Update app.py

app.py

@@ -2,7 +2,14 @@ import gradio as gr
 import pandas as pd
 import numpy as np
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
-# summary function - test for single gradio function interface
+
+
+  # load tokenizer and model, create trainer
+model_name = "j-hartmann/emotion-english-distilroberta-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+trainer = Trainer(model=model) 
+
 # summary function - test for single gradio function interfrace
 def bulk_function(filename):
   # Create class for data preparation
@@ -16,24 +23,11 @@ def bulk_function(filename):
       def __getitem__(self, idx):
           return {k: v[idx] for k, v in self.tokenized_texts.items()}
 
-  # load tokenizer and model, create trainer
-  model_name = "j-hartmann/emotion-english-distilroberta-base"
-  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)
- 
+  lines_s = [item.split("\n")[0].split(",")[-1] for item in lines][1:]
 
     # Tokenize texts and create prediction data set
   tokenized_texts = tokenizer(lines_s,truncation=True,padding=True)
@@ -77,7 +71,7 @@ def bulk_function(filename):
   df.to_csv(YOUR_FILENAME)
 
   # return dataframe for space output
-  return df
+  return YOUR_FILENAME
   
-gr.Interface(bulk_function, [gr.inputs.File(file_count="single", type="file", label="str", optional=False),],"dataframe",
+gr.Interface(bulk_function, [gr.inputs.File(file_count="single", type="file", label="str", optional=False),],["file"],
              ).launch(debug=True)