{
  "metadata": {
    "version": 1,
    "disable_limits": false
  },
  "nodes": [
    {
      "node_id": "ca0245bd-270a-45db-a597-464115684c44",
      "type": "SOURCE",
      "operator": "sagemaker.s3_source_0.1",
      "parameters": {
        "dataset_definition": {
          "__typename": "S3CreateDatasetDefinitionOutput",
          "datasetSourceType": "S3",
          "name": "abalone.csv",
          "description": null,
          "s3ExecutionContext": {
            "__typename": "S3ExecutionContext",
            "s3Uri": "s3://sagemaker-us-east-1-949335012047/feature-store-ingestion-pipeline/dataset/abalone.csv",
            "s3ContentType": "csv",
            "s3HasHeader": true,
            "s3FieldDelimiter": ",",
            "s3DirIncludesNested": false,
            "s3AddsFilenameColumn": false
          }
        }
      },
      "inputs": [],
      "outputs": [
        {
          "name": "default",
          "sampling": {
            "sampling_method": "sample_by_limit",
            "limit_rows": 50000
          }
        }
      ]
    },
    {
      "node_id": "dc681f4a-e296-48a7-83c3-a2fad429ae8c",
      "type": "TRANSFORM",
      "operator": "sagemaker.spark.infer_and_cast_type_0.1",
      "parameters": {},
      "trained_parameters": {
        "schema": {
          "record_id": "long",
          "sex": "string",
          "length": "float",
          "diameter": "float",
          "height": "float",
          "whole_weight": "float",
          "shucked_weight": "float",
          "viscera_weight": "float",
          "shell_weight": "float",
          "rings": "long"
        }
      },
      "inputs": [
        {
          "name": "default",
          "node_id": "ca0245bd-270a-45db-a597-464115684c44",
          "output_name": "default"
        }
      ],
      "outputs": [
        {
          "name": "default"
        }
      ]
    },
    {
      "node_id": "906df020-fbf7-451a-8b2f-d73a5aa56975",
      "type": "TRANSFORM",
      "operator": "sagemaker.spark.custom_pandas_0.1",
      "parameters": {
        "code": "import pandas as pd\nfrom sklearn.preprocessing import StandardScaler\n\ndf_scaled = df.drop(['record_id', 'sex','rings'], axis=1)\ndf_scaled = StandardScaler().fit_transform(df_scaled.to_numpy())\ndf_scaled = pd.DataFrame(df_scaled, columns=[\n'length','diameter','height','whole_weight','shucked_weight','viscera_weight','shell_weight'])\n\ndf = pd.concat((df_scaled, df[['record_id', 'sex','rings']]), 1)"
      },
      "inputs": [
        {
          "name": "df",
          "node_id": "dc681f4a-e296-48a7-83c3-a2fad429ae8c",
          "output_name": "default"
        }
      ],
      "outputs": [
        {
          "name": "default"
        }
      ]
    },
    {
      "node_id": "914c3ccc-b898-4cff-a12b-fcb75ceeecfc",
      "type": "TRANSFORM",
      "operator": "sagemaker.spark.encode_categorical_0.1",
      "parameters": {
        "operator": "One-hot encode",
        "one_hot_encode_parameters": {
          "invalid_handling_strategy": "Keep",
          "drop_last": false,
          "output_style": "Columns",
          "input_column": "sex"
        },
        "ordinal_encode_parameters": {
          "invalid_handling_strategy": "Replace with NaN"
        }
      },
      "trained_parameters": {
        "one_hot_encode_parameters": {
          "_hash": -1767228197713558300,
          "string_indexer_model": "P)h>@6aWAK2ms(_MpF>|VY%A?003bD000vJ003=ebYWy+bYU-WVRCdWFfcGMFnx|qOT$1EMfd)US*Jsqq_K8eH(eA3#cg<GZrafK^39C2mi%|e2!eucFXtTYRrH!d5F6q6AjwmIgbbeeB#o8>C?<w{iagrG&MKV2d#9j9A>wEdA{j3>%eJmpRdZJ^*Q=%wv;P7PqqDhO%TksLGVgX#W-pB@k3W)Kg>_TjDl~0dWhDD#_LR$4aU`oWcJ__*ES><L5tpJ*aqD!RB8=~P_jzix-)q2GOodPwDCzk4PZG?Ie>MO9*L7c97QzfYumV3{JhC=0UK4D8xku>5G~IjvP)h>@6aWAK2ms(_MpI6rg<uW<000aC000;O003=ebYWy+bYU+paA9(EEif=JFfcA-a$`#_N@ieSU}D&r_*Vb`P)h>@6aWAK2ms+`MpH>!ta^a~003+P002k;003lRbYU-WVRCdWFfcGMFfBJ_Wn^J6IWjFUV>mD^G&49jEn;P5GA%M=G-WeoHDNhnG-WMgFfcGKb8ca9aCt6pVRCVGWps^FTT8<*6i(~x2JST_g(4%cF=2+*Zgm?&5JXg%i1;9gNV=x8n08x|DP!#S`M1n2-VuB`ob!F>_8rdE@wE>D?7^c3w6tSE%MC%@=p*A40I=(BX}eVi1*3S98Nkp{e`(H_<`kL^KP$^I6;BUx@W?U>P0%vY4yO_0@>mEugC?{<tAGkTm1<2F8D|;G)lUkRtDj^Q0NZq2$E}rISazzwa&Eu&T@}42e+!^#Teh%Ot<?LF;<#EI&@*&bVVl5dAT$y~LdR6^O;!@fGZQi$<!Cz~9`OL$`;{RloM>k<Wr~Q=3(1(GF;x`38gr~>V}`p}Dlr`>+`vi7cr0=EZjN)BEvYZ-Ykr;oQAaoMM#arP*yXG=A8L3o$`ws>c{$}Acl8Er@dudefJU6Hfd+n;pl2->_X~h7HUjrEQQ2Ii;uGH^ex)8wQyy2mq!TC2AZAGtwcAO2n6$$%jKd)8`0eIF5O_&5jN;Co<GT9bHGTCf{bz4bO9KQH000080O4jvQ?}?71rh)N01yBG08Ib@0AyiwVJ|LlVRCdWFfcGMFfBJ_Wn^J6IWjFUV>mD^G&49jEn;P5GA%M=G-WeoHDNhnG-WMgFfcGKb8ca9aCt6pVRCVGWpplMa$`#_N@ieSU}D(rz2WL7^`0I8P)h*<6ay3h000O8;ATcs5dC4f+W-InVF3UD6951J0000000000q=5hc003=ebYWy+bYU-WVRCdWFfcGMFi=YY0u%!j000080N`duQ%<6VU=9EP01N;C02lxO00000000000HlEo0RRAPWprU=VRT_HE^uLTbS*G2FfcGKV{&6qO928D0~7!N00;o#W=2y<TdaD40RRAO0ssI=00000000000001_flvVe0AyiwVJ~oDa&#>)FfcGMEjMLlWMMElGA%G;I4~_VGdMUcVr6AAEiz*?Wiw?pVL4$mWi4YcFfcB2Zeeh6c`k5aa&dKKbWlqH0u%!j000080O4jvQ?}?71rh)N01yBG08Ib@00000000000HlF80{{SIVRT_HE^uLTbS*G2FfcGJH)UmHVK6x|Eihv^FfBAQI5;h0Wo0rgGGjDlGi5blIbk$qEn_e+FfMa$VQ_GHE^uLTadl;ME@N_IP)h{{000001ONm8cmV(av;zPD000",
          "one_hot_encoder_model": "P)h>@6aWAK2ms+`MpIn0<Ui8@003zL000vJ003=ebYWy+bYU-WVRCdWFfcGMFm;Z-PD3#aMt2^=^KFzirO>+~B#@|JVvVfCmtK)SISvC=-<?nd5{NDyKKnbz2XFyvg%L8pC@kpqq-sHaRWYcEP#TkZOmvs!Ho5GHcYOpHK;}qQFcuh>8)Gh4>#bg0Z`T8y`p?95&Z(1)(n>EdzNdxmy*B$E{zBR-qiM6$-a9n?r1vrIu#*qqIhO~l0^@|C(g3+hX>yZ8r&ys_tjocElIQfZ_|AK}$K(Uur#B2IGcjj|;{cu}Y(bv>l?k^$uJa#T`*n9-cD(oiP)h>@6aWAK2ms+`MpHFwm=O*D000aC000;O003=ebYWy+bYU+paA9(EEif=JFfcA-a$`#_N@ieSU}CU;vLyxpP)h>@6aWAK2ms+`MpG1}iO7Bd001xo002k;003lRbYU-WVRCdWFfcGMFfBASH90V1G&3zSF*P(TG%_+~EjVE_VJ%{0V=_26GB{&0Ib|(lFfcGKb8ca9aCt6pVRCVGWpsT~O-m~=6is8TE_C4{Lk4D10v3fa%)F`Nw7Afnh=`~=c|6iiqQlF~)Ff4^7W^6hK!1q0wu&N{z~z3NbMLt!XNTu8L4=V`NH91p(h6v^i4dAw4{d#k;A|XVuuE{kVl>MV?4KO1*^w~+|JmV<ECs=67t{5jaPqn~lZ)a(T4>)wyG`2Eg>?WRcoWeTsbwiEhdk^De$ZJBpxGvB`Pp~!JLv;Vu!p@T@43-g-Ty_aAHY5^W>$IfF!Do6Yje%TNPtNGu9x3QV~e_?%L$Kogy{AUguT@qoZGQ<+|>8HluqQr3Hs7_WNtE&tk0}7<Dp|AQ-##IW&Nv1R*7;}`nCoj=8R9KFh)!uy;$vXo-HaMNdx&|T{%%y_H?W@>nowHoQAA|NDMSUVXzF@hbCw|o&KF7dc07)Q=0Z-#dgf&h{x@%!MM<QJ5s$|b(35wHOMlR@2M<J(>zVmUYvFRBuS*Y=^*cI`#}IN_}W0|4F1X+P)h>@6aWAK2ms+`MpKf}6v7e!000mG002z@003lRbYU+paA9(EEif=JFfc7NH8nXfVl*=?GBGtYEi^JRW-T~jGhr=aWMeWoI5Ie6GC5@}V=yo<E^}^SaBz7paA9(Bb!BueV{&6lE=p!#U|?eSx#)h+xqnt>08mQ-0u%!j000080O4jvQ(Uy<KhppJ0BHdL022TJ00000000000HlEc0001OWprU=VRT_HaA9(EEif=JFfdR{0Rj{Q6aWAK2ms+`MpHFwm=O*D000aC000;O0000000000005+c1OWg5ZDn*}WMOn+FD`Ila&#>)FfcGME@N_IP)h*<6ay3h000O8;bult6s3vCegOagFaiJoNB{r;0000000000q=85Q003lRbYU-WVRCdWFfcGMFfBASH90V1G&3zSF*P(TG%_+~EjVE_VJ%{0V=_26GB{&0Ib|(lFfcGKb8ca9aCt6pVRCVGWpq$W0Rj{Q6aWAK2ms+`MpKf}6v7e!000mG002z@0000000000005+cECT=lWMOn+FD`Ila&#>)FfcGMEi^SXIWS^0Gc7VPH8d?WGBRc@IAJqkEn;M2GB`LgIAbz7Wi4YcFfcB2Zeeh6c`k5aa&dKKbS`6ZV^B*41^@s600aO80C)ia0I3520000"
        }
      },
      "inputs": [
        {
          "name": "df",
          "node_id": "906df020-fbf7-451a-8b2f-d73a5aa56975",
          "output_name": "default"
        }
      ],
      "outputs": [
        {
          "name": "default"
        }
      ]
    },
    {
      "node_id": "5827674e-d42e-4688-8609-b1aa34cc4954",
      "type": "TRANSFORM",
      "operator": "sagemaker.spark.custom_pandas_0.1",
      "parameters": {
        "code": "import time\nimport pandas as pd\n\nrecord_time_feature_name = 'record_time'\ncurrent_time_sec = int(round(time.time()))\ndf[record_time_feature_name] = pd.Series([current_time_sec]*len(df), dtype=\"float\")"
      },
      "inputs": [
        {
          "name": "df",
          "node_id": "914c3ccc-b898-4cff-a12b-fcb75ceeecfc",
          "output_name": "default"
        }
      ],
      "outputs": [
        {
          "name": "default"
        }
      ]
    }
  ]
}