Last active
July 1, 2021 15:40
-
-
Save matt-graham/af685c92cf8b8e0f5b00b7df287ea7f2 to your computer and use it in GitHub Desktop.
Comparison of different approaches to summing dict values with 'sparse' keys.
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
"""Comparison of different approaches to summing dict values with 'sparse' keys. | |
Sparse here means the keys of all dicts are drawn from a common set but only a few | |
keys (compared to the total number) are present in each. | |
""" | |
import pandas as pd | |
import numpy as np | |
import timeit | |
from string import ascii_lowercase | |
from itertools import product | |
from collections import Counter | |
def sparse_series_from_dict(data, index): | |
index_map = {k: i for i, k in enumerate(index)} | |
data_indices = [index_map[k] for k in data.keys()] | |
sorted_data_indices, sorted_data_values = zip( | |
*sorted(zip(data_indices, data.values()))) | |
sparse_index = pd.core.arrays.sparse.IntIndex(len(index), sorted_data_indices) | |
return pd.Series( | |
pd.arrays.SparseArray(sorted_data_values, sparse_index, fill_value=0), | |
index=index | |
) | |
def series_from_dict(data, index): | |
series = pd.Series(data, index=index) | |
series.fillna(0, inplace=True) | |
return series | |
def sum_inplace(iterable, total=0): | |
for val in iterable: | |
total += val | |
return total | |
def sum_update(iterable, total): | |
for val in iterable: | |
total.update(val) | |
return total | |
def print_results_string(results_dict, key, num_iter): | |
times = np.array([t / num_iter for t in results_dict[key]]) | |
print(f"{key:>20} times: min = {times.min():.2f}s, max = {times.max():.2f}s") | |
seed = 20210610 | |
num_events = 10000 | |
max_num_officers_per_event = 6 | |
num_repeats = 7 | |
num_iter = 1 | |
rng = np.random.default_rng(seed) | |
# make list of three a-z character keys of same length as officer index | |
keys = list(''.join(t) for t in product('abc', ascii_lowercase, ascii_lowercase))[:1428] | |
# simulate random appointment footprint dictionaries with non-negative time requests of | |
# [1, max_num_officers_per_event] officers chosen randomly without replacement | |
dicts = [ | |
{ | |
k: np.exp(rng.standard_normal()) | |
for k in rng.choice( | |
keys, replace=False, size=rng.integers(1, max_num_officers_per_event + 1)) | |
} | |
for _ in range(num_events) | |
] | |
# mapping functions and initial values for summations | |
func_init_and_sum_funcs = { | |
'Counter': ( | |
lambda d: Counter(d), | |
lambda: Counter(), | |
lambda s1, s2: s1 == s2, | |
(sum, sum_inplace, sum_update) | |
), | |
'Series': ( | |
lambda d: series_from_dict(d, index=keys), | |
lambda: pd.Series(0, index=keys), | |
lambda s1, s2: (s1 == s2).all(), | |
(sum, sum_inplace) | |
), | |
'SparseSeries': ( | |
lambda d: sparse_series_from_dict(d, keys), | |
lambda: sparse_series_from_dict({keys[0]: 0}, keys), | |
lambda s1, s2: (s1 == s2).all(), | |
(sum,) | |
) | |
} | |
results = {} | |
for label, (func, init, equaity_func, sum_funcs) in func_init_and_sum_funcs.items(): | |
ref_sum = sum((func(d) for d in dicts), init()) | |
for sum_func in sum_funcs: | |
the_sum = sum_func((func(d) for d in dicts), init()) | |
if not equaity_func(ref_sum, the_sum): | |
breakpoint() | |
combination = f"{sum_func.__name__}({label})" | |
results[combination] = timeit.repeat( | |
lambda: sum_func((func(d) for d in dicts), init()), | |
repeat=num_repeats, | |
number=num_iter | |
) | |
print_results_string(results, combination, num_iter) | |
results["DataFrame.sum"] = timeit.repeat( | |
lambda: pd.DataFrame({i: d for i, d in enumerate(dicts)}, index=keys).sum(axis=1), | |
repeat=num_repeats, | |
number=num_iter | |
) | |
print_results_string(results, "DataFrame.sum", num_iter) | |
results["SparseDataFrame.sum"] = timeit.repeat( | |
lambda: pd.DataFrame( | |
{i: sparse_series_from_dict(d, keys) for i, d in enumerate(dicts)}, | |
index=keys | |
).sum(axis=1), | |
repeat=num_repeats, | |
number=num_iter | |
) | |
print_results_string(results, "SparseDataFrame.sum", num_iter) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment