EWP-BplusToKstMuMu-AngAna/Code/Scripts/Python Scripts/MC Fit/diff_pair_tables_average_mc.py

import re
import numpy as np

from prettytable import PrettyTable


def main():
    bin_labels = r"$1.10 < q^2 < 6.00$"

    sample_1             = """+----------+------------------------+------------------------+-----------------------+\n
                              | Variable |         Value          |      Lower Error       |      Upper Error      |\n
                              +----------+------------------------+------------------------+-----------------------+\n
                              |   AFB    | -0.030693939006905927  | -0.0027448398251912667 | 0.0026690127045430573 |\n
                              |    FL    |   0.7641860897390124   | -0.0031519177028962353 |  0.00318403722094425  |\n
                              |    S3    | -0.009793642767841643  | -0.0039500538800350165 |  0.003962284039325228 |\n
                              |    S4    |  -0.11948833798312776  | -0.005018301784506872  |  0.005112053156795224 |\n
                              |    S5    |  -0.14672854148123884  | -0.005077800231656763  | 0.0051383664423323315 |\n
                              |    S7    | -0.0009713979621990259 | -0.005287904531482017  |  0.005275166744474821 |\n
                              |    S8    |  0.003178551357900045  | -0.005257961171467131  |  0.005258879438751017 |\n
                              |    S9    |  0.005757808359963191  | -0.004016272402049568  |  0.004019873761938199 |\n
                              +----------+------------------------+------------------------+-----------------------+""" # GENERATOR LEVEL

    sample_2             = """+---------------------------------------------------------------------------------+\n
                              |                       q2_split_$1.10 < q^2 < 6.00$_average                      |\n
                              +----------+-----------------------+-----------------------+----------------------+\n
                              | Variable |         Value         |      Lower Error      |     Upper Error      |\n
                              +----------+-----------------------+-----------------------+----------------------+\n
                              |   AFB    |  -0.03611162259371692 | -0.008731742137981694 | 0.008731742137981694 |\n
                              |    FL    |   0.7816031469957773  | -0.010041813091402643 | 0.010041813091402643 |\n
                              |    S3    | -0.004913319742985065 | -0.010997797016445892 | 0.010997797016445892 |\n
                              |    S4    |  -0.11446696701061239 |  -0.0177373887414066  |  0.0177373887414066  |\n
                              |    S5    |  -0.1162615465324004  | -0.016777187198089353 | 0.016777187198089353 |\n
                              |    S7    |  0.013450446832457594 | -0.017351060768029697 | 0.017351060768029697 |\n
                              |    S8    |  0.012943806403734165 | -0.018166933762978635 | 0.018166933762978635 |\n
                              |    S9    | -0.015991133298640343 | -0.011753160273233804 | 0.011753160273233804 |\n
                              +----------+-----------------------+-----------------------+----------------------+""" # MC LEVEL

    variables    = ["AFB", "FL", "S3", "S4", "S5", "S7", "S8", "S9"]
    select_regex = [".*AFB.*\d+", ".*FL.*\d+", ".*S3.*\d+", ".*S4.*\d+", ".*S5.*\d+", ".*S7.*\d+", ".*S8.*\d+", ".*S9.*\d+"]
    value_regex  = "[- ]\d+.\d+"
    sample_table_1   = {'1': {'AFB': None, 'FL': None, 'S3': None, 'S4': None, 'S5': None, 'S7': None, 'S8': None, 'S9': None}}
    sample_table_2   = {'1': {'AFB': None, 'FL': None, 'S3': None, 'S4': None, 'S5': None, 'S7': None, 'S8': None, 'S9': None}}
    samples = [sample_1, sample_2]

    for variable, regex in zip(variables, select_regex):
        sample_1_splitted = samples[0].splitlines()
        for line in sample_1_splitted:
            subresult = re.match(regex, line)
            if subresult != None:
                substring = subresult.group(0)
                result    = re.findall(value_regex, substring)
                value     = np.float64(result[0])
                lower_err = np.float64(result[1])
                upper_err = np.float64(result[2])

                sample_table_1['1'][variable] = (value, lower_err, upper_err)

        sample_2_splitted = samples[1].splitlines()
        for line in sample_2_splitted:
            subresult = re.match(regex, line)
            if subresult != None:
                substring = subresult.group(0)
                result    = re.findall(value_regex, substring)
                value     = np.float64(result[0])
                lower_err = np.float64(result[1])
                upper_err = np.float64(result[2])

                sample_table_2['1'][variable] = (value, lower_err, upper_err)

    info_table = PrettyTable(["Variable", r"|MC Average - Gen|", "Lower Error", "Upper Error", "Stat. Significance"])
    for name in variables:
        index = '1'
        delta_value       = np.abs(sample_table_1[index][name][0] - sample_table_2[index][name][0])
        quadratic_lower   = -np.sqrt(sample_table_1[index][name][1]**2 + sample_table_2[index][name][1]**2)
        quadratic_upper   = np.sqrt(sample_table_1[index][name][2]**2 + sample_table_2[index][name][2]**2)
        stat_significance = np.abs(delta_value / quadratic_lower)
        info_table.add_row([name, delta_value, quadratic_lower, quadratic_upper, stat_significance])
    info_table.title = f"{bin_labels} Average over 3 Bins in MC"
    print(info_table)


if __name__ == "__main__":
    main()