggle San Francisco Crime Description

Highlights:

  • This is a multi-class text classification (sentence classification) problem.
  • The goal of this project is to classify Kaggle San Francisco Crime Description into 39 classes.
  • This model was built with CNN, RNN (LSTM and GRU) and Word Embeddings on Tensorflow.

Data: Kaggle San Francisco Crime

  • Input: Descript

  • Output: Category

  • Examples:

    Descript Category
    GRAND THEFT FROM LOCKED AUTO LARCENY/THEFT
    POSSESSION OF NARCOTICS PARAPHERNALIA DRUG/NARCOTIC
    AIDED CASE, MENTAL DISTURBED NON-CRIMINAL
    AGGRAVATED ASSAULT WITH BODILY FORCE ASSAULT
    ATTEMPTED ROBBERY ON THE STREET WITH A GUN ROBBERY

Train:

  • Command: python3 train.py train_data.file train_parameters.json
  • Example: python3 train.py ./data/train.csv.zip ./training_config.json

Predict:

  • Command: python3 predict.py ./trained_results_dir/ new_data.csv
  • Example: python3 predict.py ./trained_results_1478563595/ ./data/small_samples.csv

Reference:

About

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

https://www.kaggle.com/c/sf-crime/data

License:Apache License 2.0


Languages

Language:Python 100.0%