slovnet

1
{
2
 "cells": [
3
  {
4
   "cell_type": "code",
5
   "execution_count": null,
6
   "metadata": {},
7
   "outputs": [],
8
   "source": [
9
    "%run main.py\n",
10
    "%load_ext autoreload\n",
11
    "%autoreload 2\n",
12
    "\n",
13
    "!mkdir -p {RAW_DIR}\n",
14
    "s3 = S3()"
15
   ]
16
  },
17
  {
18
   "cell_type": "code",
19
   "execution_count": null,
20
   "metadata": {},
21
   "outputs": [],
22
   "source": [
23
    "!wget https://storage.yandexcloud.net/natasha-corus/taiga/Fontanka.tar.gz -P {RAW_DIR}\n",
24
    "!wget https://storage.yandexcloud.net/natasha-corus/ods/gazeta_v1.csv.zip -P {RAW_DIR}\n",
25
    "!wget https://storage.yandexcloud.net/natasha-corus/ods/interfax_v1.csv.zip -P {RAW_DIR}\n",
26
    "!wget https://storage.yandexcloud.net/natasha-corus/lenta-ru-news.csv.gz -P {RAW_DIR}\n",
27
    "!wget https://storage.yandexcloud.net/natasha-corus/buriy/news-articles-2014.tar.bz2 -P {RAW_DIR}\n",
28
    "!wget https://storage.yandexcloud.net/natasha-corus/buriy/news-articles-2015-part1.tar.bz2 -P {RAW_DIR}\n",
29
    "!wget https://storage.yandexcloud.net/natasha-corus/buriy/news-articles-2015-part2.tar.bz2 -P {RAW_DIR}"
30
   ]
31
  },
32
  {
33
   "cell_type": "code",
34
   "execution_count": null,
35
   "metadata": {},
36
   "outputs": [],
37
   "source": [
38
    "LOADS = {\n",
39
    "    'gazeta_v1.csv.zip': load_ods_gazeta,\n",
40
    "    'interfax_v1.csv.zip': load_ods_interfax,\n",
41
    "    'Fontanka.tar.gz': load_taiga_fontanka,\n",
42
    "    'lenta-ru-news.csv.gz': load_lenta,\n",
43
    "    'news-articles-2015-part1.tar.bz2': load_buriy_news,\n",
44
    "    'news-articles-2015-part2.tar.bz2': load_buriy_news,\n",
45
    "    'news-articles-2014.tar.bz2': load_buriy_news,\n",
46
    "}\n",
47
    "\n",
48
    "\n",
49
    "lines = []  # Requires 15Gb RAM\n",
50
    "for name in listdir(RAW_DIR):\n",
51
    "    path = join_path(RAW_DIR, name)\n",
52
    "    records = LOADS[name](path)\n",
53
    "    for record in log_progress(records, desc=name):\n",
54
    "        line = re.sub('\\s+', ' ', record.text)  # news article -> single line\n",
55
    "        lines.append(line)"
56
   ]
57
  },
58
  {
59
   "cell_type": "code",
60
   "execution_count": null,
61
   "metadata": {},
62
   "outputs": [],
63
   "source": [
64
    "seed(1)\n",
65
    "shuffle(lines)"
66
   ]
67
  },
68
  {
69
   "cell_type": "code",
70
   "execution_count": null,
71
   "metadata": {},
72
   "outputs": [],
73
   "source": [
74
    "cap = 1000\n",
75
    "dump_lines(lines[:cap], TEST)\n",
76
    "dump_lines(log_progress(lines[cap:]), TRAIN)"
77
   ]
78
  },
79
  {
80
   "cell_type": "code",
81
   "execution_count": null,
82
   "metadata": {},
83
   "outputs": [],
84
   "source": [
85
    "s3.upload(TEST, S3_TEST)\n",
86
    "s3.upload(TRAIN, S3_TRAIN)"
87
   ]
88
  }
89
 ],
90
 "metadata": {
91
  "kernelspec": {
92
   "display_name": "Python 3",
93
   "language": "python",
94
   "name": "python3"
95
  },
96
  "language_info": {
97
   "codemirror_mode": {
98
    "name": "ipython",
99
    "version": 3
100
   },
101
   "file_extension": ".py",
102
   "mimetype": "text/x-python",
103
   "name": "python",
104
   "nbconvert_exporter": "python",
105
   "pygments_lexer": "ipython3",
106
   "version": "3.6.9"
107
  }
108
 },
109
 "nbformat": 4,
110
 "nbformat_minor": 2
111
}
112