def get_dataset(ds_name, path, is_generated=False, force_out_of_memory=False, verbose=True, **kwds):
"""Returns an InteractionDataset containing the data present in the path argument, and uses the
settings defined for the dataset specified in the ds_name argument. Downloads the dataset
if is not already stored."""
ds_options = DATASETS[ds_name]
if not is_stored(ds_name):
download_dataset(ds_name)
if is_generated:
return InteractionDataset(path, delimiter=',', columns=ds_options.columns, encoding=ds_options.encoding,
in_memory=not force_out_of_memory, verbose=verbose, **kwds)
else:
return InteractionDataset(path, delimiter=ds_options.delimiter, columns=ds_options.columns,
encoding=ds_options.encoding, has_header=ds_options.has_header,
in_memory=not force_out_of_memory, verbose=verbose, **kwds)
def test_interactions_ds():
df = pd.DataFrame([
[1, 1, 2],
[2, 4, 5],
[3, 3, 3],
[3, 6, 1],
],
columns=['user', 'item', 'interaction'])
return InteractionDataset.read_df(df)
def interactions_ds():
df = pd.DataFrame([
[1, 2, 3, 100],
[1, 4, 5, 50],
[1, 5, 2, 25],
[2, 2, 5, 100],
[2, 3, 2, 20],
],
columns=['user', 'item', 'interaction', 'timestamp'])
return InteractionDataset.read_df(df)
def interactions_ds():
rng = random.Random(0)
df = pd.DataFrame([[u, i, rng.randint(-1, 5)] for u in range(50)
for i in range(200) if rng.randint(0, 4) == 0],
columns=['user', 'item', 'interaction'])
print(df.values)
return leave_k_out(InteractionDataset.read_df(df),
k=5,
min_user_interactions=0,
last_timestamps=False,
seed=10)
def train_interactions_ds():
df = pd.DataFrame([
[1, 2, 3],
[1, 4, 5],
[1, 5, 2],
[2, 2, 5],
[2, 3, 2],
[3, 2, 2],
[3, 5, 5],
[3, 1, 1],
],
columns=['user', 'item', 'interaction'])
return InteractionDataset.read_df(df)
from DRecPy.Dataset import InteractionDataset
import pandas as pd
from os import remove
# create file with sample dataset
with open('tmp.csv', 'w') as f:
f.write('users,items,interactions\n')
f.write('"john","ps4",4.5\n')
f.write('"patrick","xbox",4.1\n')
f.write('"anna","brush",3.6\n')
f.write('"david","tv",2.0\n')
# load dataset into memory
df = pd.read_csv('tmp.csv')
ds_memory = InteractionDataset.read_df(df, user_label='users', item_label='items', interaction_label='interactions')
print('all values:', ds_memory.values_list())
remove('tmp.csv') # delete previously created sample dataset file
from DRecPy.Recommender.Baseline import UserKNN
from DRecPy.Dataset import InteractionDataset
from DRecPy.Evaluation.Processes import ranking_evaluation
from DRecPy.Evaluation.Splits import matrix_split
from DRecPy.Evaluation.Metrics import Precision
from DRecPy.Evaluation.Metrics import Recall
from DRecPy.Evaluation.Metrics import NDCG
ds = InteractionDataset('./cheRM_total.csv',
columns=['user', 'item', 'interaction'],
verbose=False)
ds_train, ds_test = matrix_split(ds,
min_user_interactions=20,
user_test_ratio=0.2,
item_test_ratio=0.2,
seed=25,
verbose=False)
# cosine sim
knn = UserKNN(k=10,
m=0,
sim_metric='cosine_cf',
shrinkage=None,
seed=25,
use_averages=False,
verbose=True)
knn.fit(ds_train)
evaluation = ranking_evaluation(knn,
ds_test,
from DRecPy.Recommender.Baseline import UserKNN
from DRecPy.Dataset import InteractionDataset
from DRecPy.Evaluation.Processes import ranking_evaluation
from DRecPy.Evaluation.Splits import matrix_split
from DRecPy.Evaluation.Metrics import Precision
from DRecPy.Evaluation.Metrics import Recall
from DRecPy.Evaluation.Metrics import NDCG
ds = InteractionDataset('./arm_total_1998_2019.csv',
columns=['user', 'item', 'interaction'],
verbose=False)
ds_train, ds_test = matrix_split(ds,
min_user_interactions=20,
user_test_ratio=0.2,
item_test_ratio=0.2,
seed=25,
verbose=False)
# cosine sim
knn = UserKNN(k=10,
m=0,
sim_metric='cosine_cf',
shrinkage=None,
seed=25,
use_averages=False,
verbose=True)
knn.fit(ds_train)
evaluation = ranking_evaluation(knn,
ds_test,
from DRecPy.Dataset import InteractionDataset
from os import remove
# create file with sample dataset
with open('tmp.csv', 'w') as f:
f.write('"john","ps4",4.5\n')
f.write('"patrick","xbox",4.1\n')
f.write('"anna","brush",3.6\n')
f.write('"david","tv",2.0\n')
# load dataset into memory
ds_memory = InteractionDataset('tmp.csv', columns=['user', 'item', 'interaction'])
print('all values:', ds_memory.values_list())
print('filtered values:', ds_memory.select('interaction > 3.5').values_list())
ds_memory_scaled = ds_memory.copy()
ds_memory_scaled.apply('interaction', lambda x: x / ds_memory.max('interaction'))
print('all values scaled:', ds_memory_scaled.values_list())
# load dataset out of memory
ds_out_of_memory = InteractionDataset('tmp.csv', columns=['user', 'item', 'interaction'], in_memory=False)
print('all values:', ds_out_of_memory.values_list())
print('filtered values:', ds_out_of_memory.select('interaction > 3.5').values_list())
remove('tmp.csv') # delete previously created sample dataset file