1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# PIPA Flickr Metadata Cleanup"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%reload_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import os\n",
"from os.path import join\n",
"from glob import glob\n",
"from pathlib import Path\n",
"\n",
"from tqdm import tqdm_notebook as tqdm\n",
"import pandas as pd\n",
"\n",
"import sys\n",
"sys.path.append('/work/megapixels_dev/megapixels')\n",
"from app.utils import file_utils"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load CSV"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"fp_in = '/data_store/datasets/people/pipa/research/pipa_flickr_metadata_ext.csv'\n",
"fp_out = '/data_store/datasets/people/pipa/research/pipa_flickr_metadata_test.csv'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create metadata csv output\n",
"\n",
"|nsid|path_alias|count|"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"df_flickr_meta = pd.read_csv(fp_in)\n",
"df_flickr_meta.fillna('', inplace=True)\n",
"flickr_metas = df_flickr_meta.to_dict('records')"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# create nsid lookup table\n",
"nsid_lookup = {}\n",
"alias_lookup = {}\n",
"for flickr_meta in flickr_metas:\n",
" nsid = flickr_meta['nsid']\n",
" nsid_lookup[nsid] = flickr_meta\n",
" alias_lookup[nsid] = flickr_meta['path_alias']"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"nsid_groups = df_flickr_meta.groupby('nsid')"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"items = []\n",
"for nsid, nsid_group in nsid_groups:\n",
" path_alias = alias_lookup[nsid]\n",
" obj = {'nsid': nsid, 'path_alias': path_alias, 'count': len(nsid_group)}\n",
" items.append(obj)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"df_out = pd.DataFrame.from_dict(items)\n",
"df_out.to_csv(fp_out, index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "megapixels",
"language": "python",
"name": "megapixels"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|
