noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/NLP/NLP 1/PCFG.ipynb

@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "LHS `->` RHS  \n",
+    "Element1 `|` Element2 `|` Element3  \n",
+    "`NP PP [0.4]` -- non-terminal symbol   \n",
+    "`'he' [0.6]` -- terminal symbol "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "grammarstring = \"\"\"\n",
+    "S -> NP VP [1.0]\n",
+    "NP -> NP PP [0.4] | 'he' [0.1] | 'dessert' [0.3] | 'lunch' [0.1] | 'saw' [0.1]\n",
+    "PP -> Pre NP [1.0]\n",
+    "VP -> Verb NP [0.3] | VP PP [0.7]\n",
+    "Pre -> 'with' [0.6] | 'in' [0.4]\n",
+    "Verb -> 'ate' [0.7] | 'saw' [0.3]\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk import PCFG, InsideChartParser \n",
+    "# Remember InsideChartParser\n",
+    "\n",
+    "grammar = PCFG.fromstring(grammarstring)\n",
+    "\n",
+    "parser = InsideChartParser(grammar=grammar)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['he', 'saw', 'lunch', 'with', 'dessert']"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from nltk.tokenize import word_tokenize\n",
+    "\n",
+    "sentence = \"he saw lunch with dessert\"\n",
+    "\n",
+    "tokens = word_tokenize(sentence)\n",
+    "tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "               S                       \n",
+      "  _____________|____                    \n",
+      " |                  VP                 \n",
+      " |         _________|________           \n",
+      " |        VP                 PP        \n",
+      " |    ____|____          ____|_____     \n",
+      " NP Verb       NP      Pre         NP  \n",
+      " |   |         |        |          |    \n",
+      " he saw      lunch     with     dessert\n",
+      "\n",
+      "Prob:  0.00011339999999999999\n",
+      "           S                       \n",
+      "  _________|____                    \n",
+      " |              VP                 \n",
+      " |    __________|___                \n",
+      " |   |              NP             \n",
+      " |   |      ________|____           \n",
+      " |   |     |             PP        \n",
+      " |   |     |         ____|_____     \n",
+      " NP Verb   NP      Pre         NP  \n",
+      " |   |     |        |          |    \n",
+      " he saw  lunch     with     dessert\n",
+      "\n",
+      "Prob:  6.480000000000002e-05\n"
+     ]
+    }
+   ],
+   "source": [
+    "trees = parser.parse(tokens)\n",
+    "\n",
+    "for tree in trees:\n",
+    "    tree.pretty_print() # Remember this\n",
+    "    print(\"Prob: \", tree.prob())# .prob"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

noshot/data/AIDS CN NLP/NLP/NLP 1/Prereqs.ipynb

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk.tokenize import word_tokenize\n",
+    "from nltk.corpus import stopwords\n",
+    "from nltk.util import bigrams\n",
+    "import string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sentences = [\n",
+    "    \"I love studying data science.\",\n",
+    "    \"Data science is an interesting field.\",\n",
+    "    \"Science requires data for analysis.\",\n",
+    "    \"Data is key in modern science.\",\n",
+    "    \"Data science helps in business decision-making.\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def process(line):\n",
+    "    line = line.lower()\n",
+    "    tokens = word_tokenize(line)\n",
+    "\n",
+    "    # stopwords\n",
+    "    stops = set(stopwords.words('english'))\n",
+    "    tokens = [i for i in tokens if i not in stops and i not in string.punctuation]\n",
+    "    return tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[['love', 'studying', 'data', 'science'],\n",
+       " ['data', 'science', 'interesting', 'field'],\n",
+       " ['science', 'requires', 'data', 'analysis'],\n",
+       " ['data', 'key', 'modern', 'science'],\n",
+       " ['data', 'science', 'helps', 'business', 'decision-making']]"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tokens = [process(i) for i in sentences]\n",
+    "tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def bgrm(l):\n",
+    "    return bigrams(l)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('love', 'studying'), ('studying', 'data'), ('data', 'science')]"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bigrams_all = list(bgrm(tokens[0]))\n",
+    "bigrams_all"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

noshot/data/AIDS CN NLP/NLP/NLP 1/T test.ipynb

@@ -0,0 +1,252 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "1. List out the sentences from the dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from nltk.util import bigrams\n",
+    "from nltk.corpus import stopwords   \n",
+    "from nltk.tokenize import word_tokenize\n",
+    "import string\n",
+    "from collections import defaultdict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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>Sastra University is located in Tamil Nadu.</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Students at Sastra University engage in rigoro...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>The university's main campus, Sastra Tanjore, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Sastra University offers undergraduate and pos...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Sastra University's commitment to quality educ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>The university's reputation for excellence ext...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         Sastra University is located in Tamil Nadu.\n",
+       "0  Students at Sastra University engage in rigoro...\n",
+       "1  The university's main campus, Sastra Tanjore, ...\n",
+       "2  Sastra University offers undergraduate and pos...\n",
+       "3  Sastra University's commitment to quality educ...\n",
+       "4  The university's reputation for excellence ext..."
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv(\"../sastralines.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Students at Sastra University engage in rigorous academic pursuits.',\n",
+       " \"The university's main campus, Sastra Tanjore, is known for its scenic beauty.\",\n",
+       " 'Sastra University offers undergraduate and postgraduate programs in diverse disciplines.',\n",
+       " \"Sastra University's commitment to quality education is evident in its faculty.\",\n",
+       " \"The university's reputation for excellence extends beyond national borders.\"]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "lines = df.iloc[:,0].tolist() #pandas series\n",
+    "lines[:5]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "unigramD = defaultdict(int)\n",
+    "bigramD = defaultdict(int)\n",
+    "\n",
+    "N = 0 # Wordcount\n",
+    "for line in lines:\n",
+    "    \n",
+    "    tokens = [i for i in word_tokenize(line.lower()) if i not in set(stopwords.words(\"english\")) and i not in string.punctuation]\n",
+    "    \n",
+    "    for j in tokens:\n",
+    "        unigramD[j] += 1\n",
+    "        N+= 1\n",
+    "    for j in list(bigrams(tokens)):\n",
+    "        bigramD[j] += 1\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "4. Input words, critical value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w1 = \"sastra\"\n",
+    "w2 = \"university\"\n",
+    "c = 2.0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "5. O,E"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(0.08401084010840108, 0.011875647211756669, 12.715450067040848)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "O = bigramD[(w1,w2)]/N \n",
+    "E = unigramD[(w1)]/N * unigramD[(w2)]/N \n",
+    "variance = E\n",
+    "\n",
+    "score = (O-E)/math.sqrt(variance/N)\n",
+    "O,E,score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Reject Ho\n"
+     ]
+    }
+   ],
+   "source": [
+    "if score > c:\n",
+    "    print(\"Reject Ho\")\n",
+    "else:\n",
+    "    print(\"Accept Ho\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

noshot/data/AIDS CN NLP/NLP/NLP 1/TFIDF BOW.ipynb

@@ -0,0 +1,171 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "n1DJ41rw1B0J",
+        "outputId": "ba654967-ee56-4040-e68f-4a54e3bb8dbb"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Training with Bag of Words (BoW)...\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/keras/src/layers/core/dense.py:87: 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__(activity_regularizer=activity_regularizer, **kwargs)\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 1/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 16ms/step - accuracy: 0.6667 - loss: 0.6975\n",
+            "Epoch 2/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.8333 - loss: 0.6899\n",
+            "Epoch 3/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8333 - loss: 0.6867 \n",
+            "Epoch 4/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.6667 - loss: 0.7099 \n",
+            "Epoch 5/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.7057 \n",
+            "Epoch 6/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.6741 \n",
+            "Epoch 7/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.6983 \n",
+            "Epoch 8/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6667 - loss: 0.6652 \n",
+            "Epoch 9/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.8333 - loss: 0.6382 \n",
+            "Epoch 10/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8333 - loss: 0.6347 \n",
+            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 292ms/step - accuracy: 1.0000 - loss: 0.6350\n",
+            "BoW Model Accuracy: 1.00\n",
+            "Training with TF-IDF...\n",
+            "Epoch 1/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.7130\n",
+            "Epoch 2/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.7099 \n",
+            "Epoch 3/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.7071 \n",
+            "Epoch 4/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.1667 - loss: 0.7102     \n",
+            "Epoch 5/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.3333 - loss: 0.7016 \n",
+            "Epoch 6/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.7002 \n",
+            "Epoch 7/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.5000 - loss: 0.6964 \n",
+            "Epoch 8/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6667 - loss: 0.6923 \n",
+            "Epoch 9/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.6900 \n",
+            "Epoch 10/10\n",
+            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6667 - loss: 0.6914 \n",
+            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 283ms/step - accuracy: 0.0000e+00 - loss: 0.7002\n",
+            "TF-IDF Model Accuracy: 0.00\n"
+          ]
+        }
+      ],
+      "source": [
+        "#Text Classification using Bag of Words and TF-IDF with TensorFlow.\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\n",
+        "from sklearn.preprocessing import LabelEncoder\n",
+        "import tensorflow as tf\n",
+        "from tensorflow.keras import Sequential\n",
+        "from tensorflow.keras.layers import Dense\n",
+        "\n",
+        "data = {'text': ['I love programming', 'Python is great', 'I enjoy machine learning',\n",
+        "                 'TensorFlow is a powerful tool', 'AI is the future'],\n",
+        "        'label': ['positive', 'positive', 'positive', 'positive', 'neutral']}\n",
+        "\n",
+        "df = pd.DataFrame(data)\n",
+        "label_encoder = LabelEncoder()\n",
+        "df['label'] = label_encoder.fit_transform(df['label'])\n",
+        "X_train, X_test, y_train, y_test = train_test_split(df['text'], df['label'], test_size=0.2, random_state=42)\n",
+        "\n",
+        "# Option 1: Bag of Words (BoW)\n",
+        "vectorizer_bow = CountVectorizer()\n",
+        "X_train_bow = vectorizer_bow.fit_transform(X_train).toarray()\n",
+        "X_test_bow = vectorizer_bow.transform(X_test).toarray()\n",
+        "\n",
+        "# Option 2: TF-IDF\n",
+        "vectorizer_tfidf = TfidfVectorizer()\n",
+        "X_train_tfidf = vectorizer_tfidf.fit_transform(X_train).toarray()\n",
+        "X_test_tfidf = vectorizer_tfidf.transform(X_test).toarray()\n",
+        "\n",
+        "# Build a simple neural network with TensorFlow\n",
+        "def build_model(input_dim):\n",
+        "    model = Sequential()\n",
+        "    model.add(Dense(16, activation='relu', input_dim=input_dim))\n",
+        "    model.add(Dense(8, activation='relu'))\n",
+        "    model.add(Dense(1, activation='sigmoid'))  # Binary classification (positive or neutral)\n",
+        "    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
+        "    return model\n",
+        "\n",
+        "\n",
+        "print(\"Training with Bag of Words (BoW)...\")\n",
+        "model_bow = build_model(X_train_bow.shape[1])\n",
+        "model_bow.fit(X_train_bow, y_train, epochs=10, batch_size=2, verbose=1)\n",
+        "\n",
+        "loss, accuracy = model_bow.evaluate(X_test_bow, y_test)\n",
+        "print(f'BoW Model Accuracy: {accuracy:.2f}')\n",
+        "\n",
+        "print(\"Training with TF-IDF...\")\n",
+        "model_tfidf = build_model(X_train_tfidf.shape[1])\n",
+        "model_tfidf.fit(X_train_tfidf, y_train, epochs=10, batch_size=2, verbose=1)\n",
+        "\n",
+        "\n",
+        "loss, accuracy = model_tfidf.evaluate(X_test_tfidf, y_test)\n",
+        "print(f'TF-IDF Model Accuracy: {accuracy:.2f}')\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0aZKJeRc2JQz"
+      },
+      "source": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZjkrZu5411-K"
+      },
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "gpuType": "T4",
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}