first commit

app.py

@@ -0,0 +1,73 @@
+# summary function - test for single gradio function interfrace
+def bulk_function(filename):
+  # 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)  
+
+  # read file lines
+  with open("/content/YOUR_FILENAME.csv", "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][1:]
+  print(lines_s[1:])
+ 
+
+    # Tokenize texts and create prediction data set
+  tokenized_texts = tokenizer(lines_s[1:],truncation=True,padding=True)
+  pred_dataset = SimpleDataset(tokenized_texts)
+
+    # Run predictions
+  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))
+
+    # work in progress
+  # container
+  anger = []
+  disgust = []
+  fear = []
+  joy = []
+  neutral = []
+  sadness = []
+  surprise = []
+
+  # extract scores (as many entries as exist in pred_texts)
+  for i in range(len(lines_s[1:])):
+    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 df
+  df = pd.DataFrame(list(zip(lines_s[1:],preds,labels,scores,  anger, disgust, fear, joy, neutral, sadness, surprise)), columns=['text','pred','label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
+
+  # save results to csv
+  YOUR_FILENAME = "YOUR_FILENAME_EMOTIONS_gradio.csv"  # name your output file
+  df.to_csv(YOUR_FILENAME)
+
+  # return dataframe for space output
+  return df
+# launch space
+gr.Interface(bulk_function, [gr.inputs.File(file_count="single", type="file", label="str", optional=False),], "dataframe",
+             ).launch()