Skip to content

Instantly share code, notes, and snippets.

@pemagrg1

pemagrg1/one hot encoding using Tensorflow

Created January 10, 2019 10:52
Show Gist options
  • Save pemagrg1/43b4a4ff0be12361ed0b0305dbd86dd9 to your computer and use it in GitHub Desktop.
Save pemagrg1/43b4a4ff0be12361ed0b0305dbd86dd9 to your computer and use it in GitHub Desktop.
Download ZIP
one hot encoding using Tensorflow
Raw
one hot encoding using Tensorflow
import tensorflow as tf
import pandas as pd
text = 'My cat is a great cat'
tokens = text.lower().split()
vocab = set(tokens)
vocab = pd.Series(range(len(vocab)), index=vocab)
word_ids = vocab.loc[tokens].values
inputs = tf.placeholder(tf.int32, [None])
# TensorFlow has an operation for one-hot encoding
one_hot_inputs = tf.one_hot(inputs, len(vocab))
transformed = tf.Session().run(one_hot_inputs, {inputs: word_ids})
print (transformed)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment