master-thesis/Yummly_word2vec.ipynb
2019-05-14 21:46:16 +02:00

121 lines
2.2 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import json \n",
"from pprint import pprint\n",
"from gensim.test.utils import common_texts, get_tmpfile\n",
"from gensim.models import Word2Vec\n",
"\n",
"from json_buffered_reader import JSON_buffered_reader as JSON_br\n",
"\n",
"import settings"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* reading in all ingredients with json stream:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"buffered_reader = JSON_br(settings.yummly_train)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"ingredient_sets = []"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"for recipe in buffered_reader:\n",
" ingredient_sets.append(recipe['ingredients'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* training a word2vec approach on the ingredient set"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"model = Word2Vec(ingredient_sets, size=100, window=5, min_count=1, workers=4)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.46477914"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.wv.similarity('eggs', 'pepper')"
]
},
{
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}