s440058/sport-text-classification-ball-ISI-public
1
0
Fork 0
forked from kubapok/sport-text-classification-ball-ISI-public
Code Issues Pull Requests Projects Releases Wiki Activity

add bayes

Browse Source
This commit is contained in:
s440058 2021-06-20 20:05:17 +02:00
parent 4ea8113b15
commit 2c5b3c6c96
1 changed files with 0 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
Untitled.ipynb
View File

@ -1,82 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n",
"b'Skipping line 1983: expected 1 fields, saw 2\\nSkipping line 5199: expected 1 fields, saw 2\\n'\n"
]
}
],
"source": [
"from sklearn.naive_bayes import GaussianNB\n",
"import pandas as pd\n",
"from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"\n",
"r_in = './train/train.tsv'\n",
"\n",
"r_ind_ev = './dev-0/in.tsv'\n",
"tsv_read = pd.read_table(r_in, error_bad_lines=False, sep='\\t', header=None)\n",
"tsv_read_dev = pd.read_table(r_ind_ev, error_bad_lines=False, sep='\\t', header=None)\n",
"\n",
"y_train = tsv_read[0].values\n",
"X_train = tsv_read[1].values\n",
"X_dev = tsv_read_dev[0].values\n",
"\n",
"vectorizer = TfidfVectorizer()\n",
"counts = vectorizer.fit_transform(X_train)\n",
"\n",
"\n",
"classifier = MultinomialNB()\n",
"classifier.fit(counts, y_train)\n",
"\n",
"counts2 = vectorizer.transform(X_dev)\n",
"predictions = classifier.predict(counts2)\n",
"\n",
"predictions.tofile(\"./dev-0/out.tsv\", sep='\\n')\n",
"\n",
"tsv_read_test_in = pd.read_table('./test-A/in.tsv', error_bad_lines=False, header= None)\n",
"X_test= tsv_read_test_in[0].values\n",
"\n",
"counts3 = vectorizer.transform(X_test)\n",
"predictions_test_A = classifier.predict(counts3)\n",
"predictions_test_A.tofile('./test-A/out.tsv', sep='\\n')"
]
},
{
"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": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}