added fintuned for GPT3

.gitignore

@@ -1 +1,2 @@
-keys.py 
+keys.py 
+wiki_gpt/

data/AI_checker_gpt3_remade.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eced73bd37592d7e9b002fc695eff3608be967847e298090e2275cc59b70523a
+size 548390

data/original_data_gpt3.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd7b35d2e5f88acf8b3bf35f49c6851031707a13427bed3096b2022195eee69
+size 5060493

gpt3_finetuned_model/checkpoint-15024/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

gpt3_finetuned_model/checkpoint-15024/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "models/trained_model_v11",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 30522
+}

gpt3_finetuned_model/checkpoint-15024/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e1f6afa4c90e8a4bcccdfc4cce96d793ef0a8c1877fb2248f6c82ff12d912c
+size 535727290

gpt3_finetuned_model/checkpoint-15024/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093e71706112c59b9e886af85797cd68cbeaf9414453c54b69c5c195a37da325
+size 267855978

gpt3_finetuned_model/checkpoint-15024/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a0a11db4223dccc3415193638186a90b52f9f914b3b51fd8ffdbd3c713e739
+size 1064

gpt3_finetuned_model/checkpoint-15024/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

gpt3_finetuned_model/checkpoint-15024/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

gpt3_finetuned_model/checkpoint-15024/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": 0.021361960098147392,
+  "best_model_checkpoint": "gpt3_finetuned_model/checkpoint-15024",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 15024,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.966719914802982e-05,
+      "loss": 0.0219,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.933439829605964e-05,
+      "loss": 0.012,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.900159744408946e-05,
+      "loss": 0.0141,
+      "step": 1500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.866879659211928e-05,
+      "loss": 0.0096,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8335995740149097e-05,
+      "loss": 0.0135,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8003194888178915e-05,
+      "loss": 0.021,
+      "step": 3000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7670394036208734e-05,
+      "loss": 0.0125,
+      "step": 3500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7337593184238552e-05,
+      "loss": 0.0084,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.700479233226837e-05,
+      "loss": 0.0128,
+      "step": 4500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6671991480298192e-05,
+      "loss": 0.0142,
+      "step": 5000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.633919062832801e-05,
+      "loss": 0.0143,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.600638977635783e-05,
+      "loss": 0.0087,
+      "step": 6000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.5673588924387647e-05,
+      "loss": 0.0085,
+      "step": 6500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.5340788072417466e-05,
+      "loss": 0.0122,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5007987220447286e-05,
+      "loss": 0.0126,
+      "step": 7500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4675186368477104e-05,
+      "loss": 0.014,
+      "step": 8000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.4342385516506923e-05,
+      "loss": 0.0086,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4009584664536741e-05,
+      "loss": 0.0094,
+      "step": 9000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.3676783812566561e-05,
+      "loss": 0.0136,
+      "step": 9500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.334398296059638e-05,
+      "loss": 0.0057,
+      "step": 10000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.30111821086262e-05,
+      "loss": 0.0126,
+      "step": 10500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.2678381256656018e-05,
+      "loss": 0.013,
+      "step": 11000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.2345580404685838e-05,
+      "loss": 0.0096,
+      "step": 11500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2012779552715656e-05,
+      "loss": 0.0068,
+      "step": 12000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.1679978700745476e-05,
+      "loss": 0.0057,
+      "step": 12500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1347177848775295e-05,
+      "loss": 0.0062,
+      "step": 13000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1014376996805112e-05,
+      "loss": 0.0138,
+      "step": 13500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0681576144834932e-05,
+      "loss": 0.007,
+      "step": 14000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.034877529286475e-05,
+      "loss": 0.0054,
+      "step": 14500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0015974440894568e-05,
+      "loss": 0.0061,
+      "step": 15000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9955404685835996,
+      "eval_loss": 0.021361960098147392,
+      "eval_runtime": 198.8868,
+      "eval_samples_per_second": 302.162,
+      "eval_steps_per_second": 18.885,
+      "step": 15024
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 30048,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2.288794378322357e+16,
+  "trial_name": null,
+  "trial_params": null
+}

gpt3_finetuned_model/checkpoint-15024/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723d5cdbe3a4ea51b735c6cbdf8a9dcb0dafce1461aeb999cf821459dd7890f8
+size 4536

research/02_dl_Ai_checker.ipynb

@@ -11,32 +11,42 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/ubuntu/SentenceStructureComparision/venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "from datasets import Dataset, load_dataset"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Downloading readme: 100%|██████████| 2.63k/2.63k [00:00<00:00, 19.4MB/s]\n",
-      "Downloading data: 100%|██████████| 127M/127M [00:04<00:00, 30.3MB/s]\n",
-      "Downloading data files: 100%|██████████| 1/1 [00:04<00:00,  4.21s/it]\n",
-      "Extracting data files: 100%|██████████| 1/1 [00:02<00:00,  2.09s/it]\n",
-      "Generating train split: 150000 examples [00:04, 30015.64 examples/s]\n"
+      "Downloading readme: 100%|██████████| 2.45k/2.45k [00:00<00:00, 14.5MB/s]\n",
+      "Downloading data: 100%|██████████| 2.56M/2.56M [00:00<00:00, 4.77MB/s]\n",
+      "Downloading data files: 100%|██████████| 1/1 [00:00<00:00,  1.84it/s]\n",
+      "Extracting data files: 100%|██████████| 1/1 [00:00<00:00, 603.06it/s]\n",
+      "Generating evaluation split: 100%|██████████| 238/238 [00:00<00:00, 4242.81 examples/s]\n"
      ]
     }
    ],
    "source": [
-    "dataset_name= \"aadityaubhat/GPT-wiki-intro\"\n",
+    "# dataset_name= \"aadityaubhat/GPT-wiki-intro\"\n",
+    "dataset_name= \"potsawee/wiki_bio_gpt3_hallucination\"\n",
     "\n",
     "\n",
     "\n",
@@ -45,21 +55,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "DatasetDict({\n",
-       "    train: Dataset({\n",
-       "        features: ['id', 'url', 'title', 'wiki_intro', 'generated_intro', 'title_len', 'wiki_intro_len', 'generated_intro_len', 'prompt', 'generated_text', 'prompt_tokens', 'generated_text_tokens'],\n",
-       "        num_rows: 150000\n",
+       "    evaluation: Dataset({\n",
+       "        features: ['gpt3_text', 'wiki_bio_text', 'gpt3_sentences', 'annotation', 'wiki_bio_test_idx', 'gpt3_text_samples'],\n",
+       "        num_rows: 238\n",
        "    })\n",
        "})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -70,29 +80,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Creating CSV from Arrow format: 100%|██████████| 150/150 [00:08<00:00, 18.69ba/s]\n"
+      "Creating CSV from Arrow format: 100%|██████████| 1/1 [00:00<00:00,  5.62ba/s]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "443537732"
+       "5060493"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "dataset['train'].to_csv(\"data/original_data.csv\")"
+    "dataset['evaluation'].to_csv(\"data/original_data_gpt3.csv\")"
    ]
   },
   {

research/04_distilbert_for_classification.ipynb

@@ -726,10 +726,11 @@
     }
    ],
    "source": [
+    "tokenizer.save_pretrained(\"models/tokenizer_v1\")\n",
     "model.save_pretrained(\"models/trained_model_v1\")\n",
+    "\n",
     "tokenizer.save_pretrained(\"models/trained_model_v11\")\n",
-    "model.save_pretrained(\"models/trained_model_v11\")\n",
-    "tokenizer.save_pretrained(\"models/tokenizer_v1\")"
+    "model.save_pretrained(\"models/trained_model_v11\")"
    ]
   },
   {

research/05_creating_data_using_gpt3.ipynb

@@ -0,0 +1,411 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os; os.chdir('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>url</th>\n",
+       "      <th>title</th>\n",
+       "      <th>wiki_intro</th>\n",
+       "      <th>generated_intro</th>\n",
+       "      <th>title_len</th>\n",
+       "      <th>wiki_intro_len</th>\n",
+       "      <th>generated_intro_len</th>\n",
+       "      <th>prompt</th>\n",
+       "      <th>generated_text</th>\n",
+       "      <th>prompt_tokens</th>\n",
+       "      <th>generated_text_tokens</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>63064638</td>\n",
+       "      <td>https://en.wikipedia.org/wiki/Sexhow%20railway...</td>\n",
+       "      <td>Sexhow railway station</td>\n",
+       "      <td>Sexhow railway station was a railway station b...</td>\n",
+       "      <td>Sexhow railway station was a railway station l...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>174</td>\n",
+       "      <td>78</td>\n",
+       "      <td>200 word wikipedia style introduction on 'Sexh...</td>\n",
+       "      <td>located in the town of Sexhow, on the Cumbria...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>88</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>279621</td>\n",
+       "      <td>https://en.wikipedia.org/wiki/Eti%C3%A4inen</td>\n",
+       "      <td>Etiäinen</td>\n",
+       "      <td>In Finnish folklore, all places and things, an...</td>\n",
+       "      <td>In Finnish folklore, all places and things, an...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>187</td>\n",
+       "      <td>80</td>\n",
+       "      <td>200 word wikipedia style introduction on 'Etiä...</td>\n",
+       "      <td>animate or inanimate, have a spirit or \"etiäi...</td>\n",
+       "      <td>26</td>\n",
+       "      <td>101</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>287229</td>\n",
+       "      <td>https://en.wikipedia.org/wiki/Inverse%20functi...</td>\n",
+       "      <td>Inverse function theorem</td>\n",
+       "      <td>In mathematics, specifically differential calc...</td>\n",
+       "      <td>In mathematics, specifically differential calc...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>170</td>\n",
+       "      <td>59</td>\n",
+       "      <td>200 word wikipedia style introduction on 'Inve...</td>\n",
+       "      <td>function theorem states that for every real-v...</td>\n",
+       "      <td>26</td>\n",
+       "      <td>65</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>26712375</td>\n",
+       "      <td>https://en.wikipedia.org/wiki/Stepping%20on%20...</td>\n",
+       "      <td>Stepping on Roses</td>\n",
+       "      <td>is a Japanese shōjo manga series written and i...</td>\n",
+       "      <td>is a Japanese shōjo manga series written and i...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>335</td>\n",
+       "      <td>121</td>\n",
+       "      <td>200 word wikipedia style introduction on 'Step...</td>\n",
+       "      <td>and illustrated by Maki Fujii. The series fol...</td>\n",
+       "      <td>26</td>\n",
+       "      <td>150</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>38894426</td>\n",
+       "      <td>https://en.wikipedia.org/wiki/Rob%20Bradley</td>\n",
+       "      <td>Rob Bradley</td>\n",
+       "      <td>Robert Milner \"Rob\" Bradley, Jr. (born August ...</td>\n",
+       "      <td>Robert Milner \"Rob\" Bradley, Jr. (born August ...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>170</td>\n",
+       "      <td>136</td>\n",
+       "      <td>200 word wikipedia style introduction on 'Rob ...</td>\n",
+       "      <td>29, 1973) is an American former professional ...</td>\n",
+       "      <td>28</td>\n",
+       "      <td>162</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         id                                                url  \\\n",
+       "0  63064638  https://en.wikipedia.org/wiki/Sexhow%20railway...   \n",
+       "1    279621        https://en.wikipedia.org/wiki/Eti%C3%A4inen   \n",
+       "2    287229  https://en.wikipedia.org/wiki/Inverse%20functi...   \n",
+       "3  26712375  https://en.wikipedia.org/wiki/Stepping%20on%20...   \n",
+       "4  38894426        https://en.wikipedia.org/wiki/Rob%20Bradley   \n",
+       "\n",
+       "                      title  \\\n",
+       "0    Sexhow railway station   \n",
+       "1                  Etiäinen   \n",
+       "2  Inverse function theorem   \n",
+       "3         Stepping on Roses   \n",
+       "4               Rob Bradley   \n",
+       "\n",
+       "                                          wiki_intro  \\\n",
+       "0  Sexhow railway station was a railway station b...   \n",
+       "1  In Finnish folklore, all places and things, an...   \n",
+       "2  In mathematics, specifically differential calc...   \n",
+       "3  is a Japanese shōjo manga series written and i...   \n",
+       "4  Robert Milner \"Rob\" Bradley, Jr. (born August ...   \n",
+       "\n",
+       "                                     generated_intro  title_len  \\\n",
+       "0  Sexhow railway station was a railway station l...          3   \n",
+       "1  In Finnish folklore, all places and things, an...          1   \n",
+       "2  In mathematics, specifically differential calc...          3   \n",
+       "3  is a Japanese shōjo manga series written and i...          3   \n",
+       "4  Robert Milner \"Rob\" Bradley, Jr. (born August ...          2   \n",
+       "\n",
+       "   wiki_intro_len  generated_intro_len  \\\n",
+       "0             174                   78   \n",
+       "1             187                   80   \n",
+       "2             170                   59   \n",
+       "3             335                  121   \n",
+       "4             170                  136   \n",
+       "\n",
+       "                                              prompt  \\\n",
+       "0  200 word wikipedia style introduction on 'Sexh...   \n",
+       "1  200 word wikipedia style introduction on 'Etiä...   \n",
+       "2  200 word wikipedia style introduction on 'Inve...   \n",
+       "3  200 word wikipedia style introduction on 'Step...   \n",
+       "4  200 word wikipedia style introduction on 'Rob ...   \n",
+       "\n",
+       "                                      generated_text  prompt_tokens  \\\n",
+       "0   located in the town of Sexhow, on the Cumbria...             25   \n",
+       "1   animate or inanimate, have a spirit or \"etiäi...             26   \n",
+       "2   function theorem states that for every real-v...             26   \n",
+       "3   and illustrated by Maki Fujii. The series fol...             26   \n",
+       "4   29, 1973) is an American former professional ...             28   \n",
+       "\n",
+       "   generated_text_tokens  \n",
+       "0                     88  \n",
+       "1                    101  \n",
+       "2                     65  \n",
+       "3                    150  \n",
+       "4                    162  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "original_df= pd.read_csv(\"data/original_data.csv\")\n",
+    "original_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([\"200 word wikipedia style introduction on 'Sexhow railway station'\\n    Sexhow railway station was a railway station\",\n",
+       "       \"200 word wikipedia style introduction on 'Etiäinen'\\n    In Finnish folklore, all places and things,\",\n",
+       "       \"200 word wikipedia style introduction on 'Inverse function theorem'\\n    In mathematics, specifically differential calculus, the inverse\",\n",
+       "       \"200 word wikipedia style introduction on 'Stepping on Roses'\\n    is a Japanese shōjo manga series written\"],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "original_df.prompt.values[:4]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import re\n",
+    "import openai\n",
+    "from keys import OPENAI_API_KEY\n",
+    "import dask"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai.api_key = OPENAI_API_KEY\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_openai_response(prompt:str): \n",
+    "    startertext= prompt.split(\"\\n\")[-1]\n",
+    "    \n",
+    "    response=  openai.Completion.create(\n",
+    "        model=\"gpt-3.5-turbo-instruct\",\n",
+    "        prompt=prompt,\n",
+    "        temperature=0.7,\n",
+    "        max_tokens=300,\n",
+    "        top_p=1,\n",
+    "        frequency_penalty=0.4,\n",
+    "        presence_penalty=0.1\n",
+    "    )\n",
+    "    \n",
+    "    return startertext.strip()+ response.choices[0].text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"200 word wikipedia style introduction on 'Sexhow railway station'\\n    Sexhow railway station was a railway station\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "original_df.prompt[0]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "response= get_openai_response(original_df.prompt[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Sexhow railway station was a railway station located in the small village of Sexhow, North Yorkshire, England. It was a small station on the Middlesbrough to Whitby branch line, which opened in 1865. The station served as a vital link for the local community, providing access to nearby towns and cities. The station had two platforms and a small waiting room for passengers. In its early years, it was primarily used for transporting agricultural goods and livestock. However, with the rise of tourism in the area, the station became an important stop for tourists visiting the North Yorkshire Moors National Park and the nearby coastal town of Whitby. Despite its small size and rural location, Sexhow railway station played an important role in connecting the local community to the rest of England. Unfortunately, due to declining usage and financial difficulties, the station was closed in 1960 and has since been demolished. Today, only remnants of its platforms can be seen, serving as a reminder of its once important role in the region's transportation network.\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32m/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb Cell 11\u001b[0m line \u001b[0;36m1\n\u001b[0;32m----> <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=0'>1</a>\u001b[0m original_df[\u001b[39m'\u001b[39m\u001b[39mgenerated_intro_gpt3\u001b[39m\u001b[39m'\u001b[39m]\u001b[39m=\u001b[39m original_df\u001b[39m.\u001b[39;49mgenerated_intro\u001b[39m.\u001b[39;49mapply(get_openai_response)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/pandas/core/series.py:4760\u001b[0m, in \u001b[0;36mSeries.apply\u001b[0;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[1;32m   4625\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mapply\u001b[39m(\n\u001b[1;32m   4626\u001b[0m     \u001b[39mself\u001b[39m,\n\u001b[1;32m   4627\u001b[0m     func: AggFuncType,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   4632\u001b[0m     \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs,\n\u001b[1;32m   4633\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m DataFrame \u001b[39m|\u001b[39m Series:\n\u001b[1;32m   4634\u001b[0m \u001b[39m    \u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m   4635\u001b[0m \u001b[39m    Invoke function on values of Series.\u001b[39;00m\n\u001b[1;32m   4636\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   4751\u001b[0m \u001b[39m    dtype: float64\u001b[39;00m\n\u001b[1;32m   4752\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[1;32m   4753\u001b[0m     \u001b[39mreturn\u001b[39;00m SeriesApply(\n\u001b[1;32m   4754\u001b[0m         \u001b[39mself\u001b[39;49m,\n\u001b[1;32m   4755\u001b[0m         func,\n\u001b[1;32m   4756\u001b[0m         convert_dtype\u001b[39m=\u001b[39;49mconvert_dtype,\n\u001b[1;32m   4757\u001b[0m         by_row\u001b[39m=\u001b[39;49mby_row,\n\u001b[1;32m   4758\u001b[0m         args\u001b[39m=\u001b[39;49margs,\n\u001b[1;32m   4759\u001b[0m         kwargs\u001b[39m=\u001b[39;49mkwargs,\n\u001b[0;32m-> 4760\u001b[0m     )\u001b[39m.\u001b[39;49mapply()\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/pandas/core/apply.py:1207\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1204\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mapply_compat()\n\u001b[1;32m   1206\u001b[0m \u001b[39m# self.func is Callable\u001b[39;00m\n\u001b[0;32m-> 1207\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mapply_standard()\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/pandas/core/apply.py:1287\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1281\u001b[0m \u001b[39m# row-wise access\u001b[39;00m\n\u001b[1;32m   1282\u001b[0m \u001b[39m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[1;32m   1283\u001b[0m \u001b[39m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[1;32m   1284\u001b[0m \u001b[39m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[1;32m   1285\u001b[0m \u001b[39m#  Categorical (GH51645).\u001b[39;00m\n\u001b[1;32m   1286\u001b[0m action \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mignore\u001b[39m\u001b[39m\"\u001b[39m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(obj\u001b[39m.\u001b[39mdtype, CategoricalDtype) \u001b[39melse\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[0;32m-> 1287\u001b[0m mapped \u001b[39m=\u001b[39m obj\u001b[39m.\u001b[39;49m_map_values(\n\u001b[1;32m   1288\u001b[0m     mapper\u001b[39m=\u001b[39;49mcurried, na_action\u001b[39m=\u001b[39;49maction, convert\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mconvert_dtype\n\u001b[1;32m   1289\u001b[0m )\n\u001b[1;32m   1291\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(mapped) \u001b[39mand\u001b[39;00m \u001b[39misinstance\u001b[39m(mapped[\u001b[39m0\u001b[39m], ABCSeries):\n\u001b[1;32m   1292\u001b[0m     \u001b[39m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[1;32m   1293\u001b[0m     \u001b[39m#  See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[1;32m   1294\u001b[0m     \u001b[39mreturn\u001b[39;00m obj\u001b[39m.\u001b[39m_constructor_expanddim(\u001b[39mlist\u001b[39m(mapped), index\u001b[39m=\u001b[39mobj\u001b[39m.\u001b[39mindex)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/pandas/core/base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[0;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m    918\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[1;32m    919\u001b[0m     \u001b[39mreturn\u001b[39;00m arr\u001b[39m.\u001b[39mmap(mapper, na_action\u001b[39m=\u001b[39mna_action)\n\u001b[0;32m--> 921\u001b[0m \u001b[39mreturn\u001b[39;00m algorithms\u001b[39m.\u001b[39;49mmap_array(arr, mapper, na_action\u001b[39m=\u001b[39;49mna_action, convert\u001b[39m=\u001b[39;49mconvert)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/pandas/core/algorithms.py:1814\u001b[0m, in \u001b[0;36mmap_array\u001b[0;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[1;32m   1812\u001b[0m values \u001b[39m=\u001b[39m arr\u001b[39m.\u001b[39mastype(\u001b[39mobject\u001b[39m, copy\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[1;32m   1813\u001b[0m \u001b[39mif\u001b[39;00m na_action \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m-> 1814\u001b[0m     \u001b[39mreturn\u001b[39;00m lib\u001b[39m.\u001b[39;49mmap_infer(values, mapper, convert\u001b[39m=\u001b[39;49mconvert)\n\u001b[1;32m   1815\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m   1816\u001b[0m     \u001b[39mreturn\u001b[39;00m lib\u001b[39m.\u001b[39mmap_infer_mask(\n\u001b[1;32m   1817\u001b[0m         values, mapper, mask\u001b[39m=\u001b[39misna(values)\u001b[39m.\u001b[39mview(np\u001b[39m.\u001b[39muint8), convert\u001b[39m=\u001b[39mconvert\n\u001b[1;32m   1818\u001b[0m     )\n",
+      "File \u001b[0;32mlib.pyx:2917\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n",
+      "\u001b[1;32m/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb Cell 11\u001b[0m line \u001b[0;36m4\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mget_openai_response\u001b[39m(prompt:\u001b[39mstr\u001b[39m): \n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=1'>2</a>\u001b[0m     startertext\u001b[39m=\u001b[39m prompt\u001b[39m.\u001b[39msplit(\u001b[39m\"\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m\"\u001b[39m)[\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m]\n\u001b[0;32m----> <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=3'>4</a>\u001b[0m     response\u001b[39m=\u001b[39m  openai\u001b[39m.\u001b[39;49mCompletion\u001b[39m.\u001b[39;49mcreate(\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=4'>5</a>\u001b[0m         model\u001b[39m=\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39mgpt-3.5-turbo-instruct\u001b[39;49m\u001b[39m\"\u001b[39;49m,\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=5'>6</a>\u001b[0m         prompt\u001b[39m=\u001b[39;49mprompt,\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=6'>7</a>\u001b[0m         temperature\u001b[39m=\u001b[39;49m\u001b[39m0.7\u001b[39;49m,\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=7'>8</a>\u001b[0m         max_tokens\u001b[39m=\u001b[39;49m\u001b[39m300\u001b[39;49m,\n\u001b[1;32m      <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=8'>9</a>\u001b[0m         top_p\u001b[39m=\u001b[39;49m\u001b[39m1\u001b[39;49m,\n\u001b[1;32m     <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=9'>10</a>\u001b[0m         frequency_penalty\u001b[39m=\u001b[39;49m\u001b[39m0.4\u001b[39;49m,\n\u001b[1;32m     <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=10'>11</a>\u001b[0m         presence_penalty\u001b[39m=\u001b[39;49m\u001b[39m0.1\u001b[39;49m\n\u001b[1;32m     <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=11'>12</a>\u001b[0m     )\n\u001b[1;32m     <a href='vscode-notebook-cell://ssh-remote%2B7b22686f73744e616d65223a22456d62656464696e6773227d/home/ubuntu/SentenceStructureComparision/research/05_creating_data_using_gpt3.ipynb#X14sdnNjb2RlLXJlbW90ZQ%3D%3D?line=13'>14</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m startertext\u001b[39m.\u001b[39mstrip()\u001b[39m+\u001b[39m response\u001b[39m.\u001b[39mchoices[\u001b[39m0\u001b[39m]\u001b[39m.\u001b[39mtext\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/openai/api_resources/completion.py:25\u001b[0m, in \u001b[0;36mCompletion.create\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m     23\u001b[0m \u001b[39mwhile\u001b[39;00m \u001b[39mTrue\u001b[39;00m:\n\u001b[1;32m     24\u001b[0m     \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m---> 25\u001b[0m         \u001b[39mreturn\u001b[39;00m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49mcreate(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m     26\u001b[0m     \u001b[39mexcept\u001b[39;00m TryAgain \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m     27\u001b[0m         \u001b[39mif\u001b[39;00m timeout \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m time\u001b[39m.\u001b[39mtime() \u001b[39m>\u001b[39m start \u001b[39m+\u001b[39m timeout:\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py:155\u001b[0m, in \u001b[0;36mEngineAPIResource.create\u001b[0;34m(cls, api_key, api_base, api_type, request_id, api_version, organization, **params)\u001b[0m\n\u001b[1;32m    129\u001b[0m \u001b[39m@classmethod\u001b[39m\n\u001b[1;32m    130\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mcreate\u001b[39m(\n\u001b[1;32m    131\u001b[0m     \u001b[39mcls\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    138\u001b[0m     \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mparams,\n\u001b[1;32m    139\u001b[0m ):\n\u001b[1;32m    140\u001b[0m     (\n\u001b[1;32m    141\u001b[0m         deployment_id,\n\u001b[1;32m    142\u001b[0m         engine,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    152\u001b[0m         api_key, api_base, api_type, api_version, organization, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mparams\n\u001b[1;32m    153\u001b[0m     )\n\u001b[0;32m--> 155\u001b[0m     response, _, api_key \u001b[39m=\u001b[39m requestor\u001b[39m.\u001b[39;49mrequest(\n\u001b[1;32m    156\u001b[0m         \u001b[39m\"\u001b[39;49m\u001b[39mpost\u001b[39;49m\u001b[39m\"\u001b[39;49m,\n\u001b[1;32m    157\u001b[0m         url,\n\u001b[1;32m    158\u001b[0m         params\u001b[39m=\u001b[39;49mparams,\n\u001b[1;32m    159\u001b[0m         headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[1;32m    160\u001b[0m         stream\u001b[39m=\u001b[39;49mstream,\n\u001b[1;32m    161\u001b[0m         request_id\u001b[39m=\u001b[39;49mrequest_id,\n\u001b[1;32m    162\u001b[0m         request_timeout\u001b[39m=\u001b[39;49mrequest_timeout,\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     \u001b[39mif\u001b[39;00m stream:\n\u001b[1;32m    166\u001b[0m         \u001b[39m# must be an iterator\u001b[39;00m\n\u001b[1;32m    167\u001b[0m         \u001b[39massert\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(response, OpenAIResponse)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/openai/api_requestor.py:289\u001b[0m, in \u001b[0;36mAPIRequestor.request\u001b[0;34m(self, method, url, params, headers, files, stream, request_id, request_timeout)\u001b[0m\n\u001b[1;32m    278\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mrequest\u001b[39m(\n\u001b[1;32m    279\u001b[0m     \u001b[39mself\u001b[39m,\n\u001b[1;32m    280\u001b[0m     method,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    287\u001b[0m     request_timeout: Optional[Union[\u001b[39mfloat\u001b[39m, Tuple[\u001b[39mfloat\u001b[39m, \u001b[39mfloat\u001b[39m]]] \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m,\n\u001b[1;32m    288\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m Tuple[Union[OpenAIResponse, Iterator[OpenAIResponse]], \u001b[39mbool\u001b[39m, \u001b[39mstr\u001b[39m]:\n\u001b[0;32m--> 289\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrequest_raw(\n\u001b[1;32m    290\u001b[0m         method\u001b[39m.\u001b[39;49mlower(),\n\u001b[1;32m    291\u001b[0m         url,\n\u001b[1;32m    292\u001b[0m         params\u001b[39m=\u001b[39;49mparams,\n\u001b[1;32m    293\u001b[0m         supplied_headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[1;32m    294\u001b[0m         files\u001b[39m=\u001b[39;49mfiles,\n\u001b[1;32m    295\u001b[0m         stream\u001b[39m=\u001b[39;49mstream,\n\u001b[1;32m    296\u001b[0m         request_id\u001b[39m=\u001b[39;49mrequest_id,\n\u001b[1;32m    297\u001b[0m         request_timeout\u001b[39m=\u001b[39;49mrequest_timeout,\n\u001b[1;32m    298\u001b[0m     )\n\u001b[1;32m    299\u001b[0m     resp, got_stream \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_interpret_response(result, stream)\n\u001b[1;32m    300\u001b[0m     \u001b[39mreturn\u001b[39;00m resp, got_stream, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mapi_key\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/openai/api_requestor.py:606\u001b[0m, in \u001b[0;36mAPIRequestor.request_raw\u001b[0;34m(self, method, url, params, supplied_headers, files, stream, request_id, request_timeout)\u001b[0m\n\u001b[1;32m    604\u001b[0m     _thread_context\u001b[39m.\u001b[39msession_create_time \u001b[39m=\u001b[39m time\u001b[39m.\u001b[39mtime()\n\u001b[1;32m    605\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> 606\u001b[0m     result \u001b[39m=\u001b[39m _thread_context\u001b[39m.\u001b[39;49msession\u001b[39m.\u001b[39;49mrequest(\n\u001b[1;32m    607\u001b[0m         method,\n\u001b[1;32m    608\u001b[0m         abs_url,\n\u001b[1;32m    609\u001b[0m         headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[1;32m    610\u001b[0m         data\u001b[39m=\u001b[39;49mdata,\n\u001b[1;32m    611\u001b[0m         files\u001b[39m=\u001b[39;49mfiles,\n\u001b[1;32m    612\u001b[0m         stream\u001b[39m=\u001b[39;49mstream,\n\u001b[1;32m    613\u001b[0m         timeout\u001b[39m=\u001b[39;49mrequest_timeout \u001b[39mif\u001b[39;49;00m request_timeout \u001b[39melse\u001b[39;49;00m TIMEOUT_SECS,\n\u001b[1;32m    614\u001b[0m         proxies\u001b[39m=\u001b[39;49m_thread_context\u001b[39m.\u001b[39;49msession\u001b[39m.\u001b[39;49mproxies,\n\u001b[1;32m    615\u001b[0m     )\n\u001b[1;32m    616\u001b[0m \u001b[39mexcept\u001b[39;00m requests\u001b[39m.\u001b[39mexceptions\u001b[39m.\u001b[39mTimeout \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m    617\u001b[0m     \u001b[39mraise\u001b[39;00m error\u001b[39m.\u001b[39mTimeout(\u001b[39m\"\u001b[39m\u001b[39mRequest timed out: \u001b[39m\u001b[39m{}\u001b[39;00m\u001b[39m\"\u001b[39m\u001b[39m.\u001b[39mformat(e)) \u001b[39mfrom\u001b[39;00m \u001b[39me\u001b[39;00m\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/requests/sessions.py:589\u001b[0m, in \u001b[0;36mSession.request\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m    584\u001b[0m send_kwargs \u001b[39m=\u001b[39m {\n\u001b[1;32m    585\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mtimeout\u001b[39m\u001b[39m\"\u001b[39m: timeout,\n\u001b[1;32m    586\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mallow_redirects\u001b[39m\u001b[39m\"\u001b[39m: allow_redirects,\n\u001b[1;32m    587\u001b[0m }\n\u001b[1;32m    588\u001b[0m send_kwargs\u001b[39m.\u001b[39mupdate(settings)\n\u001b[0;32m--> 589\u001b[0m resp \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msend(prep, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49msend_kwargs)\n\u001b[1;32m    591\u001b[0m \u001b[39mreturn\u001b[39;00m resp\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/requests/sessions.py:703\u001b[0m, in \u001b[0;36mSession.send\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m    700\u001b[0m start \u001b[39m=\u001b[39m preferred_clock()\n\u001b[1;32m    702\u001b[0m \u001b[39m# Send the request\u001b[39;00m\n\u001b[0;32m--> 703\u001b[0m r \u001b[39m=\u001b[39m adapter\u001b[39m.\u001b[39;49msend(request, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m    705\u001b[0m \u001b[39m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[1;32m    706\u001b[0m elapsed \u001b[39m=\u001b[39m preferred_clock() \u001b[39m-\u001b[39m start\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/requests/adapters.py:486\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m    483\u001b[0m     timeout \u001b[39m=\u001b[39m TimeoutSauce(connect\u001b[39m=\u001b[39mtimeout, read\u001b[39m=\u001b[39mtimeout)\n\u001b[1;32m    485\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> 486\u001b[0m     resp \u001b[39m=\u001b[39m conn\u001b[39m.\u001b[39;49murlopen(\n\u001b[1;32m    487\u001b[0m         method\u001b[39m=\u001b[39;49mrequest\u001b[39m.\u001b[39;49mmethod,\n\u001b[1;32m    488\u001b[0m         url\u001b[39m=\u001b[39;49murl,\n\u001b[1;32m    489\u001b[0m         body\u001b[39m=\u001b[39;49mrequest\u001b[39m.\u001b[39;49mbody,\n\u001b[1;32m    490\u001b[0m         headers\u001b[39m=\u001b[39;49mrequest\u001b[39m.\u001b[39;49mheaders,\n\u001b[1;32m    491\u001b[0m         redirect\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[1;32m    492\u001b[0m         assert_same_host\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[1;32m    493\u001b[0m         preload_content\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[1;32m    494\u001b[0m         decode_content\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[1;32m    495\u001b[0m         retries\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmax_retries,\n\u001b[1;32m    496\u001b[0m         timeout\u001b[39m=\u001b[39;49mtimeout,\n\u001b[1;32m    497\u001b[0m         chunked\u001b[39m=\u001b[39;49mchunked,\n\u001b[1;32m    498\u001b[0m     )\n\u001b[1;32m    500\u001b[0m \u001b[39mexcept\u001b[39;00m (ProtocolError, \u001b[39mOSError\u001b[39;00m) \u001b[39mas\u001b[39;00m err:\n\u001b[1;32m    501\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mConnectionError\u001b[39;00m(err, request\u001b[39m=\u001b[39mrequest)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/urllib3/connectionpool.py:790\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[0m\n\u001b[1;32m    787\u001b[0m response_conn \u001b[39m=\u001b[39m conn \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m release_conn \u001b[39melse\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m    789\u001b[0m \u001b[39m# Make the request on the HTTPConnection object\u001b[39;00m\n\u001b[0;32m--> 790\u001b[0m response \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_make_request(\n\u001b[1;32m    791\u001b[0m     conn,\n\u001b[1;32m    792\u001b[0m     method,\n\u001b[1;32m    793\u001b[0m     url,\n\u001b[1;32m    794\u001b[0m     timeout\u001b[39m=\u001b[39;49mtimeout_obj,\n\u001b[1;32m    795\u001b[0m     body\u001b[39m=\u001b[39;49mbody,\n\u001b[1;32m    796\u001b[0m     headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[1;32m    797\u001b[0m     chunked\u001b[39m=\u001b[39;49mchunked,\n\u001b[1;32m    798\u001b[0m     retries\u001b[39m=\u001b[39;49mretries,\n\u001b[1;32m    799\u001b[0m     response_conn\u001b[39m=\u001b[39;49mresponse_conn,\n\u001b[1;32m    800\u001b[0m     preload_content\u001b[39m=\u001b[39;49mpreload_content,\n\u001b[1;32m    801\u001b[0m     decode_content\u001b[39m=\u001b[39;49mdecode_content,\n\u001b[1;32m    802\u001b[0m     \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mresponse_kw,\n\u001b[1;32m    803\u001b[0m )\n\u001b[1;32m    805\u001b[0m \u001b[39m# Everything went great!\u001b[39;00m\n\u001b[1;32m    806\u001b[0m clean_exit \u001b[39m=\u001b[39m \u001b[39mTrue\u001b[39;00m\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/urllib3/connectionpool.py:536\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[0;34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[0m\n\u001b[1;32m    534\u001b[0m \u001b[39m# Receive the response from the server\u001b[39;00m\n\u001b[1;32m    535\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> 536\u001b[0m     response \u001b[39m=\u001b[39m conn\u001b[39m.\u001b[39;49mgetresponse()\n\u001b[1;32m    537\u001b[0m \u001b[39mexcept\u001b[39;00m (BaseSSLError, \u001b[39mOSError\u001b[39;00m) \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m    538\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_raise_timeout(err\u001b[39m=\u001b[39me, url\u001b[39m=\u001b[39murl, timeout_value\u001b[39m=\u001b[39mread_timeout)\n",
+      "File \u001b[0;32m~/SentenceStructureComparision/venv/lib/python3.10/site-packages/urllib3/connection.py:461\u001b[0m, in \u001b[0;36mHTTPConnection.getresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    458\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39m.\u001b[39;00m\u001b[39mresponse\u001b[39;00m \u001b[39mimport\u001b[39;00m HTTPResponse\n\u001b[1;32m    460\u001b[0m \u001b[39m# Get the response from http.client.HTTPConnection\u001b[39;00m\n\u001b[0;32m--> 461\u001b[0m httplib_response \u001b[39m=\u001b[39m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49mgetresponse()\n\u001b[1;32m    463\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m    464\u001b[0m     assert_header_parsing(httplib_response\u001b[39m.\u001b[39mmsg)\n",
+      "File \u001b[0;32m/usr/lib/python3.10/http/client.py:1375\u001b[0m, in \u001b[0;36mHTTPConnection.getresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1373\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1374\u001b[0m     \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m-> 1375\u001b[0m         response\u001b[39m.\u001b[39;49mbegin()\n\u001b[1;32m   1376\u001b[0m     \u001b[39mexcept\u001b[39;00m \u001b[39mConnectionError\u001b[39;00m:\n\u001b[1;32m   1377\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mclose()\n",
+      "File \u001b[0;32m/usr/lib/python3.10/http/client.py:318\u001b[0m, in \u001b[0;36mHTTPResponse.begin\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    316\u001b[0m \u001b[39m# read until we get a non-100 response\u001b[39;00m\n\u001b[1;32m    317\u001b[0m \u001b[39mwhile\u001b[39;00m \u001b[39mTrue\u001b[39;00m:\n\u001b[0;32m--> 318\u001b[0m     version, status, reason \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_read_status()\n\u001b[1;32m    319\u001b[0m     \u001b[39mif\u001b[39;00m status \u001b[39m!=\u001b[39m CONTINUE:\n\u001b[1;32m    320\u001b[0m         \u001b[39mbreak\u001b[39;00m\n",
+      "File \u001b[0;32m/usr/lib/python3.10/http/client.py:279\u001b[0m, in \u001b[0;36mHTTPResponse._read_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    278\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_read_status\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m--> 279\u001b[0m     line \u001b[39m=\u001b[39m \u001b[39mstr\u001b[39m(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mfp\u001b[39m.\u001b[39;49mreadline(_MAXLINE \u001b[39m+\u001b[39;49m \u001b[39m1\u001b[39;49m), \u001b[39m\"\u001b[39m\u001b[39miso-8859-1\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m    280\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(line) \u001b[39m>\u001b[39m _MAXLINE:\n\u001b[1;32m    281\u001b[0m         \u001b[39mraise\u001b[39;00m LineTooLong(\u001b[39m\"\u001b[39m\u001b[39mstatus line\u001b[39m\u001b[39m\"\u001b[39m)\n",
+      "File \u001b[0;32m/usr/lib/python3.10/socket.py:705\u001b[0m, in \u001b[0;36mSocketIO.readinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m    703\u001b[0m \u001b[39mwhile\u001b[39;00m \u001b[39mTrue\u001b[39;00m:\n\u001b[1;32m    704\u001b[0m     \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> 705\u001b[0m         \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_sock\u001b[39m.\u001b[39;49mrecv_into(b)\n\u001b[1;32m    706\u001b[0m     \u001b[39mexcept\u001b[39;00m timeout:\n\u001b[1;32m    707\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_timeout_occurred \u001b[39m=\u001b[39m \u001b[39mTrue\u001b[39;00m\n",
+      "File \u001b[0;32m/usr/lib/python3.10/ssl.py:1274\u001b[0m, in \u001b[0;36mSSLSocket.recv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m   1270\u001b[0m     \u001b[39mif\u001b[39;00m flags \u001b[39m!=\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[1;32m   1271\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m   1272\u001b[0m           \u001b[39m\"\u001b[39m\u001b[39mnon-zero flags not allowed in calls to recv_into() on \u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m\"\u001b[39m \u001b[39m%\u001b[39m\n\u001b[1;32m   1273\u001b[0m           \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m)\n\u001b[0;32m-> 1274\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mread(nbytes, buffer)\n\u001b[1;32m   1275\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m   1276\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39msuper\u001b[39m()\u001b[39m.\u001b[39mrecv_into(buffer, nbytes, flags)\n",
+      "File \u001b[0;32m/usr/lib/python3.10/ssl.py:1130\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m   1128\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1129\u001b[0m     \u001b[39mif\u001b[39;00m buffer \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m-> 1130\u001b[0m         \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_sslobj\u001b[39m.\u001b[39;49mread(\u001b[39mlen\u001b[39;49m, buffer)\n\u001b[1;32m   1131\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[1;32m   1132\u001b[0m         \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_sslobj\u001b[39m.\u001b[39mread(\u001b[39mlen\u001b[39m)\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "original_df['generated_intro_gpt3']= original_df.generated_intro.apply(get_openai_response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "original_df.to_csv(\"data/new_original_df_with_gpt3.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}