master-thesis/gensim_sandbox.ipynb

214 lines
5.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import gensim"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from gensim.test.utils import common_texts, get_tmpfile\n",
"from gensim.models import Word2Vec"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"path = get_tmpfile(\"word2vec.model\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'/tmp/word2vec.model'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"path"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"model = Word2Vec(common_texts, size=100, window=5, min_count=1, workers=4)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"model.save(\"word2vec.model\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(0, 2)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.train([[\"hello\", \"world\"]], total_examples=1, epochs=1)\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"vector = model.wv['computer']"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([-4.1360268e-03, -4.5368457e-03, 4.9407119e-03, -1.2173436e-03,\n",
" 1.8632456e-03, -3.0847099e-03, 9.4799127e-04, -2.7400992e-04,\n",
" -1.6392355e-03, -2.7422528e-03, -4.2033773e-03, -3.3297916e-03,\n",
" 4.1276743e-03, -4.7909385e-03, -3.4512556e-03, -2.4730477e-03,\n",
" 3.9467048e-03, -3.1123622e-03, 8.4940199e-04, 1.6509957e-03,\n",
" 1.9616839e-03, 2.9326702e-04, 8.3735195e-04, -3.9251014e-03,\n",
" 4.4886805e-03, 1.6525604e-03, -6.3597935e-04, 4.5339693e-03,\n",
" 3.1772670e-03, -2.1555244e-03, -1.4741931e-03, -3.0088725e-03,\n",
" -2.4554132e-05, 1.0471512e-03, 7.2246540e-04, -7.0415600e-04,\n",
" 1.0049028e-03, -1.2862401e-03, 4.2546941e-03, 3.7523378e-03,\n",
" 4.6063680e-03, 2.5315667e-03, 3.2354944e-04, 1.9442231e-03,\n",
" -3.8831339e-03, 3.4721817e-03, 4.8152893e-04, 3.7462877e-03,\n",
" -1.1004598e-03, -4.7399257e-03, 2.1483030e-03, 3.3649500e-03,\n",
" 4.6523339e-03, 4.3348838e-03, -4.2628059e-03, -2.9411956e-03,\n",
" -4.9323966e-03, 4.8694564e-03, -3.2455113e-04, 2.4327010e-04,\n",
" -9.5937803e-04, 3.3954745e-03, 1.4546780e-03, 1.4540150e-03,\n",
" 3.9641848e-03, 1.0693196e-03, -1.8705493e-03, 4.7259987e-03,\n",
" 3.6600775e-03, -4.9972837e-03, -1.0512822e-03, 3.5494359e-03,\n",
" -1.2509550e-03, 9.0227136e-04, -5.6869379e-04, 2.4727959e-04,\n",
" 1.7441555e-03, 2.0887840e-03, 1.4573885e-03, 3.2532993e-05,\n",
" -3.0203401e-03, -4.7087572e-03, -2.2450915e-04, -4.8172413e-04,\n",
" 2.2919511e-03, 6.3158554e-04, -4.7253529e-03, 4.0057153e-03,\n",
" 2.4692446e-03, -7.6975941e-04, 3.9252751e-03, -2.3655752e-03,\n",
" -4.5094200e-04, -4.7492324e-03, -1.3552406e-03, 4.7150920e-03,\n",
" 1.2312060e-03, 1.3621986e-03, 2.3288964e-03, -1.1707483e-03],\n",
" dtype=float32)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vector"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\u001b[0;31mType:\u001b[0m Word2VecKeyedVectors\n",
"\u001b[0;31mString form:\u001b[0m <gensim.models.keyedvectors.Word2VecKeyedVectors object at 0x7f743bd043c8>\n",
"\u001b[0;31mFile:\u001b[0m ~/.local/lib/python3.7/site-packages/gensim/models/keyedvectors.py\n",
"\u001b[0;31mDocstring:\u001b[0m \n",
"Mapping between words and vectors for the :class:`~gensim.models.Word2Vec` model.\n",
"Used to perform operations on the vectors such as vector lookup, distance, similarity etc.\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"?model.wv"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[['human', 'interface', 'computer'], ['survey', 'user', 'computer', 'system', 'response', 'time'], ['eps', 'user', 'interface', 'system'], ['system', 'human', 'system', 'eps'], ['user', 'response', 'time'], ['trees'], ['graph', 'trees'], ['graph', 'minors', 'trees'], ['graph', 'minors', 'survey']]\n"
]
}
],
"source": [
"print(common_texts)"
]
},
{
"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
}