本篇文章将利用TensorFlow2.0建立時間序列RNN模型，對國内的新冠肺炎疫情結束時間進行預測。資料集取自tushare。
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
#讀取資料處理資料
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
df = pd.read_csv("./data/covid-19.csv",sep = "\t")
df.plot(x = "date",y = ["confirmed_num","cured_num","dead_num"],figsize=(10,6))
plt.xticks(rotation=60)
dfdata = df.set_index("date")
dfdiff = dfdata.diff(periods=1).dropna()
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")
#用某日前8天視窗資料作為輸入預測該日資料
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))
#資料較小，可以将全部訓練資料放入到一個batch中，提升性能
ds_train = tf.data.Dataset.zip((ds_data,ds_label)).batch(38).cache()
定義模型：這裡我們用函數式模型
#考慮到新增确診，新增治愈，新增死亡人數資料不可能小于0，設計如下結構
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
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)
#考慮到新增确診，新增治愈，新增死亡人數資料不可能小于0，設計如下結構
#x = tf.maximum((1+x)*x_input[:,-1,:],0.0)
x = Block()(x_input,x)
model = models.Model(inputs = [x_input],outputs = [x])
model.summary()
'''
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, None, 3)] 0
_________________________________________________________________
lstm (LSTM) (None, None, 3) 84
_________________________________________________________________
lstm_1 (LSTM) (None, None, 3) 84
_________________________________________________________________
lstm_2 (LSTM) (None, None, 3) 84
_________________________________________________________________
lstm_3 (LSTM) (None, 3) 84
_________________________________________________________________
dense (Dense) (None, 3) 12
_________________________________________________________________
block (Block) (None, 3) 0
=================================================================
Total params: 348
Trainable params: 348
Non-trainable params: 0
_________________________________________________________________
'''
訓練模型
#自定義損失函數，考慮平方差和預測目标的比值
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
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)
## 在 Python3 下建議使用 pathlib 修正各作業系統的路徑
# from pathlib import Path
# stamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
# logdir = str(Path('./data/autograph/' + stamp))
tb_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
#如果loss在100個epoch後沒有提升，學習率減半。
lr_callback = tf.keras.callbacks.ReduceLROnPlateau(monitor="loss",factor = 0.5, patience = 100)
#當loss在200個epoch後沒有提升，則提前終止訓練。
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)
'''
隻展示最後5個
Epoch 495/500
1/1 [==============================] - 0s 50ms/step - loss: 0.0858
Epoch 496/500
1/1 [==============================] - 0s 69ms/step - loss: 0.0859
Epoch 497/500
1/1 [==============================] - 0s 63ms/step - loss: 0.0857
Epoch 498/500
1/1 [==============================] - 0s 56ms/step - loss: 0.0858
Epoch 499/500
1/1 [==============================] - 0s 54ms/step - loss: 0.0857
Epoch 500/500
1/1 [==============================] - 0s 57ms/step - loss: 0.0858
'''
評估模型
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
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")
使用模型
#使用dfresult記錄現有資料以及此後預測的疫情資料
dfresult = dfdiff[["confirmed_num","cured_num","dead_num"]].copy()
dfresult.tail()
#預測此後100天的新增走勢,将其結果添加到dfresult中
for i in range(100):
arr_predict = model.predict(tf.constant(tf.expand_dims(dfresult.values[-38:,:],axis = 0)))
dfpredict = pd.DataFrame(tf.cast(tf.floor(arr_predict),tf.float32).numpy(),
columns = dfresult.columns)
dfresult = dfresult.append(dfpredict,ignore_index=True)
dfresult.query("confirmed_num==0").head()
# 第55天開始新增确診降為0，第45天對應3月10日，也就是10天後，即預計3月20日新增确診降為0
# 注：該預測偏樂觀
dfresult.query("cured_num==0").head()
# 第164天開始新增治愈降為0，第45天對應3月10日，也就是大概4個月後，即7月10日左右全部治愈。
# 注: 該預測偏悲觀，并且存在問題，如果将每天新增治愈人數加起來，将超過累計确診人數。
儲存模型
![Tensorflow2.0學習筆記------堆疊模型[圖]](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=)