def test_sparse_to_df(test_specs, python_dataset):
# initialize the splitter
header = {
"col_user": DEFAULT_USER_COL,
"col_item": DEFAULT_ITEM_COL,
"col_rating": DEFAULT_RATING_COL,
}
# instantiate the the affinity matrix
am = AffinityMatrix(DF=python_dataset, **header)
# generate the sparse matrix representation
X, _, _ = am.gen_affinity_matrix()
# use the inverse function to generate a pandas df from a sparse matrix ordered by userID
DF = am.map_back_sparse(X, kind="ratings")
# tests: check that the two dataframes have the same elements in the same positions.
assert (
DF.userID.values.all()
== python_dataset.sort_values(by=["userID"]).userID.values.all()
)
assert (
DF.itemID.values.all()
== python_dataset.sort_values(by=["userID"]).itemID.values.all()
)
assert (
DF.rating.values.all()
== python_dataset.sort_values(by=["userID"]).rating.values.all()
)
def test_sparse_to_df(test_specs, python_dataset):
# initialize the splitter
header = {
"col_user": DEFAULT_USER_COL,
"col_item": DEFAULT_ITEM_COL,
"col_rating": DEFAULT_RATING_COL,
}
# instantiate the the affinity matrix
am = AffinityMatrix(DF=python_dataset, **header)
# generate the sparse matrix representation
X = am.gen_affinity_matrix()
# use the inverse function to generate a pandas df from a sparse matrix ordered by userID
DF = am.map_back_sparse(X, kind="ratings")
# tests: check that the two dataframes have the same elements in the same positions.
assert (
DF.userID.values.all()
== python_dataset.sort_values(by=["userID"]).userID.values.all()
)
assert (
DF.itemID.values.all()
== python_dataset.sort_values(by=["userID"]).itemID.values.all()
)
assert (
DF.rating.values.all()
== python_dataset.sort_values(by=["userID"]).rating.values.all()
)
def RBMtrain():
data = pd.read_csv("SnacksData100.csv")
header = {
"col_user": "******",
"col_item": "Product_Id",
"col_rating": "Ratings",
}
am = AffinityMatrix(DF=data, **header)
X = am.gen_affinity_matrix()
Xtr, Xtst = numpy_stratified_split(X)
model = RBM(hidden_units=600,
training_epoch=30,
minibatch_size=60,
keep_prob=0.9,
with_metrics=True)
model.fit(Xtr, Xtst)
top_k, test_time = model.recommend_k_items(Xtst)
top_k_df = am.map_back_sparse(top_k, kind='prediction')
test_df = am.map_back_sparse(Xtst, kind='ratings')
joblib.dump(top_k_df, 'testdata')
We will now fit the model and apply it to the dataset
""")
mlask(begin="\n")
### TODO HOW TO KEEP THE OUTPUT QUIET??????
train_time = model.fit(Xtr, Xtst)
### TODO HOW TO KEEP THE OUTPUT QUIET??????
top_k, test_time = model.recommend_k_items(Xtst)
# Map the index back to original ids?????
top_k_df = am.map_back_sparse(top_k, kind='prediction')
test_df = am.map_back_sparse(Xtst, kind='ratings')
top_k_df.head(10)
def ranking_metrics(data_size, data_true, data_pred, time_train, time_test, K):
eval_map = map_at_k(data_true,
data_pred,
col_user="******",
col_item="MovieID",
col_rating="Rating",
col_prediction="prediction",
relevancy_method="top_k",
k=K)