feat random pred

tasks/text.py

@@ -60,50 +60,51 @@ async def evaluate_text(request: TextEvaluationRequest):
     # Make random predictions (placeholder for actual model inference)
     true_labels = test_dataset["label"]
 
-    import torch
-    from transformers import (
-        AutoModelForSequenceClassification,
-        AutoTokenizer,
-        Trainer,
-        TrainingArguments,
-    )
-
-    model_name = "clementdesroches/distilbert_climate_ai"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=len(LABEL_MAPPING))
-
-    # Tokenize the datasets
-    def tokenize_function(examples):
-        return tokenizer(examples["quote"], padding="max_length", truncation=True)
-
-    tokenized_test_dataset = test_dataset.map(tokenize_function, batched=True)
-
-    # Set training arguments
-    training_args = TrainingArguments(
-        output_dir="./bert_classification_results",
-        evaluation_strategy="epoch",
-        save_strategy="epoch",
-        learning_rate=2e-5,
-        per_device_train_batch_size=8,
-        per_device_eval_batch_size=8,
-        num_train_epochs=30,
-        weight_decay=0.01,
-        load_best_model_at_end=True,
-    )
-
-    # Initialize the Trainer
-    trainer = Trainer(
-        model=model,
-        args=training_args,
-        eval_dataset=tokenized_test_dataset,
-        tokenizer=tokenizer,
-    )
-
-    import numpy as np
-
-    preds = trainer.predict(tokenized_test_dataset)
-
-    predictions = np.array([np.argmax(x) for x in preds[0]])
+    # import torch
+    # from transformers import (
+    #     AutoModelForSequenceClassification,
+    #     AutoTokenizer,
+    #     Trainer,
+    #     TrainingArguments,
+    # )
+
+    # model_name = "clementdesroches/distilbert_climate_ai"
+    # tokenizer = AutoTokenizer.from_pretrained(model_name)
+    # model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=len(LABEL_MAPPING))
+
+    # # Tokenize the datasets
+    # def tokenize_function(examples):
+    #     return tokenizer(examples["quote"], padding="max_length", truncation=True)
+
+    # tokenized_test_dataset = test_dataset.map(tokenize_function, batched=True)
+
+    # # Set training arguments
+    # training_args = TrainingArguments(
+    #     output_dir="./bert_classification_results",
+    #     evaluation_strategy="epoch",
+    #     save_strategy="epoch",
+    #     learning_rate=2e-5,
+    #     per_device_train_batch_size=8,
+    #     per_device_eval_batch_size=8,
+    #     num_train_epochs=30,
+    #     weight_decay=0.01,
+    #     load_best_model_at_end=True,
+    # )
+
+    # # Initialize the Trainer
+    # trainer = Trainer(
+    #     model=model,
+    #     args=training_args,
+    #     eval_dataset=tokenized_test_dataset,
+    #     tokenizer=tokenizer,
+    # )
+
+    # import numpy as np
+
+    # preds = trainer.predict(tokenized_test_dataset)
+
+    # predictions = np.array([np.argmax(x) for x in preds[0]])
+    predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
 
     # --------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE