Create new file

app.py

@@ -0,0 +1,142 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import spacy
+from spacy import displacy
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
+
+def linkify():
+  import pandas as pd
+  import streamlit as st
+  link1 = "https://stackoverflow.com/questions/71641666/hyperlink-in-streamlit-dataframe"
+  link2 = "https://stackoverflow.com/questions/71731937/how-to-plot-comparison-in-streamlit-dynamically-with-multiselect"
+  df = pd.DataFrame(
+    {
+        "url": [
+            f'<a target="_blank" href="{link1}">Hyperlink in Streamlit dataframe</a>',
+            f'<a target="_blank" href="{link2}">How to plot comparison in Streamlit dynamically with multiselect?</a>'
+        ],
+        "label": ["question", "question"]
+    }
+  )
+  doc=df.to_html(escape=False, index=False)
+  html = displacy.render(doc, style="dep", page=True)
+  return html
+
+
+# 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()}
+
+  html = linkify()
+  gradio.HTML(html)
+  
+  # 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)  
+  print(filename, type(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)
+  
+  # expect csv format to be in: 
+  # 1: ID
+  # 2: Texts
+  # no index
+  # store ids in ordered list
+  ids = df_input[df_input.columns[0]].to_list()
+
+  # store sentences in ordered list
+  # expects sentences to be in second col
+  # of csv with two cols
+  lines_s = df_input[df_input.columns[1]].to_list()
+
+    # 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)
+
+  # round scores
+  scores_rounded = [round(score, 3) for score in scores]
+
+    # scores raw
+  temp = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1,keepdims=True))
+
+  # 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)):
+    anger.append(round(temp[i][0], 3))
+    disgust.append(round(temp[i][1], 3))
+    fear.append(round(temp[i][2], 3))
+    joy.append(round(temp[i][3], 3))
+    neutral.append(round(temp[i][4], 3))
+    sadness.append(round(temp[i][5], 3))
+    surprise.append(round(temp[i][6], 3))
+
+  # 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],'max_label','max_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
+  df.to_csv(YOUR_FILENAME, index=False)
+
+  # return dataframe for space output
+  return YOUR_FILENAME
+  
+gr.Interface(bulk_function, 
+  inputs=[gr.inputs.File(file_count="single", type="file", label="Upload file", optional=False),],
+  outputs=[gr.outputs.File(label="Output file")],
+  # examples=[["YOUR_FILENAME.csv"]], # computes, doesn't export df so far
+  #["highlight", "json", "html"],
+  theme="huggingface",
+             title="Emotion Classification from CSV",
+             description="Upload csv file with 2 columns (in order): (a) ID column, (b) text column. Model: https://huggingface.co/j-hartmann/emotion-english-distilroberta-base.",
+             allow_flagging=False,
+             ).launch(debug=True)