Python Scripts used for Angular Analysis for B+toK*+Pi0mumu

Code/Scripts/Python Scripts/Generator Level Fit/angular_fit.py

@@ -0,0 +1,79 @@
+import os
+import dotenv
+import argparse
+import sys
+import pandas as pd
+import zfit
+
+from prettytable import PrettyTable
+
+dotenv.load_dotenv('../properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH'))
+
+from b2kstll.models.angular import B2Kstll
+from b2kstll.plot import plot_distributions
+
+from hep_analytics.processing.extract import FileManager
+from hep_analytics.processing.transform import select_feature
+
+
+FILE = os.getenv('FILE_GEN')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--q2bin', dest ='q2bin', default = 0)
+    args   = parser.parse_args()
+    Q2BIN  = int(args.q2bin)
+
+    bin_ranges = [(0.25, 4.00), (4.00, 8.00), (11.00, 12.50), (15.00, 18.00), (1.10, 6.00), (1.1, 2.5), (2.5, 4.0), (4.0, 6.0), (6.0, 8.0)]
+    print(f"Selected Q2 Bin Range is {bin_ranges[Q2BIN]}")
+
+    file_manager = FileManager(file = FILE, tree = "Events", 
+                               branches = ["q2", "costhetak", "costhetal", "phi"])
+    data         = file_manager.extract_data()
+    q2, costhetak, costhetal, phi = data[0], data[1], data[2], data[3]
+
+    q2, indices  = select_feature(feature = q2, limits = bin_ranges[Q2BIN])
+    costhetak    = costhetak[indices]
+    costhetal    = costhetal[indices]
+    phi          = phi[indices]
+
+    lower_costhetak_cut = float(os.getenv('LOWER_COSTHETAK_CUT'))
+    upper_costhetak_cut = float(os.getenv('UPPER_COSTHETAK_CUT'))
+    costhetak, indices  = select_feature(feature = costhetak, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2                  = q2[indices]
+    costhetal           = costhetal[indices]
+    phi                 = phi[indices]
+        
+    angular_data = pd.DataFrame({'ctl': costhetal, 'ctk': costhetak, 'phi': phi})
+    angular_data.to_csv(f"angular_fit_generator_bin_{Q2BIN}.csv", index = False)
+    x            = B2Kstll('ctl','ctk','phi')
+    obs, pdf, _  = x.get_pdf('PWave')
+    datazfit     = zfit.Data.from_pandas(df = angular_data, obs = obs)
+    nll          = zfit.loss.UnbinnedNLL(model = pdf, data = datazfit)
+    minimizer    = zfit.minimize.Minuit()
+
+    result = minimizer.minimize(nll)
+    print(result)
+    print(result.params, pdf)
+
+    param_errors, _ = result.errors()
+    print(param_errors)
+
+    info_table = PrettyTable(["Variable", "Value", "Lower Error", "Upper Error"])
+    fit_labels = ["AFB", "FL", "S3", "S4", "S5", "S7", "S8", "S9"]
+    for name in fit_labels:
+        value = result.params[name]["value"]
+        lower = result.params[name]["minuit_minos"]["lower"]
+        upper = result.params[name]["minuit_minos"]["upper"]
+        info_table.add_row([name, value, lower, upper])
+
+    print(info_table)
+
+    plot_distributions(result, suffix = f"accPwavePDF_generator_level_bin_{Q2BIN}")
+
+
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/angular_acceptance_modeling.py

@@ -0,0 +1,73 @@
+import os
+import dotenv
+import sys
+import argparse
+import mplhep
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+dotenv.load_dotenv('../properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH'))
+
+from analysis.efficiency import get_efficiency_model_class
+
+from hep_analytics.processing.extract import FileManager
+from hep_analytics.processing.transform import select_feature
+
+FILE_MC_PHSP  = os.getenv('MC_PHSP_FILE')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--q2bin', dest ='q2bin', default = 0)
+    args   = parser.parse_args()
+    Q2BIN  = int(args.q2bin)
+
+    mplhep.style.use("LHCb2")
+
+    bin_ranges = [(0.25, 4.00), (4.00, 8.00), (11.00, 12.50), (15.00, 18.00), (1.10, 6.00), (1.1, 2.5), (2.5, 4.0), (4.0, 6.0), (6.0, 8.0)]
+    print(f"Selected Q2 Bin Range is {bin_ranges[Q2BIN]}")
+
+    filemanager    = FileManager(file = FILE_MC_PHSP, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    mc_phsp_data   = filemanager.extract_data()
+    q2_mc_phsp, theta_k_mc_phsp, theta_l_mc_phsp, phi_mc_phsp = mc_phsp_data[0], mc_phsp_data[1], mc_phsp_data[2], mc_phsp_data[3]
+    q2_mc_phsp, indices  = select_feature(feature = q2_mc_phsp, limits = bin_ranges[Q2BIN])
+    phi_mc_phsp     = phi_mc_phsp[indices]
+    theta_l_mc_phsp = theta_l_mc_phsp[indices]
+    theta_k_mc_phsp = theta_k_mc_phsp[indices]
+    lower_costhetak_cut = float(os.getenv('LOWER_COSTHETAK_CUT'))
+    upper_costhetak_cut = float(os.getenv('UPPER_COSTHETAK_CUT'))
+    theta_k_mc_phsp, indices  = select_feature(feature = theta_k_mc_phsp, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_mc_phsp      = q2_mc_phsp[indices]
+    phi_mc_phsp     = phi_mc_phsp[indices]
+    theta_l_mc_phsp = theta_l_mc_phsp[indices]
+    data_mc_phsp    = [phi_mc_phsp, theta_l_mc_phsp, theta_k_mc_phsp, q2_mc_phsp]
+    
+    df     = pd.DataFrame({'ctl': data_mc_phsp[1], 'ctk': data_mc_phsp[2], 'phi': data_mc_phsp[0], 'q2': q2_mc_phsp})
+    orders = {"ctl": 4, "ctk": 6, "phi": 2}
+    ranges = {"ctl": [-1.0, 1.0], "ctk": [lower_costhetak_cut, upper_costhetak_cut], "phi": [-np.pi, np.pi]}
+
+    EffClass = get_efficiency_model_class('legendre')
+    eff      = EffClass.fit(df, ['ctl', 'ctk', 'phi'], ranges = ranges,
+                            legendre_orders = orders, calculate_cov = False, chunk_size = 2000)
+
+    out_file = eff.write_to_disk(f'acc_3d_JpsiKstMC_{Q2BIN}_bin.yaml')
+    print(out_file)
+
+    labels = {'ctl': r'$\cos \theta_L$', 'ctk': r'$\cos \theta_K$', 'phi': '$\phi$', 'q2': '$q^2$ [GeV$^2$]'}
+    for v in ['ctl', 'ctk', 'phi']:
+        plt.subplots(figsize = (15, 10))
+        plt.xlim(*ranges[v])
+        x, y = eff.project_efficiency(v, n_points = 1000)
+        plt.plot(x, y, 'b-')
+        plt.hist(df[v], density = True, bins = 50, color = 'grey', alpha = 0.5)
+        plt.ylabel("a.u.", horizontalalignment = 'right', y = 1.0)
+        plt.xlabel(labels[v], horizontalalignment = 'right', x = 1.0)
+        plt.savefig(f'acc_3d_JpsiKstMC_phsp_mc_{v}_{Q2BIN}_bin.pdf')
+        plt.close()
+
+    
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/angular_fit.py

@@ -0,0 +1,77 @@
+import os
+import dotenv
+import sys
+import argparse
+import pandas as pd
+import mplhep
+import zfit
+
+from prettytable import PrettyTable
+
+dotenv.load_dotenv('../properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH'))
+
+from b2kstll.models.angular import B2Kstll
+from b2kstll.plot import plot_distributions
+
+from hep_analytics.processing.extract import FileManager
+from hep_analytics.processing.transform import select_feature
+
+FILE_MC  = os.getenv('MC_FILE')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--q2bin', dest ='q2bin', default = 0)
+    args   = parser.parse_args()
+    Q2BIN  = int(args.q2bin)
+
+    mplhep.style.use("LHCb2")
+
+    bin_ranges = [(0.25, 4.00), (4.00, 8.00), (11.00, 12.50), (15.00, 18.00), (1.10, 6.00), (1.1, 2.5), (2.5, 4.0), (4.0, 6.0), (6.0, 8.0)]
+    print(f"Selected Q2 Bin Range is {bin_ranges[Q2BIN]}")
+
+    filemanager    = FileManager(file = FILE_MC, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    mc_data        = filemanager.extract_data()
+    q2_mc, theta_k_mc, theta_l_mc, phi_mc = mc_data[0], mc_data[1], mc_data[2], mc_data[3]
+    q2_mc, indices = select_feature(feature = q2_mc, limits = bin_ranges[Q2BIN])
+    phi_mc         = phi_mc[indices]
+    theta_l_mc     = theta_l_mc[indices]
+    theta_k_mc     = theta_k_mc[indices]
+    lower_costhetak_cut = float(os.getenv('LOWER_COSTHETAK_CUT'))
+    upper_costhetak_cut = float(os.getenv('UPPER_COSTHETAK_CUT'))
+    theta_k_mc, indices  = select_feature(feature = theta_k_mc, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_mc          = q2_mc[indices]
+    phi_mc         = phi_mc[indices]
+    theta_l_mc     = theta_l_mc[indices]
+    
+    angular_data = pd.DataFrame({'ctl': theta_l_mc, 'ctk': theta_k_mc, 'phi': phi_mc})
+    angular_data.to_csv(f"ang_fit_mc_{Q2BIN}_bin.csv", index = False)
+    x = B2Kstll('ctl','ctk','phi')
+    x.set_acc(f"./acc_3d_JpsiKstMC_{Q2BIN}_bin.yaml")
+    obs, pdf, params = x.get_pdf('PWave')
+
+    datazfit  = zfit.Data.from_pandas(df = angular_data, obs = obs)
+    nll       = zfit.loss.UnbinnedNLL(model = pdf, data = datazfit)
+    minimizer = zfit.minimize.Minuit()
+    result    = minimizer.minimize(nll)
+
+    param_errors, _ = result.errors()
+    print(param_errors)
+
+    info_table = PrettyTable(["Variable", "Value", "Lower Error", "Upper Error"])
+    fit_labels = ["AFB", "FL", "S3", "S4", "S5", "S7", "S8", "S9"]
+    for name in fit_labels:
+        value = result.params[name]["value"]
+        lower = result.params[name]["minuit_minos"]["lower"]
+        upper = result.params[name]["minuit_minos"]["upper"]
+        info_table.add_row([name, value, lower, upper])
+
+    print(info_table)
+
+    plot_distributions(result, suffix = f"accPwavePDF_mc_ang_fit_{Q2BIN}_bin")
+
+    
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/diff_pair_tables_average_mc.py

@@ -0,0 +1,83 @@
+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()

Code/Scripts/Python Scripts/MC Fit/diff_pair_tables_average_mc_reweighted.py

@@ -0,0 +1,81 @@
+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
+                              | Variable |         Value         |      Lower Error       |      Upper Error      |\n
+                              +----------+-----------------------+------------------------+-----------------------+\n
+                              |   AFB    | -0.012550006150333942 | -0.0026956457681952418 | 0.0026965400452885245 |\n
+                              |    FL    |   0.775244817820803   | -0.0030583204477219544 |  0.003052276555621123 |\n
+                              |    S3    | -0.004731791649125892 | -0.0035876206689923096 | 0.0035671656402230033 |\n
+                              |    S4    |  -0.12872329698226329 | -0.0054353577466807685 |  0.005452103886085265 |\n
+                              |    S5    |  -0.13102847916212362 | -0.005094396678852025  |  0.005083576918431511 |\n
+                              |    S7    |  0.014829855067600298 | -0.005251337297972407  |  0.005258433080994564 |\n
+                              |    S8    |  0.011919411650166327 | -0.005666331650738382  |  0.005691209183046813 |\n
+                              |    S9    | -0.013513044362093558 | -0.0036909184587611017 | 0.0036915155625497006 |\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 reweighted - 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}"
+    print(info_table)
+
+
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/diff_pair_tables_mc_gen.py

@@ -0,0 +1,81 @@
+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
+                              | Variable |         Value         |      Lower Error      |     Upper Error      |\n
+                              +----------+-----------------------+-----------------------+----------------------+\n
+                              |   AFB    | -0.006858788562096526 | -0.006288887141153866 | 0.006202211516385528 |\n
+                              |    FL    |   0.7741933027966281  | -0.007196527356496095 | 0.006980839734409447 |\n
+                              |    S3    | -0.005794055258693013 | -0.008257409210173627 | 0.008381420647898805 |\n
+                              |    S4    |  -0.13252141252161223 | -0.012754778513953539 | 0.012393845350580537 |\n
+                              |    S5    |  -0.13982805972042112 | -0.011883305368342971 | 0.011682110709131568 |\n
+                              |    S7    |  0.01499315459684105  | -0.012227400419826324 | 0.012191295064893278 |\n
+                              |    S8    |  0.010750628153590385 | -0.013096041377945507 | 0.013227158788846905 |\n
+                              |    S9    | -0.013084904237743692 |  -0.00855475117009418 | 0.008616146883219716 |\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 - 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}"
+    print(info_table)
+
+
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/reweighted_angular_acceptance_modeling.py

@@ -0,0 +1,94 @@
+import os
+import dotenv
+import sys
+import argparse
+import mplhep
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+dotenv.load_dotenv('../properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH'))
+
+from analysis.efficiency import get_efficiency_model_class
+
+from hep_analytics.processing.extract import FileManager
+from hep_analytics.processing.transform import select_feature, reweight_feature
+from hep_analytics.processing.visualisation import reweight_comparing_plot
+
+FILE_GEN     = os.getenv('GEN_FILE')
+FILE_MC_PHSP = os.getenv('MC_PHSP_FILE')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--q2bin', dest ='q2bin', default = 0)
+    args   = parser.parse_args()
+    Q2BIN  = int(args.q2bin)
+
+    mplhep.style.use("LHCb2")
+
+    bin_ranges = [(0.25, 4.00), (4.00, 8.00), (11.00, 12.50), (15.00, 18.00), (1.10, 6.00), (1.1, 2.5), (2.5, 4.0), (4.0, 6.0), (6.0, 8.0)]
+    print(f"Selected Q2 Bin Range is {bin_ranges[Q2BIN]}")
+
+    bin_labels     = [r"$0.25 < q^2 < 4.00$", r"$4.00 < q^2 < 8.00$", r"$11.00 < q^2 < 12.50$",
+                      r"$15.00 < q^2 < 18.00$", r"$1.10 < q^2 < 6.00$",
+                      r"$1.1 < q^2 < 2.5$", r"$2.5 < q^2 < 4.0$", r"$4.0 < q^2 < 6.0$", r"$6.0 < q^2 < 8.0$"]
+
+    filemanager     = FileManager(file = FILE_MC_PHSP, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    mc_phsp_data    = filemanager.extract_data()
+    q2_mc_phsp, theta_k_mc_phsp, theta_l_mc_phsp, phi_mc_phsp = mc_phsp_data[0], mc_phsp_data[1], mc_phsp_data[2], mc_phsp_data[3]
+    q2_mc_phsp, indices = select_feature(feature = q2_mc_phsp, limits = bin_ranges[Q2BIN])
+    phi_mc_phsp     = phi_mc_phsp[indices]
+    theta_l_mc_phsp = theta_l_mc_phsp[indices]
+    theta_k_mc_phsp = theta_k_mc_phsp[indices]
+    lower_costhetak_cut = float(os.getenv('LOWER_COSTHETAK_CUT'))
+    upper_costhetak_cut = float(os.getenv('UPPER_COSTHETAK_CUT'))
+    theta_k_mc_phsp, indices  = select_feature(feature = theta_k_mc_phsp, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_mc_phsp      = q2_mc_phsp[indices]
+    phi_mc_phsp     = phi_mc_phsp[indices]
+    theta_l_mc_phsp = theta_l_mc_phsp[indices]
+
+    filemanager = FileManager(file = FILE_GEN, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    gen_data    = filemanager.extract_data()
+    q2_gen, theta_k_gen, theta_l_gen, phi_gen = gen_data[0], gen_data[1], gen_data[2], gen_data[3]
+    q2_gen, indices = select_feature(feature = q2_gen, limits = bin_ranges[Q2BIN])
+    phi_gen     = phi_gen[indices]
+    theta_l_gen = theta_l_gen[indices]
+    theta_k_gen = theta_k_gen[indices]
+    theta_k_gen, indices  = select_feature(feature = theta_k_gen, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_gen      = q2_gen[indices]
+    phi_gen     = phi_gen[indices]
+    theta_l_gen = theta_l_gen[indices]
+
+    q2_mc_phsp_weights = reweight_feature(original_feature = q2_mc_phsp, target_feature = q2_gen, n_bins = 25)
+    reweight_comparing_plot(original_feature = q2_mc_phsp, target_feature = q2_gen, weights = q2_mc_phsp_weights,
+        n_bins = 25, suptitle = f"{bin_labels[Q2BIN]}", 
+        titles = ["Q2 MC PHSP", "Q2 MC PHSP (reweighted)", "Q2 Gen"], save = f"reweighted_q2_gen_mc_phsp_{Q2BIN}_bin.png")
+    
+    df       = pd.DataFrame({'ctl': theta_l_mc_phsp, 'ctk': theta_k_mc_phsp, 'phi': phi_mc_phsp, 'q2': q2_mc_phsp, 'weights': q2_mc_phsp_weights})
+    orders   = {"ctl": 4, "ctk": 6, "phi": 2}
+    ranges   = {"ctl": [-1.0, 1.0], "ctk": [lower_costhetak_cut, upper_costhetak_cut], "phi": [-np.pi, np.pi]}
+    EffClass = get_efficiency_model_class('legendre')
+    eff      = EffClass.fit(df, ['ctl', 'ctk', 'phi'], weight_var = "weights", ranges = ranges,
+                            legendre_orders = orders, calculate_cov = False, chunk_size = 2000)
+
+    out_file = eff.write_to_disk(f'acc_3d_JpsiKstMC_reweighted_{Q2BIN}_bin.yaml')
+    print(out_file)
+
+    labels = {'ctl': r'$\cos \theta_L$', 'ctk': r'$\cos \theta_K$', 'phi': '$\phi$', 'q2': '$q^2$ [GeV$^2$]'}
+    for v in ['ctl', 'ctk', 'phi']:
+        fig, ax = plt.subplots(figsize = (15, 10))
+        plt.xlim(*ranges[v])
+        x, y = eff.project_efficiency(v, n_points = 1000)
+        plt.plot(x, y, 'b-')
+        plt.hist(df[v], density = True, bins = 50, color = 'grey', alpha = 0.5)
+        plt.ylabel("a.u.", horizontalalignment = 'right', y = 1.0)
+        plt.xlabel(labels[v], horizontalalignment = 'right', x = 1.0)
+        plt.savefig(f'acc_3d_JpsiKstMC_{v}_{Q2BIN}_bin.pdf')
+        plt.close()
+
+    
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/reweighted_angular_fit.py

@@ -0,0 +1,97 @@
+import os
+import dotenv
+import sys
+import argparse
+import pandas as pd
+import mplhep
+import zfit
+from prettytable import PrettyTable
+
+dotenv.load_dotenv('../properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH'))
+
+from b2kstll.models.angular import B2Kstll
+from b2kstll.plot import plot_distributions
+
+from hep_analytics.processing.extract import FileManager
+from hep_analytics.processing.transform import select_feature, reweight_feature
+from hep_analytics.processing.visualisation import reweight_comparing_plot
+
+FILE_MC  = os.getenv('MC_FILE')
+FILE_GEN = os.getenv('GEN_FILE')
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--q2bin', dest ='q2bin', default = 0)
+    args   = parser.parse_args()
+    Q2BIN  = int(args.q2bin)
+
+    mplhep.style.use("LHCb2")
+
+    bin_ranges = [(0.25, 4.00), (4.00, 8.00), (11.00, 12.50), (15.00, 18.00), (1.10, 6.00), (1.1, 2.5), (2.5, 4.0), (4.0, 6.0), (6.0, 8.0)]
+    print(f"Selected Q2 Bin Range is {bin_ranges[Q2BIN]}")
+
+    bin_labels = [r"$0.25 < q^2 < 4.00$", r"$4.00 < q^2 < 8.00$", r"$11.00 < q^2 < 12.50$",
+                  r"$15.00 < q^2 < 18.00$", r"$1.10 < q^2 < 6.00$",
+                  r"$1.1 < q^2 < 2.5$", r"$2.5 < q^2 < 4.0$", r"$4.0 < q^2 < 6.0$", r"$6.0 < q^2 < 8.0$"]
+
+    filemanager    = FileManager(file = FILE_MC, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    mc_data        = filemanager.extract_data()
+    q2_mc, theta_k_mc, theta_l_mc, phi_mc = mc_data[0], mc_data[1], mc_data[2], mc_data[3]
+    q2_mc, indices = select_feature(feature = q2_mc, limits = bin_ranges[Q2BIN])
+    phi_mc         = phi_mc[indices]
+    theta_l_mc     = theta_l_mc[indices]
+    theta_k_mc     = theta_k_mc[indices]
+    lower_costhetak_cut = float(os.getenv('LOWER_COSTHETAK_CUT'))
+    upper_costhetak_cut = float(os.getenv('UPPER_COSTHETAK_CUT'))
+    theta_k_mc, indices  = select_feature(feature = theta_k_mc, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_mc          = q2_mc[indices]
+    phi_mc         = phi_mc[indices]
+    theta_l_mc     = theta_l_mc[indices]
+
+    filemanager = FileManager(file = FILE_GEN, tree = "Events", branches = ["q2", "costhetak", "costhetal", "phi"])
+    gen_data    = filemanager.extract_data()
+    q2_gen, theta_k_gen, theta_l_gen, phi_gen = gen_data[0], gen_data[1], gen_data[2], gen_data[3]
+    q2_gen, indices = select_feature(feature = q2_gen, limits = bin_ranges[Q2BIN])
+    phi_gen     = phi_gen[indices]
+    theta_l_gen = theta_l_gen[indices]
+    theta_k_gen = theta_k_gen[indices]
+    theta_k_gen, indices  = select_feature(feature = theta_k_gen, limits = (lower_costhetak_cut, upper_costhetak_cut))
+    q2_gen      = q2_gen[indices]
+    phi_gen     = phi_gen[indices]
+    theta_l_gen = theta_l_gen[indices]
+    
+    angular_data     = pd.DataFrame({'ctl': theta_l_mc, 'ctk': theta_k_mc, 'phi': phi_mc})
+    angular_data.to_csv(f"ang_fit_mc_q2_bins_{Q2BIN}_bin.csv", index = False)
+    x                = B2Kstll('ctl','ctk','phi')
+    x.set_acc(f"./acc_3d_JpsiKstMC_reweighted_4_bin.yaml")
+    obs, pdf, _      = x.get_pdf('PWave')
+
+    q2_mc_weights = reweight_feature(original_feature = q2_mc, target_feature = q2_gen, n_bins = 25)
+    reweight_comparing_plot(original_feature = q2_mc, target_feature = q2_gen, weights = q2_mc_weights,
+        n_bins = 25, suptitle = f"{bin_labels[Q2BIN]}", titles = ["Q2 MC", "Q2 MC (reweighted)", "Q2 Gen"], save = "reweighted_q2_gen_mc.png")
+
+    datazfit        = zfit.Data.from_pandas(df = angular_data, obs = obs, weights = q2_mc_weights)
+    nll             = zfit.loss.UnbinnedNLL(model = pdf, data = datazfit)
+    minimizer       = zfit.minimize.Minuit()
+    result          = minimizer.minimize(nll)
+    param_errors, _ = result.errors()
+    print(param_errors)
+
+    info_table = PrettyTable(["Variable", "Value", "Lower Error", "Upper Error"])
+    fit_labels = ["AFB", "FL", "S3", "S4", "S5", "S7", "S8", "S9"]
+    for name in fit_labels:
+        value = result.params[name]["value"]
+        lower = result.params[name]["minuit_minos"]["lower"]
+        upper = result.params[name]["minuit_minos"]["upper"]
+        info_table.add_row([name, value, lower, upper])
+
+    print(info_table)
+
+    plot_distributions(result, suffix = f"accPwavePDF_{Q2BIN}_bin_reweighted_mc")
+
+    
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/MC Fit/table_average_to_compare.py

@@ -0,0 +1,97 @@
+import re
+import numpy as np
+
+from prettytable import PrettyTable
+
+
+def main():
+    table_1 = """+----------+-----------------------+-----------------------+----------------------+\n
+                 | Variable |         Value         |      Lower Error      |     Upper Error      |\n
+                 +----------+-----------------------+-----------------------+----------------------+\n
+                 |   AFB    |  -0.1327941714665493  | -0.011751983569979923 | 0.011695518975582573 |\n
+                 |    FL    |   0.778784190310989   | -0.013786738313616998 | 0.01334631516152801  |\n
+                 |    S3    |  0.012016752919524067 | -0.014186281678810328 | 0.01390470699489175  |\n
+                 |    S4    | 0.0030912112690471196 |  -0.02494551503535478 | 0.02500682819273369  |\n
+                 |    S5    |  0.06257482631549156  | -0.022576669869741432 | 0.02267902660423071  |\n
+                 |    S7    |  0.026461647341068015 | -0.022870493984060422 | 0.022709046371542273 |\n
+                 |    S8    |  0.022528200778115424 | -0.024500119399894143 | 0.02444883875849664  |\n
+                 |    S9    | -0.010047596608480971 | -0.015100958783891871 | 0.01497061747614531  |\n
+                 +----------+-----------------------+-----------------------+----------------------+"""
+
+    table_2 = """+----------+-----------------------+-----------------------+----------------------+\n
+                 | Variable |         Value         |      Lower Error      |     Upper Error      |\n
+                 +----------+-----------------------+-----------------------+----------------------+\n
+                 |   AFB    | -0.044313915998597596 | -0.011266005942710903 | 0.011376116194169396 |\n
+                 |    FL    |   0.8080898316779715  | -0.012903371237386076 | 0.012627755576193413 |\n
+                 |    S3    | -0.001350693384098943 |  -0.01425102196417036 | 0.014014236056631763 |\n
+                 |    S4    |  -0.16348388538343442 | -0.022982703026786865 | 0.02353050491741336  |\n
+                 |    S5    |  -0.12998638915138938 |  -0.02207623402690808 | 0.02230804022923196  |\n
+                 |    S7    | -0.019175072605277906 | -0.022219297227352726 | 0.02233298418372788  |\n
+                 |    S8    |  0.03896504393685167  |  -0.02306667997644898 | 0.023056355590581525 |\n
+                 |    S9    | -0.026410777123662296 |  -0.01497373735832672 | 0.015237714795859537 |\n
+                 +----------+-----------------------+-----------------------+----------------------+"""
+
+    table_3 = """+----------+-----------------------+-----------------------+----------------------+\n
+                 | Variable |         Value         |      Lower Error      |     Upper Error      |\n
+                 +----------+-----------------------+-----------------------+----------------------+\n
+                 |   AFB    |  0.06877321968399613  |  -0.00873785505692959 | 0.008866035437567673 |\n
+                 |    FL    |   0.7579354189983714  |  -0.01048129883366948 | 0.01017491937670441  |\n
+                 |    S3    |  -0.02540601876438032 | -0.012075664333196083 | 0.012192632205060838 |\n
+                 |    S4    |  -0.18300822691744986 | -0.015545142299112552 | 0.016136099542591972 |\n
+                 |    S5    |  -0.28137307676130335 |  -0.0160784362375397  | 0.01630021297009425  |\n
+                 |    S7    |  0.033064765761582675 |  -0.01837491321971226 | 0.018457429889962827 |\n
+                 |    S8    | -0.022661825503764606 | -0.018831356033962507 | 0.018816177761568176 |\n
+                 |    S9    |  -0.01151502616377776 | -0.012778180225448249 | 0.013091600028830737 |\n
+                 +----------+-----------------------+-----------------------+----------------------+"""
+
+    bin_labels     = [r"$0.25 < q^2 < 4.00$", r"$4.00 < q^2 < 8.00$", r"$11.00 < q^2 < 12.50$",
+                      r"$15.00 < q^2 < 18.00$", r"$1.10 < q^2 < 6.00$",
+                      r"$1.1 < q^2 < 2.5$", r"$2.5 < q^2 < 4.0$", r"$4.0 < q^2 < 6.0$", r"$6.0 < q^2 < 8.0$"]
+
+    tables       = [table_1, table_2, table_3]
+    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+"
+    samples      = {'1': {'AFB': None, 'FL': None, 'S3': None, 'S4': None, 'S5': None, 'S7': None, 'S8': None, 'S9': None},
+                    '2': {'AFB': None, 'FL': None, 'S3': None, 'S4': None, 'S5': None, 'S7': None, 'S8': None, 'S9': None},
+                    '3': {'AFB': None, 'FL': None, 'S3': None, 'S4': None, 'S5': None, 'S7': None, 'S8': None, 'S9': None},
+                   }
+
+    for index in range(len(tables)):
+        for variable, regex in zip(variables, select_regex):
+            splitted = tables[index].splitlines()
+            for line in 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])
+
+                    samples[str(index + 1)][variable] = (value, lower_err, upper_err)
+
+    fit_variables_split = [[] for _ in range(8)]
+    fit_errors_split    = [[] for _ in range(8)]
+    for value in samples.values():
+        count = 0
+        for fitvalue in value.values():
+            fit_variables_split[count].append(fitvalue[0])
+            fit_errors_split[count].append(np.sqrt(fitvalue[1]**2 + fitvalue[2]**2))
+            count += 1
+
+    info_table = PrettyTable(["Variable", "Value", "Lower Error", "Upper Error"])
+    info_table.title = f"q2_split_{bin_labels[4]}_average"
+    fit_labels = ["AFB", "FL", "S3", "S4", "S5", "S7", "S8", "S9"]
+    count = 0
+    for name, fit_split_var, fit_err_split in zip(fit_labels, fit_variables_split, fit_errors_split):
+        fit_avg     = np.mean(fit_split_var)
+        error_split = 1/3 * np.sqrt(fit_err_split[0]**2 + fit_err_split[1]**2 + fit_err_split[2]**2)
+        info_table.add_row([name, fit_avg, -error_split, error_split])
+        count += 1
+
+    print(info_table)
+
+    
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/properties.env

@@ -0,0 +1,7 @@
+LOWER_COSTHETAK_CUT=-1.00
+UPPER_COSTHETAK_CUT=0.851
+SYS_PATH=../../
+SYS_PATH_LEVEL_1=../
+GEN_FILE=../../KplusPi0Resolved_Run2_MC_EvtGen_FCNC.root
+MC_FILE=../../KplusPi0Resolved_Run2_MC_FCNC.root
+MC_PHSP_FILE="../../KplusPi0Resolved_Run2_PHSP_FCNC.root"

Code/Scripts/Python Scripts/requirements.txt

@@ -0,0 +1,208 @@
+absl-py==0.15.0
+aenum==3.1.11
+algopy==0.5.7
+analysis @ git+https://github.com/mayou36/analysis-tools@5db2f64e48cac26954d182b62eea7665d26847d2
+appdirs==1.4.4
+argon2-cffi @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi_1640817743617/work
+argon2-cffi-bindings @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi-bindings_1649500321618/work
+asdf==2.11.1
+asdf-standard==1.0.2
+asdf-transform-schemas==0.2.2
+asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1618968359944/work
+astunparse==1.6.3
+attrs @ file:///home/conda/feedstock_root/build_artifacts/attrs_1640799537051/work
+awkward==1.8.0
+awkward0==0.15.5
+-e git+https://gitlab.cern.ch/LHCb-RD/ewp-bd2ksteeangular-legacy.git@c5e306ac36ce7de31ff8c0e2f1833c1d3b2e1dcb#egg=b2kstll&subdirectory=b2kstll
+backcall @ file:///home/conda/feedstock_root/build_artifacts/backcall_1592338393461/work
+backports.functools-lru-cache @ file:///home/conda/feedstock_root/build_artifacts/backports.functools_lru_cache_1618230623929/work
+beautifulsoup4 @ file:///home/conda/feedstock_root/build_artifacts/beautifulsoup4_1649463573192/work
+bleach @ file:///home/conda/feedstock_root/build_artifacts/bleach_1649361991009/work
+cachetools==4.2.4
+certifi==2021.10.8
+cffi @ file:///home/conda/feedstock_root/build_artifacts/cffi_1636046055389/work
+charset-normalizer==2.0.12
+ckmutil==0.3.2
+clang==5.0
+cloudpickle==2.0.0
+colorama @ file:///home/conda/feedstock_root/build_artifacts/colorama_1602866480661/work
+colored==1.4.3
+colorlog==6.6.0
+ConfigArgParse==1.5.3
+connection-pool==0.0.3
+contextlib2==21.6.0
+cycler==0.11.0
+datrie==0.8.2
+debugpy @ file:///home/conda/feedstock_root/build_artifacts/debugpy_1649586347330/work
+decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
+defusedxml @ file:///home/conda/feedstock_root/build_artifacts/defusedxml_1615232257335/work
+dm-tree==0.1.7
+docutils==0.18.1
+dotmap==1.3.30
+dpath==2.0.6
+entrypoints @ file:///home/conda/feedstock_root/build_artifacts/entrypoints_1643888246732/work
+executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1646044401614/work
+fasteners==0.17.3
+fastjsonschema @ file:///home/conda/feedstock_root/build_artifacts/python-fastjsonschema_1641751198313/work/dist
+flatbuffers==1.12
+flavio==2.3.3
+flit_core @ file:///home/conda/feedstock_root/build_artifacts/flit-core_1645629044586/work/source/flit_core
+fonttools==4.33.3
+formulate==0.1.1
+future==0.18.2
+gast==0.4.0
+gitdb==4.0.9
+GitPython==3.1.27
+google-auth==1.35.0
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.46.1
+h5py==3.1.0
+hep-ml==0.7.1
+hepstats==0.5.0
+hepunits==2.2.0
+idna==3.3
+iminuit @ file:///home/conda/feedstock_root/build_artifacts/iminuit_1649770305045/work
+importlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1648728288044/work
+importlib-resources @ file:///home/conda/feedstock_root/build_artifacts/importlib_resources_1650169872758/work
+iniconfig==1.1.1
+ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1649684276995/work/dist/ipykernel-6.13.0-py3-none-any.whl
+ipyopt==0.11.0
+ipyparallel @ file:///home/conda/feedstock_root/build_artifacts/ipyparallel_1652183878568/work
+ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1651238283435/work
+ipython-genutils==0.2.0
+jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1649067096717/work
+Jinja2 @ file:///home/conda/feedstock_root/build_artifacts/jinja2_1651774399431/work
+jmespath==1.0.0
+joblib==1.1.0
+jsonschema @ file:///home/conda/feedstock_root/build_artifacts/jsonschema-meta_1651798819471/work
+jupyter-client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1652061014773/work
+jupyter-core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1652365269273/work
+jupyterlab-pygments @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_pygments_1649936611996/work
+keras==2.6.0
+Keras-Preprocessing==1.1.2
+kiwisolver==1.4.2
+llvmlite==0.38.0
+Markdown==3.3.7
+MarkupSafe @ file:///home/conda/feedstock_root/build_artifacts/markupsafe_1648737556467/work
+matplotlib==3.5.2
+matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1631080358261/work
+metakernel @ file:///home/conda/feedstock_root/build_artifacts/metakernel_1648594625035/work
+mistune @ file:///home/conda/feedstock_root/build_artifacts/mistune_1635844679781/work
+mplhep==0.3.23
+mplhep-data==0.0.3
+mpmath==1.2.1
+nbclient @ file:///home/conda/feedstock_root/build_artifacts/nbclient_1652155694429/work
+nbconvert @ file:///home/conda/feedstock_root/build_artifacts/nbconvert-meta_1649676641343/work
+nbformat @ file:///home/conda/feedstock_root/build_artifacts/nbformat_1651607001005/work
+nest-asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1648959695634/work
+nlopt==2.7.0
+notebook @ file:///home/conda/feedstock_root/build_artifacts/notebook_1650363291341/work
+numba @ file:///home/conda/feedstock_root/build_artifacts/numba_1652226553013/work
+numdifftools==0.9.40
+numexpr==2.8.1
+numpy==1.19.5
+oauthlib==3.2.0
+opt-einsum==3.3.0
+ordered-set==4.1.0
+packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1637239678211/work
+pandas==1.4.2
+pandocfilters @ file:///home/conda/feedstock_root/build_artifacts/pandocfilters_1631603243851/work
+parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1638334955874/work
+particle==0.20.1
+patsy==0.5.2
+pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1602535608087/work
+pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
+Pillow==9.1.0
+plac==1.3.5
+pluggy==1.0.0
+portalocker @ file:///home/conda/feedstock_root/build_artifacts/portalocker_1645465641398/work
+prettytable==3.3.0
+progressbar2==4.0.0
+prometheus-client @ file:///home/conda/feedstock_root/build_artifacts/prometheus_client_1649447152425/work
+prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1649130487073/work
+protobuf==3.20.1
+psutil @ file:///home/conda/feedstock_root/build_artifacts/psutil_1648872973590/work
+ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
+PuLP==2.6.0
+pure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work
+py==1.11.0
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser @ file:///home/conda/feedstock_root/build_artifacts/pycparser_1636257122734/work
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1650904496387/work
+pylha==0.4
+pyparsing @ file:///home/conda/feedstock_root/build_artifacts/pyparsing_1652235407899/work
+PyRoot==0.3.0
+pyrsistent @ file:///home/conda/feedstock_root/build_artifacts/pyrsistent_1649013355209/work
+pytest==7.1.2
+python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work
+python-dotenv==0.20.0
+python-utils==3.2.2
+pytz==2022.1
+PyYAML==6.0
+pyzmq @ file:///home/conda/feedstock_root/build_artifacts/pyzmq_1649055645150/work
+ratelimiter==1.2.0.post0
+requests==2.27.1
+requests-oauthlib==1.3.1
+retry==0.9.2
+root-numpy @ file:///home/conda/feedstock_root/build_artifacts/root_numpy_1642275926538/work
+root-pandas==0.7.0
+rsa==4.8
+rundec==0.5.2
+scikit-learn==1.1.0
+scipy==1.8.0
+seaborn==0.11.2
+semantic-version==2.9.0
+Send2Trash @ file:///home/conda/feedstock_root/build_artifacts/send2trash_1628511208346/work
+six==1.15.0
+smart-open==6.0.0
+smmap==5.0.0
+snakemake==7.6.2
+soupsieve @ file:///home/conda/feedstock_root/build_artifacts/soupsieve_1638550740809/work
+stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1644872665635/work
+statsmodels==0.13.2
+stopit==1.1.2
+sympy==1.10.1
+tables==3.7.0
+tabulate==0.8.9
+tensorboard==2.6.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.6.3
+tensorflow-addons==0.16.1
+tensorflow-estimator==2.6.0
+tensorflow-gpu==2.6.3
+tensorflow-graphics-gpu==1.0.0
+tensorflow-probability==0.13.0
+termcolor==1.1.0
+terminado @ file:///home/conda/feedstock_root/build_artifacts/terminado_1649103779998/work
+texttable==1.6.4
+tf-quant-finance==0.0.1.dev30
+Theano==1.0.5
+threadpoolctl==3.1.0
+tinycss2 @ file:///home/conda/feedstock_root/build_artifacts/tinycss2_1637612658783/work
+tomli==2.0.1
+toposort==1.7
+tornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1648827245914/work
+tqdm @ file:///home/conda/feedstock_root/build_artifacts/tqdm_1649051611147/work
+traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1652201717608/work
+typeguard==2.13.3
+typing-extensions==3.10.0.2
+uhi==0.3.1
+uncertainties==3.1.6
+uproot==4.2.3
+uproot3-methods==0.10.1
+urllib3==1.26.9
+voluptuous==0.13.1
+wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1600965781394/work
+webencodings==0.5.1
+Werkzeug==2.1.2
+wilson==2.2.1
+wrapt==1.12.1
+xgboost==1.6.1
+xrootd==5.4.2
+yamlloader==1.1.0
+yte==1.4.0
+zfit==0.8.3
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1649012893348/work

Code/Scripts/Python Scripts/root_file_inspect.py

@@ -0,0 +1,29 @@
+import os
+import dotenv
+import sys
+import argparse
+
+dotenv.load_dotenv('properties.env')
+
+sys.path.insert(0, os.getenv('SYS_PATH_LEVEL_1'))
+
+from rootio import RootIO
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--file', dest = 'file', default = '')
+    parser.add_argument('--regex', dest = 'regex', default = '')
+    args   = parser.parse_args()
+    FILE   = args.file
+    regex  = args.regex
+
+    rootio = RootIO(FILE)
+    if regex:
+        rootio.get_information(regex = regex)
+        return
+    rootio.get_information()
+        
+
+if __name__ == "__main__":
+    main()

Code/Scripts/Python Scripts/rootio.py

@@ -0,0 +1,37 @@
+import os
+import re
+import uproot
+
+
+class RootIO:
+    def __init__(self, path_to_file: str):
+        if not os.path.exists(path = path_to_file):
+            raise ValueError("Path does not exists!")
+        self.path_to_file = path_to_file
+
+
+    def get_information(self, regex: str = None) -> None:
+        with uproot.open(self.path_to_file) as file:
+            print(f"File classnames:\n{file.classnames()}")
+            for classname, classtype in file.classnames().items():
+                print(f"Classname:\n{classname}")
+                print(f"Classtype:\n{classtype}")
+                print(f"Content of the class:")
+                for name, branch in file[classname].items():
+                    print(f"{name}: {branch}")
+                if regex != None:
+                    print(f"Regex search results:")
+                    attributes = file[classname].keys()
+                    for attribute in attributes:
+                        result = self.__find_pattern_in_text(regex = regex, text = attribute)
+                        if result != "":
+                            print(f"{result}")
+
+
+    def __find_pattern_in_text(self, regex: str, text: str) -> str:
+        search_result = re.search(pattern = regex, string = text)
+        result        = ""
+        if search_result != None:
+            result = search_result.group(0)
+
+        return result

Code/Scripts/hep_analytics/pathing/aggregate.py

@@ -0,0 +1,13 @@
+class PathAggregator:
+    def __init__(self, basefolder: str, directory: str, file: str, year: str = None) -> None:
+        self.basefolder = basefolder
+        self.directory  = directory
+        self.file       = file
+        self.year       = year
+
+
+    def get_path_to_file(self) -> str:
+        if self.year != None:
+            return f"./{self.basefolder}/{self.directory}/{self.year}/{self.file}"
+
+        return f"./{self.basefolder}/{self.directory}/{self.file}"

Code/Scripts/hep_analytics/processing/extract.py

@@ -0,0 +1,20 @@
+import numpy as np
+import uproot
+import typing
+from dataclasses import dataclass
+
+
+@dataclass
+class FileManager:
+    file: str
+    tree: str
+    branches: list[str]
+
+    def extract_data(self) -> list[np.ndarray]:
+        with uproot.open(self.file) as file:
+            file_tree = file[self.tree]
+            data = []
+            for branch in self.branches:
+                data.append(file_tree[branch].array(library = "np"))
+
+        return data

Code/Scripts/hep_analytics/processing/transform.py

@@ -0,0 +1,20 @@
+import numpy as np 
+
+from hep_ml.reweight import BinsReweighter
+
+
+def select_feature(feature: np.ndarray, limits: tuple[float, float]) -> tuple[np.ndarray, list]:
+    selection_indices = []
+    for index, value in enumerate(feature):
+        if value > limits[0] and value < limits[1]:
+            selection_indices.append(index)
+
+    return feature[selection_indices], selection_indices
+
+
+def reweight_feature(original_feature: list, target_feature: list, n_bins: int, n_neighs: int = 2):
+    original_weights = np.ones(len(original_feature))
+    bin_reweighter   = BinsReweighter(n_bins = n_bins, n_neighs = n_neighs)
+    bin_reweighter.fit(original = original_feature, target = target_feature, original_weight = original_weights)
+
+    return bin_reweighter.predict_weights(original = original_feature, original_weight = original_weights)

Code/Scripts/hep_analytics/processing/visualisation.py

@@ -0,0 +1,22 @@
+import matplotlib.pyplot as plt
+import mplhep
+
+
+mplhep.style.use("LHCb2")
+
+def reweight_comparing_plot(original_feature: list, target_feature: list, weights: list, n_bins: int, suptitle: str, titles: list[str], save: str) -> None:
+    if len(original_feature) != len(weights):
+        raise ValueError(f"original_feature and weights need to have the same dimension!")
+
+    fig, ax = plt.subplots(nrows = 1, ncols = 3, figsize = (30, 12.5))
+
+    ax[0].hist(original_feature, bins = n_bins)
+    ax[0].set_ylabel("counts/a.u.")
+    ax[0].set_title(titles[0])
+    ax[1].hist(original_feature, bins = n_bins, weights = weights)
+    ax[1].set_title(titles[1])
+    ax[2].hist(target_feature, bins = n_bins)
+    ax[2].set_title(titles[2])
+
+    fig.suptitle(suptitle)
+    fig.savefig(f"{save}")