Split timeline for training LSTM network












0












$begingroup$


I have faced some trouble in splitting my dataset before feeding the data into an LSTM network. My data are time series, so that the only feasible way is to split them into training and testing part according to the time.



To do that I have selected a specific date that divide the timeline according to the desired proportion (70/30).



However, it is not the first time I get stuck with the choice of the timesteps in training an LSTM network with Keras.



My code does simply what follows:



split_date = '2002-03-01'
df_train = df[:split_date]
df_test = df[split_date:]
df_train.drop(df_train.tail(1).index,inplace=True)


Once I obtain the training and the test set, I find very difficult to resize the array as 3D shaped in order to provide the data to the LSTM. This is due to the fact that if I want to include 22 timesteps in my network, it happens that both sets could not be divisible for the number of timesteps. This implies that I am not able to resize them and I can't work with LSTM properly.



Is there a simple way to deal with timeline splitting, as in this case? Do the timesteps need to be the same for the training and testing part of an LSTM? Is is necessary to maintain this correspondence? In fact, this is the cause of my troble and it is not the first time I face this problem in working with LSTM for time series.










share|improve this question









$endgroup$

















    0












    $begingroup$


    I have faced some trouble in splitting my dataset before feeding the data into an LSTM network. My data are time series, so that the only feasible way is to split them into training and testing part according to the time.



    To do that I have selected a specific date that divide the timeline according to the desired proportion (70/30).



    However, it is not the first time I get stuck with the choice of the timesteps in training an LSTM network with Keras.



    My code does simply what follows:



    split_date = '2002-03-01'
    df_train = df[:split_date]
    df_test = df[split_date:]
    df_train.drop(df_train.tail(1).index,inplace=True)


    Once I obtain the training and the test set, I find very difficult to resize the array as 3D shaped in order to provide the data to the LSTM. This is due to the fact that if I want to include 22 timesteps in my network, it happens that both sets could not be divisible for the number of timesteps. This implies that I am not able to resize them and I can't work with LSTM properly.



    Is there a simple way to deal with timeline splitting, as in this case? Do the timesteps need to be the same for the training and testing part of an LSTM? Is is necessary to maintain this correspondence? In fact, this is the cause of my troble and it is not the first time I face this problem in working with LSTM for time series.










    share|improve this question









    $endgroup$















      0












      0








      0





      $begingroup$


      I have faced some trouble in splitting my dataset before feeding the data into an LSTM network. My data are time series, so that the only feasible way is to split them into training and testing part according to the time.



      To do that I have selected a specific date that divide the timeline according to the desired proportion (70/30).



      However, it is not the first time I get stuck with the choice of the timesteps in training an LSTM network with Keras.



      My code does simply what follows:



      split_date = '2002-03-01'
      df_train = df[:split_date]
      df_test = df[split_date:]
      df_train.drop(df_train.tail(1).index,inplace=True)


      Once I obtain the training and the test set, I find very difficult to resize the array as 3D shaped in order to provide the data to the LSTM. This is due to the fact that if I want to include 22 timesteps in my network, it happens that both sets could not be divisible for the number of timesteps. This implies that I am not able to resize them and I can't work with LSTM properly.



      Is there a simple way to deal with timeline splitting, as in this case? Do the timesteps need to be the same for the training and testing part of an LSTM? Is is necessary to maintain this correspondence? In fact, this is the cause of my troble and it is not the first time I face this problem in working with LSTM for time series.










      share|improve this question









      $endgroup$




      I have faced some trouble in splitting my dataset before feeding the data into an LSTM network. My data are time series, so that the only feasible way is to split them into training and testing part according to the time.



      To do that I have selected a specific date that divide the timeline according to the desired proportion (70/30).



      However, it is not the first time I get stuck with the choice of the timesteps in training an LSTM network with Keras.



      My code does simply what follows:



      split_date = '2002-03-01'
      df_train = df[:split_date]
      df_test = df[split_date:]
      df_train.drop(df_train.tail(1).index,inplace=True)


      Once I obtain the training and the test set, I find very difficult to resize the array as 3D shaped in order to provide the data to the LSTM. This is due to the fact that if I want to include 22 timesteps in my network, it happens that both sets could not be divisible for the number of timesteps. This implies that I am not able to resize them and I can't work with LSTM properly.



      Is there a simple way to deal with timeline splitting, as in this case? Do the timesteps need to be the same for the training and testing part of an LSTM? Is is necessary to maintain this correspondence? In fact, this is the cause of my troble and it is not the first time I face this problem in working with LSTM for time series.







      deep-learning keras dataset lstm






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked yesterday









      AlexbriniAlexbrini

      375




      375






















          0






          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47536%2fsplit-timeline-for-training-lstm-network%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47536%2fsplit-timeline-for-training-lstm-network%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana