Simple example of building recommendations with RecTools

Building simple model
Visual recommendations checking

[2]:

import numpy as np
import pandas as pd

from implicit.nearest_neighbours import TFIDFRecommender

from rectools import Columns
from rectools.dataset import Dataset
from rectools.models import ImplicitItemKNNWrapperModel

Load data

[3]:

%%time
!wget https://files.grouplens.org/datasets/movielens/ml-1m.zip
!unzip ml-1m.zip

--2022-07-28 11:00:39--  https://files.grouplens.org/datasets/movielens/ml-1m.zip
Resolving files.grouplens.org (files.grouplens.org)... 128.101.65.152
Connecting to files.grouplens.org (files.grouplens.org)|128.101.65.152|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 5917549 (5,6M) [application/zip]
Saving to: ‘ml-1m.zip.1’

ml-1m.zip.1         100%[===================>]   5,64M  4,04MB/s    in 1,4s

2022-07-28 11:00:41 (4,04 MB/s) - ‘ml-1m.zip.1’ saved [5917549/5917549]

Archive:  ml-1m.zip
   creating: ml-1m/
  inflating: ml-1m/movies.dat
  inflating: ml-1m/ratings.dat
  inflating: ml-1m/README
  inflating: ml-1m/users.dat
CPU times: user 43.8 ms, sys: 28.6 ms, total: 72.4 ms
Wall time: 2.38 s

[4]:

%%time
ratings = pd.read_csv(
    "ml-1m/ratings.dat",
    sep="::",
    engine="python",  # Because of 2-chars separators
    header=None,
    names=[Columns.User, Columns.Item, Columns.Weight, Columns.Datetime],
)
print(ratings.shape)
ratings.head()

(1000209, 4)
CPU times: user 4 s, sys: 173 ms, total: 4.17 s
Wall time: 4.18 s

[4]:

	user_id	item_id	weight	datetime
0	1	1193	5	978300760
1	1	661	3	978302109
2	1	914	3	978301968
3	1	3408	4	978300275
4	1	2355	5	978824291

[5]:

%%time
movies = pd.read_csv(
    "ml-1m/movies.dat",
    sep="::",
    engine="python",  # Because of 2-chars separators
    header=None,
    names=[Columns.Item, "title", "genres"],
)
print(movies.shape)
movies.head()

(3883, 3)
CPU times: user 13.3 ms, sys: 1.91 ms, total: 15.2 ms
Wall time: 14 ms

[5]:

	item_id	title	genres
0	1	Toy Story (1995)	Animation\|Children's\|Comedy
1	2	Jumanji (1995)	Adventure\|Children's\|Fantasy
2	3	Grumpier Old Men (1995)	Comedy\|Romance
3	4	Waiting to Exhale (1995)	Comedy\|Drama
4	5	Father of the Bride Part II (1995)	Comedy

Build model

[6]:

# Prepare dataset to build and use model
dataset = Dataset.construct(ratings)

[7]:

%%time
# Fit model and generate recommendations for all users
model = ImplicitItemKNNWrapperModel(TFIDFRecommender(K=10))
model.fit(dataset)
recos = model.recommend(
    users=ratings[Columns.User].unique(),
    dataset=dataset,
    k=10,
    filter_viewed=True,
)

CPU times: user 2.35 s, sys: 55.5 ms, total: 2.41 s
Wall time: 2.42 s

[8]:

# Sample of recommendations - it's sorted by relevance (= rank) for each user
recos.head()

[8]:

	user_id	item_id	score	rank
0	1	364	20.436578	1
1	1	1196	15.716834	2
2	1	318	15.625371	3
3	1	2096	14.876911	4
4	1	2571	12.718620	5

Check recommendations

[9]:

# Select random user, see history of views and reco for this user
user_id = 3883
user_viewed = ratings.query("user_id == @user_id").merge(movies, on="item_id")
user_recos = recos.query("user_id == @user_id").merge(movies, on="item_id")

[10]:

# History, but only films that user likes
user_viewed.query("weight > 3")

[10]:

	user_id	item_id	weight	datetime	title	genres
0	3883	2997	5	967134212	Being John Malkovich (1999)	Comedy
2	3883	1265	5	967134285	Groundhog Day (1993)	Comedy\|Romance
4	3883	2858	5	965822230	American Beauty (1999)	Comedy\|Drama
10	3883	2369	4	965822136	Desperately Seeking Susan (1985)	Comedy\|Romance
14	3883	3189	4	965822296	My Dog Skip (1999)	Comedy
16	3883	1784	4	965822136	As Good As It Gets (1997)	Comedy\|Drama
17	3883	2599	4	967134250	Election (1999)	Comedy
18	3883	34	4	967134285	Babe (1995)	Children's\|Comedy\|Drama

[11]:

# Recommendations
user_recos.sort_values("rank")

[11]:

	user_id	item_id	score	rank	title	genres
0	3883	2396	13.991358	1	Shakespeare in Love (1998)	Comedy\|Romance
1	3883	2762	10.249648	2	Sixth Sense, The (1999)	Thriller
2	3883	318	7.728188	3	Shawshank Redemption, The (1994)	Drama
3	3883	608	7.617913	4	Fargo (1996)	Crime\|Drama\|Thriller
4	3883	356	5.674010	5	Forrest Gump (1994)	Comedy\|Romance\|War
5	3883	2395	5.508895	6	Rushmore (1998)	Comedy
6	3883	223	5.398012	7	Clerks (1994)	Comedy
7	3883	593	5.335058	8	Silence of the Lambs, The (1991)	Drama\|Thriller
8	3883	296	4.828189	9	Pulp Fiction (1994)	Crime\|Drama
9	3883	2959	4.615653	10	Fight Club (1999)	Drama

[ ]: