Update app.py

app.py

@@ -1,9 +1,79 @@
 import streamlit as st
-from transformers import pipeline
+import torch
+import pandas as pd
+from transformers import AutoTokenizer,  AutoModelForSeq2SeqLM
 
-pipe = pipeline('sentiment-analysis')
-text = st.text_area('enter text')
+class preProcess:
+    def __init__(self, filename, titlename):
+      self.filename = filename
+      self.title = titlename + '\n'
 
-if text:  
-    out = pipe(text)
-    st.json(out)
+    def read_data(self):
+      df = pd.read_csv(self.filename)
+      return df
+
+
+    def check_columns(self, df):
+      if (len(df.columns) > 3):
+        st.error('File has more than 3 coloumns.')
+        return False
+      if (len(df.columns) == 0):
+        st.error('File has no column.')
+        return False
+      else:
+        return True
+
+    def format_data(self, df):
+        headers = [[] for i in range(0, len(df.columns))]
+        for i in range(len(df.columns)):
+            headers[i] = list(df[df.columns[i]])
+        zipped = list(zip(*headers))
+        res = [' '.join(map(str,tups)) for tups in zipped]
+        input_format = ' labels ' + ' - '.join(list(df.columns)) +  ' values '  + ' , '.join(res)
+
+        return input_format
+
+
+    def combine_title_data(self,df):
+      data = self.format_data(df)
+      title_data = ' '.join([self.title,data])
+      
+      return title_data
+      
+class Model:
+    def __init__(self,text,mode):
+      self.padding = 'max_length'
+      self.truncation = True
+      self.prefix = 'C2T: '
+      self.device = device = "cuda:0" if torch.cuda.is_available() else "cpu"
+      self.text = text
+      if mode.lower() == 'simple':
+        self.tokenizer = AutoTokenizer.from_pretrained('saadob12/t5_C2T_big')
+        self.model = AutoModelForSeq2SeqLM.from_pretrained('saadob12/t5_C2T_big').to(self.device)
+      elif mode.lower() == 'analytical':
+        self.tokenizer = AutoTokenizer.from_pretrained('saadob12/t5_C2T_autochart')
+        self.model = AutoModelForSeq2SeqLM.from_pretrained('saadob12/t5_C2T_autochart').to(self.device)
+
+    def generate(self):
+      tokens = self.tokenizer.encode(self.prefix + self.text,  truncation=self.truncation, padding=self.padding, return_tensors='pt').to(self.device)
+      generated = self.model.generate(tokens, num_beams=4, max_length=256)
+      tgt_text = self.tokenizer.decode(generated[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
+      summary = str(tgt_text).strip('[]""')
+      return summary
+      
+      
+      
+def main():
+'''
+    pre = preProcess('test.csv', 'Comparison between two models')
+    contents = pre.read_data()
+    check = pre.check_columns(contents)
+    if check:
+      title_data = pre.combine_title_data(contents)
+      print(title_data)
+      model = Model(title_data, 'simple')
+      summary = model.generate()'''
+     uploaded_file = st.file_uploader("Choose a file")
+if __name__ == "__main__":
+    main()
+