code_test/select_hard_CI.py

import pandas as pd
import os
import shutil

source_path = '/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/unlabel_11_12/'
dist_path_01 = '/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_11_12_hard_score_01/train/'
dist_path_02 = '/home/shanwei-luo/teamdata/anomaly_detection_active_learning/data0422/smd12_11_12_hard_score_02/train/'
infer_data=pd.read_csv('./test_unlabel_11_12.csv')
print(infer_data.shape)

infer_data.info()
infer_data.describe()
infer_data.head()

print(infer_data['score'])
print(infer_data['Image_Name'])
infer_data = infer_data.sort_values('score',ascending=False)
select_01 = []
select_02 = []
for index, row in infer_data.iterrows():
    #print(row['Image_Name'], row['score'])
    if len(select_01) < 2750:
        select_01.append(row['Image_Name'])
    if row['score']<0.85 and len(select_02)<2750:
        select_02.append(row['Image_Name'])

print(len(select_01))
print(len(select_02))

count_img = 0
count_label = 0
for file in select_01:
    shutil.copy(source_path+'images/'+file, dist_path_01+'images/'+file)
    count_img += 1
    if os.path.exists(source_path+'labels/'+file.replace(".jpg",".txt")):
        shutil.copy(source_path+'labels/'+file.replace(".jpg",".txt"), dist_path_01+'labels/'+file.replace(".jpg",".txt"))
        count_label += 1
print(count_img, count_label)

count_img = 0
count_label = 0
for file in select_02:
    shutil.copy(source_path+'images/'+file, dist_path_02+'images/'+file)
    count_img += 1
    if os.path.exists(source_path+'labels/'+file.replace(".jpg",".txt")):
        shutil.copy(source_path+'labels/'+file.replace(".jpg",".txt"), dist_path_02+'labels/'+file.replace(".jpg",".txt"))
        count_label += 1
print(count_img, count_label)

'''print(len(infer_data['feature'][0]))
feat = infer_data['feature'][0].split(",")
print(len(feat))
print(feat[0])'''