@author: Winham # CPSC_hybrid.py: 使用xgboost混合深度学习网络和人工特征,得到最后结果 """ import os import numpy as np import xgboost as xgb from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix from CPSC_config import Config import CPSC_utils as utils os.environ["CUDA_VISIBLE_DEVICES"] = "-1" config = Config() config.MODEL_PATH = 'E:/CPSC_Scheme/Net_models/' config.MAN_FEATURE_PATH = 'E:/CPSC_Scheme/Man_features/' records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, _, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) train_records, val_records, train_labels, val_labels = train_test_split( train_val_records,
import xgboost as xgb from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix from CPSC_config import Config import CPSC_utils as utils import tensorflow as tf from keras.backend.tensorflow_backend import set_session from evaluate_12ECG_score import evaluate_score os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["CUDA_VISIBLE_DEVICES"] = "-1" config = Config() config.MODEL_PATH = '/home/zyhk/桌面/CPSC_Scheme-master/model_t/' config.MAN_FEATURE_PATH = '/home/zyhk/桌面/CPSC_Scheme-master/Man_features/' records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, _, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) train_records, val_records, train_labels, val_labels = train_test_split( train_val_records,
import numpy from driver import dataread,get_classes,getdata_class,load_challenge_data,get_12ECG_features from evaluate_12ECG_score import evaluate_score import xgboost as xgb os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2' warnings.filterwarnings("ignore") config = Config() from tensorflow.python.client import device_lib print(device_lib.list_local_devices()) # DATA_PATH= '/home/zyhk/桌面/datanpy/' # REVISED_LABEL='/home/zyhk/桌面/CPSC_Scheme-master/recordlabel.npy' # records_name = np.array(os.listdir(DATA_PATH)) # records_label = np.load(REVISED_LABEL) - 1 # class_num = len(np.unique(records_label)) # define 10-fold cross validation test harness # seed = 7 # numpy.random.seed(seed) # kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed) # 取出训练集和测试集病人对应导联信号,并进行切片和z-score标准化 --------------------------------------------------------
import CPSC_utils as utils import tensorflow as tf from keras.backend.tensorflow_backend import set_session import tensorflow as tf from keras import backend as bk os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() # gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.7) config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2' warnings.filterwarnings("ignore") config = Config() records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) # 划分训练,验证与测试集 ----------------------------------------------------------------------------------------------- train_val_records, test_records, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) del test_records, test_labels train_records, val_records, train_labels, val_labels = train_test_split( train_val_records,
import os import warnings import numpy as np import tensorflow as tf from keras import backend as bk from keras.models import load_model from keras.utils import to_categorical from sklearn.preprocessing import scale from sklearn.model_selection import train_test_split from CPSC_config import Config import CPSC_utils as utils os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2' warnings.filterwarnings("ignore") config = Config() config.MODEL_PATH = 'E:/CPSC_Scheme/Net_models/' records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, test_records, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) train_records, val_records, train_labels, val_labels = train_test_split( train_val_records, train_val_labels,
from sklearn.model_selection import train_test_split import numpy as np from sklearn.metrics import roc_auc_score from CPSC_config import Config import CPSC_utils as utils import tensorflow as tf from keras.backend.tensorflow_backend import set_session from evaluate_12ECG_score import evaluate_score os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["CUDA_VISIBLE_DEVICES"] = "-1" config = Config() config.MODEL_PATH = 'E:/challenge2020/CPSC_Scheme-master/model_t/' config.MAN_FEATURE_PATH = 'E:/challenge2020/CPSC_Scheme-master/Man_features/' records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, _, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) train_records, val_records, train_labels, val_labels = train_test_split( train_val_records,
from keras.utils import to_categorical from sklearn.preprocessing import scale from sklearn.model_selection import train_test_split from CPSC_config import Config import CPSC_utils as utils from keras.backend.tensorflow_backend import set_session os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2' warnings.filterwarnings("ignore") config = Config() config.MODEL_PATH = '/home/zyhk/桌面/CPSC_Scheme-master/model_t/' records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, test_records, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) train_records, val_records, train_labels, val_labels = train_test_split( train_val_records, train_val_labels,
from sklearn.metrics import confusion_matrix from sklearn.model_selection import train_test_split from CPSC_model import Net1 from CPSC_config import Config import CPSC_utils as utils from keras.backend.tensorflow_backend import set_session os.environ["CUDA_VISIBLE_DEVICES"] = "0" # 指定GPU config = tf.ConfigProto() config.gpu_options.allow_growth = True # 按需 set_session(tf.Session(config=config)) os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2' warnings.filterwarnings("ignore") config = Config() records_name = np.array(os.listdir(config.DATA_PATH)) records_label = np.load(config.REVISED_LABEL) - 1 class_num = len(np.unique(records_label)) train_val_records, test_records, train_val_labels, test_labels = train_test_split( records_name, records_label, test_size=0.2, random_state=config.RANDOM_STATE) del test_records, test_labels train_records, val_records, train_labels, val_labels = train_test_split( train_val_records, train_val_labels,