app

app.py

@@ -1,7 +1,33 @@
 import gradio as gr
+import pandas as pd
+import torch
+import numpy as np
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-def greet(name):
-    return "Hello " + name + "!!"
+tokenizer = AutoTokenizer.from_pretrained("mnavas/roberta-finetuned-CPV_Spanish")
+model = AutoModelForSequenceClassification.from_pretrained("mnavas/roberta-finetuned-CPV_Spanish")
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+cpv = pd.read_csv("cpv.csv")
+df = pd.read_csv("code-desc.csv")
+
+labels = df.columns[1:]
+cpv = cpv.columns[1:]
+
+id2label = {idx:label for idx, label in enumerate(labels)}
+label2id = {label:idx for idx, label in enumerate(labels)}
+    
+def askcpv(description):
+    
+    encoding = tokenizer(description, return_tensors="pt")
+    encoding = {k: v.to(model.device) for k,v in encoding.items()}
+    outputs = model(**encoding)
+    sigmoid = torch.nn.Sigmoid()
+    probs = sigmoid(logits.squeeze().cpu())
+    probabilites = torch.nn.functional.softmax(out[0], dim=0)
+    values, indices = torch.topk(probabilites, k=10)
+    # turn predicted id's into actual label names
+    # predicted_labels = [id2label[idx] for idx, label in enumerate(predictions) if label == 1.0]
+    # return predicted_labels
+    return {cpv[i]: v.item() for i, v in zip(indices, values)}
+
+gr.Interface(fn=askcpv, inputs="textbox", outputs="label").launch()