Modify tables

Prediction.py

@@ -41,7 +41,7 @@ def predict_csv(data, text_col, tokenizer, model, device, text_bs=16, max_token_
     y_inten = final_pred.numpy().T
 
     for i in range(len(LABEL_COLUMNS)):
-      data[LABEL_COLUMNS[i]] = y_inten[i].tolist()
+      data[LABEL_COLUMNS[i]] = [round(i, 8) for i in y_inten[i].tolist()]
     return data
 
 @torch.no_grad()
@@ -63,6 +63,7 @@ def predict_single(sentence, tokenizer, model, device, max_token_len=128):
     ).logits
     prediction = torch.softmax(logits, dim=1)
     y_inten = prediction.flatten().cpu().numpy().T.tolist()
+    y_inten = [round(i, 8) for i in y_inten]
     return y_inten
 
 def model_factory(local_path, device):

app.py

@@ -24,13 +24,12 @@ manager = model_factory("./models", device)
 
 
 def single_sentence(sentence):
-    df = []
     model_name = 'All_Data'
     dct = manager[model_name]
     model, tokenizer = dct['model'], dct['tokenizer']
     predictions = predict_single(sentence, tokenizer, model, device)
-    df.append(predictions)
-    return df
+    predictions.sort(reverse=True)
+    return list(zip(LABEL_COLUMNS, predictions))
 
 def csv_process(csv_file, attr="content"):
     current_time = datetime.now()
@@ -76,9 +75,9 @@ with gr.Blocks(theme=my_theme, title='Murphy') as demo:
                 # Detailed information about our model:
                 ...
                 """)
-        tab_output = gr.DataFrame(label='Probability Predictions:', 
-                                  headers=LABEL_COLUMNS,
-                                  datatype=["str"] * (len(LABEL_COLUMNS)),
+        tab_output = gr.DataFrame(label='Predictions:', 
+                                  headers=["Label", "Probability"],
+                                  datatype=["str", "number"],
                                   interactive=False)
         with gr.Row():
             button_ss = gr.Button("Submit", variant="primary")

assets/Prediction.py.bak

@@ -126,4 +126,7 @@ kick_fk_doc_result = predict(Data,"content", tokenizer,kick_model, device, LABEL
 
 fk_result = get_result(Data, kick_fk_doc_result, LABEL_COLUMNS)
 
-fk_result.to_csv("output/prediction_origin_Kickstarter.csv")
+fk_result.to_csv("output/prediction_origin_Kickstarter.csv")
+
+
+# tab_output = gr.Label(label='Probability Predictions:', value=dict(zip(LABEL_COLUMNS, [0]*len(LABEL_COLUMNS))))