This commit is contained in:
Jan Przybylski 2021-04-20 19:12:08 +02:00
parent 5d7436ffe9
commit e92ad61864

View File

@ -1,103 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'text_data' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-3-d179e01d96de>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mw2v_model\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgensim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodels\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mWord2Vec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtext_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m300\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmin_count\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0miter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m50\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0mw2v_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwv\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'word'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'text_data' is not defined"
]
}
],
"source": [
"from nltk.tokenize import sent_tokenize, word_tokenize\n",
"import warnings\n",
" \n",
"warnings.filterwarnings(action = 'ignore')\n",
" \n",
"import gensim\n",
"from gensim.models import Word2Vec\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"import numpy as np\n",
"from sklearn.datasets import load_iris\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.naive_bayes import GaussianNB\n",
"\n",
"sample = open(\"/train/in.tsv\", \"r\")\n",
"s = sample.read()\n",
" \n",
"# Replaces escape character with space\n",
"f = s.replace(\"\\n\", \" \")\n",
" \n",
"data = []\n",
" \n",
"# iterate through each sentence in the file\n",
"for i in sent_tokenize(f):\n",
" temp = []\n",
" \n",
" # tokenize the sentence into words\n",
" for j in word_tokenize(i):\n",
" temp.append(j.lower())\n",
" \n",
" data.append(temp)\n",
" \n",
"# Create CBOW model\n",
"model1 = gensim.models.Word2Vec(data, min_count = 1, \n",
" size = 100, window = 5)\n",
" \n",
"w2v_model = gensim.models.Word2Vec(text_data, size=300, min_count=1, window=5, iter=50)\n",
"w2v_model.wv['word']\n",
"\n",
"with open(\"train/in.tsv\") as f:\n",
" content = f.readlines()\n",
" with open(\"train/expected.tsv\") as ff:\n",
" y = ff.readlines()\n",
" vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = False)\n",
" vectorizer = TfidfVectorizer()\n",
" x = vectorizer.fit_transform(content)\n",
" x=x.toarray()\n",
" y=y.toarray()\n",
" model = GaussianNB()\n",
" model.fit(x,y)\n",
" y_pred = model.predict([[0,1]])\n",
" print(y_pred)"
]
},
{
"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": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}