104 lines
2.7 KiB
Plaintext
104 lines
2.7 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 34,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"import numpy as np\n",
|
||
|
|
"import torch\n",
|
||
|
|
"import gensim.downloader as gn\n",
|
||
|
|
"import csv\n",
|
||
|
|
"from nltk.tokenize import word_tokenize"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": []
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 36,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"STEP 3 - PREPROCESSING\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"names = ['content', 'id', 'label']\n",
|
||
|
|
"train_data_content = pd.read_table('train/in.tsv', error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = ['content', 'id'])\n",
|
||
|
|
"train_data_labels = pd.read_table('train/expected.tsv', error_bad_lines = False, header = None, quoting=csv.QUOTE_NONE, names = ['label'])\n",
|
||
|
|
"dev_data = pd.read_table('dev-0/in.tsv', error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = ['content', 'id'])\n",
|
||
|
|
"test_data = pd.read_table('test-A/in.tsv', error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = ['content', 'id'])\n",
|
||
|
|
"\n",
|
||
|
|
"print('STEP 3 - PREPROCESSING')\n",
|
||
|
|
"# lowercase all content\n",
|
||
|
|
"X_train = train_data_content['content'].str.lower()\n",
|
||
|
|
"y_train = train_data_labels['label']\n",
|
||
|
|
"X_dev = dev_data['content'].str.lower()\n",
|
||
|
|
"X_test = test_data['content'].str.lower()\n",
|
||
|
|
"\n",
|
||
|
|
"# tokenize datasets\n",
|
||
|
|
"X_train = [word_tokenize(content) for content in X_train]\n",
|
||
|
|
"X_dev = [word_tokenize(content) for content in X_dev]\n",
|
||
|
|
"X_test = [word_tokenize(content) for content in X_test]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 37,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"[==================================================] 100.0% 1662.8/1662.8MB downloaded\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"w2v = gn.load('word2vec-google-news-300')\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
|
||
|
|
}
|