rangaswamymr opened a new issue #30:
URL: https://github.com/apache/incubator-bluemarlin/issues/30


   As per the weekly meeting discussions, the hyper parameter 
"train_skip_first" value 12 was the reason for difference in predictions using 
the model you shared and the model we trained. Below is the predicted data and 
accuracy before and after updating the train_skip_first.
   <html xmlns:v="urn:schemas-microsoft-com:vml"
   xmlns:o="urn:schemas-microsoft-com:office:office"
   xmlns:x="urn:schemas-microsoft-com:office:excel"
   xmlns="http://www.w3.org/TR/REC-html40";>
   
   <head>
   
   <meta name=ProgId content=Excel.Sheet>
   <meta name=Generator content="Microsoft Excel 15">
   <link id=Main-File rel=Main-File
   href="file:///C:\Users\R00244~1\AppData\Local\Temp\msohtmlclip1\01\clip.htm">
   <link rel=File-List
   
href="file:///C:\Users\R00244~1\AppData\Local\Temp\msohtmlclip1\01\clip_filelist.xml">
   <style>
   <!--table
        {mso-displayed-decimal-separator:"\.";
        mso-displayed-thousand-separator:"\,";}
   @page
        {margin:.75in .7in .75in .7in;
        mso-header-margin:.3in;
        mso-footer-margin:.3in;}
   tr
        {mso-height-source:auto;}
   col
        {mso-width-source:auto;}
   br
        {mso-data-placement:same-cell;}
   td
        {padding-top:1px;
        padding-right:1px;
        padding-left:1px;
        mso-ignore:padding;
        color:black;
        font-size:11.0pt;
        font-weight:400;
        font-style:normal;
        text-decoration:none;
        font-family:Calibri, sans-serif;
        mso-font-charset:0;
        mso-number-format:General;
        text-align:general;
        vertical-align:bottom;
        border:none;
        mso-background-source:auto;
        mso-pattern:auto;
        mso-protection:locked visible;
        white-space:nowrap;
        mso-rotate:0;}
   .xl65
        {mso-number-format:"_\(* \#\,\#\#0_\)\;_\(* \\\(\#\,\#\#0\\\)\;_\(* 
\0022-\0022??_\)\;_\(\@_\)";}
   .xl66
        {mso-number-format:"_\(* \#\,\#\#0_\)\;_\(* \\\(\#\,\#\#0\\\)\;_\(* 
\0022-\0022??_\)\;_\(\@_\)";
        background:#DDEBF7;
        mso-pattern:black none;}
   .xl67
        {background:#DDEBF7;
        mso-pattern:black none;}
   .xl68
        {border:.5pt solid windowtext;}
   .xl69
        {mso-number-format:"_\(* \#\,\#\#0_\)\;_\(* \\\(\#\,\#\#0\\\)\;_\(* 
\0022-\0022??_\)\;_\(\@_\)";
        border:.5pt solid windowtext;
        white-space:normal;}
   .xl70
        {mso-number-format:"_\(* \#\,\#\#0_\)\;_\(* \\\(\#\,\#\#0\\\)\;_\(* 
\0022-\0022??_\)\;_\(\@_\)";
        border:.5pt solid windowtext;
        background:#DDEBF7;
        mso-pattern:black none;
        white-space:normal;}
   .xl71
        {border:.5pt solid windowtext;
        white-space:normal;}
   .xl72
        {mso-number-format:"_\(* \#\,\#\#0_\)\;_\(* \\\(\#\,\#\#0\\\)\;_\(* 
\0022-\0022??_\)\;_\(\@_\)";
        border:.5pt solid windowtext;}
   .xl73
        {border:.5pt solid windowtext;
        background:#DDEBF7;
        mso-pattern:black none;}
   -->
   </style>
   </head>
   
   <body link="#0563C1" vlink="#954F72">
   
   
   
   Slot id | Actual values | Model trained Using feeder files shared by   BM 
with train_skip_first = 0 | Predictions   using model trained after changing 
train_skip_first = 12
   -- | -- | -- | --
   a47eavw7ex | 618,874,425 | 710379690 | 679778335
   66bcd2720e5011e79bc8fa163e05184e | 141,771,777 | 150189391 | 134106959
   x0ej5xhk60kjwq | 140,838,705 | 166090973 | 150899108
   l03493p0r3 | 111,445,915 | 95256513 | 97194166
   7b0d7b55ab0c11e68b7900163e3e481d | 105,754,734 | 110975030 | 89637188
   b6le0s4qo8 | 101,684,589 | 116538098 | 108032992
   e351de37263311e6af7500163e291137 | 77,548,938 | 85192615 | 69053892
   a290af82884e11e5bdec00163e291137 | 72,593,126 | 78752741 | 62835164
   68bcd2720e5011e79bc8fa163e05184e | 48,699,653 | 52896931 | 43842830
   f1iprgyl13 | 38,603,295 | 40964141 | 33260309
   w3wx3nv9ow5i97 | 35,212,394 | 32632932 | 29544796
   w9fmyd5r0i | 33,533,582 | 35375640 | 31485616
   d971z9825e | 26,376,462 | 29203099 | 20635427
   l2d4ec6csv | 21,556,143 | 27453184 | 27377759
   z041bf6g4s | 17,440,168 | 25409583 | 6177790
   71bcd2720e5011e79bc8fa163e05184e | 12,459,624 | 10217224 | 8926710
   5cd1c663263511e6af7500163e291137 | 7,096,585 | 6485828 | 5206453
   x2fpfbm8rt | 6,390,364 | 6004435 | 4104797
   d9jucwkpr3 | 4,475,456 | 6371902 | 4366933
   k4werqx13k | 4,464,357 | 4717659 | 3375137
   a8syykhszz | 886,345 | 880801 | 790722
   j1430itab9wj3b | 864,567 | 698216 | 797136
   s4z85pd1h8 | 637,263 | 714682 | 562948
   d4d7362e879511e5bdec00163e291137 | 188,922 | 42751 | 35520
   17dd6d8098bf11e5bdec00163e291137 | 168,582 | 60899 | 92402
   
   
   
   </body>
   
   </html>
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to