loo.py/collectSimPerformance at main · asprediatribe/loo.py · 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
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
#!/bin/bash

# Set the working folder
working_folder="/home/s2216474/toSiSeMatDatastore/thomas"

# Create the performances subfolder if it doesn't exist
performances_folder="$working_folder/performances"
mkdir -p "$performances_folder"

# Initialize variables for the total number of steps
total_steps=0
output_file="concatenated_output.txt"

# Function to extract data from each simulation folder
process_simulation_folder() {
    simulation_folder="$1"
    cof="$2"
    adsorbate="$3"
    simulation="$4"

    # Generate the XY data file name based on the current COF, adsorbate, and simulation
    xy_file="$performances_folder/${cof}_${adsorbate}_${simulation}_data.dat"

    # Empty the output and XY data files if they already exist
    > $output_file
    > $xy_file

    # Concatenate all files matching the pattern into one output file
    #cat qstat"$simulation_folder"/Output*/*/o* >> "$output_file"
	#find "$simulation_folder"/Output*/ -type f -name "o*" -printf '%T@ %p\n' | sort -n | cut -d' ' -f2- | xargs cat >> "$output_file"

	for dir in $(ls "$simulation_folder" | grep '^Output_' | sed 's/Output_//' | sort -t_ -k1.7,1.10n -k1.4,1.5n -k1.1,1.2n -k2,2n | sed 's/^/Output_/'); do
		cat "$simulation_folder/$dir"/*/o* >> "$output_file"
		echo "$dir"
	done


    # Extract the total number of steps
    steps=$(grep -oP 'Current cycle: \d+ out of \d+' "$output_file" | awk '{print $5}' | tail -1)
    total_steps=$((total_steps + steps))

    # Initialize variables to hold the data
    cycle=""
    total_energy=""
    adsads_energy=""
    host_adsorbate_energy=""
    stp_per_g=""
    mg_per_g=""
	molecules=""
	read_data=yes

    # Read through the output file line by line
    while IFS= read -r line; do
        # Check if the line contains the cycle information
        if [[ $line == "Current cycle: "* ]]; then
            # If we have already collected data for a previous cycle, save it
            if [[ -n $cycle && -n $total_energy && -n $adsads_energy && -n $host_adsorbate_energy && -n $stp_per_g && -n $mg_per_g ]]; then
                echo "$cycle $total_energy $adsads_energy $host_adsorbate_energy $molecules $stp_per_g $mg_per_g" >> "$xy_file"
				#echo "$cycle $total_energy $adsads_energy $host_adsorbate_energy $molecules $stp_per_g $mg_per_g"

			read_data=yes

			fi

            # Reset variables for the new cycle
            cycle=$(echo $line | awk '{print $3}')
            total_energy="NaN"
            adsads_energy="NaN"
            host_adsorbate_energy="NaN"
            stp_per_g="NaN"
            mg_per_g="NaN"
			molecules="NaN"


		elif [[ $line =~ "excess adsorption:  " ]]; then
            read_data=no

		elif [[ $line =~ "current number of integer" ]]; then
            molecules=$(echo $line | awk '{print $9}')

        # Check if the line contains the value corresponding to cm^3 STP/g
        elif [[ $line =~ "3 STP" && $read_data =~ "yes" ]]; then
			stp_per_g=$(echo $line | awk '{print $1}')

        # Check if the line contains the value corresponding to mg/g
        elif [[ $line =~ "mg/g" && $read_data =~ "yes"  ]]; then
            mg_per_g=$(echo $line | awk '{print $11}')

        # Check if the line contains the total potential energy
        elif [[ $line =~ "Current total potential energy: " ]]; then
            total_energy=$(echo $line | awk '{print $5}')

        # Check if the line contains the Host-Host energy
        elif [[ $line =~ "Current Adsorbate-Adsorbate energy: " ]]; then
            adsads_energy=$(echo $line | awk '{print $4}')

        # Check if the line contains the Host-Adsorbate energy
        elif [[ $line =~ "Current Host-Adsorbate energy: " ]]; then
            host_adsorbate_energy=$(echo $line | awk '{print $4}')

        fi

    done < "$output_file"

    # After the loop, save the last cycle's data if it exists
    if [[ -n $cycle && -n $total_energy && -n $adsads_energy && -n $host_adsorbate_energy && -n $stp_per_g && -n $mg_per_g ]]; then
        echo "$cycle $total_energy $adsads_energy $host_adsorbate_energy $molecules $stp_per_g $mg_per_g" >> "$xy_file"
    fi

	total_steps= $(more $xy_file | wc -l)

	# Print the total number of steps for this simulation
	echo "Total number of steps for $cof $adsorbate $simulation: $total_steps"
}

# Loop through each COF, adsorbate, and simulation directory
for cof in $working_folder/*ddec; do
    for adsorbate in $cof/*; do
        for simulation in $adsorbate/*; do
            # Extract folder names
            cof_name=$(basename "$cof")
            adsorbate_name=$(basename "$adsorbate")
            simulation_name=$(basename "$simulation")
            process_simulation_folder "$simulation" "$cof_name" "$adsorbate_name" "$simulation_name"
        done
    done
done