testmodelsonpre

app.py

@@ -23,50 +23,50 @@ if option == 'MILESTONE 3':
     tokenizer_0 = AutoTokenizer.from_pretrained(model_name_0)
     classifier_0 = pipeline(task="sentiment-analysis", model=model_0, tokenizer=tokenizer_0)
 
-    # model_name_1 = "Rathgeberj/milestone3_1"
-    # # model_1 = AutoModelForSequenceClassification.from_pretrained(model_name_1)
-    # model_1 = BertForMaskedLM.from_pretrained(model_name_1)
-    # tokenizer_1 = AutoTokenizer.from_pretrained(model_name_1)
-    # classifier_1 = pipeline(task="sentiment-analysis", model=model_1, tokenizer=tokenizer_1)
-
-    # model_name_2 = "Rathgeberj/milestone3_2"
-    # # model_2 = AutoModelForSequenceClassification.from_pretrained(model_name_2)
-    # model_2 = BertForMaskedLM.from_pretrained(model_name_2)
-    # tokenizer_2 = AutoTokenizer.from_pretrained(model_name_2)
-    # classifier_2 = pipeline(task="sentiment-analysis", model=model_2, tokenizer=tokenizer_2)
-
-    # model_name_3 = "Rathgeberj/milestone3_3"
-    # # model_3 = AutoModelForSequenceClassification.from_pretrained(model_name_3)
-    # model_3 = BertForMaskedLM.from_pretrained(model_name_3)
-    # tokenizer_3 = AutoTokenizer.from_pretrained(model_name_3)
-    # classifier_3 = pipeline(task="sentiment-analysis", model=model_3, tokenizer=tokenizer_3)
-
-    # model_name_4 = "Rathgeberj/milestone3_4"
-    # # model_4 = AutoModelForSequenceClassification.from_pretrained(model_name_4)
-    # model_4 = BertForMaskedLM.from_pretrained(model_name_4)
-    # tokenizer_4 = AutoTokenizer.from_pretrained(model_name_4)
-    # classifier_4 = pipeline(task="sentiment-analysis", model=model_4, tokenizer=tokenizer_4)
-
-    # model_name_5 = "Rathgeberj/milestone3_5"
-    # # model_5 = AutoModelForSequenceClassification.from_pretrained(model_name_5)
-    # model_5 = BertForMaskedLM.from_pretrained(model_name_5)
-    # tokenizer_5 = AutoTokenizer.from_pretrained(model_name_5)
-    # classifier_5 = pipeline(task="sentiment-analysis", model=model_5, tokenizer=tokenizer_5)
-
-    # models = [model_0, model_1, model_2, model_3, model_4, model_5]
-    # tokenizers = [tokenizer_0, tokenizer_1, tokenizer_2, tokenizer_3, tokenizer_4, tokenizer_5]
-    # classifiers = [classifier_0, classifier_1, classifier_2, classifier_3, classifier_4, classifier_5]
-
-    X_train = [textIn]
-    batch_0 = tokenizer_0(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
-
-    with torch.no_grad():
-        outputs = model_0(**batch_0, labels=torch.tensor([1, 0]))
-        predictions = F.softmax(outputs.logits, dim=1)
-        labels = torch.argmax(predictions, dim=1)
-        labels = [model.config.id2label[label_id] for label_id in labels.tolist()]
-
-    st.write(predictions['label'])
+    model_name_1 = "Rathgeberj/milestone3_1"
+    # model_1 = AutoModelForSequenceClassification.from_pretrained(model_name_1)
+    model_1 = BertForMaskedLM.from_pretrained(model_name_1)
+    tokenizer_1 = AutoTokenizer.from_pretrained(model_name_1)
+    classifier_1 = pipeline(task="sentiment-analysis", model=model_1, tokenizer=tokenizer_1)
+
+    model_name_2 = "Rathgeberj/milestone3_2"
+    # model_2 = AutoModelForSequenceClassification.from_pretrained(model_name_2)
+    model_2 = BertForMaskedLM.from_pretrained(model_name_2)
+    tokenizer_2 = AutoTokenizer.from_pretrained(model_name_2)
+    classifier_2 = pipeline(task="sentiment-analysis", model=model_2, tokenizer=tokenizer_2)
+
+    model_name_3 = "Rathgeberj/milestone3_3"
+    # model_3 = AutoModelForSequenceClassification.from_pretrained(model_name_3)
+    model_3 = BertForMaskedLM.from_pretrained(model_name_3)
+    tokenizer_3 = AutoTokenizer.from_pretrained(model_name_3)
+    classifier_3 = pipeline(task="sentiment-analysis", model=model_3, tokenizer=tokenizer_3)
+
+    model_name_4 = "Rathgeberj/milestone3_4"
+    # model_4 = AutoModelForSequenceClassification.from_pretrained(model_name_4)
+    model_4 = BertForMaskedLM.from_pretrained(model_name_4)
+    tokenizer_4 = AutoTokenizer.from_pretrained(model_name_4)
+    classifier_4 = pipeline(task="sentiment-analysis", model=model_4, tokenizer=tokenizer_4)
+
+    model_name_5 = "Rathgeberj/milestone3_5"
+    # model_5 = AutoModelForSequenceClassification.from_pretrained(model_name_5)
+    model_5 = BertForMaskedLM.from_pretrained(model_name_5)
+    tokenizer_5 = AutoTokenizer.from_pretrained(model_name_5)
+    classifier_5 = pipeline(task="sentiment-analysis", model=model_5, tokenizer=tokenizer_5)
+
+    models = [model_0, model_1, model_2, model_3, model_4, model_5]
+    tokenizers = [tokenizer_0, tokenizer_1, tokenizer_2, tokenizer_3, tokenizer_4, tokenizer_5]
+    classifiers = [classifier_0, classifier_1, classifier_2, classifier_3, classifier_4, classifier_5]
+
+    # X_train = [textIn]
+    # batch = tokenizer_0(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
+
+    # with torch.no_grad():
+    #     outputs = model_0(**batch_0, labels=torch.tensor([1, 0]))
+    #     predictions = F.softmax(outputs.logits, dim=1)
+    #     labels = torch.argmax(predictions, dim=1)
+    #     labels = [model.config.id2label[label_id] for label_id in labels.tolist()]
+
+    # st.write(predictions['label'])
 
 
     col = ['Tweet', 'Highest_Toxicity_Class_Overall', 'Score_Overall', 'Highest_Toxicity_Class_Except_Toxic', 'Score_Except_Toxic']
@@ -87,15 +87,18 @@ if option == 'MILESTONE 3':
     HTCET = [0]*10
     SET = [0]*10
 
-    # for i in range(10):
-    #     X_train = pre_populated_tweets[i]
-    #     batch = tokenizer_0(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
-
-    # with torch.no_grad():
-    #     outputs = model(**batch_0, labels=torch.tensor([1, 0]))
-    #     predictions = F.softmax(outputs.logits, dim=1)
-    #     labels = torch.argmax(predictions, dim=1)
-    #     labels = [model.config.id2label[label_id] for label_id in labels.tolist()]
+    pred_data = []
+
+    for i in range(10):
+        X_train = pre_populated_tweets[i]
+        for j in range(6):
+            batch = tokenizers[j](X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
+            with torch.no_grad():
+                outputs = models[j](**batch, labels=torch.tensor([1, 0]))
+                predictions = F.softmax(outputs.logits, dim=1)
+                labels = torch.argmax(predictions, dim=1)
+                labels = [model.config.id2label[label_id] for label_id in labels.tolist()]
+                pred_data.append(predictions)