کاوش اطلاعات سیگنال در مراقبت‌های پزشکی

# -*- coding: utf-8 -*-
"""
Created on Thu Dec 17 00:04:41 2020

@author:Milad
"""
import os
import numpy as np
from keras.models import Sequential
from keras import layers
from keras.utils import to_categorical
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_recall_fscore_support
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import pylab as pl
from sklearn import preprocessing

########### Functions ###########

defgetFileList(directory = os.path.dirname(os.path.realpath(__file__))):
    list = os.listdir(directory)
    return list

def getModel(x_train, x_validation, train, validation):
    #building a linear stack of layers with the sequential model
model = Sequential()


    #RNN Layer
    model.add(layers.LSTM(20, return_sequences=True, activation='relu', input_shape=(x_train.shape[1], x_train.shape[2])))

    #flatten output of conv
    model.add(layers.Flatten()) #this converts our 3D feature maps to 1D feature vectors
    ##Fully connected layer
    model.add(layers.Dense(128, activation='relu'))
    model.add(layers.Dense(64, activation='sigmoid'))
    model.add(layers.Dense(13, activation='softmax'))

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(x_train, train, epochs = 8, verbose = False, validation_data = (x_validation, validation), batch_ )
return model, history

def getPrediction(model, x_train, x_test, train):
    model.evaluate(x_train, train, verbose = False)
    predictions = model.predict(x_test)
    return predictions

########### Load dataset

Path = 'Experiment I'
Temp1 = getFileList('Experiment I')
Inputs = []
Labels = []
L = -1
for i in range(len(Temp1)):
    L+=1
    temp = getFileList(os.path.join(Path, Temp1[i]))
    for j in [2, 5, 6, 13]:
        Temp2 = np.loadtxt(os.path.join(Path, Temp1[i], Temp[j]))
        for k in range(Temp2.shape[0]):
            Inputs.append(Temp2[k])
            Labels.append(L)

Inputs = np.array(Inputs)
Labels = np.array(Labels)

########### Pre-process

# Standardization
min_max_scaler = preprocessing.MinMaxScaler()
Inputs = min_max_scaler.fit_transform(Inputs)

########### Partition data to train and test
X_temp, X_test, y_temp, y_test=train_test_split(Inputs, Labels, test_size=0.2, random_state=42)
X_train, X_validation, y_train, y_validation = train_test_split(X_temp, y_temp, test_size=0.3, random_state=42)

########### Create and Train Network

# Reshape data to match with network
X_train = X_train.reshape(X_train.shape[0], 1, X_train.shape[1])
X_validation = X_validation.reshape(X_validation.shape[0], 1, X_validation.shape[1])
X_test = X_test.reshape(X_test.shape[0], 1, X_test.shape[1])
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
y_validation = to_categorical(y_validation)


#Train
model, history = getModel(X_train, X_validation, y_train, y_validation)
print(model.summary())

########### Test trained Model on test data

Temp1 = getPrediction(model, X_train, X_test, y_train)
Temp1 = np.round(Temp1)

########### Evaluate Results

result1 = precision_recall_fscore_support(y_test, Temp1)
print("Fscore:", result1[2])
print("Precision:", result1[0])
print("Recall:", result1[1])
Accuracy = accuracy_score(y_test, Temp1)
print("Accuracy:", accuracy_score(y_test, Temp1))
Precision = result1[0]
Recall = result1[1]
Fscore = result1[2]

############## Show results

# Loss Curves
plt.figure(figsize=[8,6])
plt.plot(history.history['loss'], 'r',linewidth=3.0)
plt.plot(history.history['val_loss'], 'b',linewidth=3.0)
plt.legend(['Training loss', 'Validation Loss'],fontsize=18)
plt.xlabel('Epochs',fontsize=16)
plt.ylabel('Loss',fontsize=16)
plt.title('Loss Curves',fontsize=16)

# Accuracy Curves
plt.figure(figsize=[8,6])
plt.plot(history.history['acc'], 'r',linewidth=3.0)
plt.plot(history.history['val_acc'], 'b',linewidth=3.0)
plt.legend(['Training Accuracy', 'Validation Accuracy'],fontsize=18)
plt.xlabel('Epochs',fontsize=16)
plt.ylabel('Accuracy',fontsize=16)
plt.title('Accuracy Curves',fontsize=16)

# Confusion Chart
Out_test = [np.argmax(y, axis=None, out=None) for y in Temp1]
Temp2 = y_test
y_test = [np.argmax(y, axis=None, out=None) for y in Temp2]
cm = confusion_matrix(y_test, Out_test)
Print(cm)
pl.matshow(cm)
pl.title('Confusion matrix of the classifier')
pl.colorbar()
pl.show()