Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -12,7 +12,7 @@ books = pd.read_csv('BX_Books.csv', encoding='latin-1', delimiter=';', header=No
|
|
| 12 |
# Merge the data
|
| 13 |
merged_data = ratings.merge(books)
|
| 14 |
|
| 15 |
-
dls = CollabDataLoaders.from_df(ratings, item_name='
|
| 16 |
|
| 17 |
class CollabNN(Module):
|
| 18 |
def __init__(self, user_sz, item_sz, y_range=(0,10.5), n_act=150):
|
|
@@ -57,22 +57,22 @@ print("Loaded Both")
|
|
| 57 |
|
| 58 |
# Function to get top N recommendations for a user using the Dot Product Model
|
| 59 |
def get_top_recommendations_dot(user_id, dls, n=3):
|
| 60 |
-
item_ids = dls.classes['
|
| 61 |
user_ids = [user_id] * len(item_ids)
|
| 62 |
user_item_pairs = torch.tensor(list(zip(user_ids, item_ids))).to(learn_dot.model.device)
|
| 63 |
predictions_dot = learn_dot.model(user_item_pairs).squeeze().tolist()
|
| 64 |
top_indices = sorted(range(len(predictions_dot)), key=lambda i: predictions_dot[i], reverse=True)[:n]
|
| 65 |
-
top_recommendations = [dls.classes['
|
| 66 |
return top_recommendations
|
| 67 |
|
| 68 |
# Function to get top N recommendations for a user using the CollabNN Model
|
| 69 |
def get_top_recommendations_nn(user_id, n=3):
|
| 70 |
-
item_ids = dls.classes['
|
| 71 |
user_ids = [user_id] * len(item_ids)
|
| 72 |
user_item_pairs = torch.tensor(list(zip(user_ids, item_ids))).to(deep_learner.model.device)
|
| 73 |
predictions_nn = deep_learner.model(user_item_pairs).squeeze().tolist()
|
| 74 |
top_indices = sorted(range(len(predictions_nn)), key=lambda i: predictions_nn[i], reverse=True)[:n]
|
| 75 |
-
top_recommendations = [dls.classes['
|
| 76 |
return top_recommendations
|
| 77 |
|
| 78 |
# Create a Gradio interface
|
|
|
|
| 12 |
# Merge the data
|
| 13 |
merged_data = ratings.merge(books)
|
| 14 |
|
| 15 |
+
dls = CollabDataLoaders.from_df(ratings, item_name='Book-Title', bs=8192)
|
| 16 |
|
| 17 |
class CollabNN(Module):
|
| 18 |
def __init__(self, user_sz, item_sz, y_range=(0,10.5), n_act=150):
|
|
|
|
| 57 |
|
| 58 |
# Function to get top N recommendations for a user using the Dot Product Model
|
| 59 |
def get_top_recommendations_dot(user_id, dls, n=3):
|
| 60 |
+
item_ids = dls.classes['Book-Title'].o2i[ratings['Book-Title']]
|
| 61 |
user_ids = [user_id] * len(item_ids)
|
| 62 |
user_item_pairs = torch.tensor(list(zip(user_ids, item_ids))).to(learn_dot.model.device)
|
| 63 |
predictions_dot = learn_dot.model(user_item_pairs).squeeze().tolist()
|
| 64 |
top_indices = sorted(range(len(predictions_dot)), key=lambda i: predictions_dot[i], reverse=True)[:n]
|
| 65 |
+
top_recommendations = [dls.classes['Book-Title'].i2o[item_id] for item_id in top_indices]
|
| 66 |
return top_recommendations
|
| 67 |
|
| 68 |
# Function to get top N recommendations for a user using the CollabNN Model
|
| 69 |
def get_top_recommendations_nn(user_id, n=3):
|
| 70 |
+
item_ids = dls.classes['Book-Title'].o2i[ratings['Book-Title']]
|
| 71 |
user_ids = [user_id] * len(item_ids)
|
| 72 |
user_item_pairs = torch.tensor(list(zip(user_ids, item_ids))).to(deep_learner.model.device)
|
| 73 |
predictions_nn = deep_learner.model(user_item_pairs).squeeze().tolist()
|
| 74 |
top_indices = sorted(range(len(predictions_nn)), key=lambda i: predictions_nn[i], reverse=True)[:n]
|
| 75 |
+
top_recommendations = [dls.classes['Book-Title'].i2o[item_id] for item_id in top_indices]
|
| 76 |
return top_recommendations
|
| 77 |
|
| 78 |
# Create a Gradio interface
|