def extract_features()

in src/feature_extractor.py [0:0]

• 10 lines of code
• 3 McCabe index (conditional complexity)

    def extract_features(self, text):
        inputs = self.tokenizer(text, return_tensors="np", padding=True, truncation=True)
        # Prepare the input_feed with all required inputs
        input_feed = {
            self.ort_session.get_inputs()[0].name: inputs["input_ids"],
            self.ort_session.get_inputs()[1].name: inputs["attention_mask"],
        }

        # Check if 'token_type_ids' is required by the model
        if len(self.ort_session.get_inputs()) > 2:
            input_feed[self.ort_session.get_inputs()[2].name] = inputs.get("token_type_ids", None)

        # Run inference
        outputs = self.ort_session.run(None, input_feed)
        # return outputs[0], inputs["attention_mask"]
        # Squeeze the batch dimension to ensure shape [seqLength, embedDim]
        return np.squeeze(outputs[0], axis=0), inputs["attention_mask"].squeeze(axis=0)