Python/other/scoring_algorithm.py

89 lines
2.6 KiB
Python
Raw Normal View History

"""
developed by: markmelnic
original repo: https://github.com/markmelnic/Scoring-Algorithm
Analyse data using a range based percentual proximity algorithm
and calculate the linear maximum likelihood estimation.
The basic principle is that all values supplied will be broken
down to a range from 0 to 1 and each column's score will be added
up to get the total score.
==========
Example for data of vehicles
price|mileage|registration_year
20k |60k |2012
22k |50k |2011
23k |90k |2015
16k |210k |2010
We want the vehicle with the lowest price,
lowest mileage but newest registration year.
Thus the weights for each column are as follows:
[0, 0, 1]
"""
def procentual_proximity(
source_data: list[list[float]], weights: list[int]
) -> list[list[float]]:
"""
weights - int list
possible values - 0 / 1
0 if lower values have higher weight in the data set
1 if higher values have higher weight in the data set
>>> procentual_proximity([[20, 60, 2012],[23, 90, 2015],[22, 50, 2011]], [0, 0, 1])
[[20, 60, 2012, 2.0], [23, 90, 2015, 1.0], [22, 50, 2011, 1.3333333333333335]]
"""
# getting data
data_lists: list[list[float]] = []
for data in source_data:
for i, el in enumerate(data):
if len(data_lists) < i + 1:
data_lists.append([])
data_lists[i].append(float(el))
score_lists: list[list[float]] = []
# calculating each score
for dlist, weight in zip(data_lists, weights):
mind = min(dlist)
maxd = max(dlist)
score: list[float] = []
# for weight 0 score is 1 - actual score
if weight == 0:
for item in dlist:
try:
score.append(1 - ((item - mind) / (maxd - mind)))
except ZeroDivisionError:
score.append(1)
elif weight == 1:
for item in dlist:
try:
score.append((item - mind) / (maxd - mind))
except ZeroDivisionError:
score.append(0)
# weight not 0 or 1
else:
raise ValueError(f"Invalid weight of {weight:f} provided")
score_lists.append(score)
# initialize final scores
final_scores: list[float] = [0 for i in range(len(score_lists[0]))]
# generate final scores
Add flake8 pluin flake8 bugbear to pre-commit (#7132) * ci(pre-commit): Add ``flake8-builtins`` additional dependency to ``pre-commit`` (#7104) * refactor: Fix ``flake8-builtins`` (#7104) * fix(lru_cache): Fix naming conventions in docstrings (#7104) * ci(pre-commit): Order additional dependencies alphabetically (#7104) * fix(lfu_cache): Correct function name in docstring (#7104) * Update strings/snake_case_to_camel_pascal_case.py Co-authored-by: Christian Clauss <cclauss@me.com> * Update data_structures/stacks/next_greater_element.py Co-authored-by: Christian Clauss <cclauss@me.com> * Update digital_image_processing/index_calculation.py Co-authored-by: Christian Clauss <cclauss@me.com> * Update graphs/prim.py Co-authored-by: Christian Clauss <cclauss@me.com> * Update hashes/djb2.py Co-authored-by: Christian Clauss <cclauss@me.com> * refactor: Rename `_builtin` to `builtin_` ( #7104) * fix: Rename all instances (#7104) * refactor: Update variable names (#7104) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * ci: Create ``tox.ini`` and ignore ``A003`` (#7123) * revert: Remove function name changes (#7104) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Rename tox.ini to .flake8 * Update data_structures/heap/heap.py Co-authored-by: Dhruv Manilawala <dhruvmanila@gmail.com> * refactor: Rename `next_` to `next_item` (#7104) * ci(pre-commit): Add `flake8` plugin `flake8-bugbear` (#7127) * refactor: Follow `flake8-bugbear` plugin (#7127) * fix: Correct `knapsack` code (#7127) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci Co-authored-by: Christian Clauss <cclauss@me.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Dhruv Manilawala <dhruvmanila@gmail.com>
2022-10-13 16:03:06 +00:00
for slist in score_lists:
for j, ele in enumerate(slist):
final_scores[j] = final_scores[j] + ele
# append scores to source data
for i, ele in enumerate(final_scores):
source_data[i].append(ele)
return source_data