Update app.py

app.py

@@ -4,12 +4,6 @@ import numpy as np
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
 
 
-  # 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
@@ -32,10 +26,26 @@ def bulk_function(filename):
   print(filename.name)
 
 
+  # check type of input file
+  if filename.name.split(".")[1] == "csv":
+    print("entered")
+    # read file, drop index if exists
+    df_input = pd.read_csv(filename.name, index_col=False)
+    if df_input.columns[0] == "Unnamed: 0":
+      df_input = df_input.drop("Unnamed: 0", axis=1)
+  elif filename.name.split(".")[1] == "xlsx":
+    df_input = pd.read_excel(filename.name, index_col=False)
+    # handle Unnamed
+    if df_input.columns[0] == "Unnamed: 0":
+      df_input = df_input.drop("Unnamed: 0", axis=1)
+  else:
+    return
+
+
   # read csv
   # even if index given, drop it
-  df_input = pd.read_csv(filename.name, index_col=False)
-  print("df_input", df_input)
+  #df_input = pd.read_csv(filename.name, index_col=False)
+  #print("df_input", df_input)
   
   # expect csv format to be in: 
   # 1: ID
@@ -87,7 +97,7 @@ def bulk_function(filename):
     surprise.append(round(temp[i][6], 2))
 
   # define df
-  df = pd.DataFrame(list(zip(ids,lines_s,labels,scores_rounded, anger, disgust, fear, joy, neutral, sadness, surprise)), columns=[df_input.columns[0],     df_input.columns[1],'label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
+  df = pd.DataFrame(list(zip(ids,lines_s,labels,scores_rounded, anger, disgust, fear, joy, neutral, sadness, surprise)), columns=[df_input.columns[0], df_input.columns[1],'label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
   print(df)
   # save results to csv
   YOUR_FILENAME = filename.name.split(".")[0] + "_emotion_predictions" + ".csv"  # name your output file