如何对群集数据使用lstm？

问题描述

我有一个具有不同配置文件的用户时间序列数据集。我想使用lstm预测每个用户提前1天。我要解决的问题是首先将具有相同行为的用户聚类。然后，在每个组中训练不同的lstm模型，以便每个lstm模型将负责该组用户，并将使用该组的时间序列数据进行训练。在测试场景中，我将首先找到新用户的集群，然后根据经过训练的相应集群的lstm进行预测。通过这种方法，我希望最小化模型的均方根。 我已经开始使用https://tslearn.readthedocs.io/en/stable/库来对数据进行聚类。

我的问题与使用lstm有关。我的方法中的lstm部分真的有意义吗？我应该使用一个全局lstm来训练不同的集群，还是应该为集群分别设置lstm模型？我是lstm及其功能的新手，所以将不胜感激。

谢谢。

解决方法

这是您考虑的一种选择。

from pandas_datareader import data as wb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pylab import rcParams
from sklearn.preprocessing import MinMaxScaler

start = '2019-06-30'
end = '2020-06-30'

tickers = ['GOOG']

thelen = len(tickers)

price_data = []
for ticker in tickers:
    prices = wb.DataReader(ticker,start = start,end = end,data_source='yahoo')[['Open','Adj Close']]
    price_data.append(prices.assign(ticker=ticker)[['ticker','Open','Adj Close']])

#names = np.reshape(price_data,(len(price_data),1))

df = pd.concat(price_data)
df.reset_index(inplace=True)

for col in df.columns: 
    print(col) 
    
#used for setting the output figure size
rcParams['figure.figsize'] = 20,10
#to normalize the given input data
scaler = MinMaxScaler(feature_range=(0,1))
#to read input data set (place the file name inside  ' ') as shown below


df['Adj Close'].plot()
plt.legend(loc=2)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()

ntrain = 80
df_train = df.head(int(len(df)*(ntrain/100)))
ntest = -80
df_test = df.tail(int(len(df)*(ntest/100)))


#importing the packages 
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense,Dropout,LSTM

#dataframe creation
seriesdata = df.sort_index(ascending=True,axis=0)
new_seriesdata = pd.DataFrame(index=range(0,len(df)),columns=['Date','Adj Close'])
length_of_data=len(seriesdata)
for i in range(0,length_of_data):
    new_seriesdata['Date'][i] = seriesdata['Date'][i]
    new_seriesdata['Adj Close'][i] = seriesdata['Adj Close'][i]
#setting the index again
new_seriesdata.index = new_seriesdata.Date
new_seriesdata.drop('Date',axis=1,inplace=True)
#creating train and test sets this comprises the entire data’s present in the dataset
myseriesdataset = new_seriesdata.values
totrain = myseriesdataset[0:255,:]
tovalid = myseriesdataset[255:,:]
#converting dataset into x_train and y_train
scalerdata = MinMaxScaler(feature_range=(0,1))
scale_data = scalerdata.fit_transform(myseriesdataset)
x_totrain,y_totrain = [],[]
length_of_totrain=len(totrain)
for i in range(60,length_of_totrain):
    x_totrain.append(scale_data[i-60:i,0])
    y_totrain.append(scale_data[i,0])
x_totrain,y_totrain = np.array(x_totrain),np.array(y_totrain)
x_totrain = np.reshape(x_totrain,(x_totrain.shape[0],x_totrain.shape[1],1))


#LSTM neural network
lstm_model = Sequential()
lstm_model.add(LSTM(units=50,return_sequences=True,input_shape=(x_totrain.shape[1],1)))
lstm_model.add(LSTM(units=50))
lstm_model.add(Dense(1))
lstm_model.compile(loss='mean_squared_error',optimizer='adadelta')
lstm_model.fit(x_totrain,y_totrain,epochs=10,batch_size=1,verbose=2)
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
myinputs = myinputs.reshape(-1,1)
myinputs  = scalerdata.transform(myinputs)
tostore_test_result = []
for i in range(60,myinputs.shape[0]):
    tostore_test_result.append(myinputs[i-60:i,0])
tostore_test_result = np.array(tostore_test_result)
tostore_test_result = np.reshape(tostore_test_result,(tostore_test_result.shape[0],tostore_test_result.shape[1],1))
myclosing_priceresult = lstm_model.predict(tostore_test_result)
myclosing_priceresult = scalerdata.inverse_transform(myclosing_priceresult)
    
totrain = df_train
tovalid = df_test

#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values

# finally...
#  Printing the next day’s predicted stock price. 
print(len(tostore_test_result));
print(myclosing_priceresult);