Newer
Older
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "df568295-31af-4fde-b402-8adecdf57f13",
"metadata": {},
"outputs": [],
"source": [
"from sqlalchemy import create_engine, text\n",
"engine = create_engine(\"mysql+mysqlconnector://root:abc@127.0.0.1:3306/cs544\")\n",
"conn = engine.connect()"
]
},
{
"cell_type": "code",
"id": "8cabbb35-3d75-44ee-886c-6aa871a01d68",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"list(conn.execute(text(\"\"\"\n",
" show tables\n",
"\"\"\")))"
]
},
{
"cell_type": "code",
"id": "b68ba375-c9c9-4677-9d9d-310d1927a276",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# table: users\n",
"# columns: id, name, phone\n",
"# name is required\n",
"# id uniquely identifies row\n",
"conn.execute(text(\"\"\"\n",
" create table users (\n",
" id int,\n",
" name text NOT NULL,\n",
" phone text,\n",
" PRIMARY KEY (id)\n",
" )\n",
"\"\"\"))"
]
},
{
"cell_type": "code",
"id": "00a5b5b9-8e91-4d90-99ad-e85a1756ea88",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conn.execute(text(\"\"\"\n",
" create table accounts (\n",
" user_id int,\n",
" name text NOT NULL,\n",
" amount int NOT NULL,\n",
" FOREIGN KEY (user_id) references users(id)\n",
" )\n",
"\"\"\"))"
]
},
{
"cell_type": "code",
"id": "9739d58c-8004-4844-a609-7ed95bdbf9aa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('accounts',), ('users',)]"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"list(conn.execute(text(\"\"\"\n",
" show tables\n",
"\"\"\")))"
]
},
{
"cell_type": "code",
"id": "1fc2171c-9f09-4b40-b5e0-fcb84870ec7d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<sqlalchemy.engine.cursor.CursorResult at 0x7c45c97122e0>"
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conn.execute(text(\"\"\"\n",
" INSERT INTO users (id, name) VALUES (1, \"tyler\")\n",
"\"\"\"))"
]
},
{
"cell_type": "code",
"id": "a96a9978-0927-4886-bd72-225150f9a5a2",
"metadata": {},
"outputs": [],
"source": [
"# conn.execute(text(\"\"\"\n",
"# INSERT INTO users (id, name) VALUES (1, \"tyler\")\n",
"# \"\"\"))"
]
},
{
"cell_type": "code",
"id": "0dbc816b-4f66-4b19-bcb6-e1b5212ef469",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[(1, 'tyler', None)]"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"list(conn.execute(text(\"\"\"\n",
" SELECT *\n",
" FROM users\n",
"\"\"\")))"
]
},
{
"cell_type": "code",
"id": "45c24702-0285-43fe-ae0e-b9d01adc2a37",
"metadata": {},
"outputs": [],
"source": [
"conn.commit()"
]
},
{
"cell_type": "code",
"id": "2a18a93d-20c1-4f02-875a-e6154ad7aef5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<sqlalchemy.engine.cursor.CursorResult at 0x7c45c9712d60>"
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conn.execute(text(\"\"\"\n",
" INSERT INTO accounts (user_id, name, amount)\n",
" VALUES (1, \"A\", 10), (1, \"B\", 20)\n",
"\"\"\"))"
]
},
{
"cell_type": "code",
"id": "753e807c-51d8-4190-9e8b-92e95bc8030b",
"metadata": {},
"outputs": [],
"source": [
"conn.commit()"
]
},
{
"cell_type": "code",
"id": "ca9c9379-ba53-42f0-9e11-eed9921adc01",
"metadata": {},
"outputs": [],
"source": [
"# this would break an invariant, so it's not allowed!\n",
"# foreign keys are still referencing user id 1\n",
"#\n",
"# conn.execute(text(\"\"\"\n",
"# DELETE FROM users WHERE id = 1;\n",
"# \"\"\"))"
]
},
{
"cell_type": "code",
"id": "75ae1cff-684a-4c04-9ce3-f619edea898c",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"id": "de914434-5eb7-465b-aec4-8bec6953b623",
"metadata": {},
"outputs": [],
"source": [
"url = \"https://raw.githubusercontent.com/cfpb/api/master/resources/datasets/hmda/code_sheets/\"\n",
"df = pd.read_csv(url + \"action_taken.csv\")\n",
"df.to_sql(\"actions\", conn, index=False, if_exists=\"replace\")\n",
"df = pd.read_csv(url + \"loan_type.csv\")\n",
"df.to_sql(\"loan_types\", conn, index=False, if_exists=\"replace\")\n",
"df = pd.read_csv(url + \"loan_purpose.csv\")\n",
"df.to_sql(\"purposes\", conn, index=False, if_exists=\"replace\")\n",
"conn.commit()"
]
},
{
"cell_type": "code",
"id": "4c24c47e-8f03-4b84-9647-6fd1559a4b0b",
"metadata": {},
"outputs": [],
"source": [
"import pyarrow as pa\n",
"import pyarrow.csv, pyarrow.parquet\n",
"\n",
"t = pa.parquet.read_table(\n",
" \"loans.parquet\", \n",
" columns=[\"lei\", \"action_taken\", \"loan_type\",\n",
" \"loan_amount\", \"interest_rate\", \"loan_purpose\", \"income\"\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"id": "a0f419e7-b0d7-4bf1-94ad-4c4ca961ada6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"447367"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"t.to_pandas().to_sql(\"loans\", conn, index=False,\n",
" if_exists=\"replace\", chunksize=10_000)"
]
},
{
"cell_type": "code",
"id": "96846d26-3aa8-414a-a925-eafa9fe60f50",
"metadata": {},
"outputs": [],
"source": [
"conn.commit()"
]
},
{
"cell_type": "markdown",
"id": "24e3be3e-5296-44fa-a850-c1e0df34cd38",
"metadata": {},
"source": [
"# Transactions"
]
},
{
"cell_type": "code",
"id": "791ad3aa-0a41-4c5c-b1ee-6d9b5b95e023",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
]
}
],
"source": [
"conn.execute(text(\"\"\"\n",
"update accounts set amount = amount + 5 where name = 'B'\n",
"\"\"\"))\n",
"conn.execute(text(\"\"\"\n",
"update accounts set amount = amount - 5 where name = 'A'\n",
"\"\"\"))\n",
"\n",
"# invariant: account cannot go negative\n",
"remaining_amount = list(conn.execute(text(\n",
" \"select amount from accounts where name = 'A'\"\n",
")))[0][0]\n",
"print(\"remaining:\", remaining_amount)\n",
"if remaining_amount >= 0:\n",
" print(\"commit!\")\n",
" conn.commit()\n",
"else:\n",
" print(\"rollback!\")\n",
" conn.rollback()"
]
},
{
"cell_type": "code",
"id": "10f7d983-69fc-4800-b529-b7f19e0cdb73",
"metadata": {},
"outputs": [],
"source": [
"# conn.rollback() or conn.commit()"
]
},
{
"cell_type": "markdown",
"id": "49392cee-e7b9-4ce0-9ce3-961965443b3d",
"metadata": {},
"source": [
"# Analyze/Query the Data"
]
},
{
"cell_type": "code",
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
"id": "ed5f92fc-ac76-4307-bd0c-6b714ed5a699",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>action_taken</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Loan originated</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>Application approved but not accepted</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Application denied by financial institution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>Application withdrawn by applicant</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>File closed for incompleteness</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>Loan purchased by the institution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>7</td>\n",
" <td>Preapproval request denied by financial instit...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>8</td>\n",
" <td>Preapproval request approved but not accepted</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id action_taken\n",
"0 1 Loan originated\n",
"1 2 Application approved but not accepted\n",
"2 3 Application denied by financial institution\n",
"3 4 Application withdrawn by applicant\n",
"4 5 File closed for incompleteness\n",
"5 6 Loan purchased by the institution\n",
"6 7 Preapproval request denied by financial instit...\n",
"7 8 Preapproval request approved but not accepted"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# what are all the possible actions? Practice SELECT/FROM.\n",
"pd.read_sql(\"\"\"\n",
"SELECT *\n",
"FROM actions\n",
"\"\"\", conn)"
]
},
{
"cell_type": "code",
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
"id": "8349be60-02f4-43bb-9cf2-568bc70d2c75",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>lei</th>\n",
" <th>action_taken</th>\n",
" <th>loan_type</th>\n",
" <th>loan_amount</th>\n",
" <th>interest_rate</th>\n",
" <th>loan_purpose</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>305000.0</td>\n",
" <td>3.875</td>\n",
" <td>1</td>\n",
" <td>108.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>65000.0</td>\n",
" <td>NA</td>\n",
" <td>1</td>\n",
" <td>103.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>75000.0</td>\n",
" <td>3.25</td>\n",
" <td>1</td>\n",
" <td>146.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>155000.0</td>\n",
" <td>4.0</td>\n",
" <td>32</td>\n",
" <td>70.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>305000.0</td>\n",
" <td>3.25</td>\n",
" <td>1</td>\n",
" <td>71.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>175000.0</td>\n",
" <td>3.375</td>\n",
" <td>1</td>\n",
" <td>117.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>575000.0</td>\n",
" <td>4.5</td>\n",
" <td>1</td>\n",
" <td>180.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>105000.0</td>\n",
" <td>5.375</td>\n",
" <td>1</td>\n",
" <td>180.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>54930034MNPILHP25H80</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>85000.0</td>\n",
" <td>3.375</td>\n",
" <td>1</td>\n",
" <td>136.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>549300FQ2SN6TRRGB032</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>405000.0</td>\n",
" <td>Exempt</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" lei action_taken loan_type loan_amount interest_rate \\\n",
"0 54930034MNPILHP25H80 6 1 305000.0 3.875 \n",
"1 54930034MNPILHP25H80 4 1 65000.0 NA \n",
"2 54930034MNPILHP25H80 6 1 75000.0 3.25 \n",
"3 54930034MNPILHP25H80 1 1 155000.0 4.0 \n",
"4 54930034MNPILHP25H80 1 1 305000.0 3.25 \n",
"5 54930034MNPILHP25H80 1 1 175000.0 3.375 \n",
"6 54930034MNPILHP25H80 1 1 575000.0 4.5 \n",
"7 54930034MNPILHP25H80 1 1 105000.0 5.375 \n",
"8 54930034MNPILHP25H80 1 1 85000.0 3.375 \n",
"9 549300FQ2SN6TRRGB032 1 1 405000.0 Exempt \n",
"\n",
" loan_purpose income \n",
"0 1 108.0 \n",
"1 1 103.0 \n",
"2 1 146.0 \n",
"3 32 70.0 \n",
"4 1 71.0 \n",
"5 1 117.0 \n",
"6 1 180.0 \n",
"7 1 180.0 \n",
"8 1 136.0 \n",
"9 1 NaN "
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# what are the first 10 loans? Practice LIMIT.\n",
"pd.read_sql(\"\"\"\n",
"SELECT *\n",
"FROM loans\n",
"LIMIT 10\n",
"\"\"\", conn)"
]
},
{
"cell_type": "code",
"id": "f99ed83c-d50c-43f7-bf3c-7307bb30801b",
"metadata": {},
"outputs": [],
"source": [
"# projection: choosing what columns (SELECT)"
]
},
{
"cell_type": "code",
"id": "d2fe1388-b308-4f8c-8a63-c426c0f1b787",
"metadata": {},
"outputs": [],
"source": [
"# selection: filtering rows (WHERE)"
]
},
{
"cell_type": "code",
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
"id": "0da82d35-5e7f-481b-a3fe-9d828b541794",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>interest_rate</th>\n",
" <th>loan_thousands</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3.875</td>\n",
" <td>305.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NA</td>\n",
" <td>65.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3.25</td>\n",
" <td>75.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.0</td>\n",
" <td>155.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3.25</td>\n",
" <td>305.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>3.375</td>\n",
" <td>175.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.5</td>\n",
" <td>575.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.375</td>\n",
" <td>105.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>3.375</td>\n",
" <td>85.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Exempt</td>\n",
" <td>405.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" interest_rate loan_thousands\n",
"0 3.875 305.0\n",
"1 NA 65.0\n",
"2 3.25 75.0\n",
"3 4.0 155.0\n",
"4 3.25 305.0\n",
"5 3.375 175.0\n",
"6 4.5 575.0\n",
"7 5.375 105.0\n",
"8 3.375 85.0\n",
"9 Exempt 405.0"
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# what are the first 10 interest rates and loan amounts (in thousands)? Practice SELECT.\n",
"pd.read_sql(\"\"\"\n",
"SELECT interest_rate, loan_amount / 1000 AS loan_thousands\n",
"FROM loans\n",
"LIMIT 10\n",
"\"\"\", conn)"
]
},
{
"cell_type": "code",
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
"id": "4ee4b0cb-7671-4570-9e18-fcd4b8c0394c",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>lei</th>\n",
" <th>action_taken</th>\n",
" <th>loan_type</th>\n",
" <th>loan_amount</th>\n",
" <th>interest_rate</th>\n",
" <th>loan_purpose</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>254900IER2H3R8YLBW04</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>105000.0</td>\n",
" <td>2.875</td>\n",
" <td>31</td>\n",
" <td>1530000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3Y4U8VZURTYWI1W2K376</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>7455000.0</td>\n",
" <td>NA</td>\n",
" <td>4</td>\n",
" <td>94657029.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>549300CS1XP28EERR469</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>75000.0</td>\n",
" <td>4.99</td>\n",
" <td>4</td>\n",
" <td>2030000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>549300CS1XP28EERR469</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>205000.0</td>\n",
" <td>3.75</td>\n",
" <td>1</td>\n",
" <td>7291000.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" lei action_taken loan_type loan_amount interest_rate \\\n",
"0 254900IER2H3R8YLBW04 1 1 105000.0 2.875 \n",
"1 3Y4U8VZURTYWI1W2K376 3 1 7455000.0 NA \n",
"2 549300CS1XP28EERR469 1 1 75000.0 4.99 \n",
"3 549300CS1XP28EERR469 1 1 205000.0 3.75 \n",
"\n",
" loan_purpose income \n",
"0 31 1530000.0 \n",
"1 4 94657029.0 \n",
"2 4 2030000.0 \n",
"3 1 7291000.0 "
]
},
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# what are the loans for individuals with income over $1 million? Practice WHERE.\n",
"pd.read_sql(\"\"\"\n",
"SELECT *\n",
"FROM loans\n",
"WHERE income > 1000000\n",
"\"\"\", conn)"
]
},
{
"cell_type": "code",
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"id": "d64a2a5e-e2d4-42a3-a894-9283160d2636",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>lei</th>\n",
" <th>action_taken</th>\n",
" <th>loan_type</th>\n",
" <th>loan_amount</th>\n",
" <th>interest_rate</th>\n",
" <th>loan_purpose</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>549300XWUSRVVOHPRY47</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>264185000.0</td>\n",
" <td>NA</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AD6GFRVSDT01YPT1CS68</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>74755000.0</td>\n",
" <td>1.454</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AD6GFRVSDT01YPT1CS68</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>66005000.0</td>\n",
" <td>NA</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>YQI2CPR3Z44KAR0HG822</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>65005000.0</td>\n",
" <td>3.0</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>254900YA1AQXNM8QVZ06</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>63735000.0</td>\n",
" <td>2.99</td>\n",
" <td>2</td>\n",
" <td>None</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" lei action_taken loan_type loan_amount interest_rate \\\n",
"0 549300XWUSRVVOHPRY47 6 1 264185000.0 NA \n",
"1 AD6GFRVSDT01YPT1CS68 1 1 74755000.0 1.454 \n",
"2 AD6GFRVSDT01YPT1CS68 4 2 66005000.0 NA \n",
"3 YQI2CPR3Z44KAR0HG822 1 1 65005000.0 3.0 \n",
"4 254900YA1AQXNM8QVZ06 1 2 63735000.0 2.99 \n",