PyPI - noshot - Versions diffs - 0.1.0__py3-none-any.whl - Mend

noshot 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (210) hide show

noshot/data/AIDS CN NLP/NLP/NLP 2/Lab02(stemming)/exp0.ipynb ADDED Viewed

@@ -0,0 +1,274 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2ae9052e-082b-46b8-b342-c1af8b144ceb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total number of unique words: 80\n",
+      "\n",
+      "Word frequencies:\n",
+      "India 3\n",
+      ", 11\n",
+      "a 5\n",
+      "land 1\n",
+      "of 4\n",
+      "diverse 2\n",
+      "cultures 1\n",
+      "and 4\n",
+      "rich 1\n",
+      "heritage 1\n",
+      "captivates 1\n",
+      "with 3\n",
+      "its 3\n",
+      "vibrant 1\n",
+      "tapestry. 1\n",
+      "From 1\n",
+      "the 2\n",
+      "majestic 1\n",
+      "Himalayas 1\n",
+      "to 2\n",
+      "serene 1\n",
+      "backwaters 1\n",
+      "Kerala 1\n",
+      "landscapes 1\n",
+      "are 1\n",
+      "testament 1\n",
+      "nature 1\n",
+      "'s 3\n",
+      "grandeur. 1\n",
+      "Bustling 1\n",
+      "bazaars 1\n",
+      "exude 1\n",
+      "sensory 1\n",
+      "symphony 1\n",
+      "while 1\n",
+      "ancient 1\n",
+      "temples 1\n",
+      "modern 1\n",
+      "skyscrapers 1\n",
+      "stand 1\n",
+      "in 2\n",
+      "harmony. 1\n",
+      "The 1\n",
+      "nation 1\n",
+      "history 1\n",
+      "woven 1\n",
+      "tales 1\n",
+      "maharajas 1\n",
+      "independence 1\n",
+      "heroes 1\n",
+      "echoes 1\n",
+      "every 1\n",
+      "corner. 1\n",
+      "With 1\n",
+      "population 1\n",
+      "as 2\n",
+      "geography 1\n",
+      "celebrates 1\n",
+      "festivals 1\n",
+      "exuberance 1\n",
+      "uniting 1\n",
+      "people 1\n",
+      "various 1\n",
+      "faiths. 1\n",
+      "Spicy 1\n",
+      "cuisine 1\n",
+      "intricate 1\n",
+      "art 1\n",
+      "forms 1\n",
+      "Bollywood 1\n",
+      "magic 1\n",
+      "complete 1\n",
+      "this 1\n",
+      "colorful 1\n",
+      "mosaic 1\n",
+      "making 1\n",
+      "truly 1\n",
+      "extraordinary 1\n",
+      "destination 1\n",
+      ". 1\n",
+      "\n",
+      "Total number of unique pairs: 112\n",
+      "Joint probabilities:\n",
+      "India , 1\n",
+      ", a 1\n",
+      "a land 1\n",
+      "land of 1\n",
+      "of diverse 1\n",
+      "diverse cultures 1\n",
+      "cultures and 1\n",
+      "and rich 1\n",
+      "rich heritage 1\n",
+      "heritage , 1\n",
+      ", captivates 1\n",
+      "captivates with 1\n",
+      "with its 1\n",
+      "its vibrant 1\n",
+      "vibrant tapestry. 1\n",
+      "tapestry. From 1\n",
+      "From the 1\n",
+      "the majestic 1\n",
+      "majestic Himalayas 1\n",
+      "Himalayas to 1\n",
+      "to the 1\n",
+      "the serene 1\n",
+      "serene backwaters 1\n",
+      "backwaters of 1\n",
+      "of Kerala 1\n",
+      "Kerala , 1\n",
+      ", its 1\n",
+      "its landscapes 1\n",
+      "landscapes are 1\n",
+      "are a 1\n",
+      "a testament 1\n",
+      "testament to 1\n",
+      "to nature 1\n",
+      "nature 's 1\n",
+      "'s grandeur. 1\n",
+      "grandeur. Bustling 1\n",
+      "Bustling bazaars 1\n",
+      "bazaars exude 1\n",
+      "exude a 1\n",
+      "a sensory 1\n",
+      "sensory symphony 1\n",
+      "symphony , 1\n",
+      ", while 1\n",
+      "while ancient 1\n",
+      "ancient temples 1\n",
+      "temples and 1\n",
+      "and modern 1\n",
+      "modern skyscrapers 1\n",
+      "skyscrapers stand 1\n",
+      "stand in 1\n",
+      "in harmony. 1\n",
+      "harmony. The 1\n",
+      "The nation 1\n",
+      "nation 's 1\n",
+      "'s history 1\n",
+      "history , 1\n",
+      ", woven 1\n",
+      "woven with 1\n",
+      "with tales 1\n",
+      "tales of 1\n",
+      "of maharajas 1\n",
+      "maharajas and 1\n",
+      "and independence 1\n",
+      "independence heroes 1\n",
+      "heroes , 1\n",
+      ", echoes 1\n",
+      "echoes in 1\n",
+      "in every 1\n",
+      "every corner. 1\n",
+      "corner. With 1\n",
+      "With a 1\n",
+      "a population 1\n",
+      "population as 1\n",
+      "as diverse 1\n",
+      "diverse as 1\n",
+      "as its 1\n",
+      "its geography 1\n",
+      "geography , 1\n",
+      ", India 1\n",
+      "India celebrates 1\n",
+      "celebrates festivals 1\n",
+      "festivals with 1\n",
+      "with exuberance 1\n",
+      "exuberance , 1\n",
+      ", uniting 1\n",
+      "uniting people 1\n",
+      "people of 1\n",
+      "of various 1\n",
+      "various faiths. 1\n",
+      "faiths. Spicy 1\n",
+      "Spicy cuisine 1\n",
+      "cuisine , 1\n",
+      ", intricate 1\n",
+      "intricate art 1\n",
+      "art forms 1\n",
+      "forms , 1\n",
+      ", and 1\n",
+      "and Bollywood 1\n",
+      "Bollywood 's 1\n",
+      "'s magic 1\n",
+      "magic complete 1\n",
+      "complete this 1\n",
+      "this colorful 1\n",
+      "colorful mosaic 1\n",
+      "mosaic , 1\n",
+      ", making 1\n",
+      "making India 1\n",
+      "India a 1\n",
+      "a truly 1\n",
+      "truly extraordinary 1\n",
+      "extraordinary destination 1\n",
+      "destination . 1\n",
+      "\n",
+      "The pair with the max frequency: India ,\n"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "from nltk.tokenize import TreebankWordTokenizer\n",
+    "\n",
+    "# Read the text file\n",
+    "with open(\"test.txt\") as f:\n",
+    "    text = f.read()\n",
+    "\n",
+    "# Tokenize the text\n",
+    "tokenizer = TreebankWordTokenizer()\n",
+    "tokens = tokenizer.tokenize(text)\n",
+    "\n",
+    "# Task 1: Display total number of unique words\n",
+    "unique_words = set(tokens)\n",
+    "total_unique_words = len(unique_words)\n",
+    "print(\"Total number of unique words:\", total_unique_words)\n",
+    "\n",
+    "# Task 2: Frequency of each word without duplicate entries\n",
+    "word_frequency = Counter(tokens)\n",
+    "print(\"\\nWord frequencies:\")\n",
+    "for word, freq in word_frequency.items():\n",
+    "    print(word, freq)\n",
+    "\n",
+    "# Task 3: Joint probability of each word\n",
+    "joint_probabilities = Counter(zip(tokens, tokens[1:]))\n",
+    "total_pairs = len(joint_probabilities)\n",
+    "print(\"\\nTotal number of unique pairs:\", total_pairs)\n",
+    "print(\"Joint probabilities:\")\n",
+    "for pair, freq in joint_probabilities.items():\n",
+    "    print(\" \".join(pair), freq)\n",
+    "\n",
+    "# The pair with the maximum frequency\n",
+    "max_freq_pair = max(joint_probabilities, key=joint_probabilities.get)\n",
+    "print(\"\\nThe pair with the max frequency:\", \" \".join(max_freq_pair))\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}