Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Function to make top-k recommendations to all users in a fast way for ALS model. #179

Merged
merged 18 commits into from
Jun 20, 2019
Merged

Function to make top-k recommendations to all users in a fast way for ALS model. #179

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
12f0d6d
Changes to be committed:
invalid-email-address Jan 14, 2019
8983f73
PEP8ified
invalid-email-address Jan 14, 2019
11b2807
Filter recommendations
Tych0n Mar 27, 2019
7070445
TCI numpy installation fix
Tych0n Mar 28, 2019
5fb45e8
Fixed format for TCI checks
invalid-email-address Mar 28, 2019
b6405a1
Documentation
Tych0n Mar 29, 2019
5afbfb2
Merge remote-tracking branch 'upstream/master'
Tych0n Jun 10, 2019
e30aea6
Recreated .cpp after pulling master changes
Tych0n Jun 10, 2019
1da922d
Moved function to proper place
Tych0n Jun 14, 2019
873943b
PEP8ified
Tych0n Jun 14, 2019
7a4a9ef
Fix: Moved function to proper place
Tych0n Jun 14, 2019
6dc4db8
Few checks added
Tych0n Jun 19, 2019
4588088
Unit tests
Tych0n Jun 20, 2019
c7a6fbc
PEP8ified
Tych0n Jun 20, 2019
a4d7924
Unification and fixes
Tych0n Jun 20, 2019
f061f41
PEP8ified
Tych0n Jun 20, 2019
09c1dab
Updated cythonized files
Tych0n Jun 20, 2019
cc08f37
PEP8ified
Tych0n Jun 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion implicit/_nearest_neighbours.cpp
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1,204 changes: 638 additions & 566 deletions implicit/evaluation.cpp
View file
Open in desktop

Large diffs are not rendered by default.

18 changes: 11 additions & 7 deletions implicit/evaluation.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
# distutils: language = c++
# cython: language_level=3

import tqdm
import numpy as np
from scipy.sparse import coo_matrix, csr_matrix
Expand Down Expand Up @@ -32,11 +35,11 @@ def train_test_split(ratings, train_percentage=0.8):
test_index = random_index >= train_percentage

train = csr_matrix((ratings.data[train_index],
(ratings.row[train_index], ratings.col[train_index])),
(ratings.row[train_index], ratings.col[train_index])),
shape=ratings.shape, dtype=ratings.dtype)

test = csr_matrix((ratings.data[test_index],
(ratings.row[test_index], ratings.col[test_index])),
(ratings.row[test_index], ratings.col[test_index])),
shape=ratings.shape, dtype=ratings.dtype)

test.data[test.data < 0] = 0
Expand All @@ -55,9 +58,11 @@ def precision_at_k(model, train_user_items, test_user_items, int K=10,
model : RecommenderBase
The fitted recommendation model to test
train_user_items : csr_matrix
Sparse matrix of user by item that contains elements that were used in training the model
Sparse matrix of user by item that contains elements that were used
in training the model
test_user_items : csr_matrix
Sparse matrix of user by item that contains withheld elements to test on
Sparse matrix of user by item that contains withheld elements to
test on
K : int
Number of items to test on
show_progress : bool, optional
Expand Down Expand Up @@ -90,7 +95,7 @@ def precision_at_k(model, train_user_items, test_user_items, int K=10,
progress = tqdm.tqdm(total=users, disable=not show_progress)

with nogil, parallel(num_threads=num_threads):
ids = <int *> malloc(sizeof(int) * K)
ids = <int * > malloc(sizeof(int) * K)
likes = new unordered_set[int]()
try:
for u in prange(users, schedule='guided'):
Expand Down Expand Up @@ -173,7 +178,7 @@ def mean_average_precision_at_k(model, train_user_items, test_user_items, int K=
progress = tqdm.tqdm(total=users, disable=not show_progress)

with nogil, parallel(num_threads=num_threads):
ids = <int *> malloc(sizeof(int) * K)
ids = <int * > malloc(sizeof(int) * K)
likes = new unordered_set[int]()
try:
for u in prange(users, schedule='guided'):
Expand Down Expand Up @@ -212,7 +217,6 @@ def mean_average_precision_at_k(model, train_user_items, test_user_items, int K=
return mean_ap / total


@cython.boundscheck(False)
def ndcg_at_k(model, train_user_items, test_user_items, int K=10,
show_progress=True, int num_threads=1):
""" Calculates ndcg@K for a given trained model
Expand Down
Loading