Count the words in all different phrases of a Dialogflow agent

Dialogflow Translation strings.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import json\n",
    "import re\n",
    "\n",
    "def is_number(string):\n",
    "    try:\n",
    "        float(string)\n",
    "        return True\n",
    "    except Exception:\n",
    "        return False\n",
    "    \n",
    "    \n",
    "def words(string):\n",
    "    return re.sub(\"[^\\w]\", \" \",  string).split()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = os.listdir('google-action/intents')\n",
    "files = [filename for filename in files if 'usersays' in filename]\n",
    "\n",
    "usersays = set()\n",
    "for filename in files:\n",
    "    with open('google-action/intents/' + filename) as file:\n",
    "        intent_data = json.load(file)\n",
    "        for phrase_data in intent_data:\n",
    "\n",
    "            for phrase_variation in phrase_data['data']:\n",
    "                usersays.add(phrase_variation['text'])\n",
    "            \n",
    "            \n",
    "usersays = set(string.strip() for string in usersays) \n",
    "usersays = set(string for string in usersays if len(string) > 1)            \n",
    "usersays = set(string for string in usersays if not is_number(string)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = os.listdir('google-action/entities')\n",
    "\n",
    "entities = set()\n",
    "for filename in files:\n",
    "    with open('google-action/entities/' + filename) as file:\n",
    "        entity_data = json.load(file)\n",
    "        for entity_value in entity_data:\n",
    "            entities.add(entity_value['value'])\n",
    "            for entity_synonym in entity_value['synonyms']:\n",
    "                entities.add(entity_synonym)\n",
    "            \n",
    "            \n",
    "entities = set(string.strip() for string in entities) \n",
    "entities = set(string for string in entities if len(string) > 1)            \n",
    "entities = set(string for string in entities if not is_number(string)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "count = 0\n",
    "all_phrases = set(usersays).union(entities)\n",
    "for phrase in all_phrases:\n",
    "    count += len(words(phrase))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "912"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('phrases.txt', 'w') as out:\n",
    "    out.write('\\n'.join(all_phrases))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}