noshot 0.1.7__py3-none-any.whl → 0.1.9__py3-none-any.whl

noshot/data/ML TS XAI/NLP/NLP 1/Chi2test.ipynb

@@ -1,285 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "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": 54,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from nltk.util import bigrams\n",
-    "from nltk.tokenize import word_tokenize\n",
-    "from nltk.corpus import stopwords\n",
-    "import string \n",
-    "from collections import defaultdict"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "defaultdict(int,\n",
-       "            {('love', 'studying'): 1,\n",
-       "             ('studying', 'data'): 1,\n",
-       "             ('data', 'science'): 3,\n",
-       "             ('science', 'interesting'): 1,\n",
-       "             ('interesting', 'field'): 1,\n",
-       "             ('science', 'requires'): 1,\n",
-       "             ('requires', 'data'): 1,\n",
-       "             ('data', 'analysis'): 1,\n",
-       "             ('data', 'key'): 1,\n",
-       "             ('key', 'modern'): 1,\n",
-       "             ('modern', 'science'): 1,\n",
-       "             ('science', 'helps'): 1,\n",
-       "             ('helps', 'business'): 1,\n",
-       "             ('business', 'decision-making'): 1})"
-      ]
-     },
-     "execution_count": 55,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "bigramdict = defaultdict(int)\n",
-    "for i in sentences:\n",
-    "    i = i.lower()\n",
-    "    tokens = word_tokenize(i)\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",
-    "    bigramlist = list(bigrams(tokens))\n",
-    "\n",
-    "    for j in bigramlist:\n",
-    "        bigramdict[j] += 1\n",
-    "\n",
-    "bigramdict"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "('data', 'science')"
-      ]
-     },
-     "execution_count": 56,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "##w1 = input(\"Enter word 1\").lower()\n",
-    "##w2 = input(\"Enter word 2\").lower()\n",
-    "w1 = \"data\"\n",
-    "w2 = \"science\"\n",
-    "w1,w2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[[3, 2, 0], [1, 10, 0], [0, 0, 0]]"
-      ]
-     },
-     "execution_count": 57,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "C = [[0 for i in range(3)] for j in range(3)]\n",
-    "\n",
-    "# Filling the main matrix \n",
-    "for key in bigramdict:\n",
-    "    if key[0] == w1 and key[1] == w2:\n",
-    "        C[0][0] += bigramdict[key]\n",
-    "    if key[0] == w1 and key[1] != w2:\n",
-    "        C[0][1] += bigramdict[key]\n",
-    "    if key[0] != w1 and key[1] == w2:\n",
-    "        C[1][0] += bigramdict[key]\n",
-    "    if key[0] != w1 and key[1] != w2:\n",
-    "        C[1][1] += bigramdict[key]\n",
-    "C"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[[3, 2, 5], [1, 10, 11], [4, 12, 0]]"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Filling the totals\n",
-    "# Row 0\n",
-    "C[0][2] = C[0][0] + C[0][1]\n",
-    "# Row 1\n",
-    "C[1][2] = C[1][0] + C[1][1]\n",
-    "# Col 0\n",
-    "C[2][0] = C[0][0] + C[1][0]\n",
-    "# Col 1\n",
-    "C[2][1] = C[0][1] + C[1][1]\n",
-    "\n",
-    "total = C[2][0] + C[2][1]\n",
-    "C"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[[1.25, 3.75], [2.75, 8.25]]"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Expectation matrix\n",
-    "E = [[0 for i in range(2)] for j in range(2)]\n",
-    "\n",
-    "# 00: top,left\n",
-    "E[0][0] = (C[0][2] * C[2][0]) / total\n",
-    "# 01: top, right\n",
-    "E[0][1] = (C[0][2] * C[2][1]) / total\n",
-    "# 10: bottom, left\n",
-    "E[1][0] = (C[1][2] * C[2][0]) / total\n",
-    "# 11: bottom, right\n",
-    "E[1][1] = (C[1][2] * C[2][1]) / total\n",
-    "\n",
-    "E"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "([3, 2, 1, 10], [1.25, 3.75, 2.75, 8.25])"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Flatten C\n",
-    "O = [item for sublist in C[:2] for item in sublist[:2]]\n",
-    "E = [item for sublist in E for item in sublist]\n",
-    "O, E"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "4.38030303030303"
-      ]
-     },
-     "execution_count": 61,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "score = 0\n",
-    "for i in range(len(C)):\n",
-    "    score += (O[i] - E[i])**2 / E[i]\n",
-    "score"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Reject Ho\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Critical Value \n",
-    "c = 2 #EXAMPLE \n",
-    "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/ML TS XAI/NLP/NLP 1/Hindle-Rooth.ipynb

@@ -1,179 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hello World\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\"Hello World\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import string\n",
-    "from nltk.corpus import stopwords\n",
-    "from nltk.util import bigrams \n",
-    "from nltk.tokenize import word_tokenize\n",
-    "import math\n",
-    "from collections import defaultdict"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sentences = [\n",
-    "    \"Saw the phone with me.\",\n",
-    "    \"Went to the meeting yesterday.\",\n",
-    "    \"Told the man to wait.\",\n",
-    "    \"Gave the book to her.\",\n",
-    "    \"Saw the cat with her.\"\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "preposition = \"to\"\n",
-    "noun = \"man\"\n",
-    "verb = \"wait\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "unigramD = defaultdict(int)\n",
-    "bigramD = defaultdict(int)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "stops = stopwords.words(\"english\")\n",
-    "for line in sentences:\n",
-    "    tokens = line.lower()\n",
-    "    tokens = word_tokenize(line)\n",
-    "    tokens = [i for i in tokens if i not in stops and i not in string.punctuation]\n",
-    "\n",
-    "    for token in tokens:\n",
-    "        unigramD[token] += 1\n",
-    "    \n",
-    "    for bigram in bigrams(tokens):\n",
-    "        bigramD[bigram] += 1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(0.0, 0.0, 1.0)"
-      ]
-     },
-     "execution_count": 66,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "p_verb_1 = bigramD[(verb,preposition)] / unigramD[noun]\n",
-    "\n",
-    "p_noun_1 = bigramD[(noun,preposition)] / unigramD[noun]\n",
-    "\n",
-    "p_noun_0 = 1 - p_noun_1\n",
-    "\n",
-    "p_verb_1, p_noun_1, p_noun_0"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 70,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0"
-      ]
-     },
-     "execution_count": 70,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "try: lammbda = math.log2(p_verb_1 * p_noun_0 / p_noun_1)\n",
-    "except ZeroDivisionError as e: lammbda = 0\n",
-    "lammbda"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 71,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "noun\n"
-     ]
-    }
-   ],
-   "source": [
-    "if lammbda > 0:\n",
-    "    print(\"verb\")\n",
-    "else:\n",
-    "    print(\"noun\")"
-   ]
-  }
- ],
- "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": 4
-}