126 lines
3.2 KiB
Python
126 lines
3.2 KiB
Python
# -*- 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()
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|