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
|
import click
from app.settings import types
from app.models.dataset import Dataset
from app.utils import click_utils
from app.settings import app_cfg as cfg
from app.utils.logger_utils import Logger
log = Logger.getLogger()
@click.command()
@click.option('-i', '--input', 'opt_fp_in', required=True)
@click.option('-o', '--output', 'opt_fp_out', required=True)
@click.pass_context
def cli(ctx, opt_fp_in, opt_fp_out):
"""_template_"""
import sys
from glob import glob
from os.path import join
from pathlib import Path
import time
from pprint import pprint
import pandas as pd
from tqdm import tqdm
from app.utils import file_utils
log = Logger.getLogger()
dataset_names = ['helen', 'megaface', 'adience', 'pipa', 'lfpw', 'brainwash', 'msceleb', 'duke_mtmc', 'uccs']
df = pd.DataFrame()
fp_out = opt_fp_out.replace('.csv', '_citations.csv')
for dataset_name in dataset_names:
fp_csv = join(opt_fp_in, f'{dataset_name}.csv')
_df = pd.read_csv(fp_csv)
_df = _df[_df.lat != 0]
_df.drop('id', axis=1, inplace=True)
print(dataset_name, len(_df))
df = df.append(_df, ignore_index=True)
df.to_csv(fp_out, index=False)
# create country summary
fp_out = opt_fp_out.replace('.csv', '_countries.csv')
country_groups = df.groupby('country')
summary = []
for group_name, group in country_groups:
summary.append({'country': group_name, 'citations': len(group)})
df_summary = pd.DataFrame.from_dict(summary)
df_summary.sort_values(by='citations', ascending=False, inplace=True)
df_summary.to_csv(fp_out, index=False)
pprint(df_summary)
# summary sector
summary = []
fp_out = opt_fp_out.replace('.csv', '_sector.csv')
groups = df.groupby('loc_type')
for group_name, group in groups:
summary.append({'type': group_name, 'citations': len(group)})
df_types = pd.DataFrame.from_dict(summary)
df_types.sort_values(by='citations', ascending=False, inplace=True)
df_types.to_csv(fp_out, index=False)
pprint(df_types)
|
