117 lines
2.8 KiB
Plaintext
117 lines
2.8 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"id": "835530c2-0129-4b5f-a41c-f1870ca1307f",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import os\n",
|
||
|
|
"import sklearn\n",
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"from sklearn.metrics import accuracy_score\n",
|
||
|
|
"from gzip import open as open_gz\n",
|
||
|
|
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
|
||
|
|
"from sklearn.naive_bayes import MultinomialNB\n",
|
||
|
|
"from sklearn.pipeline import make_pipeline"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 21,
|
||
|
|
"id": "5db73671-80b9-4099-85a0-08ecf77250d1",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def evaluation(x, path_out, model):\n",
|
||
|
|
" results = model.predict(x)\n",
|
||
|
|
"\n",
|
||
|
|
" with open(path_out, 'wt') as file:\n",
|
||
|
|
" for r in results:\n",
|
||
|
|
" file.write(str(r) + '\\n')"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "2120f43e-d587-4481-a04c-dea9520cecec",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"train = pd.read_csv('train/train.tsv', header = None, sep = '\\t', error_bad_lines = False)\n",
|
||
|
|
"\n",
|
||
|
|
"x_train = train[1]\n",
|
||
|
|
"y_train = train[0]\n",
|
||
|
|
"x_dev = pd.read_csv('dev-0/in.tsv',header = None, sep = '/t',engine = 'python')\n",
|
||
|
|
"x_dev = x_dev[0]\n",
|
||
|
|
"x_test = pd.read_csv('test-A/in.tsv',header = None, sep = '/t',engine = 'python')\n",
|
||
|
|
"x_test = x_test[0]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 24,
|
||
|
|
"id": "cdfefa84-e535-48e8-844a-10e24b2a3555",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"Pipeline(steps=[('tfidfvectorizer', TfidfVectorizer()),\n",
|
||
|
|
" ('multinomialnb', MultinomialNB())])"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 24,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"model = make_pipeline(TfidfVectorizer(), MultinomialNB())\n",
|
||
|
|
"model.fit(x_train, y_train)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 25,
|
||
|
|
"id": "e1b7fe0c-a21a-42cf-8cd4-46ee932d5282",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"evaluation(x_dev,'dev-0/out.tsv', model)\n",
|
||
|
|
"evaluation(x_test,'test-A/out.tsv', model)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "7a269ea0-eefd-4907-bf65-9bb53ad296b7",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": []
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3 (ipykernel)",
|
||
|
|
"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": "3.9.12"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|