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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# HELEN Prepare Flickr API"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"%reload_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import os\n",
"from os.path import join\n",
"from glob import glob, iglob\n",
"from pathlib import Path\n",
"from tqdm import tqdm_notebook as tqdm\n",
"\n",
"import h5py\n",
"from scipy import misc\n",
"from io import BytesIO\n",
"from base64 import b64decode\n",
"\n",
"from PIL import Image, ImageDraw\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import scipy.io as sio\n",
"import h5py\n",
"import numpy as np\n",
"import pandas as pd\n",
"import sys\n",
"sys.path.append('/work/megapixels_dev/megapixels/')\n",
"from app.utils import file_utils"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"fp_in = '/data_store/datasets/people/helen/research/flickr_photo_ids.txt'\n",
"fp_out = '/data_store/datasets/people/helen/research/helen_flickr_meta.csv'"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"photo_id_list = file_utils.load_text(fp_in)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"items = [{'photo_id': x.split('_')[0]} for x in photo_id_list]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame.from_dict(items)\n",
"df.to_csv(fp_out, index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Flickr API Dump\n",
"\n",
"- and create Flickr meta"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"fp_api_dump = '/data_store/datasets/people/helen/research/helen_flickr_api_dump.csv'\n",
"df = pd.read_csv(fp_api_dump)\n",
"#records = df.to_dict('records')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"groups = df.groupby('nsid')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"results = []\n",
"for nsid, group in groups:\n",
" obj = {\n",
" 'nsid': nsid,\n",
" 'count': len(group)\n",
" }\n",
" results.append(obj)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"pd.DataFrame.from_dict(results).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
}
|
