noshot 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

noshot/data/ML TS XAI/NLP/NLP 5/8.Bag of words and TF-IDF.ipynb

@@ -1,310 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "e288984d-5ed7-4349-bb04-c69da5dba922",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "0da6600d-5299-4999-ac05-0e272aa41813",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Training with Bag of Words (BoW)...\n",
-      "Epoch 1/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 17ms/step - accuracy: 0.1667 - loss: 0.94180\n",
-      "Epoch 2/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.3333 - loss: 0.8584 \n",
-      "Epoch 3/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.1667 - loss: 0.9124  \n",
-      "Epoch 4/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.8234\n",
-      "Epoch 5/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.3333 - loss: 0.8137 \n",
-      "Epoch 6/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.1667 - loss: 0.8736     \n",
-      "Epoch 7/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.1667 - loss: 0.8626.92\n",
-      "Epoch 8/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 0.3333 - loss: 0.7857\n",
-      "Epoch 9/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.3333 - loss: 0.7769\n",
-      "Epoch 10/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.3333 - loss: 0.7683\n",
-      "Epoch 11/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.7599 \n",
-      "Epoch 12/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.3333 - loss: 0.7605\n",
-      "Epoch 13/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.7529\n",
-      "Epoch 14/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.1667 - loss: 0.7893    \n",
-      "Epoch 15/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.3333 - loss: 0.7387 \n",
-      "Epoch 16/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.1667 - loss: 0.77170.811\n",
-      "Epoch 17/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.1667 - loss: 0.7609     \n",
-      "Epoch 18/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 0.1667 - loss: 0.7672   \n",
-      "Epoch 19/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.1667 - loss: 0.7476     \n",
-      "Epoch 20/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.7125\n",
-      "Epoch 21/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.3333 - loss: 0.7117\n",
-      "Epoch 22/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.1667 - loss: 0.7444 5\n",
-      "Epoch 23/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.3333 - loss: 0.7018 \n",
-      "Epoch 24/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.1667 - loss: 0.7199    \n",
-      "Epoch 25/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.5000 - loss: 0.7136\n",
-      "Epoch 26/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 848us/step - accuracy: 0.5000 - loss: 0.6845\n",
-      "Epoch 27/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.5000 - loss: 0.7001 \n",
-      "Epoch 28/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.6622  \n",
-      "Epoch 29/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.5000 - loss: 0.6915\n",
-      "Epoch 30/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.5000 - loss: 0.6891\n",
-      "Epoch 31/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - accuracy: 0.6667 - loss: 0.6513\n",
-      "Epoch 32/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.5000 - loss: 0.6813 \n",
-      "Epoch 33/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.6667 - loss: 0.64534\n",
-      "Epoch 34/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.5000 - loss: 0.6737\n",
-      "Epoch 35/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.5000 - loss: 0.67078\n",
-      "Epoch 36/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.5000 - loss: 0.6495\n",
-      "Epoch 37/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.5000 - loss: 0.66421\n",
-      "Epoch 38/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.5000 - loss: 0.6609\n",
-      "Epoch 39/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 0.5000 - loss: 0.6577\n",
-      "Epoch 40/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.5000 - loss: 0.6392\n",
-      "Epoch 41/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.5000 - loss: 0.6326 \n",
-      "Epoch 42/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6667 - loss: 0.6334 \n",
-      "Epoch 43/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 0.8333 - loss: 0.6453\n",
-      "Epoch 44/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.8333 - loss: 0.6420\n",
-      "Epoch 45/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.8333 - loss: 0.6388\n",
-      "Epoch 46/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.8333 - loss: 0.6081  \n",
-      "Epoch 47/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.6667 - loss: 0.63936\n",
-      "Epoch 48/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.6667 - loss: 0.64323\n",
-      "Epoch 49/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 0.6667 - loss: 0.6340\n",
-      "Epoch 50/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 0.8333 - loss: 0.6018  \n",
-      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 339ms/step - accuracy: 0.0000e+00 - loss: 0.7986\n",
-      "BoW Model Accuracy: 0.00\n",
-      "Training with TF-IDF...\n",
-      "Epoch 1/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 22ms/step - accuracy: 1.0000 - loss: 0.6225\n",
-      "Epoch 2/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 1.0000 - loss: 0.6307\n",
-      "Epoch 3/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 1.0000 - loss: 0.6083\n",
-      "Epoch 4/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.6007  \n",
-      "Epoch 5/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - accuracy: 1.0000 - loss: 0.6158\n",
-      "Epoch 6/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 1.0000 - loss: 0.6028\n",
-      "Epoch 7/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 1.0000 - loss: 0.5791\n",
-      "Epoch 8/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.6008\n",
-      "Epoch 9/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.5828 \n",
-      "Epoch 10/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.5744 \n",
-      "Epoch 11/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 1.0000 - loss: 0.5696\n",
-      "Epoch 12/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 1.0000 - loss: 0.5630\n",
-      "Epoch 13/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - accuracy: 1.0000 - loss: 0.5578\n",
-      "Epoch 14/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.5501 \n",
-      "Epoch 15/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 1.0000 - loss: 0.5666\n",
-      "Epoch 16/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.5416 \n",
-      "Epoch 17/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 1.0000 - loss: 0.5120\n",
-      "Epoch 18/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.5059 \n",
-      "Epoch 19/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.5205  \n",
-      "Epoch 20/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 1.0000 - loss: 0.4940 \n",
-      "Epoch 21/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.5400 \n",
-      "Epoch 22/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.50558\n",
-      "Epoch 23/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.47692\n",
-      "Epoch 24/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 1.0000 - loss: 0.5038\n",
-      "Epoch 25/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.46510\n",
-      "Epoch 26/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 1.0000 - loss: 0.4822\n",
-      "Epoch 27/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 1.0000 - loss: 0.4733\n",
-      "Epoch 28/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 1.0000 - loss: 0.4845\n",
-      "Epoch 29/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.4595  \n",
-      "Epoch 30/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 1.0000 - loss: 0.4738\n",
-      "Epoch 31/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 1.0000 - loss: 0.4876 \n",
-      "Epoch 32/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 1.0000 - loss: 0.4817\n",
-      "Epoch 33/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 1.0000 - loss: 0.4347\n",
-      "Epoch 34/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 1.0000 - loss: 0.4255\n",
-      "Epoch 35/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 1.0000 - loss: 0.4015\n",
-      "Epoch 36/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 1.0000 - loss: 0.4424  \n",
-      "Epoch 37/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 1.0000 - loss: 0.4088  \n",
-      "Epoch 38/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 1.0000 - loss: 0.4325\n",
-      "Epoch 39/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - accuracy: 1.0000 - loss: 0.4276\n",
-      "Epoch 40/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 1.0000 - loss: 0.4230\n",
-      "Epoch 41/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 1.0000 - loss: 0.4183 \n",
-      "Epoch 42/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 0.3790\n",
-      "Epoch 43/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 1.0000 - loss: 0.3728  \n",
-      "Epoch 44/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 1.0000 - loss: 0.3662 \n",
-      "Epoch 45/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 1.0000 - loss: 0.3594\n",
-      "Epoch 46/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0s/step - accuracy: 1.0000 - loss: 0.39049\n",
-      "Epoch 47/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 1.0000 - loss: 0.3864\n",
-      "Epoch 48/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 1.0000 - loss: 0.3960\n",
-      "Epoch 49/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 1.0000 - loss: 0.3338\n",
-      "Epoch 50/50\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 1.0000 - loss: 0.3699\n",
-      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 278ms/step - accuracy: 1.0000 - loss: 0.4346\n",
-      "TF-IDF Model Accuracy: 1.00\n"
-     ]
-    }
-   ],
-   "source": [
-    "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=50, 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=50, 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}')"
-   ]
-  }
- ],
- "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": "3.12.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

noshot/data/ML TS XAI/NLP/NLP 5/9.Word2Vector.ipynb

@@ -1,78 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "d2e8ca01-88e6-4574-ac39-df95af94d592",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Words most similar to 'programming':\n",
-      "the: 0.1783\n",
-      "i: 0.1607\n",
-      "a: 0.1056\n",
-      "great: 0.0922\n",
-      "python: 0.0270\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[nltk_data] Downloading package punkt to\n",
-      "[nltk_data]     C:\\Users\\sugan\\AppData\\Roaming\\nltk_data...\n",
-      "[nltk_data]   Package punkt is already up-to-date!\n"
-     ]
-    }
-   ],
-   "source": [
-    "#Implement word2vec model to explore the semantic similarity between the words.\n",
-    "import gensim\n",
-    "from gensim.models import Word2Vec\n",
-    "import nltk\n",
-    "nltk.download('punkt')\n",
-    "from nltk.tokenize import word_tokenize\n",
-    "sentences = ['I love programming', 'Python is great', 'I enjoy machine learning',\n",
-    "             'TensorFlow is a powerful tool', 'AI is the future']\n",
-    "\n",
-    "tokenized_sentences = [word_tokenize(sentence.lower()) for sentence in sentences]\n",
-    "\n",
-    "\n",
-    "model_w2v = Word2Vec(sentences=tokenized_sentences, vector_size=100, window=5, min_count=1, workers=4)\n",
-    "\n",
-    "#  word vectors (semantic similarity)\n",
-    "word = 'programming'\n",
-    "similar_words = model_w2v.wv.most_similar(word, topn=5)\n",
-    "print(f\"Words most similar to '{word}':\")\n",
-    "for sim_word, sim_score in similar_words:\n",
-    "    print(f\"{sim_word}: {sim_score:.4f}\")\n",
-    "model_w2v.save(\"word2vec_model.bin\")\n",
-    "#loaded_model = Word2Vec.load(\"word2vec_model.bin\")"
-   ]
-  }
- ],
- "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": "3.12.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}