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