Upload 2 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 embs.txt filter=lfs diff=lfs merge=lfs -text
+dataset.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,34 @@
+from transformers import BertTokenizer, BertModel
+import torch
+from sklearn.metrics.pairwise import cosine_similarity
+import pandas as pd
+import numpy as np
+import time
+
+loaded_model = BertModel.from_pretrained('model')
+loaded_tokenizer = BertTokenizer.from_pretrained('tokenizer')
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+
+
+def filter_by_ganre(df: pd.DataFrame, ganre_list: list):
+    filtered_df = df[df['ganres'].apply(lambda x: any(g in ganre_list for g in(x)))]
+    return filtered_df
+
+
+end_time = time.time()
+
+
+def recommendation(df: pd.DataFrame, embeddings:np.array, user_text: str, n=10):
+    start_time = time.time()
+    tokens = loaded_tokenizer(user_text, return_tensors="pt", padding=True, truncation=True)
+    loaded_model.to(device)
+    loaded_model.eval()
+    with torch.no_grad():
+        tokens = {key: value.to(loaded_model.device) for key, value in tokens.items()}
+        outputs = loaded_model(**tokens)
+        user_embedding = output.last_hidden_state.mean(dim=1).squeeze().cpu().detach().numpy()
+    cosine_similarities = cosine_similarity(embeddings, user_embedding.reshape(1, -1))
+    df_res = pd.DataFrame(cosine_similarities.ravel(), columns=['cos_sim']).sort_values('cos_sim', ascending=False)
+    dict_topn = df_res.iloc[:n, :].cos_sim.to_dict()
+    end_time = time.time()
+    return dict_topn

dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c10dbf7a899fbf0553bf6cab5fd11abf35cf224e4e6e4f7843fdd19144c550
+size 19266108