def test_import_ratings(self):
RatingsImporter(
source=JSONFile(file_path=file_path),
output_directory="test_ratings",
rating_configs=[
RatingsFieldConfig(field_name="review_title",
processor=TextBlobSentimentAnalysis()),
RatingsFieldConfig(field_name="text",
processor=TextBlobSentimentAnalysis()),
RatingsFieldConfig(field_name="stars",
processor=NumberNormalizer(min_=0, max_=5))
],
from_field_name="user_id",
to_field_name="item_id",
timestamp_field_name="timestamp").import_ratings()
"""
def test_graph_creation(self):
# Test multiple graph creation possibilities
# Import ratings as DataFrame
ratings_import = RatingsImporter(
source=CSVFile(ratings_filename),
rating_configs=[
RatingsFieldConfig(field_name='points',
processor=NumberNormalizer(min_=1, max_=5))
],
from_field_name='user_id',
to_field_name='item_id',
timestamp_field_name='timestamp',
)
ratings_frame = ratings_import.import_ratings()
# Create graph without setting the representation
# EX. Create graph with properties 'producer' and 'starring' from
# all exo representation, since there can be multiple exo representation
# containing the same properties
g = NXFullGraph(
source_frame=ratings_frame,
item_contents_dir=movies_dir,
user_contents_dir=user_dir,
item_exo_properties=['producer', 'starring'],
user_exo_properties=[
'1'
] # It's the column in the users DAT which identifies the gender
)
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph without setting properties,
# so ALL exo properties of the representation 0 will be retrieved
g = NXFullGraph(source_frame=ratings_frame,
item_contents_dir=movies_dir,
user_contents_dir=user_dir,
item_exo_representation="0",
user_exo_representation="0")
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying without properties
g = NXFullGraph(ratings_frame)
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertEqual(len(g.property_nodes), 0)
def test_graph_creation(self):
# Test multiple graph creation possibilities
# Import ratings as DataFrame
ratings_import = RatingsImporter(
source=CSVFile(ratings_filename),
rating_configs=[
RatingsFieldConfig(field_name='points',
processor=NumberNormalizer(min_=1, max_=5))
],
from_field_name='user_id',
to_field_name='item_id',
timestamp_field_name='timestamp',
)
ratings_frame = ratings_import.import_ratings()
# Create graph using the property 'starring' from representation '0'
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_representation="0",
item_exo_properties=['starring'])
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying only the exo representation
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_representation="0")
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying only the exo representation
g = NXTripartiteGraph(ratings_frame,
movies_dir,
item_exo_properties=['starring'])
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertGreater(len(g.property_nodes), 0)
# Create graph specifying without properties
g = NXTripartiteGraph(ratings_frame)
# Simple assert just to make sure the graph is created
self.assertGreater(len(g.user_nodes), 0)
self.assertGreater(len(g.item_nodes), 0)
self.assertEqual(len(g.property_nodes), 0)
def test_import_ratings(self):
file_path = '../../../datasets/test_import_ratings.json'
try:
with open(file_path):
pass
except FileNotFoundError:
file_path = 'datasets/test_import_ratings.json'
print(file_path)
RatingsImporter(source=JSONFile(file_path=file_path),
output_directory="test_ratings",
rating_configs=[
RatingsFieldConfig(preference_field_name="review_title",
processor=TextBlobSentimentAnalysis()),
RatingsFieldConfig(preference_field_name="text",
processor=TextBlobSentimentAnalysis()),
RatingsFieldConfig(preference_field_name="stars",
processor=NumberNormalizer(min_=0, max_=5))],
from_field_name="user_id",
to_field_name="item_id",
timestamp_field_name="timestamp").import_ratings()
def rating_config_run(config_dict: Dict):
rating_configs = []
for field in config_dict["fields"]:
class_name = field['processor'].pop('class')
class_dict = dict_detector(field["processor"])
rating_configs.append(
RatingsFieldConfig(
field_name=field["field_name"],
processor=runnable_instances[class_name](**class_dict)))
args = {}
if config_dict["source_type"] == 'sql':
pass
RatingsImporter(source=runnable_instances[config_dict["source_type"]](
file_path=config_dict["raw_source_path"], **args),
output_directory=config_dict["output_directory"],
rating_configs=rating_configs,
from_field_name=config_dict["from_field_name"],
to_field_name=config_dict["to_field_name"],
timestamp_field_name=config_dict["timestamp_field_name"]
).import_ratings()
from orange_cb_recsys.recsys.ranking_algorithms.classifier import SVM
from orange_cb_recsys.recsys.config import RecSysConfig
THIS_DIR = os.path.dirname(os.path.abspath(__file__))
contents_path = os.path.join(THIS_DIR, "../../contents")
datasets_path = os.path.join(THIS_DIR, "../../datasets")
ratings_filename = os.path.join(datasets_path, "examples/new_ratings.csv")
users_dir = os.path.join(contents_path,
"examples/ex_1/users_1600355755.1935306")
items_dir = os.path.join(contents_path,
"examples/ex_1/movies_1600355972.49884")
t_ratings = RatingsImporter(
source=CSVFile(ratings_filename),
rating_configs=[
RatingsFieldConfig(field_name='points',
processor=NumberNormalizer(min_=1, max_=5))
],
from_field_name='user_id',
to_field_name='item_id',
timestamp_field_name='timestamp',
).import_ratings()
class TestRankingEvalModel(TestCase):
def test_fit(self):
recsys_config = RecSysConfig(users_directory=users_dir,
items_directory=items_dir,
score_prediction_algorithm=None,
ranking_algorithm=ClassifierRecommender(
{'Plot': '0'}, SVM()),
from orange_cb_recsys.content_analyzer.ratings_manager.rating_processor import NumberNormalizer
from orange_cb_recsys.content_analyzer.ratings_manager.ratings_importer import RatingsFieldConfig, RatingsImporter
from orange_cb_recsys.content_analyzer.ratings_manager.sentiment_analysis import TextBlobSentimentAnalysis
from orange_cb_recsys.content_analyzer.raw_information_source import JSONFile, CSVFile
from orange_cb_recsys.evaluation import RankingAlgEvalModel, NDCG, FNMeasure, KFoldPartitioning, GiniIndex, DeltaGap, \
ReportEvalModel
from orange_cb_recsys.recsys import ClassifierRecommender, RecSysConfig, RecSys
ratings_filename = '../../../datasets/ratings_example.json'
items_ca_dir = '../../../orange_cb_recsys/movie_dir1605298315.4501655'
users_ca_dir = '../../../datasets/examples/users_dir'
stars_review_config = RatingsFieldConfig(field_name='stars',
processor=NumberNormalizer(min_=1,
max_=5))
ratings_importer = RatingsImporter(
source=JSONFile(ratings_filename),
rating_configs=[stars_review_config],
from_field_name='user_id',
to_field_name='item_id',
timestamp_field_name='timestamp',
)
ratings_frame = ratings_importer.import_ratings()
print(ratings_frame)
original_classifier_config = ClassifierRecommender(item_field='Plot',
field_representation='0',
classifier='random_forest')
def test_fit(self):
"""
item_id_list = [
'tt0112281',
'tt0112302',
'tt0112346',
'tt0112453',
'tt0112641',
'tt0112760',
'tt0112896',
'tt0113041',
'tt0113101',
'tt0113189',
'tt0113228',
'tt0113277',
'tt0113497',
'tt0113845',
'tt0113987',
'tt0114319',
'tt0114388',
'tt0114576',
'tt0114709',
'tt0114885',
]
record_list = []
for i in range(1, 7):
extract_items = set([x for i, x in enumerate(item_id_list) if np.random.randint(0, 2) == 1 and i < 10])
for item in extract_items:
record_list.append((str(i), item, str(np.random.randint(-0, 11) / 10)))
t_ratings = pd.DataFrame.from_records(record_list, columns=['from_id', 'to_id', 'score'])
"""
ratings_filename = 'datasets/examples/new_ratings.csv'
t_ratings = RatingsImporter(
source=CSVFile(ratings_filename),
rating_configs=[
RatingsFieldConfig(field_name='points',
processor=NumberNormalizer(min_=1, max_=5))
],
from_field_name='user_id',
to_field_name='item_id',
timestamp_field_name='timestamp',
).import_ratings()
print(t_ratings)
recsys_config = RecSysConfig(
users_directory='contents/examples/ex_1/users_1600355755.1935306',
items_directory='contents/examples/ex_1/movies_1600355972.49884',
score_prediction_algorithm=None,
ranking_algorithm=CentroidVector(item_field='Plot',
field_representation='1',
similarity=CosineSimilarity()),
rating_frame=t_ratings)
try:
RankingAlgEvalModel(config=recsys_config,
partitioning=KFoldPartitioning(),
metric_list=[
Precision(0.4),
Recall(0.4),
FNMeasure(1, 0.4),
MRR(0.4),
NDCG({
0: (-1, 0),
1: (0, 1)
}),
Correlation('pearson'),
Correlation('kendall'),
Correlation('spearman')
]).fit()
except TypeError:
pass
except ValueError:
pass