Create Recommender.py

Recommender.py

@@ -0,0 +1,86 @@
+import json
+import pandas as pd
+from sklearn.metrics.pairwise import cosine_similarity
+
+class Recommender :
+    def __init__(self, title_vec_col, content_vec_col, id_col):
+        self.title_vec_col = title_vec_col
+        self.content_vec_col = content_vec_col
+        self.id_col = id_col
+
+    def calculate_recom_scores (self, k, similarities) :
+        scores = list(enumerate(similarities[0]))
+        scores = sorted(scores, key=lambda x: x[1], reverse=True)
+        scores = scores[1: k + 1]
+        return scores
+
+    def str2arr (self, arr) :
+        output = list()
+        for string in arr :
+            data_list = json.loads(string)
+
+            # Convert the list to a NumPy array
+            data_array = np.array(data_list)
+            output.append(data_array)
+
+        return np.array(output)
+
+    # def recommend_k (self, table, k, id) :
+
+    #     data = np.array(list(zip(*table)))
+    #     # print(data.shape, data)
+    #     idx = int(data[0][data[self.id_col]==id].item())
+
+    #     titles = self.str2arr(data[self.title_vec_col, :])
+    #     contents = self.str2arr(data[self.content_vec_col, :])
+    #     print(titles.shape)
+    #     print(titles[int(idx)].shape)
+
+    #     titles_sim = cosine_similarity(titles[int(idx)].reshape(1, -1), titles)
+    #     print(titles_sim.shape)
+    #     contents_sim = cosine_similarity(contents[int(idx)].reshape(1, -1), contents)
+
+    #     titles_scores = self.calculate_recom_scores(k, titles_sim)
+    #     contents_scores = self.calculate_recom_scores(k, contents_sim)
+
+    #     print(titles_scores)
+    #     union_scores = np.union1d(titles_scores, contents_scores)
+
+    #     print(type(union_scores))
+    #     # union_scores = sorted(union_scores.tolist(), key=lambda x: x[1], reverse=True)
+
+    #     union_scores = sorted(union_scores.tolist(), key=lambda x: x[1] if isinstance(x, tuple) else x, reverse=True)
+
+    #     indices = [i[0] for i in union_scores]
+    #     result = data[:, np.isin(data[0,:], indices)]
+
+    #     return result[self.id_col, :].tolist()
+
+    def recommend_k(self, table, k, id):
+
+      data = np.array(list(zip(*table)))
+      idx = int(data[0][data[self.id_col] == id].item())
+
+      titles = self.str2arr(data[self.title_vec_col, :])
+      contents = self.str2arr(data[self.content_vec_col, :])
+
+      titles_sim = cosine_similarity(titles[int(idx)].reshape(1, -1), titles)
+      contents_sim = cosine_similarity(contents[int(idx)].reshape(1, -1), contents)
+
+      titles_scores = self.calculate_recom_scores(k, titles_sim)
+      contents_scores = self.calculate_recom_scores(k, contents_sim)
+
+    #   union_scores = np.union1d(titles_scores, contents_scores)
+      union_scores = list(set(titles_scores).union(set(contents_scores)))
+      union_scores = sorted(union_scores, key=lambda x: x[1] if isinstance(x, tuple) else x, reverse=True)
+    #   indices = [i[0] if isinstance(i, tuple) else i for i in union_scores]
+    #   result = data[:, np.isin(data[0, :], indices)]
+
+      unique_dict = {}
+      for t in union_scores:
+          if t[0] not in unique_dict or t[1] > unique_dict[t[0]][1]:
+              unique_dict[t[0]] = t
+      union_scores = list(unique_dict.values())
+      indices = [i[0] for i in union_scores]
+
+      return indices, union_scores, titles_scores