Fix pipeline

pipeline.py

@@ -2,7 +2,8 @@
 import tensorflow as tf
 
 class PreTrainedPipeline():
-    def __init__(self):
+    def __init__(self, path):
+        # define the best model TODO
         sequence_input = tf.keras.Input(shape=(300), name='input')
         x = tf.keras.layers.Dense(2048, activation="LeakyReLU")(sequence_input)
         x = tf.keras.layers.Dense(1024, activation="LeakyReLU")(x)
@@ -17,48 +18,55 @@ class PreTrainedPipeline():
 
         model.compile(optimizer="Adamax", loss="cosine_similarity")
 
-    def __call__(self):
-        return {
-            "text": "Hi!!!"
-        }
- 
-# def RevDict(sent,flag,model): 
-#     """ 
-#     This function recieves a sentence from the user, and turns back top_10 (for flag=0) or top_100 (for flag=1) predictions. 
-#     the input sentence will be normalized, and stop words will be removed 
-#     """ 
-     
-#     normalizer = Normalizer() 
-#     X_Normalized = normalizer.normalize(sent) 
-#     X_Tokens = word_tokenize(X_Normalized) 
-#     stopwords = [normalizer.normalize(x.strip()) for x in codecs.open(r"stopwords.txt",'r','utf-8').readlines()] 
-#     X_Tokens = [t for t in X_Tokens if t not in stopwords] 
-#     preprocessed = [' '.join(X_Tokens)][0] 
-#     sent_ids = sent2id([preprocessed]) 
-#     output=np.array((model.predict(sent_ids.reshape((1,20))).tolist()[0])) 
-#     distances=distance.cdist(output.reshape((1,300)), comparison_matrix, "cosine")[0] 
-#     min_index_100 = distances.argsort()[:100] 
-#     min_index_10 = distances.argsort()[:10] 
+        # model.load_weights("path to model file") TODO
+
+        self.model = model
+
+    def __call__(self, inputs):
+        return [ # Sample output, call the model here TODO
+            {'label': 'POSITIVE', 'score': 0.05},
+            {'label': 'NEGATIVE', 'score': 0.03},
+            {'label': 'معنی', 'score': 0.92},
+            {'label': f'{inputs}', 'score': 0},
+        ]
  
-#     temp=[] 
-#     if flag == 0: 
-#         for i in range(10): 
-#             temp.append(id2h[str(min_index_10[i])]) 
-#     elif flag == 1: 
-#         for i in range(100): 
-#             temp.append(id2h[str(min_index_100[i])]) 
-     
-#     for i in range(len(temp)): 
-#         print(temp[i])
+    # def RevDict(sent,flag,model): 
+    #     """ 
+    #     This function recieves a sentence from the user, and turns back top_10 (for flag=0) or top_100 (for flag=1) predictions. 
+    #     the input sentence will be normalized, and stop words will be removed 
+    #     """ 
+        
+    #     normalizer = Normalizer() 
+    #     X_Normalized = normalizer.normalize(sent) 
+    #     X_Tokens = word_tokenize(X_Normalized) 
+    #     stopwords = [normalizer.normalize(x.strip()) for x in codecs.open(r"stopwords.txt",'r','utf-8').readlines()] 
+    #     X_Tokens = [t for t in X_Tokens if t not in stopwords] 
+    #     preprocessed = [' '.join(X_Tokens)][0] 
+    #     sent_ids = sent2id([preprocessed]) 
+    #     output=np.array((model.predict(sent_ids.reshape((1,20))).tolist()[0])) 
+    #     distances=distance.cdist(output.reshape((1,300)), comparison_matrix, "cosine")[0] 
+    #     min_index_100 = distances.argsort()[:100] 
+    #     min_index_10 = distances.argsort()[:10] 
+    
+    #     temp=[] 
+    #     if flag == 0: 
+    #         for i in range(10): 
+    #             temp.append(id2h[str(min_index_10[i])]) 
+    #     elif flag == 1: 
+    #         for i in range(100): 
+    #             temp.append(id2h[str(min_index_100[i])]) 
+        
+    #     for i in range(len(temp)): 
+    #         print(temp[i])
 
-# def sent2id(sents): 
-#     sents_id=np.zeros((len(sents),20)) 
-#     for j in tqdm(range(len(sents))): 
-#         for i,word in enumerate(sents[j].split()): 
-#             try: 
-#                 sents_id[j,i] = t2id[word] 
-#             except: 
-#                 sents_id[j,i] = t2id['UNK'] 
-#             if i==19: 
-#                 break 
-#     return sents_id
+    # def sent2id(sents): 
+    #     sents_id=np.zeros((len(sents),20)) 
+    #     for j in tqdm(range(len(sents))): 
+    #         for i,word in enumerate(sents[j].split()): 
+    #             try: 
+    #                 sents_id[j,i] = t2id[word] 
+    #             except: 
+    #                 sents_id[j,i] = t2id['UNK'] 
+    #             if i==19: 
+    #                 break 
+    #     return sents_id