update

.vscode/settings.json

@@ -0,0 +1,7 @@
+{
+  "workbench.colorCustomizations": {
+    "activityBar.background": "#590F35",
+    "titleBar.activeBackground": "#7C154B",
+    "titleBar.activeForeground": "#FEFCFD"
+  }
+}

app.py

@@ -5,6 +5,10 @@ import torch.nn as nn
 from torch.utils.data import Dataset, DataLoader
 import unicodedata
 import re
+import gradio
+import json
+import numpy as np
+import pandas as pd
 
 # Undesirable patterns within texts
 patterns = {
@@ -169,7 +173,7 @@ def treat_data_input(data, etailment_txt):
               batch_size=200,drop_last=False,
               num_workers=num_workers)
   
-  return dataload_train, dataload_remain
+  return dataload_train, dataload_remain, dataload_all
 
 
 import gc
@@ -191,7 +195,7 @@ def treat_train_evaluate(dataload_train, dataload_remain):
                   weight_decay = config['weight_decay'])
 
 
-  model_few.to('cuda')
+  model_few.to(device)
   model_few.train()
 
 
@@ -214,7 +218,7 @@ def treat_sort(dataload_all,logits):
 def pipeline(data):
   # data = pd.read_csv(fil.name)
   data = pd.read_excel(data)
-  dataload_train, dataload_remain = treat_data_input(data,"its a great text")
+  dataload_train, dataload_remain, dataload_all = treat_data_input(data,"its a great text")
   logits = treat_train_evaluate(dataload_train, dataload_remain)
   treat_sort(dataload_all,logits)
   return "output.xlsx"
@@ -226,7 +230,7 @@ import gradio as gr
 with gr.Blocks() as demo:
     fil = gr.File(label="input data")
     output = gr.File(label="output data")
-    greet_btn = gr.Button("Greet")
+    greet_btn = gr.Button("Rank")
     greet_btn.click(fn=pipeline, inputs=fil, outputs=output)
 
 demo.launch()

requirements.txt

@@ -1,4 +1,5 @@
 transformers==4.16.2
 torchmetrics==0.8.0
 matplotlib==3.5.1
+gradio
 torch

utils.py

@@ -1,7 +1,61 @@
+import torch.nn.functional as F
+import torch.nn as nn
+from torch.utils.data import Dataset, DataLoader
+
+import math
+import torch
+import numpy as np
+import pandas as pd
+import time
+import transformers
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from sklearn.manifold import TSNE
+from copy import deepcopy, copy
+import seaborn as sns
+import matplotlib.pylab as plt
+from pprint import pprint
+import shutil
+import datetime
+import re
+import json
+from pathlib import Path
+
+
+from itertools import chain
+import numpy as np
+import pandas as pd
+
+
+
 import torch
 import torch.nn as nn
 from torch.utils.data import Dataset, DataLoader
 
+# Fetching pre-trained model and tokenizer
+class initializer:
+  def __init__(self, MODEL_NAME, **config):    
+    self.MODEL_NAME = MODEL_NAME
+
+    model = config.get("model")
+    tokenizer = config.get("tokenizer")
+
+    # Model
+    self.model = model.from_pretrained(MODEL_NAME, 
+                                       return_dict=True,
+                                       output_attentions = False)
+    # Tokenizer
+    self.tokenizer = tokenizer.from_pretrained(MODEL_NAME,
+                                               do_lower_case = True)
+
+config = {
+    "model": AutoModelForSequenceClassification,
+    "tokenizer": AutoTokenizer
+     }
+
+# Pre-trained model initializer (uncased sciBERT)
+initializer_model_scibert = initializer('allenai/scibert_scivocab_uncased', **config)
+# initializer_model = initializer('bert-base-uncased', **config)
+
 LABEL_MAP = {'negative': 0,
              'not included':0,
              '0':0,