"""
the :mod:`dataset` module defines some tools for managing datasets.
Users may use both *built-in* and user-defined datasets (see the
:ref:`getting_started` page for examples). Right now, four built-in datasets
are available:
* The `movielens-100k <http://grouplens.org/datasets/movielens/>`_ dataset.
* The `movielens-1m <http://grouplens.org/datasets/movielens/>`_ dataset.
* The `Jester <http://eigentaste.berkeley.edu/dataset/>`_ dataset 2.
Built-in datasets can all be loaded (or downloaded if you haven't already)
using the :meth:`Dataset.load_builtin` method. For each built-in dataset,
Surprise also provide predefined :class:`readers <Reader>` which are useful if
you want to use a custom dataset that has the same format as a built-in one.
Summary:
.. autosummary::
:nosignatures:
Dataset.load_builtin
Dataset.load_from_file
Dataset.load_from_folds
Dataset.folds
DatasetAutoFolds.split
Reader
Trainset
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from collections import defaultdict
from collections import namedtuple
import sys
import os
import zipfile
import itertools
import random
import numpy as np
from .six.moves import input
from .six.moves.urllib.request import urlretrieve
from .six.moves import range
from .six import iteritems
# directory where builtin datasets are stored. For now it's in the home
# directory under the .surprise_data. May be ask user to define it?
DATASETS_DIR = os.path.expanduser('~') + '/.surprise_data/'
# a builtin dataset has
# - an url (where to download it)
# - a path (where it is located on the filesystem)
# - the parameters of the corresponding reader
BuiltinDataset = namedtuple('BuiltinDataset', ['url', 'path', 'reader_params'])
BUILTIN_DATASETS = {
'ml-100k':
BuiltinDataset(
url='http://files.grouplens.org/datasets/movielens/ml-100k.zip',
path=DATASETS_DIR + 'ml-100k/ml-100k/u.data',
reader_params=dict(line_format='user item rating timestamp',
rating_scale=(1, 5),
sep='\t')
),
'ml-1m':
BuiltinDataset(
url='http://files.grouplens.org/datasets/movielens/ml-1m.zip',
path=DATASETS_DIR + 'ml-1m/ml-1m/ratings.dat',
reader_params=dict(line_format='user item rating timestamp',
rating_scale=(1, 5),
sep='::')
),
'jester':
BuiltinDataset(
url='http://eigentaste.berkeley.edu/dataset/jester_dataset_2.zip',
path=DATASETS_DIR + 'jester/jester_ratings.dat',
reader_params=dict(line_format='user item rating',
rating_scale=(-10, 10))
)
}
[docs]class Dataset:
"""Base class for loading datasets.
Note that you should never instantiate the :class:`Dataset` class directly
(same goes for its derived classes), but instead use one of the three
available methods for loading datasets."""
def __init__(self, reader):
self.reader = reader
self.r_min = reader.inf + reader.offset
self.r_max = reader.sup + reader.offset
@classmethod
[docs] def load_builtin(cls, name='ml-100k'):
"""Load a built-in dataset.
If the dataset has not already been loaded, it will be downloaded and
saved. You will have to split your dataset using the :meth:`split
<DatasetAutoFolds.split>` method. See an example in the :ref:`User
Guide <load_builtin_example>`.
Args:
name(:obj:`string`): The name of the built-in dataset to load.
Accepted values are 'ml-100k', 'ml-1m', and 'jester'.
Default is 'ml-100k'.
Returns:
A :obj:`Dataset` object.
Raises:
ValueError: If the ``name`` parameter is incorrect.
"""
try:
dataset = BUILTIN_DATASETS[name]
except KeyError:
raise ValueError('unknown dataset ' + name +
'. Accepted values are ' +
', '.join(BUILTIN_DATASETS.keys()) + '.')
# if dataset does not exist, offer to download it
if not os.path.isfile(dataset.path):
answered = False
while not answered:
print('Dataset ' + name + ' could not be found. Do you want '
'to download it? [Y/n] ', end='')
choice = input().lower()
if choice in ['yes', 'y', '', 'omg this is so nice of you!!']:
answered = True
elif choice in ['no', 'n', 'hell no why would i want that?!']:
answered = True
print("Ok then, I'm out!")
sys.exit()
if not os.path.exists(DATASETS_DIR):
os.makedirs(DATASETS_DIR)
print('Trying to download dataset from ' + dataset.url + '...')
urlretrieve(dataset.url, DATASETS_DIR + 'tmp.zip')
with zipfile.ZipFile(DATASETS_DIR + 'tmp.zip', 'r') as tmp_zip:
tmp_zip.extractall(DATASETS_DIR + name)
os.remove(DATASETS_DIR + 'tmp.zip')
print('Done! Dataset', name, 'has been saved to', DATASETS_DIR +
name)
reader = Reader(**dataset.reader_params)
return cls.load_from_file(file_path=dataset.path, reader=reader)
@classmethod
[docs] def load_from_file(cls, file_path, reader):
"""Load a dataset from a (custom) file.
Use this if you want to use a custom dataset and all of the ratings are
stored in one file. You will have to split your dataset using the
:meth:`split <DatasetAutoFolds.split>` method. See an example in the
:ref:`User Guide <load_from_file_example>`.
Args:
file_path(:obj:`string`): The path to the file containing ratings.
reader(:obj:`Reader`): A reader to read the file.
"""
return DatasetAutoFolds(ratings_file=file_path, reader=reader)
@classmethod
[docs] def load_from_folds(cls, folds_files, reader):
"""Load a dataset where folds (for cross-validation) are predifined by
some files.
The purpose of this method is to cover a common use case where a
dataset is already split into predefined folds, such as the
movielens-100k dataset which defines files u1.base, u1.test, u2.base,
u2.test, etc... It can also be used when you don't want to perform
cross-validation but still want to specify your training and testing
data (which comes down to 1-fold cross-validation anyway). See an
example in the :ref:`User Guide <load_from_folds_example>`.
Args:
folds_files(:obj:`iterable` of :obj:`tuples`): The list of the
folds. A fold is a tuple of the form ``(path_to_train_file,
path_to_test_file)``.
reader(:obj:`Reader`): A reader to read the files.
"""
return DatasetUserFolds(folds_files=folds_files, reader=reader)
def read_ratings(self, file_name):
"""Return a list of ratings (user, item, rating, timestamp) read from
file_name"""
with open(os.path.expanduser(file_name)) as f:
raw_ratings = [self.reader.parse_line(line) for line in
itertools.islice(f, self.reader.skip_lines, None)]
return raw_ratings
[docs] def folds(self):
"""Generator function to iterate over the folds of the Dataset.
See :ref:`User Guide <iterate_over_folds>` for usage.
Yields:
tuple: :class:`Trainset` and testset of current fold.
"""
for raw_trainset, raw_testset in self.raw_folds():
trainset = self.construct_trainset(raw_trainset)
testset = self.construct_testset(raw_testset)
yield trainset, testset
def construct_trainset(self, raw_trainset):
raw2inner_id_users = {}
raw2inner_id_items = {}
current_u_index = 0
current_i_index = 0
rm = defaultdict(int)
ur = defaultdict(list)
ir = defaultdict(list)
# user raw id, item raw id, rating, time stamp
for urid, irid, r, timestamp in raw_trainset:
try:
uid = raw2inner_id_users[urid]
except KeyError:
uid = current_u_index
raw2inner_id_users[urid] = current_u_index
current_u_index += 1
try:
iid = raw2inner_id_items[irid]
except KeyError:
iid = current_i_index
raw2inner_id_items[irid] = current_i_index
current_i_index += 1
rm[uid, iid] = r
ur[uid].append((iid, r))
ir[iid].append((uid, r))
n_users = len(ur) # number of users
n_items = len(ir) # number of items
trainset = Trainset(rm,
ur,
ir,
n_users,
n_items,
self.r_min,
self.r_max,
raw2inner_id_users,
raw2inner_id_items)
return trainset
def construct_testset(self, raw_testset):
return [(ruid, riid, r) for (ruid, riid, r, _) in raw_testset]
class DatasetUserFolds(Dataset):
"""A derived class from :class:`Dataset` for which folds (for
cross-validation) are predefined."""
def __init__(self, folds_files=None, reader=None):
Dataset.__init__(self, reader)
self.folds_files = folds_files
# check that all files actually exist.
for train_test_files in self.folds_files:
for f in train_test_files:
if not os.path.isfile(os.path.expanduser(f)):
raise ValueError('File ' + str(f) + ' does not exist.')
def raw_folds(self):
for train_file, test_file in self.folds_files:
raw_train_ratings = self.read_ratings(train_file)
raw_test_ratings = self.read_ratings(test_file)
yield raw_train_ratings, raw_test_ratings
[docs]class DatasetAutoFolds(Dataset):
"""A derived class from :class:`Dataset` for which folds (for
cross-validation) are not predefined. (Or for when there are no folds at
all)."""
def __init__(self, ratings_file=None, reader=None):
Dataset.__init__(self, reader)
self.ratings_file = ratings_file
self.n_folds = 5
self.shuffle = True
self.raw_ratings = self.read_ratings(self.ratings_file)
[docs] def build_full_trainset(self):
"""Do not split the dataset into folds and just return a trainset as
is, built from the whole dataset.
User can then query for predictions, as shown in the :ref:`User Guide
<train_on_whole_trainset>`.
Returns:
The :class:`Trainset`.
"""
return self.construct_trainset(self.raw_ratings)
def raw_folds(self):
if self.shuffle:
random.shuffle(self.raw_ratings)
self.shuffle = False # set to false for future calls to raw_folds
def k_folds(seq, n_folds):
"""Inspired from scikit learn KFold method."""
if n_folds > len(seq) or n_folds < 2:
raise ValueError('Incorrect value for n_folds.')
start, stop = 0, 0
for fold_i in range(n_folds):
start = stop
stop += len(seq) // n_folds
if fold_i < len(seq) % n_folds:
stop += 1
yield seq[:start] + seq[stop:], seq[start:stop]
return k_folds(self.raw_ratings, self.n_folds)
[docs] def split(self, n_folds=5, shuffle=True):
"""Split the dataset into folds for futur cross-validation.
If you forget to call :meth:`split`, the dataset will be automatically
shuffled and split for 5-folds cross-validation.
You can obtain repeatable splits over your all your experiments by
seeding the RNG: ::
import random
random.seed(my_seed) # call this before you call split!
Args:
n_folds(:obj:`int`): The number of folds.
shuffle(:obj:`bool`): Whether to shuffle ratings before splitting.
If ``False``, folds will always be the same each time the
experiment is run. Default is ``True``.
"""
self.n_folds = n_folds
self.shuffle = shuffle
[docs]class Reader():
"""The Reader class is used to parse a file containing ratings.
Such a file is assumed to specify only one rating per line, and each line
needs to respect the following structure: ::
user ; item ; rating ; [timestamp]
where the order of the fields and the seperator (here ';') may be
arbitrarily defined (see below). brackets indicate that the timestamp
field is optional.
Args:
name(:obj:`string`, optional): If specified, a Reader for one of the
built-in datasets is returned and any other parameter is ignored.
Accepted values are 'ml-100k', 'ml-1m', and 'jester'. Default
is ``None``.
line_format(:obj:`string`): The fields names, in the order at which
they are encountered on a line. Example: ``'item user rating'``.
sep(char): the separator between fields. Example : ``';'``.
rating_scale(:obj:`tuple`, optional): The rating scale used for every
rating. Default is ``(1, 5)``.
skip_lines(:obj:`int`, optional): Number of lines to skip at the
beginning of the file. Default is ``0``.
"""
def __init__(self, name=None, line_format=None, sep=None,
rating_scale=(1, 5), skip_lines=0):
if name:
try:
self.__init__(**BUILTIN_DATASETS[name].reader_params)
except KeyError:
raise ValueError('unknown reader ' + name +
'. Accepted values are ' +
', '.join(BUILTIN_DATASETS.keys()) + '.')
else:
self.sep = sep
self.skip_lines = skip_lines
self.inf, self.sup = rating_scale
self.offset = -self.inf + 1 if self.inf <= 0 else 0
splitted_format = line_format.split()
entities = ['user', 'item', 'rating']
if 'timestamp' in splitted_format:
self.with_timestamp = True
entities.append('timestamp')
else:
self.with_timestamp = False
# check that all fields are correct
if any(field not in entities for field in splitted_format):
raise ValueError('line_format parameter is incorrect.')
self.indexes = [splitted_format.index(entity) for entity in
entities]
def parse_line(self, line):
'''Parse a line.
Args:
line(str): The line to parse
Returns:
tuple: User id, item id, rating and timestamp. The timestamp is set
to ``None`` if it does no exist.
'''
line = line.split(self.sep)
try:
if self.with_timestamp:
uid, iid, r, timestamp = (line[i].strip().strip('"')
for i in self.indexes)
else:
uid, iid, r = (line[i].strip().strip('"')
for i in self.indexes)
timestamp = None
except IndexError:
raise ValueError(('Impossible to parse line.' +
' Check the line_format and sep parameters.'))
return uid, iid, float(r) + self.offset, timestamp
[docs]class Trainset:
"""A trainset contains all useful data that constitutes a training set.
It is used by the :meth:`train()
<surprise.prediction_algorithms.algo_base.AlgoBase.train>` method of every
prediction algorithm. You should not try to built such an object on your
own but rather use the :meth:`Dataset.folds` method or the
:meth:`DatasetAutoFolds.build_full_trainset` method.
Attributes:
rm(:obj:`defaultdict` of :obj:`int`): A dictionary containing all known
ratings. Keys are tuples (user_inner__id, item_inner_id), values
are ratings. ``rm`` stands for *ratings matrix*, even though it's
not a proper matrix object.
ur(:obj:`defaultdict` of :obj:`list`): A dictionary containing lists of
tuples of the form ``(item_inner_id, rating)``. Keys are user inner
ids. ``ur`` stands for *user ratings*.
ir(:obj:`defaultdict` of :obj:`list`): A dictionary containing lists of
tuples of the form ``(user_inner_id, rating)``. Keys are item inner
ids. ``ir`` stands for *item ratings*.
n_users: Total number of users :math:`|U|`.
n_items: Total number of items :math:`|I|`.
n_ratings: Total number of ratings :math:`|R_{train}|`.
r_min: Minimum value of the rating scale.
r_max: Maximum value of the rating scale.
global_mean: The mean of all ratings :math:`\\mu`.
"""
def __init__(self, rm, ur, ir, n_users, n_items, r_min, r_max,
raw2inner_id_users, raw2inner_id_items):
self.rm = rm
self.ur = ur
self.ir = ir
self.n_users = n_users
self.n_items = n_items
self.n_ratings = len(self.rm)
self.r_min = r_min
self.r_max = r_max
self._raw2inner_id_users = raw2inner_id_users
self._raw2inner_id_items = raw2inner_id_items
self._global_mean = None
[docs] def knows_user(self, uid):
"""Indicate if the user is part of the trainset.
A user is part of the trainset if the user has at least one rating.
Args:
uid: The (inner) user id. See :ref:`this note<raw_inner_note>`.
Returns:
``True`` if user is part of the trainset, else ``False``.
"""
return uid in self.ur
[docs] def knows_item(self, iid):
"""Indicate if the item is part of the trainset.
An item is part of the trainset if the item was rated at least once.
Args:
iid: The (inner) item id. See :ref:`this note<raw_inner_note>`.
Returns:
``True`` if item is part of the trainset, else ``False``.
"""
return iid in self.ir
[docs] def to_inner_uid(self, ruid):
"""Convert a raw **user** id to an inner id.
See :ref:`this note<raw_inner_note>`.
Args:
ruid: The user raw id.
Returns:
The user inner id.
Raises:
ValueError: When user is not part of the trainset.
"""
try:
return self._raw2inner_id_users[ruid]
except KeyError:
raise ValueError(('User ' + str(ruid) +
' is not part of the trainset.'))
[docs] def to_inner_iid(self, riid):
"""Convert a raw **item** id to an inner id.
See :ref:`this note<raw_inner_note>`.
Args:
riid: The item raw id.
Returns:
The item inner id.
Raises:
ValueError: When item is not part of the trainset.
"""
try:
return self._raw2inner_id_items[riid]
except KeyError:
raise ValueError(('Item ' + str(riid) +
' is not part of the trainset.'))
[docs] def all_ratings(self):
"""Generator function to iterate over all ratings.
Yields:
A tuple ``(uid, iid, rating)`` where ids are inner ids.
"""
for u, u_ratings in iteritems(self.ur):
for i, r in u_ratings:
yield u, i, r
[docs] def all_users(self):
"""Generator function to iterate over all users.
Yields:
Inner id of users.
"""
return range(self.n_users)
[docs] def all_items(self):
"""Generator function to iterate over all items.
Yields:
Inner id of items.
"""
return range(self.n_items)
@property
def global_mean(self):
"""Return the mean of all ratings.
It's only computed once."""
if self._global_mean is None:
self._global_mean = np.mean(
[r for (_, _, r) in self.all_ratings()])
return self._global_mean