Create evaluate.py

evaluate.py

@@ -0,0 +1,21 @@
+def get_classification_report():
+    from sklearn.metrics import classification_report
+    import pandas as pd
+
+    # Load your test data
+    df = pd.read_csv("test.csv")
+    texts = df["text"].tolist()
+    true_labels = df["label"].tolist()
+
+    # Load tokenizer and model
+    tokenizer = AutoTokenizer.from_pretrained("Shrish/mbert-sentiment")
+    model = TFAutoModelForSequenceClassification.from_pretrained("Shrish/mbert-sentiment")
+
+    # Tokenize and predict
+    inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="tf")
+    outputs = model(inputs)
+    predictions = tf.math.argmax(outputs.logits, axis=1).numpy()
+
+    # Generate report
+    report = classification_report(true_labels, predictions, target_names=["negative", "neutral", "positive"])
+    return report