{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os \n",
    "from transformers import AutoConfig, AutoTokenizer, AutoModelForSequenceClassification, DataCollatorWithPadding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_name_or_path = \"/datadrive/namlh31/codebridge/Codebert-docstring-inconsistency\"\n",
    "config = AutoConfig.from_pretrained(\n",
    " model_name_or_path,\n",
    ")\n",
    "tokenizer = AutoTokenizer.from_pretrained(\n",
    "    model_name_or_path\n",
    ")\n",
    "model = AutoModelForSequenceClassification.from_pretrained(\n",
    "model_name_or_path,\n",
    "config=config,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "examples = {'code': \"function(str){\\r\\n  var ret = new Array(str.length), len = str.length;\\r\\n  while(len--) ret[len] = str.charCodeAt(len);\\r\\n  return Uint8Array.from(ret);\\r\\n}\",\n",
    "            'docstring': 'we do not need Buffer pollyfill for now'}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "texts = (\n",
    "        (examples['docstring'], examples['code'])\n",
    "    )\n",
    "result = tokenizer(*texts, padding=\"max_length\", max_length=512, truncation=True, return_tensors= 'pt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "512\n"
     ]
    }
   ],
   "source": [
    "tokenizer.decode(result['input_ids'])\n",
    "print(len(result['input_ids']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "input = \"\"\"we do not need Buffer pollyfill for now</s></s>function(str){\\r\\n  var ret = new Array(str.length), len = str.length;\\r\\n  while(len--) ret[len] = str.charCodeAt(len);\\r\\n  return Uint8Array.from(ret);\\r\\n}\"\"\"\n",
    "rs_2 = tokenizer(input, padding=\"max_length\", max_length=512, truncation=True, return_tensors= 'pt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SequenceClassifierOutput(loss=None, logits=tensor([[ 0.2598, -0.2636]], grad_fn=<AddmmBackward0>), hidden_states=None, attentions=None)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model(**rs_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline\n",
    "import torch\n",
    "device = 0 if torch.cuda.is_available() else -1\n",
    "pipeline = pipeline(\"text-classification\", model=model, tokenizer=tokenizer, device=device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[{'label': 'Inconsistency', 'score': 0.5601343512535095}]\n"
     ]
    }
   ],
   "source": [
    "inputs = \"\"\"we do not need Buffer pollyfill for now</s></s>function(str){\n",
    "  var ret = new Array(str.length), len = str.length;\n",
    "  while(len--) ret[len] = str.charCodeAt(len);\n",
    "  return Uint8Array.from(ret);\n",
    "}\"\"\"\n",
    "prediction = pipeline(inputs)\n",
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "namlh31",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}