Finds intersections / differences between pandas DataFrames
Project description
Finds intersections / differences between pandas DataFrames
$pip install a-pandas-ex-set
import numpy as np
import pandas as pd
from a_pandas_ex_set import Setdf
df = pd.read_csv("https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv")
df2=pd.concat([df,df],ignore_index=True)
df2=df2.sample(len(df2))
df3,df4,df5=np.split(df2, 3)
setd=Setdf(df3,df4,df5)
columns=['Cabin', 'Embarked','Sex','Survived']
didis2=setd.get_difference_of_all(columns=columns)
didis3=setd.get_intersection_of_all(columns=columns)
didis4=setd.get_symmetric_difference_and(columns=columns)
print(didis2)
print(didis3)
print(didis4)
{0: PassengerId Survived Pclass ... Fare Cabin Embarked
1631 741 1 1 ... 30.0000 D45 S
1411 521 1 1 ... 93.5000 B73 S
1164 274 0 1 ... 29.7000 C118 C
487 488 0 1 ... 29.7000 B37 C
248 249 1 1 ... 52.5542 D35 S
1615 725 1 1 ... 53.1000 E8 S
318 319 1 1 ... 164.8667 C7 S
337 338 1 1 ... 134.5000 E40 C
1753 863 1 1 ... 25.9292 D17 S
1642 752 1 3 ... 12.4750 E121 S
1536 646 1 1 ... 76.7292 D33 C
449 450 1 1 ... 30.5000 C104 S
1740 850 1 1 ... 89.1042 C92 C
1670 780 1 1 ... 211.3375 B3 S
571 572 1 1 ... 51.4792 C101 S
1680 790 0 1 ... 79.2000 B82 B84 C
1462 572 1 1 ... 51.4792 C101 S
31 32 1 1 ... 146.5208 B78 C
1100 210 1 1 ... 31.0000 A31 C
1340 450 1 1 ... 30.5000 C104 S
209 210 1 1 ... 31.0000 A31 C
943 53 1 1 ... 76.7292 D33 C
751 752 1 3 ... 12.4750 E121 S
558 559 1 1 ... 79.6500 E67 S
671 672 0 1 ... 52.0000 B71 S
724 725 1 1 ... 53.1000 E8 S
520 521 1 1 ... 93.5000 B73 S
849 850 1 1 ... 89.1042 C92 C
867 868 0 1 ... 50.4958 A24 S
1562 672 0 1 ... 52.0000 B71 S
779 780 1 1 ... 211.3375 B3 S
1228 338 1 1 ... 134.5000 E40 C
645 646 1 1 ... 76.7292 D33 C
1687 797 1 1 ... 25.9292 D17 S
862 863 1 1 ... 25.9292 D17 S
922 32 1 1 ... 146.5208 B78 C
1209 319 1 1 ... 164.8667 C7 S
1196 306 1 1 ... 151.5500 C22 C26 S
1758 868 0 1 ... 50.4958 A24 S
273 274 0 1 ... 29.7000 C118 C
1139 249 1 1 ... 52.5542 D35 S
796 797 1 1 ... 25.9292 D17 S
740 741 1 1 ... 30.0000 D45 S
789 790 0 1 ... 79.2000 B82 B84 C
52 53 1 1 ... 76.7292 D33 C
1378 488 0 1 ... 29.7000 B37 C
772 773 0 2 ... 10.5000 E77 S
305 306 1 1 ... 151.5500 C22 C26 S
1449 559 1 1 ... 79.6500 E67 S
1663 773 0 2 ... 10.5000 E77 S
[50 rows x 12 columns], 1: PassengerId Survived Pclass ... Fare Cabin Embarked
21 22 1 2 ... 13.0000 D56 S
583 584 0 1 ... 40.1250 A10 C
445 446 1 1 ... 81.8583 A34 S
245 246 0 1 ... 90.0000 C78 Q
1476 586 1 1 ... 79.6500 E68 S
540 541 1 1 ... 71.0000 B22 S
366 367 1 1 ... 75.2500 D37 C
1136 246 0 1 ... 90.0000 C78 Q
879 880 1 1 ... 83.1583 C50 C
462 463 0 1 ... 38.5000 E63 S
1431 541 1 1 ... 71.0000 B22 S
275 276 1 1 ... 77.9583 D7 S
871 872 1 1 ... 52.5542 D35 S
1770 880 1 1 ... 83.1583 C50 C
1570 680 1 1 ... 512.3292 B51 B53 B55 C
1189 299 1 1 ... 30.5000 C106 S
912 22 1 2 ... 13.0000 D56 S
1762 872 1 1 ... 52.5542 D35 S
1590 700 0 3 ... 7.6500 F G63 S
1366 476 0 1 ... 52.0000 A14 S
1257 367 1 1 ... 75.2500 D37 C
1268 378 0 1 ... 211.5000 C82 C
700 701 1 1 ... 227.5250 C62 C64 C
1474 584 0 1 ... 40.1250 A10 C
585 586 1 1 ... 79.6500 E68 S
1166 276 1 1 ... 77.9583 D7 S
699 700 0 3 ... 7.6500 F G63 S
679 680 1 1 ... 512.3292 B51 B53 B55 C
630 631 1 1 ... 30.0000 A23 S
1353 463 0 1 ... 38.5000 E63 S
457 458 1 1 ... 51.8625 D21 S
1521 631 1 1 ... 30.0000 A23 S
475 476 0 1 ... 52.0000 A14 S
1336 446 1 1 ... 81.8583 A34 S
298 299 1 1 ... 30.5000 C106 S
1348 458 1 1 ... 51.8625 D21 S
377 378 0 1 ... 211.5000 C82 C
544 545 0 1 ... 106.4250 C86 C
284 285 0 1 ... 26.0000 A19 S
1435 545 0 1 ... 106.4250 C86 C
1591 701 1 1 ... 227.5250 C62 C64 C
1175 285 0 1 ... 26.0000 A19 S
[42 rows x 12 columns], 2: PassengerId Survived Pclass ... Fare Cabin Embarked
872 873 0 1 ... 5.0000 B51 B53 B55 S
712 713 1 1 ... 52.0000 C126 S
618 619 1 2 ... 39.0000 F4 S
1061 171 0 1 ... 33.5000 B19 S
527 528 0 1 ... 221.7792 C95 S
1639 749 0 1 ... 53.1000 D30 S
1509 619 1 2 ... 39.0000 F4 S
1418 528 0 1 ... 221.7792 C95 S
339 340 0 1 ... 35.5000 T S
647 648 1 1 ... 35.5000 A26 C
1538 648 1 1 ... 35.5000 A26 C
1763 873 0 1 ... 5.0000 B51 B53 B55 S
1115 225 1 1 ... 90.0000 C93 S
1603 713 1 1 ... 52.0000 C126 S
54 55 0 1 ... 61.9792 B30 C
1230 340 0 1 ... 35.5000 T S
748 749 0 1 ... 53.1000 D30 S
170 171 0 1 ... 33.5000 B19 S
224 225 1 1 ... 90.0000 C93 S
118 119 0 1 ... 247.5208 B58 B60 C
3 4 1 1 ... 53.1000 C123 S
945 55 0 1 ... 61.9792 B30 C
894 4 1 1 ... 53.1000 C123 S
1009 119 0 1 ... 247.5208 B58 B60 C
[24 rows x 12 columns]}
{0: PassengerId Survived Pclass ... Fare Cabin Embarked
1546 656 0 2 ... 73.5000 NaN S
1217 327 0 3 ... 6.2375 NaN S
664 665 1 3 ... 7.9250 NaN S
754 755 1 2 ... 65.0000 NaN S
727 728 1 3 ... 7.7375 NaN Q
... ... ... ... ... ... ...
1527 637 0 3 ... 7.9250 NaN S
814 815 0 3 ... 8.0500 NaN S
693 694 0 3 ... 7.2250 NaN C
26 27 0 3 ... 7.2250 NaN C
494 495 0 3 ... 8.0500 NaN S
[459 rows x 12 columns], 1: PassengerId Survived Pclass ... Fare Cabin Embarked
1482 592 1 1 ... 78.2667 D20 C
552 553 0 3 ... 7.8292 NaN Q
968 78 0 3 ... 8.0500 NaN S
1205 315 0 2 ... 26.2500 NaN S
1734 844 0 3 ... 6.4375 NaN C
... ... ... ... ... ... ...
568 569 0 3 ... 7.2292 NaN C
503 504 0 3 ... 9.5875 NaN S
1544 654 1 3 ... 7.8292 NaN Q
589 590 0 3 ... 8.0500 NaN S
1191 301 1 3 ... 7.7500 NaN Q
[471 rows x 12 columns], 2: PassengerId Survived Pclass ... Fare Cabin Embarked
1596 706 0 2 ... 26.0000 NaN S
792 793 0 3 ... 69.5500 NaN S
481 482 0 2 ... 0.0000 NaN S
508 509 0 3 ... 22.5250 NaN S
149 150 0 2 ... 13.0000 NaN S
... ... ... ... ... ... ...
777 778 1 3 ... 12.4750 NaN S
115 116 0 3 ... 7.9250 NaN S
169 170 0 3 ... 56.4958 NaN S
1162 272 1 3 ... 0.0000 NaN S
963 73 0 2 ... 73.5000 NaN S
[490 rows x 12 columns]}
{0: PassengerId Survived Pclass ... Fare Cabin Embarked
1546 656 0 2 ... 73.5000 NaN S
1217 327 0 3 ... 6.2375 NaN S
664 665 1 3 ... 7.9250 NaN S
754 755 1 2 ... 65.0000 NaN S
727 728 1 3 ... 7.7375 NaN Q
... ... ... ... ... ... ...
814 815 0 3 ... 8.0500 NaN S
1663 773 0 2 ... 10.5000 E77 S
693 694 0 3 ... 7.2250 NaN C
26 27 0 3 ... 7.2250 NaN C
494 495 0 3 ... 8.0500 NaN S
[509 rows x 12 columns], 1: PassengerId Survived Pclass ... Fare Cabin Embarked
1482 592 1 1 ... 78.2667 D20 C
552 553 0 3 ... 7.8292 NaN Q
968 78 0 3 ... 8.0500 NaN S
1205 315 0 2 ... 26.2500 NaN S
1734 844 0 3 ... 6.4375 NaN C
... ... ... ... ... ... ...
568 569 0 3 ... 7.2292 NaN C
503 504 0 3 ... 9.5875 NaN S
1544 654 1 3 ... 7.8292 NaN Q
589 590 0 3 ... 8.0500 NaN S
1191 301 1 3 ... 7.7500 NaN Q
[513 rows x 12 columns], 2: PassengerId Survived Pclass ... Fare Cabin Embarked
872 873 0 1 ... 5.0000 B51 B53 B55 S
712 713 1 1 ... 52.0000 C126 S
1596 706 0 2 ... 26.0000 NaN S
792 793 0 3 ... 69.5500 NaN S
481 482 0 2 ... 0.0000 NaN S
... ... ... ... ... ... ...
115 116 0 3 ... 7.9250 NaN S
1009 119 0 1 ... 247.5208 B58 B60 C
169 170 0 3 ... 56.4958 NaN S
1162 272 1 3 ... 0.0000 NaN S
963 73 0 2 ... 73.5000 NaN S
[514 rows x 12 columns]}
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
a_pandas_ex_set-0.10.tar.gz
(7.9 kB
view hashes)
Built Distribution
Close
Hashes for a_pandas_ex_set-0.10-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d6f2f82616b565dfb54b59159a2dabb70613f70f34bfe49e47a9a60d2476815e |
|
| MD5 | 56944bd1567e3391d9f0f9a2c2925af3 |
|
| BLAKE2b-256 | de2f19e3c670692627a4aa17a9c9aae78c36638ef01e347869cc35aabc99d5cd |
