Dict Comprehensions¶
Let us see how we can process Python collections using dict comprehensions.
- We will be using orders data set which will be available by running notebook related to preparing data sets.
- We will see how to get a dict using dict comprehensions. The output should contain key value pairs for each order where order_id is key and order_customer_id is the value.
In [1]:
%run 07_preparing_data_sets.ipynb
In [2]:
orders[:10]
Out[2]:
['1,2013-07-25 00:00:00.0,11599,CLOSED', '2,2013-07-25 00:00:00.0,256,PENDING_PAYMENT', '3,2013-07-25 00:00:00.0,12111,COMPLETE', '4,2013-07-25 00:00:00.0,8827,CLOSED', '5,2013-07-25 00:00:00.0,11318,COMPLETE', '6,2013-07-25 00:00:00.0,7130,COMPLETE', '7,2013-07-25 00:00:00.0,4530,COMPLETE', '8,2013-07-25 00:00:00.0,2911,PROCESSING', '9,2013-07-25 00:00:00.0,5657,PENDING_PAYMENT', '10,2013-07-25 00:00:00.0,5648,PENDING_PAYMENT']
In [3]:
len(orders)
Out[3]:
68883
In [4]:
order_customers = {int(order.split(',')[0]): int(order.split(',')[2]) for order in orders}
In [5]:
type(order_customers)
Out[5]:
dict
In [6]:
order_customers
Out[6]:
{1: 11599,
2: 256,
3: 12111,
4: 8827,
5: 11318,
6: 7130,
7: 4530,
8: 2911,
9: 5657,
10: 5648,
11: 918,
12: 1837,
13: 9149,
14: 9842,
15: 2568,
16: 7276,
17: 2667,
18: 1205,
19: 9488,
20: 9198,
21: 2711,
22: 333,
23: 4367,
24: 11441,
25: 9503,
26: 7562,
27: 3241,
28: 656,
29: 196,
30: 10039,
31: 6983,
32: 3960,
33: 5793,
34: 4189,
35: 4840,
36: 5649,
37: 5863,
38: 11586,
39: 8214,
40: 12092,
41: 8136,
42: 9776,
43: 7776,
44: 10500,
45: 2636,
46: 1549,
47: 8487,
48: 12186,
49: 1871,
50: 5225,
51: 12271,
52: 5126,
53: 4701,
54: 10628,
55: 2052,
56: 10519,
57: 7073,
58: 9213,
59: 11644,
60: 8365,
61: 4791,
62: 9111,
63: 1148,
64: 5579,
65: 5903,
66: 1792,
67: 1406,
68: 4320,
69: 2821,
70: 11809,
71: 8646,
72: 4349,
73: 8504,
74: 662,
75: 2505,
76: 6898,
77: 7915,
78: 8619,
79: 7327,
80: 3007,
81: 674,
82: 3566,
83: 1265,
84: 6789,
85: 1485,
86: 6680,
87: 3065,
88: 3809,
89: 824,
90: 9131,
91: 8912,
92: 6932,
93: 2256,
94: 11589,
95: 9032,
96: 8683,
97: 10784,
98: 5243,
99: 11542,
100: 12131,
101: 5116,
102: 8027,
103: 12256,
104: 7790,
105: 8220,
106: 395,
107: 1845,
108: 12149,
109: 9345,
110: 2746,
111: 4271,
112: 5375,
113: 10216,
114: 2091,
115: 104,
116: 8763,
117: 58,
118: 1737,
119: 8124,
120: 356,
121: 2074,
122: 2071,
123: 3695,
124: 2374,
125: 4611,
126: 610,
127: 5261,
128: 2772,
129: 9937,
130: 7509,
131: 10072,
132: 289,
133: 10604,
134: 12081,
135: 7738,
136: 9126,
137: 4211,
138: 10904,
139: 7933,
140: 4257,
141: 12128,
142: 5760,
143: 10495,
144: 2158,
145: 494,
146: 8177,
147: 275,
148: 5383,
149: 11431,
150: 236,
151: 2493,
152: 3611,
153: 8876,
154: 9993,
155: 9044,
156: 5200,
157: 8986,
158: 12345,
159: 10974,
160: 6762,
161: 4513,
162: 3304,
163: 3348,
164: 2962,
165: 1222,
166: 7834,
167: 1347,
168: 11794,
169: 2611,
170: 6295,
171: 1980,
172: 11382,
173: 9027,
174: 3358,
175: 384,
176: 2897,
177: 9151,
178: 8503,
179: 6506,
180: 10215,
181: 7473,
182: 10984,
183: 12105,
184: 210,
185: 10966,
186: 1104,
187: 1378,
188: 2889,
189: 10177,
190: 11115,
191: 16,
192: 5293,
193: 6174,
194: 2550,
195: 12096,
196: 2765,
197: 6370,
198: 7436,
199: 4608,
200: 11116,
201: 9055,
202: 8524,
203: 11791,
204: 7604,
205: 3109,
206: 8994,
207: 11643,
208: 7923,
209: 3627,
210: 10102,
211: 10372,
212: 3190,
213: 11715,
214: 3925,
215: 5925,
216: 7282,
217: 5420,
218: 3935,
219: 10655,
220: 1383,
221: 11871,
222: 8309,
223: 9068,
224: 11938,
225: 11275,
226: 9356,
227: 7410,
228: 6070,
229: 618,
230: 4921,
231: 3960,
232: 1780,
233: 12316,
234: 1010,
235: 4285,
236: 9785,
237: 11438,
238: 4939,
239: 5058,
240: 32,
241: 948,
242: 3237,
243: 32,
244: 6910,
245: 5191,
246: 9616,
247: 173,
248: 11707,
249: 7650,
250: 11668,
251: 568,
252: 9708,
253: 45,
254: 9395,
255: 10346,
256: 4199,
257: 3273,
258: 1137,
259: 3454,
260: 5135,
261: 5128,
262: 11475,
263: 8026,
264: 230,
265: 488,
266: 11085,
267: 6989,
268: 5578,
269: 11887,
270: 5689,
271: 815,
272: 428,
273: 10665,
274: 3365,
275: 10942,
276: 2221,
277: 3732,
278: 488,
279: 10372,
280: 11836,
281: 827,
282: 3551,
283: 11466,
284: 861,
285: 5011,
286: 9824,
287: 8122,
288: 8667,
289: 1195,
290: 6446,
291: 5506,
292: 11971,
293: 4731,
294: 11394,
295: 1937,
296: 6665,
297: 2281,
298: 4967,
299: 9202,
300: 11326,
301: 11999,
302: 3577,
303: 1682,
304: 1869,
305: 5618,
306: 137,
307: 8818,
308: 6829,
309: 10396,
310: 1256,
311: 410,
312: 1122,
313: 7543,
314: 10033,
315: 4375,
316: 3870,
317: 1450,
318: 8829,
319: 10445,
320: 10698,
321: 4282,
322: 2864,
323: 3020,
324: 76,
325: 4759,
326: 1604,
327: 12107,
328: 1149,
329: 1944,
330: 5175,
331: 4797,
332: 4171,
333: 2071,
334: 3752,
335: 7710,
336: 5479,
337: 6747,
338: 4666,
339: 8326,
340: 7995,
341: 10128,
342: 8809,
343: 10952,
344: 2816,
345: 11040,
346: 3646,
347: 11662,
348: 12120,
349: 9103,
350: 10672,
351: 12049,
352: 1977,
353: 2234,
354: 5862,
355: 11682,
356: 2209,
357: 2685,
358: 2979,
359: 6020,
360: 8020,
361: 8286,
362: 10167,
363: 3619,
364: 6035,
365: 2400,
366: 4422,
367: 8730,
368: 5783,
369: 189,
370: 4791,
371: 4428,
372: 776,
373: 3630,
374: 5906,
375: 6561,
376: 1369,
377: 514,
378: 10071,
379: 8735,
380: 9505,
381: 5756,
382: 8143,
383: 10509,
384: 2610,
385: 10667,
386: 3568,
387: 7193,
388: 2790,
389: 4435,
390: 5590,
391: 5816,
392: 3238,
393: 1047,
394: 76,
395: 3934,
396: 9078,
397: 4476,
398: 1365,
399: 1473,
400: 5626,
401: 9692,
402: 9547,
403: 4178,
404: 1478,
405: 9498,
406: 9023,
407: 3333,
408: 2252,
409: 11102,
410: 1288,
411: 11164,
412: 9397,
413: 7278,
414: 11776,
415: 6110,
416: 1561,
417: 11491,
418: 4269,
419: 8987,
420: 4632,
421: 7839,
422: 9664,
423: 9632,
424: 2457,
425: 10481,
426: 10419,
427: 6681,
428: 3487,
429: 8466,
430: 10779,
431: 4676,
432: 1197,
433: 792,
434: 11390,
435: 5719,
436: 7610,
437: 5351,
438: 8256,
439: 9353,
440: 7290,
441: 5239,
442: 8098,
443: 8499,
444: 10004,
445: 3859,
446: 7620,
447: 8737,
448: 7167,
449: 409,
450: 5085,
451: 10104,
452: 5128,
453: 381,
454: 5933,
455: 6575,
456: 11295,
457: 4036,
458: 5358,
459: 3687,
460: 2521,
461: 8398,
462: 5454,
463: 8709,
464: 7114,
465: 1255,
466: 10943,
467: 1719,
468: 7305,
469: 1731,
470: 6410,
471: 10861,
472: 8969,
473: 5359,
474: 8349,
475: 4567,
476: 6020,
477: 8511,
478: 7657,
479: 11138,
480: 2902,
481: 10633,
482: 9156,
483: 12341,
484: 2409,
485: 3976,
486: 1865,
487: 5698,
488: 10143,
489: 2030,
490: 9709,
491: 3945,
492: 2499,
493: 1180,
494: 8121,
495: 7242,
496: 615,
497: 846,
498: 6828,
499: 8920,
500: 2129,
501: 1987,
502: 7196,
503: 6377,
504: 6288,
505: 11952,
506: 3509,
507: 4730,
508: 6970,
509: 10739,
510: 7533,
511: 486,
512: 12000,
513: 10479,
514: 10962,
515: 5921,
516: 9204,
517: 1578,
518: 5257,
519: 4780,
520: 8074,
521: 6497,
522: 12300,
523: 4477,
524: 7622,
525: 10830,
526: 7259,
527: 5426,
528: 6147,
529: 844,
530: 6224,
531: 1950,
532: 6498,
533: 6770,
534: 6896,
535: 66,
536: 9981,
537: 10437,
538: 4871,
539: 7673,
540: 121,
541: 4985,
542: 597,
543: 7351,
544: 281,
545: 11642,
546: 7604,
547: 7220,
548: 6889,
549: 3834,
550: 9666,
551: 2867,
552: 1445,
553: 7307,
554: 10980,
555: 976,
556: 7838,
557: 4855,
558: 4562,
559: 1944,
560: 744,
561: 6059,
562: 5017,
563: 3514,
564: 2216,
565: 3850,
566: 6335,
567: 9527,
568: 11790,
569: 8532,
570: 4622,
571: 5006,
572: 6691,
573: 5964,
574: 7145,
575: 2873,
576: 7191,
577: 457,
578: 2529,
579: 4137,
580: 8677,
581: 3222,
582: 6220,
583: 4695,
584: 1263,
585: 8399,
586: 10225,
587: 6008,
588: 6348,
589: 5609,
590: 132,
591: 6431,
592: 10862,
593: 6667,
594: 1946,
595: 3531,
596: 8352,
597: 11558,
598: 11344,
599: 8005,
600: 3506,
601: 8977,
602: 6690,
603: 6184,
604: 6930,
605: 2879,
606: 1157,
607: 6376,
608: 10388,
609: 1241,
610: 1866,
611: 8422,
612: 11854,
613: 460,
614: 5738,
615: 2827,
616: 11330,
617: 6154,
618: 12037,
619: 11473,
620: 11346,
621: 7916,
622: 3892,
623: 3658,
624: 1821,
625: 5918,
626: 9123,
627: 7859,
628: 9783,
629: 6772,
630: 3449,
631: 9381,
632: 529,
633: 12249,
634: 4588,
635: 1427,
636: 10371,
637: 2259,
638: 3626,
639: 1072,
640: 6199,
641: 11558,
642: 7499,
643: 64,
644: 7295,
645: 2238,
646: 911,
647: 12319,
648: 4551,
649: 7261,
650: 4170,
651: 9264,
652: 8732,
653: 10473,
654: 286,
655: 1206,
656: 1646,
657: 1393,
658: 12386,
659: 6006,
660: 1932,
661: 2991,
662: 11165,
663: 3531,
664: 4469,
665: 5648,
666: 993,
667: 4726,
668: 8023,
669: 909,
670: 482,
671: 7926,
672: 1670,
673: 2157,
674: 1295,
675: 3414,
676: 5653,
677: 5182,
678: 9667,
679: 5535,
680: 4599,
681: 7524,
682: 9271,
683: 7183,
684: 1546,
685: 10745,
686: 7835,
687: 11639,
688: 5097,
689: 8272,
690: 7279,
691: 517,
692: 442,
693: 10081,
694: 5015,
695: 12224,
696: 11166,
697: 3126,
698: 5283,
699: 7472,
700: 2632,
701: 9742,
702: 1826,
703: 1871,
704: 11708,
705: 9639,
706: 10129,
707: 5889,
708: 5695,
709: 3161,
710: 5871,
711: 4688,
712: 4372,
713: 4826,
714: 4756,
715: 864,
716: 2581,
717: 8208,
718: 70,
719: 4768,
720: 3142,
721: 2154,
722: 9781,
723: 371,
724: 797,
725: 3837,
726: 5407,
727: 1049,
728: 5965,
729: 8467,
730: 3189,
731: 5104,
732: 7633,
733: 2724,
734: 1995,
735: 9142,
736: 8536,
737: 3567,
738: 10042,
739: 5647,
740: 6271,
741: 7481,
742: 9860,
743: 2030,
744: 2960,
745: 7435,
746: 9753,
747: 4788,
748: 1198,
749: 9270,
750: 4293,
751: 1438,
752: 3366,
753: 5094,
754: 6699,
755: 1478,
756: 8441,
757: 1648,
758: 1244,
759: 3328,
760: 444,
761: 9748,
762: 1748,
763: 943,
764: 8625,
765: 2425,
766: 12328,
767: 10174,
768: 8123,
769: 11749,
770: 12146,
771: 9026,
772: 2863,
773: 10414,
774: 11421,
775: 3547,
776: 3180,
777: 7761,
778: 5759,
779: 2004,
780: 2016,
781: 7971,
782: 12213,
783: 8321,
784: 3321,
785: 8191,
786: 8974,
787: 1150,
788: 5625,
789: 17,
790: 103,
791: 9961,
792: 12218,
793: 11007,
794: 7683,
795: 7219,
796: 11292,
797: 6527,
798: 8709,
799: 4675,
800: 9946,
801: 532,
802: 1670,
803: 5569,
804: 2697,
805: 8259,
806: 11113,
807: 1231,
808: 10509,
809: 7725,
810: 2484,
811: 10491,
812: 7073,
813: 2027,
814: 11988,
815: 11713,
816: 794,
817: 9975,
818: 8459,
819: 1714,
820: 768,
821: 8384,
822: 1492,
823: 9469,
824: 277,
825: 7429,
826: 3744,
827: 11167,
828: 2606,
829: 8977,
830: 9103,
831: 12064,
832: 132,
833: 4076,
834: 481,
835: 10640,
836: 2372,
837: 7715,
838: 3469,
839: 377,
840: 5123,
841: 8410,
842: 4038,
843: 8345,
844: 6061,
845: 5715,
846: 5643,
847: 12163,
848: 6018,
849: 8663,
850: 7382,
851: 11798,
852: 11564,
853: 5542,
854: 4186,
855: 4535,
856: 9876,
857: 833,
858: 9137,
859: 3432,
860: 9725,
861: 3164,
862: 1299,
863: 6081,
864: 12342,
865: 7052,
866: 6788,
867: 6669,
868: 2957,
869: 8657,
870: 6516,
871: 6923,
872: 6440,
873: 2117,
874: 6230,
875: 8330,
876: 7325,
877: 5012,
878: 207,
879: 3031,
880: 5400,
881: 3291,
882: 4102,
883: 4305,
884: 4909,
885: 7706,
886: 2124,
887: 4254,
888: 6610,
889: 3677,
890: 8908,
891: 5609,
892: 9537,
893: 3106,
894: 2759,
895: 7575,
896: 478,
897: 9070,
898: 5271,
899: 7707,
900: 8585,
901: 10184,
902: 1641,
903: 2199,
904: 5854,
905: 5460,
906: 7141,
907: 10661,
908: 8964,
909: 8670,
910: 2762,
911: 3608,
912: 3076,
913: 6408,
914: 6484,
915: 8495,
916: 48,
917: 9901,
918: 780,
919: 10890,
920: 12019,
921: 12,
922: 3160,
923: 5511,
924: 6615,
925: 937,
926: 8052,
927: 2520,
928: 2487,
929: 8482,
930: 954,
931: 10514,
932: 7231,
933: 446,
934: 2931,
935: 10086,
936: 7202,
937: 6899,
938: 7802,
939: 2964,
940: 5098,
941: 842,
942: 9704,
943: 2346,
944: 2917,
945: 9732,
946: 10961,
947: 2637,
948: 4289,
949: 2674,
950: 4151,
951: 3129,
952: 2250,
953: 368,
954: 5066,
955: 8117,
956: 4484,
957: 9879,
958: 12050,
959: 8993,
960: 1463,
961: 5079,
962: 9492,
963: 10558,
964: 3397,
965: 1907,
966: 11298,
967: 1706,
968: 7845,
969: 9247,
970: 7623,
971: 9478,
972: 10255,
973: 5118,
974: 6413,
975: 638,
976: 1088,
977: 7817,
978: 4130,
979: 11323,
980: 7473,
981: 5411,
982: 2873,
983: 9514,
984: 12350,
985: 5389,
986: 7820,
987: 7418,
988: 2491,
989: 370,
990: 7254,
991: 7317,
992: 7107,
993: 5122,
994: 4979,
995: 10907,
996: 12221,
997: 8786,
998: 1739,
999: 9358,
1000: 2321,
...}
In [7]:
order_customers[1]
Out[7]:
11599
In [8]:
employees = [
'1,ktrett0@independent.co.uk,6998.95',
'2,khaddock1@deviantart.com,10572.4',
'3,ecraft2@dell.com,3967.35',
'4,drussam3@t-online.de,17672.44',
'5,graigatt4@github.io,11660.67',
'6,bjaxon5@salon.com,18614.93',
'7,araulston6@list-manage.com,11550.75',
'8,mcobb7@mozilla.com,17016.15',
'9,grobardley8@unesco.org,14141.25',
'10,bbuye9@vkontakte.ru,12193.2'
]
In [9]:
highest_salaried_employees = {
int(employee.split(',')[0]): float(employee.split(',')[2])
for employee in employees
if float(employee.split(',')[2]) > 10000
}
In [10]:
highest_salaried_employees
Out[10]:
{2: 10572.4,
4: 17672.44,
5: 11660.67,
6: 18614.93,
7: 11550.75,
8: 17016.15,
9: 14141.25,
10: 12193.2}