Update app.py

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 import numpy as np
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
 # summary function - test for single gradio function interface
+# summary function - test for single gradio function interfrace
 def bulk_function(filename):
   # Create class for data preparation
   class SimpleDataset:
@@ -20,18 +21,25 @@ def bulk_function(filename):
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   model = AutoModelForSequenceClassification.from_pretrained(model_name)
   trainer = Trainer(model=model)  
+  print(filename, type(filename))
+  print(filename.name)
+
+
 
   # read file lines
   with open(filename.name, "r") as f:
     lines = f.readlines()
   # expects unnamed:0 or index, col name -> strip both
   lines_s = [item.split("\n")[0].split(",")[-1] for item in lines]
+  print(lines_s)
+  print(filename)
+ 
 
     # Tokenize texts and create prediction data set
   tokenized_texts = tokenizer(lines_s,truncation=True,padding=True)
   pred_dataset = SimpleDataset(tokenized_texts)
 
-    # Run predictions
+    # Run predictions -> predict whole df
   predictions = trainer.predict(pred_dataset)
 
     # Transform predictions to labels
@@ -65,11 +73,8 @@ def bulk_function(filename):
   df = pd.DataFrame(list(zip(lines_s,preds,labels,scores,  anger, disgust, fear, joy, neutral, sadness, surprise)), columns=['text','pred','label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
 
   # save results to csv
-  YOUR_FILENAME = "YOUR_FILENAME_EMOTIONS_gradio.csv"  # name your output file
+  YOUR_FILENAME = filename.name.split(".")[0] + "_emotion_predictions" + ".csv"  # name your output file
   df.to_csv(YOUR_FILENAME)
 
   # return dataframe for space output
-  return df
-# launch space
-gr.Interface(bulk_function, [gr.inputs.File(file_count="single", type="file", label="str", optional=False),], "dataframe",
-             ).launch()
+  return df