/classification_tensorflow

Multiple classification Documents Tensorflow 2.0 CNN-RNN-LSTM

Primary LanguagePython

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: python predict.py ./trained_results_1554545002/ ./data/small_samples.csv

Reference:

https://www.youtube.com/results?search_query=flask+tensorflow+classification

pip install paramiko"#- Example: !python train.py train.csv.zip training_config.json" "#- !wget git@github.com:niranjan8129/classification_tensorflow.git for download "