176 lines
3.7 KiB
Plaintext
176 lines
3.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 90,
|
|
"id": "7dc5e391",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import csv"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 91,
|
|
"id": "a0825c64",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"tsv_data = pd.read_csv('in.tsv', sep='\\t',header=None, quoting=csv.QUOTE_NONE)[0]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 139,
|
|
"id": "4b9092a6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"expected = pd.read_csv('expected.tsv', sep='\\t',header=None)[0]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 94,
|
|
"id": "56c39aa1",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"137314\n",
|
|
"137314\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(len(expected))\n",
|
|
"print(len(tsv_data))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 158,
|
|
"id": "d7b300ca",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"male={'silnik', 'windows', 'gb', 'mb', 'mecz', 'pc', 'opony', 'apple', 'iphone', 'zwiastuny', 'hd', 'ubuntu', 'system', 'serwer'}\n",
|
|
"female={'ciąża', 'miesiączki', 'ciasto', 'ciąże', 'zadowolona', 'antykoncepcyjne', 'ginekologia', 'tabletki', 'porodzie', 'mąż', 'krwawienie', 'ciasta'}\n",
|
|
"male = {x[:6].lower() for x in male}\n",
|
|
"female = {x[:6].lower() for x in female}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 159,
|
|
"id": "31b5864b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"trimmed_docs=[]\n",
|
|
"for document in tsv_data:\n",
|
|
" new_doc=[]\n",
|
|
" for word in str(document).lower().split():\n",
|
|
" new_doc.append(word[:6])\n",
|
|
" trimmed_docs.append(new_doc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 160,
|
|
"id": "c1f02d77",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"male_or_female=[]\n",
|
|
"for doc in trimmed_docs:\n",
|
|
" male_or_female.append((len(male&set(doc)), len(female&set(doc))))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 161,
|
|
"id": "6edfd944",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"answers=[]\n",
|
|
"for i in male_or_female:\n",
|
|
" if i[0]>i[1]:\n",
|
|
" answers.append(1)\n",
|
|
" else:\n",
|
|
" answers.append(0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 162,
|
|
"id": "40369c2b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"result=[]\n",
|
|
"for i in range(len(answers)):\n",
|
|
" if answers[i]==expected[i]:\n",
|
|
" result.append(1)\n",
|
|
" else:\n",
|
|
" result.append(0)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 163,
|
|
"id": "e296921c",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Predykcja modelu wynosi 51.007909%\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(f'Predykcja modelu wynosi {sum(result)/len(result)*100:.6f}%')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 167,
|
|
"id": "fee431a4",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df = pd.DataFrame(result)\n",
|
|
"df.to_csv('out.tsv', sep = '\\t')"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.9.7"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|