VocabularyProcessor.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.contrib.learn import preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[' T h i s i s a p e n . ', ' I a m a c a t . ']\n"
     ]
    }
   ],
   "source": [
    "docs = [\"This is a pen.\", \"I am a cat.\"]\n",
    "\n",
    "docs = [s.replace(\" \", \"\").replace(\"\", \" \") for s in docs]\n",
    "print(docs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "max length:  11\n"
     ]
    }
   ],
   "source": [
    "max_length = max([len(x.replace(\" \", \"\")) for x in docs])\n",
    "print(\"max length: \", max_length)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab_processor = preprocessing.VocabularyProcessor(max_length)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[array([1, 2, 3, 4, 3, 4, 5, 6, 7, 8, 0]), array([ 9,  5, 10,  5, 11,  5, 12,  0,  0,  0,  0])]\n"
     ]
    }
   ],
   "source": [
    "print(list(vocab_processor.fit_transform(docs)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Environment (conda_py3.6)",
   "language": "python",
   "name": "conda_py3.6"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}