Update app.py

app.py

@@ -8,4 +8,85 @@ import itertools
 import numpy as np
 from numpy import dot
 from numpy.linalg import norm
-#from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
+#from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
+
+# compute dot product of inputs
+# summary function - test for single gradio function interfrace
+def gr_cosine_similarity(sentence1, sentence2):
+  # Create class for data preparation
+  class SimpleDataset:
+      def __init__(self, tokenized_texts):
+          self.tokenized_texts = tokenized_texts
+      
+      def __len__(self):
+          return len(self.tokenized_texts["input_ids"])
+      
+      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)  
+
+  # sentences in list
+  lines_s = [sentence1, sentence2]
+  print(type(sentence1), type(sentence2))
+  print(sentence1, sentence2)
+  print(lines_s)
+ 
+    # Tokenize texts and create prediction data set
+  tokenized_texts = tokenizer(lines_s, truncation=True, padding=True)
+  pred_dataset = SimpleDataset(tokenized_texts)
+
+    # Run predictions -> predict whole df
+  predictions = trainer.predict(pred_dataset)
+
+    # Transform predictions to labels
+  preds = predictions.predictions.argmax(-1)
+  labels = pd.Series(preds).map(model.config.id2label)
+  scores = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1,keepdims=True)).max(1)
+    # scores raw
+  temp = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1, keepdims=True)).tolist()
+
+
+    # work in progress
+  # container
+  anger = []
+  disgust = []
+  fear = []
+  joy = []
+  neutral = []
+  sadness = []
+  surprise = []
+
+  print(temp)
+  # extract scores (as many entries as exist in pred_texts)
+  for i in range(len(lines_s)):
+    anger.append(temp[i][0])
+    disgust.append(temp[i][1])
+    fear.append(temp[i][2])
+    joy.append(temp[i][3])
+    neutral.append(temp[i][4])
+    sadness.append(temp[i][5])
+    surprise.append(temp[i][6])
+
+  # define both vectors for the dot product
+  # each include all values for both predictions
+  v1 = temp[0]
+  v2 = temp[1]
+  print(type(v1), type(v2))
+  # compute dot product of all 
+  dot_product = dot(v1, v2)
+
+   # define df
+  df = pd.DataFrame(list(zip(lines_s,labels, anger, disgust, fear, joy, neutral, sadness, surprise)), columns=['text','label', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
+
+  # compute cosine similarity
+  # is dot product of vectors n / norms 1*..*n vectors
+  cosine_similarity = dot_product / (norm(v1) * norm(v2))
+
+
+  # return dataframe for space output
+  return  df, cosine_similarity