from QSP400 import dataPro as data
import numpy as np
from keras.models import Sequential
from keras.regularizers import l2
from keras.layers import LSTM, Dense, Dropout, Activation, initializers, GRU, SimpleRNN, ConvLSTM2D
from keras import optimizers
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
import matplotlib.pyplot as plt
from keras.layers import Conv1D, GlobalAveragePooling1D, MaxPooling1D, BatchNormalization, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, Embedding, Bidirectional, LeakyReLU
from sklearn.metrics import roc_curve, auc
import numpy as np
# ac,label=data.ac()
ac_p, label = data.deal()
aac = data.fe()
ctd = data.CTD()
gaac = data.gaac()
X = np.concatenate((aac, gaac, ac_p), axis=1) # X=ac,ctd,kmer
# print(X)
def calculate_performace(test_num, pred_y, labels):
tp = 0
fp = 0
tn = 0
fn = 0
for index in range(test_num):
if labels[index] == 1:
if labels[index] == pred_y[index]:
tp = tp + 1
from QSP400 import dataPro as data
import numpy as np
from keras import optimizers
from keras.models import model_from_yaml
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.metrics import roc_curve, auc
aac,label=data.fe()
gaac=data.gaac()
ac_p,label=data.deal()
yaml_string = open('model_arthitecture_2.yaml', 'r')
model = model_from_yaml(yaml_string)
yaml_string_lstm = open('lstm.yaml', 'r')
model_lstm = model_from_yaml(yaml_string_lstm)
x_test = np.concatenate(( aac,gaac,ac_p),axis=1)
print(x_test.shape)
all_labels=[]
all_prob = {}
all_prob[0] = []
real_labels = []
for val in label:
if val == 1:
real_labels.append(1)
else:
real_labels.append(0)
train_label_new = []
# global all_labels
# global all_prob
all_labels = all_labels + real_labels