# Masking for different dates in different examples (using LSTM)

**URL:** https://community.konduit.ai/t/masking-for-different-dates-in-different-examples-using-lstm/972
**Category:** DL4J
**Created:** [November 3, 2020, 10:56am UTC](https://community.konduit.ai/t/masking-for-different-dates-in-different-examples-using-lstm/972 "2020-11-03T10:56:31Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![miterial](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/miterial/32/351_2.png) [@miterial](https://community.konduit.ai/u/miterial)
#### Post date: [November 3, 2020, 10:56am UTC](https://community.konduit.ai/t/masking-for-different-dates-in-different-examples-using-lstm/972/1 "2020-11-03T10:56:32Z")

</div>

I have multiple training sets that look like this (feature values don’t matter, the “Date” field is a timestamp):  
Example #1:

```auto
   Date | Feature1 | Feature2
   123 4 56
   124 7 44
   126 3 60

```

Example #2:

```auto
    Date | Feature1 | Feature2
    123 3 52
    125 5 54
    126 8 38

```

My Labels for #1:

```auto
    1
    2
    3

```

My Labels for #2:

```auto
    4
    5
    6

```

So in first example data for for “Date=125” is missing and in second example - for “Date=124”. I know that there is `AlignmentMode` parameter for `SequenceRecordReaderDataSetIterator` but as far I as I understand it can only fill up the data if something is missing in the beginning or the end (for example, if my example #1 didn’t have a row with “Date=124”). Is it possible to provide training data like I have it in the examples above or do I need to fill with zeros the features/labels row for “Date=125” in #1 and for “Date=124” in #2 before creating `SequenceRecordReaderDataSetIterator`?