GTN Tutorial: Data manipulation Olympics - all steps and exercises

Last updated Nov 20, 2024

Launch in Tutorial Mode question
License: None Specified, defaults to CC-BY-4.0
Tests: ❌ Results: Not yet automated

flowchart TD
  0["ℹ️ Input Dataset\nolympics.tsv"];
  style 0 stroke:#2c3143,stroke-width:4px;
  1["ℹ️ Input Dataset\ncountry-information.tsv"];
  style 1 stroke:#2c3143,stroke-width:4px;
  2["ℹ️ Input Dataset\nolympics_2022.tsv"];
  style 2 stroke:#2c3143,stroke-width:4px;
  3["Line/Word/Character count"];
  0 -->|output| 3;
  4["tabular-to-csv"];
  0 -->|output| 4;
  5["Sort"];
  0 -->|output| 5;
  6["Sort"];
  0 -->|output| 6;
  7["Sort"];
  0 -->|output| 7;
  8["Sort"];
  0 -->|output| 8;
  9["Sort"];
  0 -->|output| 9;
  10["Sort"];
  0 -->|output| 10;
  11["Filter"];
  0 -->|output| 11;
  12["Filter"];
  0 -->|output| 12;
  13["Count"];
  0 -->|output| 13;
  14["Count"];
  0 -->|output| 14;
  15["Count"];
  0 -->|output| 15;
  16["Count"];
  0 -->|output| 16;
  17["Datamash"];
  0 -->|output| 17;
  18["Count"];
  0 -->|output| 18;
  19["Datamash"];
  0 -->|output| 19;
  20["Filter"];
  0 -->|output| 20;
  21["Filter"];
  0 -->|output| 21;
  22["Filter"];
  0 -->|output| 22;
  23["Filter"];
  0 -->|output| 23;
  24["Filter"];
  0 -->|output| 24;
  25["Filter"];
  0 -->|output| 25;
  26["Filter"];
  0 -->|output| 26;
  27["Compute"];
  0 -->|output| 27;
  28["Compute"];
  0 -->|output| 28;
  29["Cut"];
  0 -->|output| 29;
  30["Column Regex Find And Replace"];
  0 -->|output| 30;
  31["Column Regex Find And Replace"];
  0 -->|output| 31;
  32["Column Regex Find And Replace"];
  0 -->|output| 32;
  33["Cut"];
  0 -->|output| 33;
  34["Cut"];
  0 -->|output| 34;
  35["Datamash"];
  0 -->|output| 35;
  36["Datamash"];
  0 -->|output| 36;
  37["Datamash"];
  0 -->|output| 37;
  38["Datamash"];
  0 -->|output| 38;
  39["Datamash"];
  0 -->|output| 39;
  40["Count"];
  0 -->|output| 40;
  41["Column Regex Find And Replace"];
  0 -->|output| 41;
  42["Split file"];
  0 -->|output| 42;
  43["Join two Datasets"];
  0 -->|output| 43;
  1 -->|output| 43;
  44["Remove beginning"];
  2 -->|output| 44;
  45["Sort"];
  11 -->|out_file1| 45;
  46["Filter"];
  12 -->|out_file1| 46;
  47["Cut"];
  28 -->|out_file1| 47;
  48["Unique"];
  29 -->|out_file1| 48;
  49["Count"];
  41 -->|out_file1| 49;
  50["Datamash"];
  41 -->|out_file1| 50;
  51["Concatenate datasets"];
  0 -->|output| 51;
  44 -->|out_file1| 51;
  52["Filter"];
  45 -->|outfile| 52;
  53["Sort"];
  46 -->|out_file1| 53;
  54["Remove beginning"];
  47 -->|out_file1| 54;
  55["Select first"];
  47 -->|out_file1| 55;
  56["Sort"];
  48 -->|outfile| 56;
  57["Unique"];
  54 -->|out_file1| 57;
  58["Concatenate datasets"];
  55 -->|out_file1| 58;
  57 -->|outfile| 58;
  59["Join two Datasets"];
  0 -->|output| 59;
  58 -->|out_file1| 59;
  60["Cut"];
  59 -->|out_file1| 60;
  61["Line/Word/Character count"];
  60 -->|out_file1| 61;