Sysadmin_detection/Sysadmin_detection_script at master · sbudai/Sysadmin_detection · GitHub

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
#!/bin/bash

# the following arguments should be provided by the user of this bash script
for i in "$@"
do
case $i in
    -td=*|--trainingdirectory=*)
		TrainingDirectory="${i#*=}"
		shift # past argument=value
    ;;
    -tsd=*|--testdirectory=*)
		TestDirectory="${i#*=}"
		shift # past argument=value
	;;
    -wd=*|--workingdirectory=*)
		WorkingDirectory="${i#*=}"
		shift # past argument=value
    ;;
    *)
        # unknown option
    ;;
esac
done

# detecting the current directory
baseline=$PWD

# dropping previous equivalent files
rm -f ${WorkingDirectory/[.]/$baseline}"all_history.csv"
rm -f ${WorkingDirectory/[.]/$baseline}"public_test.csv"
rm -f ${WorkingDirectory/[.]/$baseline}"public_test_scored.csv"

# creating new merged file with appropiate header ("date" column will be added)
cd "${TrainingDirectory/[.]/$baseline}"
first=$(ls | sort -n | head -1)
head -n+1 $first > tmp.csv
awk -F"," -v col="date" -v OFS="," '{print col, $0}' tmp.csv > ${WorkingDirectory/[.]/$baseline}"all_history.csv"
rm -f tmp.csv

# appending those daily training files into a merged one (all_history.csv)
# plus adding "date" values from filenames into the first column
cd ${TrainingDirectory/[.]/$baseline}
for pathfilename in ${TrainingDirectory/[.]/$baseline}*
do
	filename=$(echo $pathfilename | tail -c 11)
	echo $filename
	awk -F"," -v col="$filename" -v OFS="," '{print col, $0}' $pathfilename | tail -n+2 >> ${WorkingDirectory/[.]/$baseline}"all_history.csv"
done
/bin/sleep 1

# renaming 2 column of all_history.csv
sed -i '1s/date/date_of_session/' ${WorkingDirectory/[.]/$baseline}"all_history.csv"
sed -i '1s/commands/commands_in_session/' ${WorkingDirectory/[.]/$baseline}"all_history.csv"
/bin/sleep 0.2

# replacing "[" command with "opening_square_bracket" in all_history.csv
sed -i 's/\[/opening_square_bracket/g' ${WorkingDirectory/[.]/$baseline}"all_history.csv"
/bin/sleep 0.2

# copying public_test.csv into working directory
cp ${TestDirectory/[.]/$baseline}"public_test.csv" ${WorkingDirectory/[.]/$baseline}"public_test.csv"
/bin/sleep 0.2

# renaming 1 column of public_test.csv
sed -i '1s/commands/commands_in_session/' ${WorkingDirectory/[.]/$baseline}"public_test.csv"
/bin/sleep 0.2

# replacing "[" command with "opening_square_bracket" in public_test.csv
sed -i 's/\[/opening_square_bracket/g' ${WorkingDirectory/[.]/$baseline}"public_test.csv"
/bin/sleep 0.2

# celebrate
echo "The all_history.csv merged training data has been prepared in working directory."
echo "The public_test.csv test data has been prepared in working directory."
/bin/sleep 1

# step back to original directory
cd "${WorkingDirectory/[.]/$baseline}"
/bin/sleep 0.2

# switching to R
Rscript engine_script.R ${WorkingDirectory/[.]/$baseline}