# -*- coding: utf-8 -*-
"""
Created on Wed Sep 11 11:57:30 2024
    永辉现场试验输出数据的 1:1 性能评估
    适用于202410前数据保存版本的，需调用 OneToOneCompare.txt
@author: ym
"""
import os
import numpy as np
import matplotlib.pyplot as plt

def read_one2one_data(filepath):
    simiList = []
    with open(filepath, 'r', encoding='utf-8') as f:
        lines = f.readlines()
        
        split_flag = False
        simi_dict = {}
        for i, line in enumerate(lines):
            line = line.strip()
            if not line:
                if len(simi_dict): simiList.append(simi_dict)
                simi_dict = {}
                continue

            label = line.split(':')[0].strip()
            value = line.split(':')[1].strip()

            if label.find("SeqDir") >= 0:
                simi_dict["SeqDir"] = value
            if label.isdigit() and len(label) >= 8:
                
                simi_max, simi_min = value.strip(',').split('.')
                simi_dict["barcode"] = label
                simi_dict["simi_max"] = float(simi_max) / 1000
                simi_dict["simi_min"] = float(simi_min) / 1000
        
        if len(simi_dict): simiList.append(simi_dict)
                
    return simiList

def plot_pr_curve(matrix):
    
    simimax, simimean = [], []
    need_analysis = []
    for simidict in matrix:
        simimax.append(simidict["simi_max"])
        simimean.append(simidict["simi_min"])
        if simidict["simi_max"]>0.6:
            need_analysis.append(simidict)

    simimax = np.array(simimax)
    simimean = np.array(simimean)

    TPFN_max = len(simimax)
    TPFN_mean = len(simimean)

    fig, axs = plt.subplots(2, 1)
    axs[0].hist(simimax, bins=60, edgecolor='black')
    axs[0].set_xlim([-0.2, 1])
    axs[0].set_title(f'Same Barcode, Num: {TPFN_max}')
    axs[1].hist(simimean, bins=60, edgecolor='black')
    axs[1].set_xlim([-0.2, 1])
    axs[1].set_title(f'Cross Barcode, Num: {TPFN_mean}')
    # plt.savefig(f'./result/{file}_hist.png')  # svg, png, pdf
 
    Recall_Neg = []
    Thresh = np.linspace(-0.2, 1, 100)
    for th in Thresh:
        TN = np.sum(simimax < th)
        Recall_Neg.append(TN/TPFN_max)

    fig, ax = plt.subplots()  
    ax.plot(Thresh, Recall_Neg, 'b', label='Recall_Pos: TP/TPFN')
    ax.set_xlim([0, 1])
    ax.set_ylim([0, 1])
    ax.grid(True)
    ax.set_title('Positive recall')
    ax.set_xlabel(f"Num: {TPFN_max}")     
    ax.legend()
    plt.show() 
    # plt.savefig(f'./result/{file}_pr.png')  # svg, png, pdf
    
    print("Have done!") 
    pass

                
def main():
    filepaths = [r"\\192.168.1.28\share\测试_202406\0913_扫A放B\0913_1\OneToOneCompare.txt",
                 r"\\192.168.1.28\share\测试_202406\0913_扫A放B\0913_2\OneToOneCompare.txt",
                 r"\\192.168.1.28\share\测试_202406\0914_扫A放B\0914_1\OneToOneCompare.txt",
                 r"\\192.168.1.28\share\测试_202406\0914_扫A放B\0914_2\OneToOneCompare.txt"
                ]
    
    simiList = []
    for fp in filepaths:
        slist = read_one2one_data(fp)
        simiList.extend(slist)

    plot_pr_curve(simiList)
    
    

if __name__ == "__main__":
    main()