Created
April 14, 2022 15:06
-
-
Save westandskif/362930891265815c474d37400108d603 to your computer and use it in GitHub Desktop.
how-can-i-use-pandas-explode-crosstab-and-count-number-of-occurence-for-large-d/71591146
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from convtools import conversion as c | |
# fmt: off | |
input_data = [ | |
{ "id": 1, "listElements": [ "apple", "peer", ["apple", "peer"], "banana", "chocolate", ["chocolate", "apple"], ], }, | |
{ "id": 2, "listElements": [ "ginger", "peer", ["ginger", "sugar"], "tofu", ["tofu", "veggie"], "chocolate", ], }, | |
{ "id": 3, "listElements": [ "steak", "beef", ["beef", "potatoes"], "banana", ], }, | |
] | |
# fmt: on | |
# generated ad hoc converter function; run on startup and reuse further | |
# option A | |
converter = ( | |
c.iter( | |
c.zip( | |
c.repeat(c.item("id")), | |
c.item("listElements").iter( | |
c.if_( | |
c.call_func(isinstance, c.this, list), | |
c.this.as_type(tuple), | |
) | |
), | |
) | |
) | |
.flatten() | |
.pipe( | |
c.group_by(c.item(1)).aggregate( | |
{ | |
"ingredient": c.item(1), | |
"ids": c.ReduceFuncs.Array(c.item(0)), | |
"count": c.ReduceFuncs.Count(), | |
} | |
) | |
) | |
.gen_converter() | |
) | |
result = converter(input_data) | |
assert result == [ | |
{"ingredient": "apple", "ids": [1], "count": 1}, | |
{"ingredient": "peer", "ids": [1, 2], "count": 2}, | |
{"ingredient": ("apple", "peer"), "ids": [1], "count": 1}, | |
{"ingredient": "banana", "ids": [1, 3], "count": 2}, | |
{"ingredient": "chocolate", "ids": [1, 2], "count": 2}, | |
{"ingredient": ("chocolate", "apple"), "ids": [1], "count": 1}, | |
{"ingredient": "ginger", "ids": [2], "count": 1}, | |
{"ingredient": ("ginger", "sugar"), "ids": [2], "count": 1}, | |
{"ingredient": "tofu", "ids": [2], "count": 1}, | |
{"ingredient": ("tofu", "veggie"), "ids": [2], "count": 1}, | |
{"ingredient": "steak", "ids": [3], "count": 1}, | |
{"ingredient": "beef", "ids": [3], "count": 1}, | |
{"ingredient": ("beef", "potatoes"), "ids": [3], "count": 1}, | |
] | |
# option B | |
converter = ( | |
c.iter( | |
c.zip( | |
c.repeat(c.item("id")), | |
c.item("listElements").iter( | |
c.if_( | |
c.call_func(isinstance, c.this, list), | |
c.this.as_type(tuple), | |
) | |
), | |
) | |
) | |
.flatten() | |
.pipe( | |
c.group_by(c.item(1)).aggregate( | |
( | |
c.item(1), | |
c.ReduceFuncs.Array(c.item(0)), | |
) | |
) | |
) | |
.as_type(dict) | |
.gen_converter() | |
) | |
result = converter(input_data) | |
assert result == { | |
"apple": [1], | |
"peer": [1, 2], | |
("apple", "peer"): [1], | |
"banana": [1, 3], | |
"chocolate": [1, 2], | |
("chocolate", "apple"): [1], | |
"ginger": [2], | |
("ginger", "sugar"): [2], | |
"tofu": [2], | |
("tofu", "veggie"): [2], | |
"steak": [3], | |
"beef": [3], | |
("beef", "potatoes"): [3], | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment