Learn practical skills, build real-world projects, and advance your career

Reuters Story Categorization

Step 1: Define the Problem & Collect Data

Q: What are you trying to predict?

A: Classifying newswires into categories.

Q: What will your input data be?

A: Newswires text.

Q: What type of problem are you facing?

A: Multi-label multi-class classification

Q: What is the size of your dataset?

A: 8982 training examples, 2246 test examples

from keras.datasets import reuters
(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)
Using TensorFlow backend. /home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6 return f(*args, **kwds)

Step 2: Pick Success Metrics