From 99c0a3c722e0c3fba7b70306be9df2efc7be0f44 Mon Sep 17 00:00:00 2001 From: "casey.morter" Date: Sat, 7 Sep 2024 08:51:38 +1000 Subject: [PATCH] join tool updates --- SimpleWorkflow/SimpleWorkflow.bak | 104 +++++++++-- SimpleWorkflow/SimpleWorkflow.yxmd | 139 ++++++++++++-- Untitled.png | Bin 3460 -> 0 bytes scratchpad.ipynb | 279 ++++++++++++++--------------- 4 files changed, 348 insertions(+), 174 deletions(-) delete mode 100644 Untitled.png diff --git a/SimpleWorkflow/SimpleWorkflow.bak b/SimpleWorkflow/SimpleWorkflow.bak index bc40270..8e18823 100644 --- a/SimpleWorkflow/SimpleWorkflow.bak +++ b/SimpleWorkflow/SimpleWorkflow.bak @@ -1,5 +1,5 @@ - + @@ -63,7 +63,15 @@ - C:\Users\casey.morter\AppData\Local\Temp\Engine_1076_e92ddd5f524045a79cff90fef659b528_\Engine_33528_b9fe906502c14eb3ad38d38f04c81ab2_.yxdb + C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_93f5c2999bcb8c478c002b15166e2b45~.yxdb + + + + + + + + @@ -83,19 +91,27 @@ + + 5 8 + z + a 6 9 + b + d 7 10 + c + c @@ -136,12 +152,12 @@ - + - @@ -155,18 +171,22 @@ - + + - + + - - + + + + @@ -186,7 +206,15 @@ - C:\Users\casey.morter\AppData\Local\Temp\Engine_1076_e92ddd5f524045a79cff90fef659b528_\Engine_33528_96b3fed5c185423dafa9c8e54e621b39_.yxdb + C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_ab9b90f8fc991440905d667f1d5c7325~.yxdb + + + + +
+ + + @@ -239,7 +267,7 @@ - C:\Users\casey.morter\AppData\Local\Temp\Engine_1076_e92ddd5f524045a79cff90fef659b528_\Engine_33528_7a751c4879e24850ab691e9dd40c3227_.yxdb + C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_dd72ded80941104b9b9be56761379cb2~.yxdb @@ -265,6 +293,7 @@ .\SimpleWorkflowOut.csv + False CRLF , @@ -283,6 +312,44 @@ + + + + + + + + + + + + + + + a + a + 4 + + + b + d + 6 + + + c + z + 7 + + + + + + + + + + + @@ -297,14 +364,6 @@ - - - - - - - - @@ -329,6 +388,14 @@ + + + + + + + + @@ -340,6 +407,7 @@ + diff --git a/SimpleWorkflow/SimpleWorkflow.yxmd b/SimpleWorkflow/SimpleWorkflow.yxmd index 02b97b8..0480f3d 100644 --- a/SimpleWorkflow/SimpleWorkflow.yxmd +++ b/SimpleWorkflow/SimpleWorkflow.yxmd @@ -1,5 +1,5 @@ - + @@ -63,7 +63,7 @@ - C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_93f5c2999bcb8c478c002b15166e2b45~.yxdb + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb @@ -125,7 +125,7 @@ - + @@ -147,7 +147,7 @@ - + @@ -166,7 +166,7 @@ - + @@ -202,11 +202,11 @@ - + - C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_ab9b90f8fc991440905d667f1d5c7325~.yxdb + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb @@ -226,7 +226,7 @@ - + @@ -245,7 +245,7 @@ - + @@ -263,11 +263,11 @@ - + - C:\Users\Casey\AppData\Local\Temp\Engine_4072_8b6c0740e308d445ab856d90eb0e4ee9_\Engine_4072_dd72ded80941104b9b9be56761379cb2~.yxdb + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb @@ -287,13 +287,12 @@ - + .\SimpleWorkflowOut.csv - False CRLF , @@ -350,6 +349,100 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + HamCheeseJoin + HamCheeseJoin + + + + + + + + + + + + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb + + + + + + + + + + + + + + + + + + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb + + + + + + + + + + + + + + + + + + C:\Users\casey.morter\AppData\Local\Temp\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb + + + + +
+ + + + + + + + + + + + @@ -364,6 +457,14 @@ + + + + + + + + @@ -396,6 +497,18 @@ + + + + + + + + + + + + diff --git a/Untitled.png b/Untitled.png deleted file mode 100644 index e070928b3df9a96abd6e1075683e17abe49f68fd..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 3460 zcma)832+q075zQaGdr{QYF9!h5(11kO<@Cah%q2A5(XqYKro1uagc4Oh*NeT6vRpe z3^*Ysd1c{`$^i1V ztl9E(;jxmyy5h5&a+7Ui3VkO^-W#%E(}t}x_9-b-=Dt7Ew)OXH{MPmTjvs%1>CpW6 z{@JfDU3TI8(V1TQ({b-+y&IUf^IyiVC%m1SU0U^@Rn3`Ahdkc&)$xcXd3zwpY!IRWVk&W=hq9H;emi|KY*;z9rt` zC3C)0x2D=VxX2!SD!6UDE9sf#^WM;Yx#INv%2(I_V(Oyp`4fkvjG5i^(yS3Pss~nY z*sl`h?8q3UgH7h(&oH2#)8kjC^70&ie1x z-tdfJ{SGWx{@bIU?R#_3jKa;?rf2QR3qz((|9jEV)Kig{uV(ih7aMl!FIS_nedVKz zfj_bI!%wX9^6*g6PyVrc(&jf=`St39yHBh>QsW*T-}&77Zwl8AdcOp!PS*c%`H>?- zPaUfLa`)?-&)RYd_Rsm0xZRbfbIbOwK78n-6^nV*!Y`U_$44#yO#9o@%P=nL(!v*4 z01WG!_>q+#KJx|&Z52h+CfVv~Z#rhwTR(sG2PjIbm^8bhU`cs-+2RT)SY9^2qHICV zj~7qhHgwFe~RfqA!61Z^;kJ{ifYN&^K?D!w$is*&&9Q}@mXH&ari zh6bbCRVaM4@9kcr>iPwJzxR}!k*=$0a<9CM?5xy=#`xzao6tZc!n!q(D7ODUJVFc= z=1k6eGRGNk7|dWSo+MI#c5mmDv3`6d%e*IqM@L4FCfFO<&yyYiU?ve<+!Ua>o7a)~cVbtn65EpX9({iVGjgxQ%IPC~sY!w; zM43oIlnKEwnzw7&{$q9cHr(7JNRKaY8OAdhH1T1~0I5#^NzjO7XFv##8_jxEjrsYR zD27zFbIg5IM$HFCkIbNUvKp;wfU@GeCvr@mBg`ljBs*s@;E}qU)+fi~h}9(>L%1Xq z3UxKmeZHeFL1v=n+(|iQMS+ohbye2E<|C5A`E5d?wRN^rHw7*WBBhoI=dMLpZn=cG z4;bhM-9u^6Oc1iFw108FV@Q_iaA;g~5$Xp{tXR;{!(cOs%SIF%C=QSvEg^dNSj*h< zqg@@x=Lf3^jkm_*&*o=T&d;4OMj4Q$+w3|}k%$s7%ZiwhRtns(dl_{)MTbjt`$d<} zk>N^q3XOH))0bM2fBkNv-p9KnNl4txg4}t}`o|9ir#s3FgNvAk0+_lL(pnn1W>B9; zgovAio12QjxTUp-hG8d0znmn1o2m+(;|uq+7`2oP=& z(1{r(kzl;FHDX4kWS!XDK|v9Dt0}4`$V$U?<@gsh$VMzt10CZYItmQKm|c)Jthel; zO-wfhwXNlH5%6NT1wkN;NGA2fi64VZI2FJqfsE|iscO$o^8wuMbQ}Tip(7`Qa&z+s z_J)} z@KFO(5V{@hp6{BSLlF9;tCC=tnnp#A$p@AQ76t5CI%Q!JZ?&S9sYo`NU|QHg5I|(0 zL_ul+F%EVyQZF>MBuXr%7|_=9JD9PxHA1f<3Y;(o90@T*AZ?7}5u^*2E&!AC5O0W4 zBWya|O_Ibxv_LX}8bqeeaqr=iu^s!r!iLbv%st-GCS#ai3~SF41qoeF@Q&o*3jqif zu?<+XDcnkEtLoONLW!yXl?j!>?z~f@etaT=AS$M{(Q#Vchkhq)nFz#1#srScBk#C< zOh-lqL7*ZUU@p~4&fsdQ3w%l7@?o}csuGNLa;$Wk{MUo`XhBOIQB5!faJ4!Z()I_EvRd!0U2dpH}{Gi!DH@O~!NP`N&+|)$ns|n^iMhAML{{S5P z@^(XzMKp(@+swGkbTM%ZS$G#2TEeR3vKI2R+zM#7JXSqn-$dDsCU&D9YJ%bG#+55= zg@j3ecXad_UDv&mbUV`0KP{!V7dwc>Ir1$LCL-6IVW^3TOXPS?B0rrhSe(!jtU$ z&Dslfj)2W63od3!2J&tpMU){$7WQH6Hco~56(VB_W4{MYtgROJe%kc!vkeZ%edyhs z9_{A~-p6KT<@d?y7qADMvO|)v5u-MC8)k}BmR;_ctZ0%=YUbjh^K}*54\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('2', 'AlteryxSelect 2', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('3', 'BrowseV2 3', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('4', 'TextInput 4', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('5', 'AlteryxSelect 5', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('6', 'Formula 6', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n", - "('7', 'Join 7', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('10', 'BrowseV2 10', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('11', 'Formula 11', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n", - "('12', 'Sample 12', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n", - "('13', 'BrowseV2 13', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('14', 'DbFileOutput 14', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n", - "('15', 'TextInput 15', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('1', 'TextInput (1)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('2', 'AlteryxSelect (2)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('3', 'BrowseV2 (3)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('4', 'TextInput (4)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('5', 'AlteryxSelect (5)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('6', 'Formula (6)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n", + "('7', 'Join (7)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('10', 'BrowseV2 (10)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('11', 'Formula (11)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n", + "('12', 'Sample (12)', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n", + "('13', 'BrowseV2 (13)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('14', 'DbFileOutput (14)', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n", + "('15', 'TextInput (15)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", "('16', 'HamCheeseJoin', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n HamCheeseJoin\\n HamCheeseJoin\\n \\n \\n \\n \\n \\n ')\n", - "('17', 'BrowseV2 17', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('18', 'BrowseV2 18', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('19', 'BrowseV2 19', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n" + "('17', 'BrowseV2 (17)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('18', 'BrowseV2 (18)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('19', 'BrowseV2 (19)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n" ] } ], @@ -65,7 +65,7 @@ "\n", " tool_name = node.find('Properties/Annotation/Name').text\n", " if not tool_name:\n", - " tool_name = tool_type + \" \" + tool_id\n", + " tool_name = tool_type + \" (\" + tool_id + \")\"\n", "\n", " content = ET.tostring(node, encoding='unicode')\n", " results.append((tool_id, tool_name, content))\n", @@ -87,7 +87,7 @@ }, { "cell_type": "code", - "execution_count": 59, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -126,78 +126,97 @@ }, { "cell_type": "code", - "execution_count": 62, + "execution_count": 30, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " HamCheeseJoin\n", - " HamCheeseJoin\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n" + "L: shape: (2, 4)\n", + "┌──────────┬──────────┬─────┬────────┐\n", + "│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese │\n", + "│ --- ┆ --- ┆ --- ┆ --- │\n", + "│ str ┆ str ┆ str ┆ str │\n", + "╞══════════╪══════════╪═════╪════════╡\n", + "│ 5 ┆ 8 ┆ z ┆ a │\n", + "│ 7 ┆ 10 ┆ c ┆ c │\n", + "└──────────┴──────────┴─────┴────────┘\n", + "J: shape: (1, 7)\n", + "┌──────────┬──────────┬─────┬────────┬───────────┬──────────────┬───────┐\n", + "│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese ┆ Ham_right ┆ Cheese_right ┆ Count │\n", + "│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n", + "│ str ┆ str ┆ str ┆ str ┆ str ┆ str ┆ str │\n", + "╞══════════╪══════════╪═════╪════════╪═══════════╪══════════════╪═══════╡\n", + "│ 6 ┆ 9 ┆ b ┆ d ┆ b ┆ d ┆ 6 │\n", + "└──────────┴──────────┴─────┴────────┴───────────┴──────────────┴───────┘\n", + "R: shape: (2, 3)\n", + "┌─────┬────────┬───────┐\n", + "│ Ham ┆ Cheese ┆ Count │\n", + "│ --- ┆ --- ┆ --- │\n", + "│ str ┆ str ┆ str │\n", + "╞═════╪════════╪═══════╡\n", + "│ a ┆ a ┆ 4 │\n", + "│ c ┆ z ┆ 7 │\n", + "└─────┴────────┴───────┘\n" ] } ], "source": [ "def tool_join(join_spec: dict, df_L: pl.DataFrame, df_R: pl.DataFrame):\n", + " \"\"\" Generates join tool code \"\"\"\n", + " # dynamic_code = \"df_output = df_L.with_columns(\\n\"\n", " pass\n", "\n", + " \n", "\n", + "\n", + "\n", + "# Join spec\n", "xml_join_tool = results[6][2]\n", "join_spec = getConf_Join(xml_join_tool)\n", "\n", - "# print(join_spec)\n", - "\n", - "# print(tool_join(join_spec, ))\n", - "\n", - "# Testing\n", "# Input L: TextInput 4\n", "In_L = input_textInput(results[3][2])\n", "# Input R: TextInput 15\n", - "In_R = input_textInput(results[14][2])\n", - "\n", - "# Join: Join 16\n", + "In_R = input_textInput(results[12][2])\n", "\n", + "# print(join_spec)\n", "# print(In_L, In_R)\n", - "print(results[13][2])\n" + "\n", + "\n", + "## Out L\n", + "# Column 3\tColumn 4\tHam\tCheese\n", + "# 7\t 10\t c\tc\n", + "# 5\t 8\t z\ta\n", + "\n", + "## Out J\n", + "# Column 3\tColumn 4\tHam\tCheese\tRight_Ham\tRight_Cheese\tCount\n", + "# 6\t 9\t b\td\t b\t d\t 6\n", + "\n", + "## Out R\n", + "# Ham\tCheese\tCount\n", + "# a\t a\t 4\n", + "# c\t z\t 7\n", + "\n", + "\n", + "print(\"L:\", In_L.join(In_R, on=join_spec['joinParams'], how='anti'))\n", + "\n", + "print(\"J:\", In_L.join(In_R, on=join_spec['joinParams'], how='inner', coalesce=False))\n", + "\n", + "print(\"R:\", In_R.join(In_L, on=join_spec['joinParams'], how='anti'))" ] }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -271,7 +290,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -290,7 +309,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -318,9 +337,17 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'joinParams': ['Ham', 'Cheese'], 'fields': {'Right_Ham': ['Right_Ham', 'Right_', None, None], 'Right_Cheese': ['Right_Cheese', 'Right_', None, None], 'Right_Column 3': ['Right_Column 3', 'Right_', 'V_String', '11'], 'Right_Column 4': ['Right_Column 4', 'Right_', 'Int64', '8']}}\n" + ] + } + ], "source": [ "def getConf_Join(xml_string):\n", " root = ET.fromstring(xml_string)\n", @@ -357,7 +384,7 @@ "\n", " return dict_JoinTool\n", "\n", - "# print(getConf_Join(xml_join_tool))" + "print(getConf_Join(xml_join_tool))" ] }, { @@ -369,60 +396,19 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "1 TextInput\n", - "shape: (3, 2)\n", - "┌─────────┬──────────┐\n", - "│ Column1 ┆ Column 2 │\n", - "│ --- ┆ --- │\n", - "│ str ┆ str │\n", - "╞═════════╪══════════╡\n", - "│ 1 ┆ 4 │\n", - "│ 2 ┆ 5 │\n", - "│ 3 ┆ 6 │\n", - "└─────────┴──────────┘\n", - "2 AlteryxSelect\n", - "3 BrowseV2\n", - "4 TextInput\n", - "shape: (3, 4)\n", - "┌──────────┬──────────┬─────┬────────┐\n", - "│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese │\n", - "│ --- ┆ --- ┆ --- ┆ --- │\n", - "│ str ┆ str ┆ str ┆ str │\n", - "╞══════════╪══════════╪═════╪════════╡\n", - "│ 5 ┆ 8 ┆ z ┆ a │\n", - "│ 6 ┆ 9 ┆ b ┆ d │\n", - "│ 7 ┆ 10 ┆ c ┆ c │\n", - "└──────────┴──────────┴─────┴────────┘\n", - "5 AlteryxSelect\n", - "6 Formula\n", - "7 Join\n", - "10 BrowseV2\n", - "11 Formula\n", - "12 Sample\n", - "13 BrowseV2\n", - "14 DbFileOutput\n", - "15 TextInput\n", - "shape: (3, 3)\n", - "┌─────┬────────┬───────┐\n", - "│ Ham ┆ Cheese ┆ Count │\n", - "│ --- ┆ --- ┆ --- │\n", - "│ str ┆ str ┆ str │\n", - "╞═════╪════════╪═══════╡\n", - "│ a ┆ a ┆ 4 │\n", - "│ b ┆ d ┆ 6 │\n", - "│ c ┆ z ┆ 7 │\n", - "└─────┴────────┴───────┘\n", - "16 Join\n", - "17 BrowseV2\n", - "18 BrowseV2\n", - "19 BrowseV2\n" + "ename": "ParseError", + "evalue": "syntax error: line 1, column 0 ()", + "output_type": "error", + "traceback": [ + "Traceback \u001b[1;36m(most recent call last)\u001b[0m:\n", + "\u001b[0m File \u001b[0;32mc:\\Users\\casey.morter\\AppData\\Local\\miniconda3\\envs\\polaryx\\Lib\\site-packages\\IPython\\core\\interactiveshell.py:3577\u001b[0m in \u001b[0;35mrun_code\u001b[0m\n exec(code_obj, self.user_global_ns, self.user_ns)\u001b[0m\n", + "\u001b[0m Cell \u001b[0;32mIn[11], line 6\u001b[0m\n ToolType = ET.fromstring(ToolXML).find(\".//GuiSettings\").attrib['Plugin'].split(\".\")[2]\u001b[0m\n", + "\u001b[1;36m File \u001b[1;32mc:\\Users\\casey.morter\\AppData\\Local\\miniconda3\\envs\\polaryx\\Lib\\xml\\etree\\ElementTree.py:1335\u001b[1;36m in \u001b[1;35mXML\u001b[1;36m\n\u001b[1;33m parser.feed(text)\u001b[1;36m\n", + "\u001b[1;36m File \u001b[1;32m\u001b[1;36m\u001b[0m\n\u001b[1;31mParseError\u001b[0m\u001b[1;31m:\u001b[0m syntax error: line 1, column 0\n" ] } ], @@ -442,7 +428,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -487,11 +473,11 @@ ], "source": [ "# Tool 1: TextInput\n", - "xml_tool1 = results[3][1]\n", + "xml_tool1 = results[3][2]\n", "df_in = input_textInput(xml_tool1)\n", "print(\"\\n############### Input dataframe (TextInput):\\n\", df_in)\n", "# Tool 2: Select\n", - "col_spec = getConf_Select(results[4][1])\n", + "col_spec = getConf_Select(results[4][2])\n", "# Generate code from \n", "code = tool_select(col_spec)\n", "print(\"\\n############### Generated code from Select tool: \\n\", code)\n", @@ -503,30 +489,30 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "('1', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('2', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('3', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('4', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('5', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('6', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n", - "('7', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('10', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('11', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n", - "('12', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n", - "('13', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('14', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n", - "('15', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('16', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('17', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('18', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", - "('19', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n" + "('1', 'TextInput (1)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('2', 'AlteryxSelect (2)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('3', 'BrowseV2 (3)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('4', 'TextInput (4)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('5', 'AlteryxSelect (5)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('6', 'Formula (6)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n", + "('7', 'Join (7)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('10', 'BrowseV2 (10)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('11', 'Formula (11)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n", + "('12', 'Sample (12)', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n", + "('13', 'BrowseV2 (13)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('14', 'DbFileOutput (14)', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n", + "('15', 'TextInput (15)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('16', 'HamCheeseJoin', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n HamCheeseJoin\\n HamCheeseJoin\\n \\n \\n \\n \\n \\n ')\n", + "('17', 'BrowseV2 (17)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('18', 'BrowseV2 (18)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n", + "('19', 'BrowseV2 (19)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n
\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n" ] } ], @@ -535,6 +521,13 @@ " print(tool)" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, { "cell_type": "code", "execution_count": null,