NovoRank/Config.py at main · BISCodeRepo/NovoRank · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
def read_config(PATH_config_text):

    data_configs = {}

    with open(PATH_config_text, encoding='UTF8') as config_file:
        for line in config_file:
            if line[0] == '#':
                pass
            else:
                if 'precusor_search_ppm' in line:
                    data_configs['PPM'] = float(line.split('=')[1].split('#')[0].strip())
                elif 'elution_time' in line:
                    data_configs['ELUTION_TIME'] = int(line.split('=')[1].split('#')[0].strip())
                elif 'training' in line:
                    if line.split('=')[1].split('#')[0].strip() == 'False' or line.split('=')[1].split('#')[0].strip() == 'false':
                        temp = False
                    else:
                        temp = True
                    data_configs['TRAIN'] = temp
                elif 'mgf_remove' in line:
                    data_configs['MGF_REMOVE'] = line.split('=')[1].split('#')[0].strip()
                elif 'mgf_xcorr' in line:
                    data_configs['MGF_XCORR'] = line.split('=')[1].split('#')[0].strip()
                elif 'xcorr_result' in line:
                    data_configs['XCORR_RESULT'] = line.split('=')[1].split('#')[0].strip()
                elif 'cluster_result_path' in line:
                    data_configs['CLUSTER_PATH'] = line.split('=')[1].split('#')[0].strip()
                elif 'denovo_result_csv ' in line:
                    data_configs['DE_NOVO'] = line.split('=')[1].split('#')[0].strip()
                elif 'db_result_csv ' in line:
                    data_configs['DB'] = line.split('=')[1].split('#')[0].strip()
                elif 'mgf_path' in line:
                    data_configs['MGF_PATH'] = line.split('=')[1].split('#')[0].strip()
                elif 'features_csv ' in line:
                    data_configs['RESULT_NAME'] = line.split('=')[1].split('#')[0].strip()
                elif 'pre_trained_model ' in line:
                    data_configs['PRE_TRAINED_MODEL'] = line.split('=')[1].split('#')[0].strip()
                elif 'val_size' in line:
                    temp = line.split('=')[1].split('#')[0].strip()
                    if temp == '':
                        data_configs['VAL_SIZE'] = temp
                    else:
                        data_configs['VAL_SIZE'] = float(temp)
                elif 'epoch' in line:
                    temp = line.split('=')[1].split('#')[0].strip()
                    if temp == '':
                        data_configs['EPOCH'] = temp
                    else:
                        data_configs['EPOCH'] = int(temp)
                elif 'batch_size' in line:
                    temp = line.split('=')[1].split('#')[0].strip()
                    if temp == '':
                        data_configs['BATCH'] = temp
                    else:
                        data_configs['BATCH'] = int(temp)
                elif 'early_stopping' in line:
                    if line.split('=')[1].split('#')[0].strip() == 'False' or line.split('=')[1].split('#')[0].strip() == 'false':
                        temp = False
                    else:
                        temp = True
                    data_configs['EARLY_STOPPING'] = temp
                elif 'model_save_name' in line:
                    data_configs['MODEL_NAME'] = line.split('=')[1].split('#')[0].strip()
                elif 'result_name' in line:
                    data_configs['FINAL_RESULT'] = line.split('=')[1].split('#')[0].strip()

    return data_configs