{
  "id": 415488,
  "title": "ERROR while Tokenizing the data for encoding",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/415488",
  "author_name": "JagadishR_16",
  "post_date": "2023-06-06T16:50:49.135000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<pre><code>`\ntrain_encodings = tokenizer((train_x[]), padding=, truncation=, return_tensors=)\nval_encodings = tokenizer((valid_x[]), padding=, truncation=, return_tensors=)```\n</code></pre>\n<p>Getting Name error for 'text' <br>\nCan you suggest which column is better of tokenzing</p>",
  "messages": [
    {
      "id": 2290263,
      "postDate": "2023-06-06T16:50:49.137Z",
      "content": "<pre><code>`\ntrain_encodings = tokenizer((train_x[]), padding=, truncation=, return_tensors=)\nval_encodings = tokenizer((valid_x[]), padding=, truncation=, return_tensors=)```\n</code></pre>\n<p>Getting Name error for 'text' <br>\nCan you suggest which column is better of tokenzing</p>",
      "rawMarkdown": "```python\n`# Tokenize and convert sequences to input tensors\ntrain_encodings = tokenizer(list(train_x['text']), padding=True, truncation=True, return_tensors='pt')\nval_encodings = tokenizer(list(valid_x['text']), padding=True, truncation=True, return_tensors='pt')```\n```\nGetting Name error for 'text' \nCan you suggest which column is better of tokenzing\n\n",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2290263": "```python\n`# Tokenize and convert sequences to input tensors\ntrain_encodings = tokenizer(list(train_x['text']), padding=True, truncation=True, return_tensors='pt')\nval_encodings = tokenizer(list(valid_x['text']), padding=True, truncation=True, return_tensors='pt')```\n```\nGetting Name error for 'text' \nCan you suggest which column is better of tokenzing\n\n"
  }
}