tensorflow2.0处理时间序列

tensorflow2.0处理时间序列

知识点：
1.自定义层
2.使用LSTM预测
3.LSTM调试
4.自定义损失函数
5.预测时间序列

# !/usr/bin/python
# -*- coding: utf-8 -*-
# @Time    : 2021/11/3 10:16
# @Author  : 郑浩鑫
# @Email   : [email protected]
# @File    : class3.py
# @Software: PyCharm
'''
时间序列建模预测星光肺炎
自建layer层，保证预测的值是大于0


'''
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras import models,layers,losses,metrics,callbacks


# 查看原始的值，每天的数量
df = pd.read_csv("G:/resourceCode_github/eat_tensorflow2_in_30_days-master/data/covid-19.csv",sep = "\t")
df.plot(x = "date",y = ["confirmed_num","cured_num","dead_num"],figsize=(10,6))
plt.xticks(rotation=60)  #xticks到底有什么用，其实就是想把坐标轴变成自己想要的样子  rotation旋转60°
plt.show()

# 查看每天新增
dfdata = df.set_index("date")
dfdiff = dfdata.diff(periods=1).dropna()  # 沿着指定轴计算第N维的离散差值
dfdiff = dfdiff.reset_index("date")
dfdiff.plot(x = "date",y = ["confirmed_num","cured_num","dead_num"],figsize=(10,6))
plt.xticks(rotation=60)
dfdiff = dfdiff.drop("date",axis = 1).astype("float32")
plt.show()


#用某日前8天窗口数据作为输入预测该日数据

# drop_remainder：表示在少于batch_size元素的情况下是否应删除最后一批 ; 默认是不删除
WINDOW_SIZE = 8
def batch_dataset(dataset):
    dataset_batched = dataset.batch(WINDOW_SIZE,drop_remainder=True)
    return dataset_batched

ds_data = tf.data.Dataset.from_tensor_slices(tf.constant(dfdiff.values,dtype = tf.float32)).window(WINDOW_SIZE,shift=1).flat_map(batch_dataset)
ds_label = tf.data.Dataset.from_tensor_slices(tf.constant(dfdiff.values[WINDOW_SIZE:],dtype = tf.float32))  #用于创建dataset,其元素是给定张量的切片的元素


#数据较小，可以将全部训练数据放入到一个batch中，提升性能
ds_train = tf.data.Dataset.zip((ds_data,ds_label)).batch(38).cache()
print(ds_train)


#考虑到新增确诊，新增治愈，新增死亡人数数据不可能小于0，设计如下结构
class Block(layers.Layer):
    def __init__(self, **kwargs):
        super(Block, self).__init__(**kwargs)
    def call(self, x_input,x):
        x_out = tf.maximum((1+x)*x_input[:,-1,:],0.0)
        return x_out
    def get_config(self):
        config = super(Block, self).get_config()
        return config

# 构建模型
tf.keras.backend.clear_session()
x_input = layers.Input(shape = (None,3),dtype = tf.float32)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x_input)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x)
x = layers.LSTM(3,input_shape=(None,3))(x)
x = layers.Dense(3)(x)
#考虑到新增确诊，新增治愈，新增死亡人数数据不可能小于0，设计如下结构
#x = tf.maximum((1+x)*x_input[:,-1,:],0.0)
x = Block()(x_input,x)
model = models.Model(inputs = [x_input],outputs = [x])
print(model.summary())

#自定义损失函数，考虑平方差和预测目标的比值
class MSPE(losses.Loss):
    def call(self,y_true,y_pred):
        err_percent = (y_true - y_pred)**2/(tf.maximum(y_true**2,1e-7))
        mean_err_percent = tf.reduce_mean(err_percent)
        return mean_err_percent
    def get_config(self):
        config = super(MSPE, self).get_config()
        return config

# 循环神经网络调试较为困难，需要设置多个不同的学习率多次尝试，以取得较好的效果。
import os
import datetime
optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=optimizer,loss=MSPE(name = "MSPE"))
stamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
logdir = os.path.join('data', 'autograph', stamp)

tb_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
#如果loss在100个epoch后没有提升，学习率减半。
lr_callback = tf.keras.callbacks.ReduceLROnPlateau(monitor="loss",factor = 0.5, patience = 100)
#当loss在200个epoch后没有提升，则提前终止训练。
stop_callback = tf.keras.callbacks.EarlyStopping(monitor = "loss", patience= 200)
callbacks_list = [tb_callback,lr_callback,stop_callback]

history = model.fit(ds_train,epochs=500,callbacks = callbacks_list)


import matplotlib.pyplot as plt
def plot_metric(history, metric):
    train_metrics = history.history[metric]
    epochs = range(1, len(train_metrics) + 1)
    plt.plot(epochs, train_metrics, 'bo--')
    plt.title('Training '+ metric)
    plt.xlabel("Epochs")
    plt.ylabel(metric)
    plt.legend(["train_"+metric])
    plt.show()

plot_metric(history,"loss")

#使用dfresult记录现有数据以及此后预测的疫情数据
dfresult = dfdiff[["confirmed_num","cured_num","dead_num"]].copy()
print(dfresult.tail())


# #预测此后100天的新增走势,将其结果添加到dfresult中
for i in range(100):
    arr_predict = model.predict(tf.constant(tf.expand_dims(dfresult.values[-38:,:],axis = 0)))  #tf.expand_dims 增加一个维度，axis = 0
    dfpredict = pd.DataFrame(tf.cast(tf.floor(arr_predict),tf.float32).numpy(),columns = dfresult.columns)
    dfresult = dfresult.append(dfpredict,ignore_index=True)

    print(dfresult.query("confirmed_num==0").head())  # 查询confirmed_num列中数值为0的行记录
    print(dfresult.query("cured_num==0").head())
    print(dfresult.query("dead_num==0").head())



# 第60天开始，新增死亡降为0，第45天对应3月10日，也就是大概15天后，即20200325
# 该预测较为合理