feed-products.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feed unique products to Vespa"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 332,
   "metadata": {},
   "outputs": [],
   "source": [
    "feed_status = []\n",
    "for uid,df in all.groupby('product_uid'):\n",
    "    title = df['product_title'].iloc[0]\n",
    "    description = df['product_description'].iloc[0]\n",
    "    queries = []\n",
    "    df['search_term'].apply(lambda x: queries.append(x))\n",
    "    attributes = []\n",
    "    p = product_attributes[product_attributes.product_uid==uid]\n",
    "    p['value'].apply(lambda x: attributes.append(x))\n",
    "    brand = p[p.name == 'MFG Brand Name']\n",
    "    brand = None if brand.empty else brand['value'].iloc[0]\n",
    "    title_embedding,description_embedding = session.run(\n",
    "        sentence_embeddings, feed_dict={sentence: [title,description]})\n",
    "    success,vespa_json = feed_product_to_vespa(title, description, \n",
    "                          brand, attributes, uid, queries, title_embedding, description_embedding)   \n",
    "    feed_status.append((success,vespa_json))"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}