Mxnet RNN時系列予測

Question

私は時系列データの観測のために5つのラグ変数を持つRNNモデルを構築するはずのコードブロックを持っています。ここでは、コードは次のとおりです。それをmx.rnnの呼び出しで

library(Quandl) 
key<-"*******************" 
Quandl.api_key(key) 

sh_stock_ex <- Quandl("YAHOO/SS_600292", type="xts") 
library(xts) 
data <- scale(sh_stock_ex[-1,5]) 
feat <- merge(na.trim(lag(data,1)), na.trim(lag(data,2)), na.trim(lag(data,3)), na.trim(lag(data,4)), 
       na.trim(lag(data,5)), all=FALSE) 

dataset <- merge(feat, data, all = FALSE) 
colnames(dataset) <- c("lag.1", "lag.2","lag.3","lag.4","lag.5", "obj") 

index <- 1:4000 
training <- as.data.frame(dataset[index,]) 
testing <- as.data.frame(dataset[-index,]) 

library(mxnet) 
train.x <- data.matrix(training[,-6]) 
train.y <- training[,6] 
test.x <- data.matrix(testing[,-6]) 
test.y <- testing[,6] 

get.label <- function(X) { 
    label <- array(0, dim=dim(X)) 
    d <- dim(X)[1] 
    w <- dim(X)[2] 
    for (i in 0:(w-1)) { 
    for (j in 1:d) { 
     label[i*d+j] <- X[(i*d+j)%%(w*d)+1] 
    } 
    } 
    return (label) 
} 
X.train.label <- get.label(t(train.x)) 
X.val.label <- get.label(t(test.x)) 

X.train <- list(data=t(train.x), label=X.train.label) 
X.val <- list(data=t(test.x), label=X.val.label) 


#X.train <- list(data=t(train.x), label=X.train.label) 
#X.val <- list(data=t(test.x), label=X.val.label) 

batch.size = 5 
seq.len = 5 
num.hidden = 3 
num.embed = 3 
num.rnn.layer = 1 
num.lstm.layer = 1 
num.round = 1 
update.period = 1 
learning.rate= 0.1 
wd=0.00001 
clip_gradient=1 

mx.set.seed(0) 
model <- mx.rnn(X.train, X.val, num.rnn.layer=num.rnn.layer, seq.len=seq.len, num.hidden=num.hidden, 
       num.embed=num.embed, num.label=5, batch.size=batch.size, input.size=5, ctx = mx.cpu(), 
       num.round = num.round, update.period = update.period, initializer = mx.init.uniform(0.01), 
       dropout = 0, optimizer = "sgd", batch.norm = FALSE, 
       learning.rate=learning.rate, wd=wd, clip_gradient=clip_gradient) 

#preds = predict(model,t(test.x)) 

mx.rnn.inference(num.rnn.layer = num.rnn.layer,input.size = 5,num.hidden = num.hidden, 
       num.embed = num.embed,num.label = 5,batch.size = batch.size,ctx = mx.cpu(), 
       dropout = 0,batch.norm = FALSE,arg.params = model$arg.params) 

は、次のエラーが発生します。

[15:36:29] src/operator/./reshape-inl.h:311: Using target_shape will be deprecated. 
[15:36:29] src/operator/./reshape-inl.h:311: Using target_shape will be deprecated. 
[15:36:29] src/operator/./reshape-inl.h:311: Using target_shape will be deprecated. 
[15:36:29] src/operator/./reshape-inl.h:311: Using target_shape will be deprecated. 
[15:36:29] C:/Users/qkou/mxnet/dmlc-core/include/dmlc/logging.h:235: [15:36:29] src/ndarray/ndarray.cc:231: Check failed: from.shape() == to->shape() operands shape mismatch 
Error in exec$update.arg.arrays(arg.arrays, match.name, skip.null) : 
    [15:36:29] src/ndarray/ndarray.cc:231: Check failed: from.shape() == to->shape() operands shape mismatch 

は、それは私がこのたびを取得することはありません。このコードが実際に実行される前にいくつか実行されています。 何が起こっているのか把握してくれたら助かりますか？

Answer 1

おそらく問題は、Quandlから受け取ったデータまたは処理方法です。

NAがna.trim()の後にアレイに残ります（NAが真ん中にある場合）。たぶんそれは、いくつかの状況で一致する形状の失敗を引き起こします。もう一度失敗したら、入力の状態を調べることをお勧めします。

それ以外の場合、追加のコールバックをいくつか追加した後、コードは有効です。ここでは、パラメータは、インラインと合成データを使用して追加している：

Iter [1] Train: Time: 0.0565540790557861 sec, NLL=1.24340298398393, Perp=3.46739289327374 
Iter [1] Val: NLL=0.972949155822989, Perp=2.6457356516903 
Iter [2] Train: Time: 0.0448548793792725 sec, NLL=1.05087134012195, Perp=2.86014218926439 
Iter [2] Val: NLL=0.933895505149184, Perp=2.5444016267033 
Iter [3] Train: Time: 0.0413610935211182 sec, NLL=1.03151336330655, Perp=2.80530807416766 
Iter [3] Val: NLL=0.928943917861239, Perp=2.53183394062849 
Iter [4] Train: Time: 0.0391628742218018 sec, NLL=1.02448851825416, Perp=2.78567027662271 
Iter [4] Val: NLL=0.929383579241022, Perp=2.53294733497252 
Iter [5] Train: Time: 0.0570688247680664 sec, NLL=1.02105997322465, Perp=2.77613583461354 
Iter [5] Val: NLL=0.931082768161547, Perp=2.53725494970957 
Iter [6] Train: Time: 0.0490150451660156 sec, NLL=1.01910802455776, Perp=2.77072224521523 
Iter [6] Val: NLL=0.932948367271994, Perp=2.54199286844103 
Iter [7] Train: Time: 0.0413157939910889 sec, NLL=1.01788873616316, Perp=2.76734599446694 
Iter [7] Val: NLL=0.934675413492902, Perp=2.54638680078803 
Iter [8] Train: Time: 0.039240837097168 sec, NLL=1.01707631967569, Perp=2.76509866995983 
Iter [8] Val: NLL=0.936200143876176, Perp=2.5502723155392 
Iter [9] Train: Time: 0.054689884185791 sec, NLL=1.01650758366912, Perp=2.76352650590005 
Iter [9] Val: NLL=0.937529913411492, Perp=2.55366584577767 
Iter [10] Train: Time: 0.0455291271209717 sec, NLL=1.01609363851068, Perp=2.762382794216 
Iter [10] Val: NLL=0.938689138057902, Perp=2.55662783463834 

を私は予測を実行する場合は、私が受け取る：：

library(mxnet) 
library(zoo) 

dataset <- data.frame(lag.1 = rexp(100), lag.2 = rexp(100), lag.3 = rexp(100), lag.4 = rexp(100), lag.5 = rexp(100), obj = rexp(100)) 

index <- 1:80 
training <- as.data.frame(dataset[index,]) 
testing <- as.data.frame(dataset[-index,]) 

train.x <- data.matrix(training[,-6]) 
train.y <- training[,6] 
test.x <- data.matrix(testing[,-6]) 
test.y <- testing[,6] 

get.label <- function(X) { 
    label <- array(0, dim=dim(X)) 
    d <- dim(X)[1] 
    w <- dim(X)[2] 
    for (i in 0:(w-1)) { 
    for (j in 1:d) { 
     label[i*d+j] <- X[(i*d+j)%%(w*d)+1] 
    } 
    } 
    return (label) 
} 

X.train.label <- get.label(t(train.x)) 
X.val.label <- get.label(t(test.x)) 

X.train <- list(data=t(train.x), label=X.train.label) 
X.val <- list(data=t(test.x), label=X.val.label) 

mx.set.seed(0) 
model <- mx.rnn(X.train, 
       X.val, 
       num.rnn.layer=1, 
       seq.len=5, 
       num.hidden=3, 
       num.embed=3, 
       num.label=5, 
       batch.size=5, 
       input.size=5, 
       ctx = mx.cpu(), 
       num.round = 10, 
       update.period = 1, 
       initializer = mx.init.uniform(0.01), 
       dropout = 0, 
       optimizer = "sgd", 
       batch.norm = FALSE, 
       learning.rate=0.1, 
       wd=0.00001, 
       batch.end.callback=mx.callback.log.train.metric(100), 
       epoch.end.callback=mx.callback.log.train.metric(100), 
       clip_gradient=1) 


inference_model <- mx.rnn.inference(num.rnn.layer=1, 
       input.size=5, 
       num.hidden=3, 
       num.embed=3, 
       num.label=5, 
       batch.size=5, 
       ctx = mx.cpu(), 
       dropout = 0, 
       batch.norm = FALSE, 
       arg.params = model$arg.params) 

forward_return <- mx.rnn.forward(inference_model, rexp(5), FALSE) 

私はそれを実行した場合、私が手

[1] "prob" 
      [,1]  [,2]  [,3]  [,4]  [,5] 
[1,] 0.64961344 0.64961344 0.64961344 0.64961344 0.64961469 
[2,] 0.21320672 0.21320672 0.21320672 0.21320672 0.21320683 
[3,] 0.08818325 0.08818325 0.08818325 0.08818325 0.08818299 
[4,] 0.03633073 0.03633073 0.03633073 0.03633073 0.03633021 
[5,] 0.01266575 0.01266575 0.01266575 0.01266575 0.01266531