From d0bb749d085a2a57cc71f1d901929cdac68c10b1 Mon Sep 17 00:00:00 2001
From: Salla Kaushik <sallakaushik@gmail.com>
Date: Sun, 5 Jan 2025 02:14:19 +0530
Subject: [PATCH] Added "Expanding Contractions" Feature to Preprocessing

---
 .../aossie-fake-news-tfidf-nn.ipynb           | 606 ++++--------------
 1 file changed, 140 insertions(+), 466 deletions(-)

diff --git a/ML/Fake NEWS/Models/Jupyter Notebook/aossie-fake-news-tfidf-nn.ipynb b/ML/Fake NEWS/Models/Jupyter Notebook/aossie-fake-news-tfidf-nn.ipynb
index 9648a657..d27a9ea6 100644
--- a/ML/Fake NEWS/Models/Jupyter Notebook/aossie-fake-news-tfidf-nn.ipynb	
+++ b/ML/Fake NEWS/Models/Jupyter Notebook/aossie-fake-news-tfidf-nn.ipynb	
@@ -2,67 +2,142 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Requirement already satisfied: nltk in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (3.8.1)\n",
-      "Requirement already satisfied: tqdm in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (4.66.4)\n",
-      "Requirement already satisfied: keras in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (3.3.3)\n",
-      "Requirement already satisfied: tensorflow in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (2.16.1)\n",
-      "Requirement already satisfied: click in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from nltk) (8.1.7)\n",
-      "Requirement already satisfied: joblib in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from nltk) (1.4.2)\n",
-      "Requirement already satisfied: regex>=2021.8.3 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from nltk) (2024.5.15)\n",
-      "Requirement already satisfied: colorama in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tqdm) (0.4.6)\n",
-      "Requirement already satisfied: absl-py in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (2.1.0)\n",
-      "Requirement already satisfied: numpy in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (1.26.4)\n",
-      "Requirement already satisfied: rich in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (13.7.1)\n",
-      "Requirement already satisfied: namex in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (0.0.8)\n",
-      "Requirement already satisfied: h5py in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (3.11.0)\n",
-      "Requirement already satisfied: optree in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (0.11.0)\n",
-      "Requirement already satisfied: ml-dtypes in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from keras) (0.3.2)\n",
-      "Requirement already satisfied: tensorflow-intel==2.16.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow) (2.16.1)\n",
-      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.6.3)\n",
-      "Requirement already satisfied: flatbuffers>=23.5.26 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (24.3.25)\n",
-      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.5.4)\n",
-      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.2.0)\n",
-      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (18.1.1)\n",
-      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.3.0)\n",
-      "Requirement already satisfied: packaging in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (24.0)\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 c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.25.3)\n",
-      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.31.0)\n",
-      "Requirement already satisfied: setuptools in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (69.5.1)\n",
-      "Requirement already satisfied: six>=1.12.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
-      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.4.0)\n",
-      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.11.0)\n",
-      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
-      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.63.0)\n",
-      "Requirement already satisfied: tensorboard<2.17,>=2.16 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.16.2)\n",
-      "Requirement already satisfied: markdown-it-py>=2.2.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from rich->keras) (3.0.0)\n",
-      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from rich->keras) (2.18.0)\n",
-      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.16.1->tensorflow) (0.43.0)\n",
-      "Requirement already satisfied: mdurl~=0.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from markdown-it-py>=2.2.0->rich->keras) (0.1.2)\n",
-      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (3.3.2)\n",
-      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (3.7)\n",
-      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (2.2.1)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (2024.6.2)\n",
-      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.6)\n",
-      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (0.7.2)\n",
-      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.0.3)\n",
-      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\visha\\anaconda3\\envs\\pyenv\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (2.1.5)\n"
+      "Collecting nltk\n",
+      "  Downloading nltk-3.9.1-py3-none-any.whl.metadata (2.9 kB)\n",
+      "Requirement already satisfied: tqdm in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (4.66.4)\n",
+      "Collecting keras\n",
+      "  Downloading keras-3.7.0-py3-none-any.whl.metadata (5.8 kB)\n",
+      "Collecting tensorflow\n",
+      "  Downloading tensorflow-2.18.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.1 kB)\n",
+      "Collecting click (from nltk)\n",
+      "  Downloading click-8.1.8-py3-none-any.whl.metadata (2.3 kB)\n",
+      "Collecting joblib (from nltk)\n",
+      "  Downloading joblib-1.4.2-py3-none-any.whl.metadata (5.4 kB)\n",
+      "Collecting regex>=2021.8.3 (from nltk)\n",
+      "  Downloading regex-2024.11.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
+      "Collecting absl-py (from keras)\n",
+      "  Downloading absl_py-2.1.0-py3-none-any.whl.metadata (2.3 kB)\n",
+      "Collecting numpy (from keras)\n",
+      "  Downloading numpy-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (62 kB)\n",
+      "Collecting rich (from keras)\n",
+      "  Downloading rich-13.9.4-py3-none-any.whl.metadata (18 kB)\n",
+      "Collecting namex (from keras)\n",
+      "  Downloading namex-0.0.8-py3-none-any.whl.metadata (246 bytes)\n",
+      "Collecting h5py (from keras)\n",
+      "  Downloading h5py-3.12.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.5 kB)\n",
+      "Collecting optree (from keras)\n",
+      "  Downloading optree-0.13.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (47 kB)\n",
+      "Collecting ml-dtypes (from keras)\n",
+      "  Downloading ml_dtypes-0.5.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (21 kB)\n",
+      "Requirement already satisfied: packaging in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from keras) (24.1)\n",
+      "Collecting astunparse>=1.6.0 (from tensorflow)\n",
+      "  Downloading astunparse-1.6.3-py2.py3-none-any.whl.metadata (4.4 kB)\n",
+      "Collecting flatbuffers>=24.3.25 (from tensorflow)\n",
+      "  Downloading flatbuffers-24.12.23-py2.py3-none-any.whl.metadata (876 bytes)\n",
+      "Collecting gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 (from tensorflow)\n",
+      "  Downloading gast-0.6.0-py3-none-any.whl.metadata (1.3 kB)\n",
+      "Collecting google-pasta>=0.1.1 (from tensorflow)\n",
+      "  Downloading google_pasta-0.2.0-py3-none-any.whl.metadata (814 bytes)\n",
+      "Collecting libclang>=13.0.0 (from tensorflow)\n",
+      "  Downloading libclang-18.1.1-py2.py3-none-manylinux2010_x86_64.whl.metadata (5.2 kB)\n",
+      "Collecting opt-einsum>=2.3.2 (from tensorflow)\n",
+      "  Downloading opt_einsum-3.4.0-py3-none-any.whl.metadata (6.3 kB)\n",
+      "Collecting protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.3 (from tensorflow)\n",
+      "  Downloading protobuf-5.29.2-cp38-abi3-manylinux2014_x86_64.whl.metadata (592 bytes)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from tensorflow) (2.32.3)\n",
+      "Requirement already satisfied: setuptools in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from tensorflow) (72.1.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from tensorflow) (1.17.0)\n",
+      "Collecting termcolor>=1.1.0 (from tensorflow)\n",
+      "  Downloading termcolor-2.5.0-py3-none-any.whl.metadata (6.1 kB)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from tensorflow) (4.12.2)\n",
+      "Collecting wrapt>=1.11.0 (from tensorflow)\n",
+      "  Downloading wrapt-1.17.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.4 kB)\n",
+      "Collecting grpcio<2.0,>=1.24.3 (from tensorflow)\n",
+      "  Downloading grpcio-1.68.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.9 kB)\n",
+      "Collecting tensorboard<2.19,>=2.18 (from tensorflow)\n",
+      "  Downloading tensorboard-2.18.0-py3-none-any.whl.metadata (1.6 kB)\n",
+      "Collecting numpy (from keras)\n",
+      "  Downloading numpy-2.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
+      "Collecting ml-dtypes (from keras)\n",
+      "  Downloading ml_dtypes-0.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from astunparse>=1.6.0->tensorflow) (0.43.0)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from requests<3,>=2.21.0->tensorflow) (3.3.2)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from requests<3,>=2.21.0->tensorflow) (3.7)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from requests<3,>=2.21.0->tensorflow) (2.2.2)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from requests<3,>=2.21.0->tensorflow) (2024.12.14)\n",
+      "Collecting markdown>=2.6.8 (from tensorboard<2.19,>=2.18->tensorflow)\n",
+      "  Downloading Markdown-3.7-py3-none-any.whl.metadata (7.0 kB)\n",
+      "Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard<2.19,>=2.18->tensorflow)\n",
+      "  Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl.metadata (1.1 kB)\n",
+      "Collecting werkzeug>=1.0.1 (from tensorboard<2.19,>=2.18->tensorflow)\n",
+      "  Downloading werkzeug-3.1.3-py3-none-any.whl.metadata (3.7 kB)\n",
+      "Collecting markdown-it-py>=2.2.0 (from rich->keras)\n",
+      "  Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)\n",
+      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /home/salla-kaushik/conda_root/lib/python3.12/site-packages (from rich->keras) (2.18.0)\n",
+      "Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich->keras)\n",
+      "  Downloading mdurl-0.1.2-py3-none-any.whl.metadata (1.6 kB)\n",
+      "Collecting MarkupSafe>=2.1.1 (from werkzeug>=1.0.1->tensorboard<2.19,>=2.18->tensorflow)\n",
+      "  Downloading MarkupSafe-3.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n",
+      "Downloading nltk-3.9.1-py3-none-any.whl (1.5 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading keras-3.7.0-py3-none-any.whl (1.2 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m3.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading tensorflow-2.18.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (615.5 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m615.5/615.5 MB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mm eta \u001b[36m0:00:01\u001b[0m[36m0:00:04\u001b[0m\n",
+      "\u001b[?25hDownloading absl_py-2.1.0-py3-none-any.whl (133 kB)\n",
+      "Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)\n",
+      "Downloading flatbuffers-24.12.23-py2.py3-none-any.whl (30 kB)\n",
+      "Downloading gast-0.6.0-py3-none-any.whl (21 kB)\n",
+      "Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)\n",
+      "Downloading grpcio-1.68.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.9 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.9/5.9 MB\u001b[0m \u001b[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m[36m0:00:01\u001b[0mm eta \u001b[36m0:00:01\u001b[0m0m\n",
+      "\u001b[?25hDownloading h5py-3.12.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading libclang-18.1.1-py2.py3-none-manylinux2010_x86_64.whl (24.5 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.5/24.5 MB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mm eta \u001b[36m0:00:01\u001b[0m[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading ml_dtypes-0.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.2 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading numpy-2.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (19.2 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m19.2/19.2 MB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mm eta \u001b[36m0:00:01\u001b[0m[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hDownloading opt_einsum-3.4.0-py3-none-any.whl (71 kB)\n",
+      "Downloading protobuf-5.29.2-cp38-abi3-manylinux2014_x86_64.whl (319 kB)\n",
+      "Downloading regex-2024.11.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (796 kB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m796.9/796.9 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+      "\u001b[?25hDownloading tensorboard-2.18.0-py3-none-any.whl (5.5 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m4.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m:01\u001b[0m\n",
+      "\u001b[?25hDownloading termcolor-2.5.0-py3-none-any.whl (7.8 kB)\n",
+      "Downloading wrapt-1.17.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (89 kB)\n",
+      "Downloading click-8.1.8-py3-none-any.whl (98 kB)\n",
+      "Downloading joblib-1.4.2-py3-none-any.whl (301 kB)\n",
+      "Downloading namex-0.0.8-py3-none-any.whl (5.8 kB)\n",
+      "Downloading optree-0.13.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (385 kB)\n",
+      "Downloading rich-13.9.4-py3-none-any.whl (242 kB)\n",
+      "Downloading Markdown-3.7-py3-none-any.whl (106 kB)\n",
+      "Downloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
+      "Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl (6.6 MB)\n",
+      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m:01\u001b[0m\n",
+      "\u001b[?25hDownloading werkzeug-3.1.3-py3-none-any.whl (224 kB)\n",
+      "Downloading MarkupSafe-3.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (23 kB)\n",
+      "Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n",
+      "Installing collected packages: namex, libclang, flatbuffers, wrapt, termcolor, tensorboard-data-server, regex, protobuf, optree, opt-einsum, numpy, mdurl, MarkupSafe, markdown, joblib, grpcio, google-pasta, gast, click, astunparse, absl-py, werkzeug, nltk, ml-dtypes, markdown-it-py, h5py, tensorboard, rich, keras, tensorflow\n",
+      "Successfully installed MarkupSafe-3.0.2 absl-py-2.1.0 astunparse-1.6.3 click-8.1.8 flatbuffers-24.12.23 gast-0.6.0 google-pasta-0.2.0 grpcio-1.68.1 h5py-3.12.1 joblib-1.4.2 keras-3.7.0 libclang-18.1.1 markdown-3.7 markdown-it-py-3.0.0 mdurl-0.1.2 ml-dtypes-0.4.1 namex-0.0.8 nltk-3.9.1 numpy-2.0.2 opt-einsum-3.4.0 optree-0.13.1 protobuf-5.29.2 regex-2024.11.6 rich-13.9.4 tensorboard-2.18.0 tensorboard-data-server-0.7.2 tensorflow-2.18.0 termcolor-2.5.0 werkzeug-3.1.3 wrapt-1.17.0\n"
      ]
     }
    ],
    "source": [
-    "!pip install nltk tqdm keras tensorflow"
+    "!pip install nltk tqdm keras tensorflow contractions"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -92,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101,425 +176,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-1 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TfidfVectorizer(max_features=80, stop_words=&#x27;english&#x27;, token_pattern=&#x27;\\\\w{1,}&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;TfidfVectorizer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html\">?<span>Documentation for TfidfVectorizer</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TfidfVectorizer(max_features=80, stop_words=&#x27;english&#x27;, token_pattern=&#x27;\\\\w{1,}&#x27;)</pre></div> </div></div></div></div>"
-      ],
-      "text/plain": [
-       "TfidfVectorizer(max_features=80, stop_words='english', token_pattern='\\\\w{1,}')"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
+     "ename": "NameError",
+     "evalue": "name 'totaldata' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[11], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m tfidf_vect\u001b[38;5;241m.\u001b[39mfit(\u001b[43mtotaldata\u001b[49m)\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'totaldata' is not defined"
+     ]
     }
    ],
    "source": [
@@ -551,6 +220,7 @@
     "import numpy as np\n",
     "from sklearn import feature_extraction\n",
     "from tqdm import tqdm\n",
+    "import contractions #Update for expanding contractions\n",
     "\n",
     "\n",
     "_wnl = nltk.WordNetLemmatizer()\n",
@@ -564,6 +234,10 @@
     "    return [normalize_word(t) for t in nltk.word_tokenize(s)]\n",
     "\n",
     "\n",
+    "def expanding_contractions(s):\n",
+    "    return contractions.fix(s)\n",
+    "\n",
+    "\n",
     "def clean(s):\n",
     "    # Cleans a string: Lowercasing, trimming, removing non-alphanumeric\n",
     "\n",
@@ -1517,7 +1191,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "base",
    "language": "python",
    "name": "python3"
   },
@@ -1531,7 +1205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,