blob: c295dc68c30e01f5e7743759c8b891ee1c2d84f9 (
plain)
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
|
#!/usr/bin/env python3
import argparse
from pathlib import Path
from pprint import pprint
import pandas as pd
import LogParser
import utils
import tab_switch
argparser = argparse.ArgumentParser(description="OCR-Logfile evaluation")
argparser.add_argument("vp_dir", help="Directory with all VPs")
args = argparser.parse_args()
data_path = Path(args.vp_dir)
all_vp = [x for x in data_path.iterdir() if x.is_dir()]
vp_results = []
tab_results = []
log_tab_results = []
for vp_path in all_vp:
log = LogParser.extract_activities(LogParser.get_log_data(vp_path))
log = LogParser.generate_log(log)
history = LogParser.get_history_db(vp_path)
log = LogParser.match_urls(history, log)
LogParser.write_logfile(vp_path, log)
video_path = next(vp_path.glob("*.mkv"))
ocr_path = vp_path / "analysis_results.csv"
log_path = vp_path / "logs.csv"
df = utils.combine_ocr_logs(video_path, ocr_path, log_path)
df = df.fillna("")
df["vp_code"] = vp_path.stem
df = utils.calc_levenshtein_distance(df)
url_groups = utils.group_urls(list(df["url"].values))
pprint(len(url_groups))
df.to_csv(f"{vp_path}/metrics.csv")
utils.write_grouped_metrics(df, url_groups, vp_path)
df = pd.read_csv(f"{vp_path}/metrics_grps.csv")
tab_df = tab_switch.tab_switches_per_type(df, "group_index")
tab_results.append(tab_df)
tab_df.to_csv(f"{vp_path}/tabswitches.csv")
log_tab_df = tab_switch.tab_switches_per_type(df, "log_url")
log_tab_results.append(log_tab_df)
log_tab_df.to_csv(f"{vp_path}/log_tabswitches.csv")
vp_results.append(df)
evals = utils.evaluate_results(tab_results, log_tab_results)
evals.to_csv(f"{data_path}/evaluation.csv")
|
