FFT
顺手记录一下工作。
快速傅里叶变换 (Fast Fourier Transform)
preprocess
from scipy.io import loadmat
import numpy as np
import os
from sklearn import preprocessing # 0-1编码
from sklearn.model_selection import StratifiedShuffleSplit # 随机划分，保证每一类比例相同
def prepro(d_path, length=0, number=0, normal=True, rate=[0, 0, 0], enc=False, enc_step=28):
# 获得该文件夹下所有.mat文件名
filenames = os.listdir(d_path)
def capture(original_path):
files = {}
for i in filenames:
# 文件路径
file_path = os.path.join(d_path, i)
file = loadmat(file_path)
file_keys = file.keys()
for key in file_keys:
if 'DE' in key:
files[i] = file[key].ravel()
return files
def slice_enc(data, slice_rate=rate[1] + rate[2]):
keys = data.keys()
Train_Samples = {}
Test_Samples = {}
for i in keys:
slice_data = data[i]
all_lenght = len(slice_data)
# end_index = int(all_lenght * (1 - slice_rate))
samp_train = int(number * (1 - slice_rate)) # 1000(1-0.3)
Train_sample = []
Test_Sample = []
for j in range(samp_train):
sample = slice_data[j*150: j*150 + length]
Train_sample.append(sample)
# 抓取测试数据
for h in range(number - samp_train):
sample = slice_data[samp_train*150 + length + h*150: samp_train*150 + length + h*150 + length]
Test_Sample.append(sample)
Train_Samples[i] = Train_sample
Test_Samples[i] = Test_Sample
return Train_Samples, Test_Samples
# 仅抽样完成，打标签
def add_labels(train_test):
X = []
Y = []
label = 0
for i in filenames:
x = train_test[i]
X += x
lenx = len(x)
Y += [label] * lenx
label += 1
return X, Y
def scalar_stand(Train_X, Test_X):
# 用训练集标准差标准化训练集以及测试集
data_all = np.vstack((Train_X, Test_X))
scalar = preprocessing.StandardScaler().fit(data_all)
Train_X = scalar.transform(Train_X)
Test_X = scalar.transform(Test_X)
return Train_X, Test_X
def valid_test_slice(Test_X, Test_Y):
test_size = rate[2] / (rate[1] + rate[2])
ss = StratifiedShuffleSplit(n_splits=1, test_size=test_size)
Test_Y = np.asarray(Test_Y, dtype=np.int32)
for train_index, test_index in ss.split(Test_X, Test_Y):
X_valid, X_test = Test_X[train_index], Test_X[test_index]
Y_valid, Y_test = Test_Y[train_index], Test_Y[test_index]
return X_valid, Y_valid, X_test, Y_test
# 从所有.mat文件中读取出数据的字典
data = capture(original_path=d_path)
# 将数据切分为训练集、测试集
train, test = slice_enc(data)
# 为训练集制作标签，返回X，Y
Train_X, Train_Y = add_labels(train)
# 为测试集制作标签，返回X，Y
Test_X, Test_Y = add_labels(test)
# 训练数据/测试数据 是否标准化.
if normal:
Train_X, Test_X = scalar_stand(Train_X, Test_X)
Train_X = np.asarray(Train_X)
Test_X = np.asarray(Test_X)
# 将测试集切分为验证集和测试集.
Valid_X, Valid_Y, Test_X, Test_Y = valid_test_slice(Test_X, Test_Y)
return Train_X, Train_Y, Valid_X, Valid_Y, Test_X, Test_Y一维数据快速傅里叶变换（1d-FFT）
缺少哪个包就直接去pip
from tensorflow import keras
from sklearn.metrics import confusion_matrix
import tensorflow.keras as keras
import tensorflow.keras.layers as layers
from datetime import datetime
from tensorflow_core.python.keras import layers
import tensorflow as tf
import random
import matplotlib.pyplot as plt
from scipy.fftpack import fft
import numpy as np
from preprocess import prepro
def fft_data():
length = 784
number = 300 # 每类样本的数量
normal = True # 是否标准化
rate = [0.6, 0.2, 0.2] # 测试集验证集划分比例
path = r'C:/Users/LIU/Desktop/xianligong/CaseWesternReserveUniversityData-master/1HP'
x_train, y_train, x_valid, y_valid, x_test, y_test = prepro(
d_path=path,
length=length,
number=number,
normal=normal,
rate=rate,
enc=False, enc_step=28)
y_valid, y_test = y_valid[:, np.newaxis], y_test[:, np.newaxis]
x_test = np.vstack((x_valid, x_test))
y_test = np.vstack((y_valid, y_test))
x_train = np.array(x_train)
y_train = np.array(y_train)
x_test = np.array(x_test)
y_test = np.array(y_test)
y_test = np.squeeze(y_test)
return x_train, y_train, x_valid, y_valid, x_test, y_test
def fft_transform():
x_train0, y_train0, x_valid0, y_valid0, x_test0, y_test0 = fft_data()
x_train1 = []
x_valid1 = []
x_test1 = []
N = 784
for i in range(len(x_train0)):
y1 = x_train0[i]
yf1 = abs(fft(y1)) / N # 归一化处理
yf2 = yf1[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
#yf2 = yf1[range(N)]
x_train1.append(yf2)
for i in range(len(x_valid0)):
y2 = x_valid0[i]
yf3 = abs(fft(y2)) / N # 归一化处理
yf4 = yf3[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
#yf4 = yf3[range(N)]
x_valid1.append(yf4)
for i in range(len(x_test0)):
y2 = x_test0[i]
yf3 = abs(fft(y2)) / N # 归一化处理
yf4 = yf3[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
#yf4 = yf3[range(N)]
x_test1.append(yf4)
x_train3 = np.array(x_train1)
x_valid3 = np.array(x_valid1)
x_test3 = np.array(x_test1)
return x_train3, y_train0, x_valid3, y_valid0, x_test3, y_test0
x_train, y_train, x_valid, y_valid, x_test, y_test = fft_transform()
#绘制FFT结果
plt.plot(x_train[0])
plt.title('FFT of Mixed wave)', fontsize=10, color='#F08080')
plt.show()
print(x_train.shape)
print(x_valid.shape)
print(x_test.shape)
print(y_train.shape)
print(y_valid.shape)
print(y_test.shape)
y_train = [int(i) for i in y_train]
y_valid = [int(i) for i in y_valid]
y_test = [int(i) for i in y_test]
# 打乱顺序
index = [i for i in range(len(x_train))]
random.seed(1)
random.shuffle(index)
x_train = np.array(x_train)[index]
y_train = np.array(y_train)[index]
index1 = [i for i in range(len(x_valid))]
random.shuffle(index1)
x_valid = np.array(x_valid)[index1]
y_valid = np.array(y_valid)[index1]
index2 = [i for i in range(len(x_test))]
random.shuffle(index2)
x_test = np.array(x_test)[index2]
y_test = np.array(y_test)[index2]
print(x_train.shape)
print(x_valid.shape)
print(x_test.shape)
print(y_train)
print(y_valid)
print(y_test)
print("x_train的最大值和最小值：", x_train.max(), x_train.min())
print("x_test的最大值和最小值：", x_test.max(), x_test.min())
x_train = tf.reshape(x_train, (len(x_train), 392, 1))
x_valid = tf.reshape(x_valid, (len(x_valid), 392, 1))
x_test = tf.reshape(x_test, (len(x_test), 392, 1))
# 保存最佳模型
class CustomModelCheckpoint(keras.callbacks.Callback):
def __init__(self, model, path):
self.model = model
self.path = path
self.best_loss = np.inf
def on_epoch_end(self, epoch, logs=None):
val_loss = logs['val_loss']
if val_loss < self.best_loss:
print("\nValidation loss decreased from {} to {}, saving model".format(self.best_loss, val_loss))
self.model.save_weights(self.path, overwrite=True)
self.best_loss = val_loss
# 模型定义
def mymodel():
inputs = keras.Input(shape=(x_train.shape[1], x_train.shape[2]))
h1 = layers.Conv1D(filters=8, kernel_size=3, strides=1, padding='same', activation='relu')(inputs)
h1 = layers.MaxPool1D(pool_size=2, strides=2, padding='same')(h1)
h1 = layers.Conv1D(filters=16, kernel_size=3, strides=1, padding='same', activation='relu')(h1)
h1 = layers.MaxPool1D(pool_size=2, strides=2, padding='same')(h1)
h1 = layers.Flatten()(h1)
h1 = layers.Dropout(0.6)(h1)
h1 = layers.Dense(32, activation='relu')(h1)
h1 = layers.Dense(10, activation='softmax')(h1)
deep_model = keras.Model(inputs, h1, name="cnn")
return deep_model
model = mymodel()
model.summary()
startdate = datetime.utcnow() # 获取当前时间
# 编译模型
model.compile(
optimizer=keras.optimizers.Adam(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
history = model.fit(x_train, y_train,
batch_size=256, epochs=50, verbose=1,
validation_data=(x_valid, y_valid),
callbacks=[CustomModelCheckpoint(
model, r'best_fft_1dcnn.h5')])
#加载模型
model.load_weights(filepath='best_fft_1dcnn.h5')
# 编译模型
model.compile(loss='sparse_categorical_crossentropy', optimizer=keras.optimizers.Adam(), metrics=['accuracy'])
# 评估模型
scores = model.evaluate(x_test, y_test, verbose=1)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))
y_predict = model.predict(x_test)
y_pred_int = np.argmax(y_predict, axis=1)
print(y_pred_int[0:5])
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred_int, digits=4))
def acc_line():
# 绘制acc和loss曲线
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(acc)) # Get number of epochs
# 画accuracy曲线
plt.plot(epochs, acc, 'r', linestyle='-.')
plt.plot(epochs, val_acc, 'b', linestyle='dashdot')
plt.title('Training and validation accuracy')
plt.xlabel("Epochs")
plt.ylabel("Accuracy")
plt.legend(["Accuracy", "Validation Accuracy"])
plt.figure()
# 画loss曲线
plt.plot(epochs, loss, 'r', linestyle='-.')
plt.plot(epochs, val_loss, 'b', linestyle='dashdot')
plt.title('Training and validation loss')
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend(["Loss", "Validation Loss"])
# plt.figure()
plt.show()
acc_line()
# 绘制混淆矩阵
def confusion():
y_pred_gailv = model.predict(x_test, verbose=1)
y_pred_int = np.argmax(y_pred_gailv, axis=1)
print(len(y_pred_int))
con_mat = confusion_matrix(y_test.astype(str), y_pred_int.astype(str))
print(con_mat)
classes = list(set(y_train))
classes.sort()
plt.imshow(con_mat, cmap=plt.cm.Blues)
indices = range(len(con_mat))
plt.xticks(indices, classes)
plt.yticks(indices, classes)
plt.colorbar()
plt.xlabel('guess')
plt.ylabel('true')
for first_index in range(len(con_mat)):
for second_index in range(len(con_mat[first_index])):
plt.text(first_index, second_index, con_mat[second_index][first_index], va='center', ha='center')
plt.show()
confusion()
二维时频图快速傅里叶变换（2d-FFT）
前面都大差不差，如果在可视化部分需要增加或修改X,Y轴，两种方法：1.通过代码直接修改，比如字体大小或者XY轴名称（过完周末再写）；2.通过PowerPoint或WPS直接去添加文本框，然后合并图层。
from tensorflow import keras
from sklearn.metrics import confusion_matrix
import tensorflow.keras as keras
import tensorflow.keras.layers as layers
from datetime import datetime
from tensorflow_core.python.keras import layers
import tensorflow as tf
import matplotlib.pyplot as plt
from scipy.fftpack import fft
import numpy as np
from fft.preprocess import prepro
def fft_data():
length = 784
number = 300 # 每类样本的数量
normal = True # 是否标准化
rate = [0.6, 0.2, 0.2] # 测试集验证集划分比例
path = r'C:/Users/LIU/Desktop/xianligong/CaseWesternReserveUniversityData-master/1HP'
x_train, y_train, x_valid, y_valid, x_test, y_test = prepro(
d_path=path,
length=length,
number=number,
normal=normal,
rate=rate,
enc=False, enc_step=28)
y_valid, y_test = y_valid[:, np.newaxis], y_test[:, np.newaxis]
x_test = np.vstack((x_valid, x_test))
y_test = np.vstack((y_valid, y_test))
x_train = np.array(x_train)
y_train = np.array(y_train)
x_test = np.array(x_test)
y_test = np.array(y_test)
y_test = np.squeeze(y_test)
return x_train, y_train, x_valid, y_valid, x_test, y_test
def fft_transform():
x_train0, y_train0, x_valid0, y_valid0, x_test0, y_test0 = fft_data()
x_train1 = []
x_valid1 = []
x_test1 = []
N = 784
for i in range(len(x_train0)):
y1 = x_train0[i]
yf1 = abs(fft(y1)) / N # 归一化处理
# yf2 = yf1[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
yf2 = yf1[range(N)]
x_train1.append(yf2)
for i in range(len(x_valid0)):
y2 = x_valid0[i]
yf3 = abs(fft(y2)) / N # 归一化处理
# yf4 = yf3[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
yf4 = yf3[range(N)]
x_valid1.append(yf4)
for i in range(len(x_test0)):
y2 = x_test0[i]
yf3 = abs(fft(y2)) / N # 归一化处理
# yf4 = yf3[range(int(len(yf1) / 2))] # 由于对称性，只取一半区间
yf4 = yf3[range(N)]
x_test1.append(yf4)
x_train3 = np.array(x_train1)
x_valid3 = np.array(x_valid1)
x_test3 = np.array(x_test1)
return x_train3, y_train0, x_valid3, y_valid0, x_test3, y_test0
x_train, y_train, x_valid, y_valid, x_test, y_test = fft_transform()
# 绘制FFT结果
plt.plot(x_train[0])
plt.title('FFT of Mixed wave)', fontsize=10, color='#F08080')
plt.show()
print(x_train.shape)
print(x_valid.shape)
print(x_test.shape)
print(y_train.shape)
print(y_valid.shape)
print(y_test.shape)
y_train = [int(i) for i in y_train]
y_valid = [int(i) for i in y_valid]
y_test = [int(i) for i in y_test]
# 打乱顺序
index = [i for i in range(len(x_train))]
random.seed(1)
random.shuffle(index)
x_train = np.array(x_train)[index]
y_train = np.array(y_train)[index]
index1 = [i for i in range(len(x_valid))]
random.shuffle(index1)
x_valid = np.array(x_valid)[index1]
y_valid = np.array(y_valid)[index1]
index2 = [i for i in range(len(x_test))]
random.shuffle(index2)
x_test = np.array(x_test)[index2]
y_test = np.array(y_test)[index2]
print(x_train.shape)
print(x_valid.shape)
print(x_test.shape)
print(y_train)
print(y_valid)
print(y_test)
print("x_train的最大值和最小值：", x_train.max(), x_train.min())
print("x_test的最大值和最小值：", x_test.max(), x_test.min())
x_train = tf.reshape(x_train, (len(x_train), 28, 28, 1))
x_valid = tf.reshape(x_valid, (len(x_valid), 28, 28, 1))
x_test = tf.reshape(x_test, (len(x_test), 28, 28, 1))
# 保存最佳模型
class CustomModelCheckpoint(keras.callbacks.Callback):
def __init__(self, model, path):
self.model = model
self.path = path
self.best_loss = np.inf
def on_epoch_end(self, epoch, logs=None):
val_loss = logs['val_loss']
if val_loss < self.best_loss:
print("\nValidation loss decreased from {} to {}, saving model".format(self.best_loss, val_loss))
self.model.save_weights(self.path, overwrite=True)
self.best_loss = val_loss
def mymodel():
inputs = keras.Input(shape=(x_train.shape[1], x_train.shape[2], x_train.shape[3]))
h1 = layers.Conv2D(filters=8, kernel_size=(3, 3), strides=(1,1), padding='same', activation='relu')(inputs)
h1 = layers.MaxPool2D(pool_size=(2,2), strides=(2, 2), padding='same')(h1)
h1 = layers.Conv2D(filters=16, kernel_size=(3,3), strides=(1,1), padding='same', activation='relu')(h1)
h1 = layers.MaxPool2D(pool_size=(2,2), strides=(2,2), padding='same')(h1)
h1 = layers.Flatten()(h1)
h1 = layers.Dense(32, activation='relu')(h1)
h1 = layers.Dense(10, activation='softmax')(h1)
deep_model = keras.Model(inputs, h1, name="cnn")
return deep_model
model = mymodel()
model.summary()
startdate = datetime.utcnow() # 获取当前时间
# 编译模型
model.compile(
optimizer=keras.optimizers.Adam(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
history = model.fit(x_train, y_train,
batch_size=256, epochs=50, verbose=1,
validation_data=(x_valid, y_valid),
callbacks=[CustomModelCheckpoint(
model, r'best_fft_2dcnn.h5')])
#加载模型
model.load_weights(filepath='best_fft_2dcnn.h5')
# 编译模型
model.compile(loss='sparse_categorical_crossentropy', optimizer=keras.optimizers.Adam(), metrics=['accuracy'])
# 评估模型
scores = model.evaluate(x_test, y_test, verbose=1)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))
y_predict = model.predict(x_test)
y_pred_int = np.argmax(y_predict, axis=1)
# print(y_pred_int[0:5])
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred_int, digits=4))
def acc_line():
# 绘制acc和loss曲线
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(acc)) # Get number of epochs
# 画accuracy曲线
plt.plot(epochs, acc, 'r', linestyle='-.')
plt.plot(epochs, val_acc, 'b', linestyle='dashdot')
plt.title('Training and validation accuracy')
plt.xlabel("Epochs")
plt.ylabel("Accuracy")
plt.legend(["Accuracy", "Validation Accuracy"])
plt.figure()
# 画loss曲线
plt.plot(epochs, loss, 'r', linestyle='-.')
plt.plot(epochs, val_loss, 'b', linestyle='dashdot')
plt.title('Training and validation loss')
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend(["Loss", "Validation Loss"])
plt.show()
acc_line()
# 绘制混淆矩阵
def confusion():
y_pred_gailv = model.predict(x_test, verbose=1)
y_pred_int = np.argmax(y_pred_gailv, axis=1)
print(len(y_pred_int))
con_mat = confusion_matrix(y_test.astype(str), y_pred_int.astype(str))
print(con_mat)
classes = list(set(y_train))
classes.sort()
plt.imshow(con_mat, cmap=plt.cm.Blues)
indices = range(len(con_mat))
plt.xticks(indices, classes)
plt.yticks(indices, classes)
plt.colorbar()
plt.xlabel('guess')
plt.ylabel('true')
for first_index in range(len(con_mat)):
for second_index in range(len(con_mat[first_index])):
plt.text(first_index, second_index, con_mat[second_index][first_index], va='center', ha='center')
plt.show()
confusion()
写在最后
中间定义的那个模型
def mymodel
用了很简单的一个模型，如果需要特定的模型需求，只需要在最前面from引一下。
然后在model=这个地方也修改一下。
有不会的可以私信问我，看到会回，一起进步，一起学习。