Upload 4 files

New_Retail_NLP_Project (1).ipynb

@@ -0,0 +1,1544 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "51d0f551",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: nltk in ./anaconda3/lib/python3.11/site-packages (3.8.1)\n",
+      "Requirement already satisfied: click in ./anaconda3/lib/python3.11/site-packages (from nltk) (8.0.4)\n",
+      "Requirement already satisfied: joblib in ./anaconda3/lib/python3.11/site-packages (from nltk) (1.2.0)\n",
+      "Requirement already satisfied: regex>=2021.8.3 in ./anaconda3/lib/python3.11/site-packages (from nltk) (2022.7.9)\n",
+      "Requirement already satisfied: tqdm in ./anaconda3/lib/python3.11/site-packages (from nltk) (4.65.0)\n",
+      "Requirement already satisfied: tensorflow in ./anaconda3/lib/python3.11/site-packages (2.17.0)\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (2.1.0)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (1.6.3)\n",
+      "Requirement already satisfied: flatbuffers>=24.3.25 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (24.3.25)\n",
+      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (0.6.0)\n",
+      "Requirement already satisfied: google-pasta>=0.1.1 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: h5py>=3.10.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (3.11.0)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (18.1.1)\n",
+      "Requirement already satisfied: ml-dtypes<0.5.0,>=0.3.1 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (0.4.0)\n",
+      "Requirement already satisfied: opt-einsum>=2.3.2 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (3.3.0)\n",
+      "Requirement already satisfied: packaging in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (23.1)\n",
+      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (4.25.4)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (2.31.0)\n",
+      "Requirement already satisfied: setuptools in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (68.0.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (1.16.0)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (2.4.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (4.9.0)\n",
+      "Requirement already satisfied: wrapt>=1.11.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (1.14.1)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (1.65.4)\n",
+      "Requirement already satisfied: tensorboard<2.18,>=2.17 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (2.17.0)\n",
+      "Requirement already satisfied: keras>=3.2.0 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (0.37.1)\n",
+      "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in ./anaconda3/lib/python3.11/site-packages (from tensorflow) (1.24.3)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in ./anaconda3/lib/python3.11/site-packages (from astunparse>=1.6.0->tensorflow) (0.38.4)\n",
+      "Requirement already satisfied: rich in ./anaconda3/lib/python3.11/site-packages (from keras>=3.2.0->tensorflow) (13.7.1)\n",
+      "Requirement already satisfied: namex in ./anaconda3/lib/python3.11/site-packages (from keras>=3.2.0->tensorflow) (0.0.8)\n",
+      "Requirement already satisfied: optree in ./anaconda3/lib/python3.11/site-packages (from keras>=3.2.0->tensorflow) (0.12.1)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in ./anaconda3/lib/python3.11/site-packages (from requests<3,>=2.21.0->tensorflow) (2.0.4)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in ./anaconda3/lib/python3.11/site-packages (from requests<3,>=2.21.0->tensorflow) (3.4)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in ./anaconda3/lib/python3.11/site-packages (from requests<3,>=2.21.0->tensorflow) (1.26.16)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in ./anaconda3/lib/python3.11/site-packages (from requests<3,>=2.21.0->tensorflow) (2023.7.22)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in ./anaconda3/lib/python3.11/site-packages (from tensorboard<2.18,>=2.17->tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in ./anaconda3/lib/python3.11/site-packages (from tensorboard<2.18,>=2.17->tensorflow) (0.7.2)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in ./anaconda3/lib/python3.11/site-packages (from tensorboard<2.18,>=2.17->tensorflow) (2.2.3)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in ./anaconda3/lib/python3.11/site-packages (from werkzeug>=1.0.1->tensorboard<2.18,>=2.17->tensorflow) (2.1.1)\n",
+      "Requirement already satisfied: markdown-it-py>=2.2.0 in ./anaconda3/lib/python3.11/site-packages (from rich->keras>=3.2.0->tensorflow) (2.2.0)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in ./anaconda3/lib/python3.11/site-packages (from rich->keras>=3.2.0->tensorflow) (2.15.1)\n",
+      "Requirement already satisfied: mdurl~=0.1 in ./anaconda3/lib/python3.11/site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.2.0->tensorflow) (0.1.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install nltk\n",
+    "!pip install tensorflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "16af452c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package punkt to\n",
+      "[nltk_data]     /Users/preethamreddygollapalli/nltk_data...\n",
+      "[nltk_data]   Package punkt is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import re\n",
+    "import string\n",
+    "import nltk\n",
+    "from nltk.tokenize import sent_tokenize # tries to convert paragraph to sentences\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from nltk.corpus import stopwords\n",
+    "from gensim.models import Word2Vec\n",
+    "import ast\n",
+    "import tensorflow as tf\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from keras.preprocessing.sequence import pad_sequences\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, Dropout, LSTM, Embedding\n",
+    "from tensorflow.keras.metrics import MeanAbsoluteError\n",
+    "from sklearn.metrics import r2_score\n",
+    "\n",
+    "nltk.download('punkt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "4ada6af5",
+   "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>Story Name</th>\n",
+       "      <th>Test case Acceptance criteria</th>\n",
+       "      <th>Test Steps</th>\n",
+       "      <th>Test Data</th>\n",
+       "      <th>Expected Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ACIP-247941</td>\n",
+       "      <td>Weekly Ad - tap on any product offer - tap on ...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>Email: [email protected], Albertsons= 8...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ACIP-95038</td>\n",
+       "      <td>As a PdM, I want to ensure that the L2 entry p...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ver...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>User should be able to login successfully and ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>US-41769</td>\n",
+       "      <td>As a customer, I should see age restriction me...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ent...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Your order contains age-restricted items. Some...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ACIP-237923</td>\n",
+       "      <td>Verify Banner navigation for the below banners...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>Email: [email protected], Albertsons= 8...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ACIP-234885</td>\n",
+       "      <td>Display the Meal Plans banner based on the ban...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>Email: [email protected] / any new user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Story Name                      Test case Acceptance criteria  \\\n",
+       "0  ACIP-247941  Weekly Ad - tap on any product offer - tap on ...   \n",
+       "1   ACIP-95038  As a PdM, I want to ensure that the L2 entry p...   \n",
+       "2     US-41769  As a customer, I should see age restriction me...   \n",
+       "3  ACIP-237923  Verify Banner navigation for the below banners...   \n",
+       "4  ACIP-234885  Display the Meal Plans banner based on the ban...   \n",
+       "\n",
+       "                                          Test Steps  \\\n",
+       "0  User logs into UMA application with valid user...   \n",
+       "1  Login UMA app with valid email/ mobile no. Ver...   \n",
+       "2  Login UMA app with valid email/ mobile no. Ent...   \n",
+       "3  User logs into UMA application with valid user...   \n",
+       "4  User logs into UMA application with valid user...   \n",
+       "\n",
+       "                                           Test Data  \\\n",
+       "0  Email: [email protected], Albertsons= 8...   \n",
+       "1                                                NaN   \n",
+       "2                                                NaN   \n",
+       "3  Email: [email protected], Albertsons= 8...   \n",
+       "4  Email: [email protected] / any new user...   \n",
+       "\n",
+       "                                     Expected Result  \n",
+       "0  User navigates to Home page on UMA application...  \n",
+       "1  User should be able to login successfully and ...  \n",
+       "2  Your order contains age-restricted items. Some...  \n",
+       "3  User navigates to Home page on UMA application...  \n",
+       "4  User navigates to Home page on UMA application...  "
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv(\"/Users/preethamreddygollapalli/Downloads/AI Test cases (2).csv\")\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "b74aecf9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Story Name                       object\n",
+       "Test case Acceptance criteria    object\n",
+       "Test Steps                       object\n",
+       "Test Data                        object\n",
+       "Expected Result                  object\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "1468adf1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5, 5)"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "bf818e79",
+   "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>Story Name</th>\n",
+       "      <th>Test case Acceptance criteria</th>\n",
+       "      <th>Test Steps</th>\n",
+       "      <th>Test Data</th>\n",
+       "      <th>Expected Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>3</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>5</td>\n",
+       "      <td>3</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>ACIP-247941</td>\n",
+       "      <td>Weekly Ad - tap on any product offer - tap on ...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>Email: [email protected], Albertsons= 8...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         Story Name                      Test case Acceptance criteria  \\\n",
+       "count             5                                                  5   \n",
+       "unique            5                                                  5   \n",
+       "top     ACIP-247941  Weekly Ad - tap on any product offer - tap on ...   \n",
+       "freq              1                                                  1   \n",
+       "\n",
+       "                                               Test Steps  \\\n",
+       "count                                                   5   \n",
+       "unique                                                  5   \n",
+       "top     User logs into UMA application with valid user...   \n",
+       "freq                                                    1   \n",
+       "\n",
+       "                                                Test Data  \\\n",
+       "count                                                   3   \n",
+       "unique                                                  3   \n",
+       "top     Email: [email protected], Albertsons= 8...   \n",
+       "freq                                                    1   \n",
+       "\n",
+       "                                          Expected Result  \n",
+       "count                                                   5  \n",
+       "unique                                                  5  \n",
+       "top     User navigates to Home page on UMA application...  \n",
+       "freq                                                    1  "
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "dd77a3b7",
+   "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>Test case Acceptance criteria</th>\n",
+       "      <th>Test Steps</th>\n",
+       "      <th>Expected Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Weekly Ad - tap on any product offer - tap on ...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>As a PdM, I want to ensure that the L2 entry p...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ver...</td>\n",
+       "      <td>User should be able to login successfully and ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>As a customer, I should see age restriction me...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ent...</td>\n",
+       "      <td>Your order contains age-restricted items. Some...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Verify Banner navigation for the below banners...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Display the Meal Plans banner based on the ban...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test case Acceptance criteria  \\\n",
+       "0  Weekly Ad - tap on any product offer - tap on ...   \n",
+       "1  As a PdM, I want to ensure that the L2 entry p...   \n",
+       "2  As a customer, I should see age restriction me...   \n",
+       "3  Verify Banner navigation for the below banners...   \n",
+       "4  Display the Meal Plans banner based on the ban...   \n",
+       "\n",
+       "                                          Test Steps  \\\n",
+       "0  User logs into UMA application with valid user...   \n",
+       "1  Login UMA app with valid email/ mobile no. Ver...   \n",
+       "2  Login UMA app with valid email/ mobile no. Ent...   \n",
+       "3  User logs into UMA application with valid user...   \n",
+       "4  User logs into UMA application with valid user...   \n",
+       "\n",
+       "                                     Expected Result  \n",
+       "0  User navigates to Home page on UMA application...  \n",
+       "1  User should be able to login successfully and ...  \n",
+       "2  Your order contains age-restricted items. Some...  \n",
+       "3  User navigates to Home page on UMA application...  \n",
+       "4  User navigates to Home page on UMA application...  "
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.drop(['Story Name', 'Test Data'], axis = 1)\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b775b74d",
+   "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>Test case Acceptance criteria</th>\n",
+       "      <th>Test Steps</th>\n",
+       "      <th>Expected Result</th>\n",
+       "      <th>Test_case_Acceptance_criteria</th>\n",
+       "      <th>Test_Steps</th>\n",
+       "      <th>Expected_Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Weekly Ad - tap on any product offer - tap on ...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "      <td>[Weekly, Ad, -, tap, on, any, product, offer, ...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>As a PdM, I want to ensure that the L2 entry p...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ver...</td>\n",
+       "      <td>User should be able to login successfully and ...</td>\n",
+       "      <td>[As, a, PdM,, I, want, to, ensure, that, the, ...</td>\n",
+       "      <td>[Login, UMA, app, with, valid, email/, mobile,...</td>\n",
+       "      <td>[User, should, be, able, to, login, successful...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>As a customer, I should see age restriction me...</td>\n",
+       "      <td>Login UMA app with valid email/ mobile no. Ent...</td>\n",
+       "      <td>Your order contains age-restricted items. Some...</td>\n",
+       "      <td>[As, a, customer,, I, should, see, age, restri...</td>\n",
+       "      <td>[Login, UMA, app, with, valid, email/, mobile,...</td>\n",
+       "      <td>[Your, order, contains, age-restricted, items....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Verify Banner navigation for the below banners...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "      <td>[Verify, Banner, navigation, for, the, below, ...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Display the Meal Plans banner based on the ban...</td>\n",
+       "      <td>User logs into UMA application with valid user...</td>\n",
+       "      <td>User navigates to Home page on UMA application...</td>\n",
+       "      <td>[Display, the, Meal, Plans, banner, based, on,...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test case Acceptance criteria  \\\n",
+       "0  Weekly Ad - tap on any product offer - tap on ...   \n",
+       "1  As a PdM, I want to ensure that the L2 entry p...   \n",
+       "2  As a customer, I should see age restriction me...   \n",
+       "3  Verify Banner navigation for the below banners...   \n",
+       "4  Display the Meal Plans banner based on the ban...   \n",
+       "\n",
+       "                                          Test Steps  \\\n",
+       "0  User logs into UMA application with valid user...   \n",
+       "1  Login UMA app with valid email/ mobile no. Ver...   \n",
+       "2  Login UMA app with valid email/ mobile no. Ent...   \n",
+       "3  User logs into UMA application with valid user...   \n",
+       "4  User logs into UMA application with valid user...   \n",
+       "\n",
+       "                                     Expected Result  \\\n",
+       "0  User navigates to Home page on UMA application...   \n",
+       "1  User should be able to login successfully and ...   \n",
+       "2  Your order contains age-restricted items. Some...   \n",
+       "3  User navigates to Home page on UMA application...   \n",
+       "4  User navigates to Home page on UMA application...   \n",
+       "\n",
+       "                       Test_case_Acceptance_criteria  \\\n",
+       "0  [Weekly, Ad, -, tap, on, any, product, offer, ...   \n",
+       "1  [As, a, PdM,, I, want, to, ensure, that, the, ...   \n",
+       "2  [As, a, customer,, I, should, see, age, restri...   \n",
+       "3  [Verify, Banner, navigation, for, the, below, ...   \n",
+       "4  [Display, the, Meal, Plans, banner, based, on,...   \n",
+       "\n",
+       "                                          Test_Steps  \\\n",
+       "0  [User, logs, into, UMA, application, with, val...   \n",
+       "1  [Login, UMA, app, with, valid, email/, mobile,...   \n",
+       "2  [Login, UMA, app, with, valid, email/, mobile,...   \n",
+       "3  [User, logs, into, UMA, application, with, val...   \n",
+       "4  [User, logs, into, UMA, application, with, val...   \n",
+       "\n",
+       "                                     Expected_Result  \n",
+       "0  [User, navigates, to, Home, page, on, UMA, app...  \n",
+       "1  [User, should, be, able, to, login, successful...  \n",
+       "2  [Your, order, contains, age-restricted, items....  \n",
+       "3  [User, navigates, to, Home, page, on, UMA, app...  \n",
+       "4  [User, navigates, to, Home, page, on, UMA, app...  "
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Tokenize the strings by splitting on spaces\n",
+    "df['Test_case_Acceptance_criteria'] = df['Test case Acceptance criteria'].apply(lambda x: x.split() if isinstance(x, str) else [])\n",
+    "df['Test_Steps'] = df['Test Steps'].apply(lambda x: x.split() if isinstance(x, str) else [])\n",
+    "df['Expected_Result'] = df['Expected Result'].apply(lambda x: x.split() if isinstance(x, str) else [])\n",
+    "\n",
+    "# Inspect the tokenized data\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "61e06a49",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test case Acceptance criteria    0\n",
+      "Test Steps                       0\n",
+      "Expected Result                  0\n",
+      "Test_case_Acceptance_criteria    0\n",
+      "Test_Steps                       0\n",
+      "Expected_Result                  0\n",
+      "dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df.isna().sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ca46d0a6",
+   "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>Test_case_Acceptance_criteria</th>\n",
+       "      <th>Test_Steps</th>\n",
+       "      <th>Expected_Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[Weekly, Ad, -, tap, on, any, product, offer, ...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[As, a, PdM,, I, want, to, ensure, that, the, ...</td>\n",
+       "      <td>[Login, UMA, app, with, valid, email/, mobile,...</td>\n",
+       "      <td>[User, should, be, able, to, login, successful...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[As, a, customer,, I, should, see, age, restri...</td>\n",
+       "      <td>[Login, UMA, app, with, valid, email/, mobile,...</td>\n",
+       "      <td>[Your, order, contains, age-restricted, items....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[Verify, Banner, navigation, for, the, below, ...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[Display, the, Meal, Plans, banner, based, on,...</td>\n",
+       "      <td>[User, logs, into, UMA, application, with, val...</td>\n",
+       "      <td>[User, navigates, to, Home, page, on, UMA, app...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test_case_Acceptance_criteria  \\\n",
+       "0  [Weekly, Ad, -, tap, on, any, product, offer, ...   \n",
+       "1  [As, a, PdM,, I, want, to, ensure, that, the, ...   \n",
+       "2  [As, a, customer,, I, should, see, age, restri...   \n",
+       "3  [Verify, Banner, navigation, for, the, below, ...   \n",
+       "4  [Display, the, Meal, Plans, banner, based, on,...   \n",
+       "\n",
+       "                                          Test_Steps  \\\n",
+       "0  [User, logs, into, UMA, application, with, val...   \n",
+       "1  [Login, UMA, app, with, valid, email/, mobile,...   \n",
+       "2  [Login, UMA, app, with, valid, email/, mobile,...   \n",
+       "3  [User, logs, into, UMA, application, with, val...   \n",
+       "4  [User, logs, into, UMA, application, with, val...   \n",
+       "\n",
+       "                                     Expected_Result  \n",
+       "0  [User, navigates, to, Home, page, on, UMA, app...  \n",
+       "1  [User, should, be, able, to, login, successful...  \n",
+       "2  [Your, order, contains, age-restricted, items....  \n",
+       "3  [User, navigates, to, Home, page, on, UMA, app...  \n",
+       "4  [User, navigates, to, Home, page, on, UMA, app...  "
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.drop(['Test case Acceptance criteria', 'Test Steps', 'Expected Result'], axis = 1)\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f211722a",
+   "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>Test_case_Acceptance_criteria</th>\n",
+       "      <th>Test_Steps</th>\n",
+       "      <th>Expected_Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[Weekly, Ad, -, tap, product, offer, -, tap, A...</td>\n",
+       "      <td>[User, logs, UMA, application, valid, user's, ...</td>\n",
+       "      <td>[User, navigates, Home, page, UMA, application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[PdM,, want, ensure, L2, entry, points, workin...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[User, able, login, successfully, home, page, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[customer,, see, age, restriction, message, ch...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[order, contains, age-restricted, items., Some...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[Verify, Banner, navigation, banners, places, ...</td>\n",
+       "      <td>[User, logs, UMA, application, valid, user's, ...</td>\n",
+       "      <td>[User, navigates, Home, page, UMA, application...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[Display, Meal, Plans, banner, based, banner.,...</td>\n",
+       "      <td>[User, logs, UMA, application, valid, user's, ...</td>\n",
+       "      <td>[User, navigates, Home, page, UMA, application...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test_case_Acceptance_criteria  \\\n",
+       "0  [Weekly, Ad, -, tap, product, offer, -, tap, A...   \n",
+       "1  [PdM,, want, ensure, L2, entry, points, workin...   \n",
+       "2  [customer,, see, age, restriction, message, ch...   \n",
+       "3  [Verify, Banner, navigation, banners, places, ...   \n",
+       "4  [Display, Meal, Plans, banner, based, banner.,...   \n",
+       "\n",
+       "                                          Test_Steps  \\\n",
+       "0  [User, logs, UMA, application, valid, user's, ...   \n",
+       "1  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "2  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "3  [User, logs, UMA, application, valid, user's, ...   \n",
+       "4  [User, logs, UMA, application, valid, user's, ...   \n",
+       "\n",
+       "                                     Expected_Result  \n",
+       "0  [User, navigates, Home, page, UMA, application...  \n",
+       "1  [User, able, login, successfully, home, page, ...  \n",
+       "2  [order, contains, age-restricted, items., Some...  \n",
+       "3  [User, navigates, Home, page, UMA, application...  \n",
+       "4  [User, navigates, Home, page, UMA, application...  "
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stop_words = set(stopwords.words('english'))\n",
+    "\n",
+    "# Function to remove stopwords\n",
+    "def remove_stopwords(tokens):\n",
+    "    return [token for token in tokens if token.lower() not in stop_words]\n",
+    "\n",
+    "# Apply stopwords removal\n",
+    "df['Test_case_Acceptance_criteria'] = df['Test_case_Acceptance_criteria'].apply(remove_stopwords)\n",
+    "df['Test_Steps'] = df['Test_Steps'].apply(remove_stopwords)\n",
+    "df['Expected_Result'] = df['Expected_Result'].apply(remove_stopwords)\n",
+    "\n",
+    "# Inspect the data after stopwords removal\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "057555fe",
+   "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>Test_case_Acceptance_criteria</th>\n",
+       "      <th>Test_Steps</th>\n",
+       "      <th>Expected_Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[Weekly, Ad, -, tap, product, offer, -, tap, A...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[PdM,, want, ensure, L2, entry, point, work, f...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[User, able, login, successfully, home, page, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[customer,, see, age, restriction, message, ch...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[order, contain, age-restricted, items., Someo...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[Verify, Banner, navigation, banner, place, di...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[Display, Meal, Plans, banner, base, banner., ...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application....</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test_case_Acceptance_criteria  \\\n",
+       "0  [Weekly, Ad, -, tap, product, offer, -, tap, A...   \n",
+       "1  [PdM,, want, ensure, L2, entry, point, work, f...   \n",
+       "2  [customer,, see, age, restriction, message, ch...   \n",
+       "3  [Verify, Banner, navigation, banner, place, di...   \n",
+       "4  [Display, Meal, Plans, banner, base, banner., ...   \n",
+       "\n",
+       "                                          Test_Steps  \\\n",
+       "0  [User, log, UMA, application, valid, user's, c...   \n",
+       "1  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "2  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "3  [User, log, UMA, application, valid, user's, c...   \n",
+       "4  [User, log, UMA, application, valid, user's, c...   \n",
+       "\n",
+       "                                     Expected_Result  \n",
+       "0  [User, navigate, Home, page, UMA, application....  \n",
+       "1  [User, able, login, successfully, home, page, ...  \n",
+       "2  [order, contain, age-restricted, items., Someo...  \n",
+       "3  [User, navigate, Home, page, UMA, application,...  \n",
+       "4  [User, navigate, Home, page, UMA, application....  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "lemmatizer = WordNetLemmatizer()\n",
+    "\n",
+    "# Function to lemmatize tokens\n",
+    "def lemmatize_tokens(tokens):\n",
+    "    return [lemmatizer.lemmatize(token, pos = 'v') for token in tokens]\n",
+    "\n",
+    "# Apply lemmatization\n",
+    "df['Test_case_Acceptance_criteria'] = df['Test_case_Acceptance_criteria'].apply(lemmatize_tokens)\n",
+    "df['Test_Steps'] = df['Test_Steps'].apply(lemmatize_tokens)\n",
+    "df['Expected_Result'] = df['Expected_Result'].apply(lemmatize_tokens)\n",
+    "\n",
+    "# Inspect the data after lemmatization\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "249dd661",
+   "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>Test_case_Acceptance_criteria</th>\n",
+       "      <th>Test_Steps</th>\n",
+       "      <th>Expected_Result</th>\n",
+       "      <th>Acceptance_criteria_embeddings</th>\n",
+       "      <th>Test_Steps_embeddings</th>\n",
+       "      <th>Expected_Result_embeddings</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[Weekly, Ad, -, tap, product, offer, -, tap, A...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application....</td>\n",
+       "      <td>[2.9078821e-05, 0.0009868374, 0.0006897929, 0....</td>\n",
+       "      <td>[-0.00090376585, 0.0015351841, 0.00077817513, ...</td>\n",
+       "      <td>[-0.00075740286, 0.0017703008, 7.018649e-05, 0...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[PdM,, want, ensure, L2, entry, point, work, f...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[User, able, login, successfully, home, page, ...</td>\n",
+       "      <td>[4.9687253e-05, -0.0002648631, -0.0011476703, ...</td>\n",
+       "      <td>[-0.0007915226, 0.0008593759, 0.00056966604, -...</td>\n",
+       "      <td>[0.00035405744, 0.0019673503, -0.00071650144, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[customer,, see, age, restriction, message, ch...</td>\n",
+       "      <td>[Login, UMA, app, valid, email/, mobile, no., ...</td>\n",
+       "      <td>[order, contain, age-restricted, items., Someo...</td>\n",
+       "      <td>[-0.0019043502, -0.0007733393, -0.00047627056,...</td>\n",
+       "      <td>[-0.0010107799, -0.0004325275, 0.0025766247, 0...</td>\n",
+       "      <td>[-0.0022062701, -0.0032818727, 0.0012025184, -...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[Verify, Banner, navigation, banner, place, di...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application,...</td>\n",
+       "      <td>[0.00079187436, 0.001024591, -0.00025014183, -...</td>\n",
+       "      <td>[-0.00082380656, 0.0015335361, 0.0008829938, 0...</td>\n",
+       "      <td>[-0.0007905865, 0.0017265088, 0.00018967084, 0...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[Display, Meal, Plans, banner, base, banner., ...</td>\n",
+       "      <td>[User, log, UMA, application, valid, user's, c...</td>\n",
+       "      <td>[User, navigate, Home, page, UMA, application....</td>\n",
+       "      <td>[0.0006987122, 0.0025012388, 0.00094601634, -0...</td>\n",
+       "      <td>[-0.0006520124, 0.00076459144, 0.0014451812, 0...</td>\n",
+       "      <td>[-0.00028285536, 0.0013591949, -0.00073397934,...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       Test_case_Acceptance_criteria  \\\n",
+       "0  [Weekly, Ad, -, tap, product, offer, -, tap, A...   \n",
+       "1  [PdM,, want, ensure, L2, entry, point, work, f...   \n",
+       "2  [customer,, see, age, restriction, message, ch...   \n",
+       "3  [Verify, Banner, navigation, banner, place, di...   \n",
+       "4  [Display, Meal, Plans, banner, base, banner., ...   \n",
+       "\n",
+       "                                          Test_Steps  \\\n",
+       "0  [User, log, UMA, application, valid, user's, c...   \n",
+       "1  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "2  [Login, UMA, app, valid, email/, mobile, no., ...   \n",
+       "3  [User, log, UMA, application, valid, user's, c...   \n",
+       "4  [User, log, UMA, application, valid, user's, c...   \n",
+       "\n",
+       "                                     Expected_Result  \\\n",
+       "0  [User, navigate, Home, page, UMA, application....   \n",
+       "1  [User, able, login, successfully, home, page, ...   \n",
+       "2  [order, contain, age-restricted, items., Someo...   \n",
+       "3  [User, navigate, Home, page, UMA, application,...   \n",
+       "4  [User, navigate, Home, page, UMA, application....   \n",
+       "\n",
+       "                      Acceptance_criteria_embeddings  \\\n",
+       "0  [2.9078821e-05, 0.0009868374, 0.0006897929, 0....   \n",
+       "1  [4.9687253e-05, -0.0002648631, -0.0011476703, ...   \n",
+       "2  [-0.0019043502, -0.0007733393, -0.00047627056,...   \n",
+       "3  [0.00079187436, 0.001024591, -0.00025014183, -...   \n",
+       "4  [0.0006987122, 0.0025012388, 0.00094601634, -0...   \n",
+       "\n",
+       "                               Test_Steps_embeddings  \\\n",
+       "0  [-0.00090376585, 0.0015351841, 0.00077817513, ...   \n",
+       "1  [-0.0007915226, 0.0008593759, 0.00056966604, -...   \n",
+       "2  [-0.0010107799, -0.0004325275, 0.0025766247, 0...   \n",
+       "3  [-0.00082380656, 0.0015335361, 0.0008829938, 0...   \n",
+       "4  [-0.0006520124, 0.00076459144, 0.0014451812, 0...   \n",
+       "\n",
+       "                          Expected_Result_embeddings  \n",
+       "0  [-0.00075740286, 0.0017703008, 7.018649e-05, 0...  \n",
+       "1  [0.00035405744, 0.0019673503, -0.00071650144, ...  \n",
+       "2  [-0.0022062701, -0.0032818727, 0.0012025184, -...  \n",
+       "3  [-0.0007905865, 0.0017265088, 0.00018967084, 0...  \n",
+       "4  [-0.00028285536, 0.0013591949, -0.00073397934,...  "
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_tokens = df['Test_case_Acceptance_criteria'].tolist() + df['Test_Steps'].tolist() + df['Expected_Result'].tolist()\n",
+    "\n",
+    "# Train the Word2Vec model\n",
+    "word2vec_model = Word2Vec(sentences=all_tokens, vector_size=100, window=5, min_count=1, sg=0)\n",
+    "\n",
+    "# Function to get embeddings for tokens\n",
+    "def get_embeddings(tokens, model):\n",
+    "    embeddings = []\n",
+    "    for token in tokens:\n",
+    "        if token in model.wv:\n",
+    "            embeddings.append(model.wv[token])\n",
+    "        else:\n",
+    "            embeddings.append(np.zeros(model.vector_size))  # Handle out-of-vocabulary words\n",
+    "    return np.mean(embeddings, axis=0)  # Mean vector for the document\n",
+    "\n",
+    "# Apply the function to each column\n",
+    "df['Acceptance_criteria_embeddings'] = df['Test_case_Acceptance_criteria'].apply(lambda tokens: get_embeddings(tokens, word2vec_model) if tokens else np.nan)\n",
+    "df['Test_Steps_embeddings'] = df['Test_Steps'].apply(lambda tokens: get_embeddings(tokens, word2vec_model) if tokens else np.nan)\n",
+    "df['Expected_Result_embeddings'] = df['Expected_Result'].apply(lambda tokens: get_embeddings(tokens, word2vec_model) if tokens else np.nan)\n",
+    "\n",
+    "# Verify the final DataFrame\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f36d8564",
+   "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>Acceptance_criteria_embeddings</th>\n",
+       "      <th>Test_Steps_embeddings</th>\n",
+       "      <th>Expected_Result_embeddings</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[2.9078821e-05, 0.0009868374, 0.0006897929, 0....</td>\n",
+       "      <td>[-0.00090376585, 0.0015351841, 0.00077817513, ...</td>\n",
+       "      <td>[-0.00075740286, 0.0017703008, 7.018649e-05, 0...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[4.9687253e-05, -0.0002648631, -0.0011476703, ...</td>\n",
+       "      <td>[-0.0007915226, 0.0008593759, 0.00056966604, -...</td>\n",
+       "      <td>[0.00035405744, 0.0019673503, -0.00071650144, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[-0.0019043502, -0.0007733393, -0.00047627056,...</td>\n",
+       "      <td>[-0.0010107799, -0.0004325275, 0.0025766247, 0...</td>\n",
+       "      <td>[-0.0022062701, -0.0032818727, 0.0012025184, -...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[0.00079187436, 0.001024591, -0.00025014183, -...</td>\n",
+       "      <td>[-0.00082380656, 0.0015335361, 0.0008829938, 0...</td>\n",
+       "      <td>[-0.0007905865, 0.0017265088, 0.00018967084, 0...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[0.0006987122, 0.0025012388, 0.00094601634, -0...</td>\n",
+       "      <td>[-0.0006520124, 0.00076459144, 0.0014451812, 0...</td>\n",
+       "      <td>[-0.00028285536, 0.0013591949, -0.00073397934,...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      Acceptance_criteria_embeddings  \\\n",
+       "0  [2.9078821e-05, 0.0009868374, 0.0006897929, 0....   \n",
+       "1  [4.9687253e-05, -0.0002648631, -0.0011476703, ...   \n",
+       "2  [-0.0019043502, -0.0007733393, -0.00047627056,...   \n",
+       "3  [0.00079187436, 0.001024591, -0.00025014183, -...   \n",
+       "4  [0.0006987122, 0.0025012388, 0.00094601634, -0...   \n",
+       "\n",
+       "                               Test_Steps_embeddings  \\\n",
+       "0  [-0.00090376585, 0.0015351841, 0.00077817513, ...   \n",
+       "1  [-0.0007915226, 0.0008593759, 0.00056966604, -...   \n",
+       "2  [-0.0010107799, -0.0004325275, 0.0025766247, 0...   \n",
+       "3  [-0.00082380656, 0.0015335361, 0.0008829938, 0...   \n",
+       "4  [-0.0006520124, 0.00076459144, 0.0014451812, 0...   \n",
+       "\n",
+       "                          Expected_Result_embeddings  \n",
+       "0  [-0.00075740286, 0.0017703008, 7.018649e-05, 0...  \n",
+       "1  [0.00035405744, 0.0019673503, -0.00071650144, ...  \n",
+       "2  [-0.0022062701, -0.0032818727, 0.0012025184, -...  \n",
+       "3  [-0.0007905865, 0.0017265088, 0.00018967084, 0...  \n",
+       "4  [-0.00028285536, 0.0013591949, -0.00073397934,...  "
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.drop(['Test_case_Acceptance_criteria', 'Test_Steps', 'Expected_Result'], axis = 1)\n",
+    "df.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "53d82554",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = np.array(df['Acceptance_criteria_embeddings'].tolist())\n",
+    "y_test_steps = np.array(df['Test_Steps_embeddings'].tolist())\n",
+    "y_expected_result = np.array(df['Expected_Result_embeddings'].tolist())\n",
+    "\n",
+    "# Reshape data for LSTM: (samples, timesteps, features)\n",
+    "X = X.reshape((X.shape[0], 1, X.shape[1]))\n",
+    "y_test_steps = y_test_steps.reshape((y_test_steps.shape[0], 1, y_test_steps.shape[1]))\n",
+    "y_expected_result = y_expected_result.reshape((y_expected_result.shape[0], 1, y_expected_result.shape[1]))\n",
+    "\n",
+    "# Split the data into training and testing sets\n",
+    "X_train, X_test, y_train_test_steps, y_test_test_steps = train_test_split(X, y_test_steps, test_size=0.2, random_state=42)\n",
+    "_, _, y_train_expected_result, y_test_expected_result = train_test_split(X, y_expected_result, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "dc4930ed",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/preethamreddygollapalli/anaconda3/lib/python3.11/site-packages/keras/src/layers/rnn/rnn.py:204: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
+      "  super().__init__(**kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.layers import LSTM, Dense, TimeDistributed\n",
+    "\n",
+    "# Define the model for Test Steps\n",
+    "model_test_steps = Sequential([\n",
+    "    LSTM(50, activation='relu', input_shape=(X_train.shape[1], X_train.shape[2]), return_sequences=True),\n",
+    "    TimeDistributed(Dense(X_train.shape[2]))\n",
+    "])\n",
+    "\n",
+    "model_test_steps.compile(optimizer='adam', loss='mse')\n",
+    "\n",
+    "# Define the model for Expected Result\n",
+    "model_expected_result = Sequential([\n",
+    "    LSTM(50, activation='relu', input_shape=(X_train.shape[1], X_train.shape[2]), return_sequences=True),\n",
+    "    TimeDistributed(Dense(X_train.shape[2]))\n",
+    "])\n",
+    "\n",
+    "model_expected_result.compile(optimizer='adam', loss='mse')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "f7e70874",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 533ms/step - loss: 2.2174e-06 - val_loss: 9.4766e-07\n",
+      "Epoch 2/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 1.0551e-06 - val_loss: 6.0476e-07\n",
+      "Epoch 3/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 8.6695e-07 - val_loss: 6.1300e-07\n",
+      "Epoch 4/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 9.7589e-07 - val_loss: 6.2904e-07\n",
+      "Epoch 5/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 1.0319e-06 - val_loss: 6.0141e-07\n",
+      "Epoch 6/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 9.9991e-07 - val_loss: 5.6963e-07\n",
+      "Epoch 7/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 9.3908e-07 - val_loss: 5.5550e-07\n",
+      "Epoch 8/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 8.8153e-07 - val_loss: 5.5216e-07\n",
+      "Epoch 9/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 8.3433e-07 - val_loss: 5.5272e-07\n",
+      "Epoch 10/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 8.0194e-07 - val_loss: 5.5084e-07\n",
+      "Epoch 1/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 617ms/step - loss: 2.4237e-06 - val_loss: 1.0210e-06\n",
+      "Epoch 2/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 1.4453e-06 - val_loss: 8.3659e-07\n",
+      "Epoch 3/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.2441e-06 - val_loss: 9.3372e-07\n",
+      "Epoch 4/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.3035e-06 - val_loss: 1.0286e-06\n",
+      "Epoch 5/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.3807e-06 - val_loss: 1.0422e-06\n",
+      "Epoch 6/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 1.3993e-06 - val_loss: 9.8222e-07\n",
+      "Epoch 7/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.3536e-06 - val_loss: 8.9309e-07\n",
+      "Epoch 8/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.2750e-06 - val_loss: 8.2297e-07\n",
+      "Epoch 9/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 1.2075e-06 - val_loss: 7.9015e-07\n",
+      "Epoch 10/10\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 1.1735e-06 - val_loss: 7.8403e-07\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x3215e4750>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Train the model for Test Steps\n",
+    "model_test_steps.fit(X_train, y_train_test_steps, epochs=10, batch_size=32, validation_split=0.2)\n",
+    "\n",
+    "# Train the model for Expected Result\n",
+    "model_expected_result.fit(X_train, y_train_expected_result, epochs=10, batch_size=32, validation_split=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "ba6fa0de",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error for Test Steps: 2.547742951719556e-06\n",
+      "Mean Squared Error for Expected Result: 1.5647674445062876e-06\n"
+     ]
+    }
+   ],
+   "source": [
+    "mse_test_steps = model_test_steps.evaluate(X_test, y_test_test_steps, verbose=0)\n",
+    "print(f'Mean Squared Error for Test Steps: {mse_test_steps}')\n",
+    "\n",
+    "# Evaluate the model for Expected Result\n",
+    "mse_expected_result = model_expected_result.evaluate(X_test, y_test_expected_result, verbose=0)\n",
+    "print(f'Mean Squared Error for Expected Result: {mse_expected_result}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "b25dda8b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n",
+      "Predicted Test Steps Embeddings: [[[-8.4391527e-04  8.3808292e-04  9.2794985e-04  6.3661160e-04\n",
+      "    1.4777145e-04 -4.8993941e-04  6.3069363e-04  2.0756002e-03\n",
+      "   -8.7469915e-04 -1.1720757e-03 -6.2859093e-04 -9.6428773e-04\n",
+      "    1.0144784e-03 -6.3690939e-05 -3.8700749e-04 -7.1150030e-04\n",
+      "    5.5333151e-04  9.2034061e-05 -1.0463977e-03 -5.2145477e-03\n",
+      "    8.5559912e-04 -5.3791492e-04  2.6520165e-03 -8.6638553e-04\n",
+      "   -7.5741264e-04  5.9628719e-04 -6.6239189e-04 -8.7471894e-04\n",
+      "   -9.9208625e-04  8.2071731e-04  4.4646338e-04  8.4726338e-04\n",
+      "    9.5180282e-04 -8.4265345e-04 -5.4202758e-04  1.6481500e-03\n",
+      "   -2.2101693e-04 -9.7025535e-04 -6.7334180e-04 -2.8382645e-03\n",
+      "    6.2619505e-04 -1.0893656e-03 -8.7078079e-04 -2.0926578e-04\n",
+      "    8.1423775e-04  8.4379961e-04 -1.6668448e-04 -9.9032815e-04\n",
+      "    9.5974747e-04  8.5376378e-05  6.4395380e-04 -2.3663426e-03\n",
+      "   -7.3024776e-04  4.5859173e-04 -1.1602787e-03  5.6848535e-04\n",
+      "    2.6010780e-04 -1.0128880e-03 -2.1443174e-03 -2.6855108e-04\n",
+      "   -4.5336629e-04  6.6400541e-04  8.6696784e-04 -8.9265942e-04\n",
+      "   -2.0976812e-03  8.8741013e-04  1.0340458e-03  9.4049744e-04\n",
+      "   -2.5883170e-03  1.6136141e-03 -9.2293258e-04  8.5503218e-04\n",
+      "    1.2474646e-03 -1.5019166e-05  9.6433581e-04  2.4179585e-04\n",
+      "    7.6161108e-05  6.6559250e-04 -2.3543791e-04  1.0006825e-03\n",
+      "    2.9814860e-04 -7.5365568e-04 -2.1536734e-03  8.8814070e-04\n",
+      "   -1.2573856e-03 -1.0502129e-03  5.2467862e-04 -6.8704574e-04\n",
+      "    7.3569722e-04 -4.7312939e-04  2.2936910e-03  8.2683226e-04\n",
+      "    9.9437268e-05 -1.2628101e-04  3.2667362e-03  9.2687435e-04\n",
+      "    8.7968190e-04 -8.3866203e-04 -8.7905704e-05 -1.0417018e-03]]]\n",
+      "Predicted Expected Result Embeddings: [[[-6.00951666e-04 -8.71340380e-05  2.10425234e-04  1.77528680e-04\n",
+      "    8.00210983e-05 -1.85253297e-03  4.65850317e-04  3.56995873e-03\n",
+      "   -8.36861320e-04 -6.41276536e-04  9.27919289e-04 -5.45815798e-04\n",
+      "   -3.05406691e-04  7.55917281e-04  1.03734914e-04  2.38866487e-05\n",
+      "    7.79760536e-04 -8.88810202e-04 -8.77981714e-04 -2.83502182e-03\n",
+      "    4.05026833e-04  6.70524372e-04  4.63965582e-04 -7.13920599e-05\n",
+      "   -1.02403646e-04 -8.36344901e-04 -6.75997231e-04  7.48908031e-04\n",
+      "   -1.09156314e-03  7.66666722e-04  1.19300978e-03 -7.83136347e-04\n",
+      "    8.18963978e-04 -1.27818645e-03 -1.85861718e-03  2.35299161e-03\n",
+      "    9.13300086e-04 -3.06413101e-04 -1.55945239e-03 -9.19050653e-04\n",
+      "   -5.39628905e-04 -6.51296170e-04 -1.40835065e-04 -4.40066768e-04\n",
+      "    1.64291263e-03 -9.18515027e-04 -3.14408244e-04  2.30843452e-05\n",
+      "    6.91586174e-04  6.74205832e-04 -6.55808544e-05 -4.83483251e-04\n",
+      "   -1.72121217e-04 -6.61872444e-04 -8.81674583e-04 -8.80461157e-05\n",
+      "   -5.44943148e-04  1.00790197e-03 -1.34598825e-03  1.66665553e-03\n",
+      "    3.33746721e-04  8.65762937e-04  8.99292936e-04 -9.54890158e-04\n",
+      "   -5.94305107e-04  9.11348965e-04  2.88407644e-03  7.95712927e-04\n",
+      "   -1.11689197e-03  2.58971867e-03 -6.90977846e-04  2.21353053e-04\n",
+      "    7.32570188e-05 -5.61508466e-04  8.17475026e-04  9.93824913e-04\n",
+      "    8.48811760e-04  5.58658561e-04 -8.79892672e-04 -1.04590645e-03\n",
+      "   -6.82677957e-04  8.21857655e-04 -8.91812611e-04  1.62078207e-03\n",
+      "   -1.80392992e-03  2.16952423e-04  3.11806944e-04  5.39015047e-04\n",
+      "   -9.99061740e-08  9.94091504e-04  3.61588714e-03  2.67144089e-04\n",
+      "   -1.72064669e-04 -8.35217419e-04  1.40309369e-03 -4.59492789e-04\n",
+      "    9.69752960e-04 -8.42938258e-04 -3.16075137e-04  1.21560282e-04]]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "new_acceptance_criteria = df['Acceptance_criteria_embeddings'].tolist()[0]\n",
+    "new_acceptance_criteria = np.array(new_acceptance_criteria).reshape((1, 1, len(new_acceptance_criteria)))\n",
+    "\n",
+    "# Make predictions\n",
+    "predicted_test_steps = model_test_steps.predict(new_acceptance_criteria)\n",
+    "predicted_expected_result = model_expected_result.predict(new_acceptance_criteria)\n",
+    "\n",
+    "print(f'Predicted Test Steps Embeddings: {predicted_test_steps}')\n",
+    "print(f'Predicted Expected Result Embeddings: {predicted_expected_result}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "cf073637",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mae_test_steps = MeanAbsoluteError()\n",
+    "mae_expected_result = MeanAbsoluteError()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "d77deaa0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step\n",
+      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step\n",
+      "Mean Absolute Error for Test Steps: 0.0012983311899006367\n",
+      "Mean Absolute Error for Expected Result: 0.0009957090951502323\n",
+      "R-squared for Test Steps: 0.13273363428637874\n",
+      "R-squared for Expected Result: 0.1580453613077316\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_pred_test_steps = model_test_steps.predict(X_test)\n",
+    "y_pred_expected_result = model_expected_result.predict(X_test)\n",
+    "\n",
+    "# Calculate MAE for Test Steps\n",
+    "mae_test_steps_value = mae_test_steps(y_test_test_steps, y_pred_test_steps).numpy()\n",
+    "print(f'Mean Absolute Error for Test Steps: {mae_test_steps_value}')\n",
+    "\n",
+    "# Calculate MAE for Expected Result\n",
+    "mae_expected_result_value = mae_expected_result(y_test_expected_result, y_pred_expected_result).numpy()\n",
+    "print(f'Mean Absolute Error for Expected Result: {mae_expected_result_value}')\n",
+    "\n",
+    "# Calculate R-squared for Test Steps\n",
+    "r2_test_steps = r2_score(y_test_test_steps.flatten(), y_pred_test_steps.flatten())\n",
+    "print(f'R-squared for Test Steps: {r2_test_steps}')\n",
+    "\n",
+    "# Calculate R-squared for Expected Result\n",
+    "r2_expected_result = r2_score(y_test_expected_result.flatten(), y_pred_expected_result.flatten())\n",
+    "print(f'R-squared for Expected Result: {r2_expected_result}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ea62b59f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

model_expected_result.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee100706f6b0dbe1210944b92e6ec17edbee4d8876c006ea730bbf4e5d627435
+size 452632

model_test_steps.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b00a6397c7000ff46f63afeb41675a64fe1c319abae9459cace8deea528d8f7
+size 453080

word2vec_model (1).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09880657bc9da02e6aa6d8d2adfd483516a1f2e3e677c8e5bb6dc0d5e80f6f14
+size 272565