noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/NLP/NLP 2/Lab03(parse-tree)/lab3.ipynb

@@ -0,0 +1,549 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0c125b29",
+   "metadata": {},
+   "source": [
+    "# Exp 3\n",
+    "\n",
+    "**To do**:\n",
+    "    Parse tree for ambiguous sentence.\n",
+    "\n",
+    "Code credits - **Hari Kishan, Geeks for Geeks**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "693a6ba6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "          s                   \n",
+      "          |                    \n",
+      "          vp                  \n",
+      "  ________|____                \n",
+      " |             np             \n",
+      " |     ________|_____          \n",
+      " |    |              np       \n",
+      " |    |              |         \n",
+      " |    |              np       \n",
+      " |    |         _____|____     \n",
+      " |    |        np         |   \n",
+      " |    |        |          |    \n",
+      " v    d        n          n   \n",
+      " |    |        |          |    \n",
+      "Book the     dinner     flight\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from nltk import *\n",
+    "n1=Tree('np',[Tree('np',[Tree('n',['dinner'])]),Tree('n',['flight'])])\n",
+    "np=Tree('np',[Tree('d',['the']),Tree('np',[n1])])\n",
+    "vp=Tree('vp',[Tree('v',['Book']),np])\n",
+    "tree=Tree('s',[vp])\n",
+    "tree.pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9ae808bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "      s                   \n",
+      "      |                    \n",
+      "      vp                  \n",
+      "  ____|_______________     \n",
+      " |        |           np  \n",
+      " |        |           |    \n",
+      " |        np          np  \n",
+      " |     ___|____       |    \n",
+      " v    d        np     np  \n",
+      " |    |        |      |    \n",
+      "Book the     dinner flight\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from nltk import *\n",
+    "np2=Tree('np',[Tree('np',[Tree('np',['flight'])])])\n",
+    "np1=Tree('np',[Tree('d',['the']), Tree('np',['dinner'])])\n",
+    "vp=Tree('vp',[Tree('v',['Book']),np1,np2])\n",
+    "tree=Tree('s',[vp])\n",
+    "tree.pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "b926774a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total number of unique words: 92\n",
+      "\n",
+      "Word frequencies:\n",
+      "After 1\n",
+      "graduating 1\n",
+      "of 9\n",
+      "a 6\n",
+      "Madras 1\n",
+      "Institute 1\n",
+      "Technology 1\n",
+      "in 2\n",
+      "1960 1\n",
+      ", 7\n",
+      "Kalam 2\n",
+      "Aeronautical 1\n",
+      "Development 3\n",
+      "Establishment 1\n",
+      "the 7\n",
+      "Defence 2\n",
+      "Research 2\n",
+      "and 2\n",
+      "Organisation 1\n",
+      "( 2\n",
+      "by 4\n",
+      "Press 1\n",
+      "Information 1\n",
+      "Bureau 1\n",
+      "Government 1\n",
+      "India 1\n",
+      ") 2\n",
+      "as 2\n",
+      "scientist 1\n",
+      "after 1\n",
+      "becoming 1\n",
+      "member 1\n",
+      "& 1\n",
+      "Service 1\n",
+      "DRDS 1\n",
+      ". 1\n",
+      "He 1\n",
+      "started 1\n",
+      "his 2\n",
+      "career 1\n",
+      "designing 1\n",
+      "small 1\n",
+      "hovercraft 1\n",
+      "but 1\n",
+      "remained 1\n",
+      "unconvinced 1\n",
+      "choice 1\n",
+      "job 1\n",
+      "at 1\n",
+      "DRDO.alam 1\n",
+      "was 1\n",
+      "invited 1\n",
+      "Raja 1\n",
+      "Ramanna 1\n",
+      "to 2\n",
+      "witness 1\n",
+      "country 1\n",
+      "'s 1\n",
+      "first 1\n",
+      "nuclear 1\n",
+      "test 1\n",
+      "Smiling 1\n",
+      "Buddha 1\n",
+      "representative 1\n",
+      "TBRL 1\n",
+      "even 1\n",
+      "though 1\n",
+      "he 1\n",
+      "had 1\n",
+      "not 1\n",
+      "participated 1\n",
+      "its 1\n",
+      "development. 1\n",
+      "In 1\n",
+      "1970s 1\n",
+      "also 1\n",
+      "directed 1\n",
+      "two 1\n",
+      "projects 1\n",
+      "Project 2\n",
+      "Devil 1\n",
+      "Valiant 1\n",
+      "which 1\n",
+      "sought 1\n",
+      "develop 1\n",
+      "ballistic 1\n",
+      "missiles 1\n",
+      "from 1\n",
+      "technology 1\n",
+      "successful 1\n",
+      "SLV 1\n",
+      "programme 1\n",
+      "\n",
+      "Total number of unique pairs: 125\n",
+      "Joint probabilities:\n",
+      "After graduating 1\n",
+      "graduating of 1\n",
+      "of a 3\n",
+      "a Madras 1\n",
+      "Madras Institute 1\n",
+      "Institute of 1\n",
+      "of Technology 1\n",
+      "Technology in 1\n",
+      "in 1960 1\n",
+      "1960 , 1\n",
+      ", Kalam 2\n",
+      "Kalam of 1\n",
+      "a Aeronautical 1\n",
+      "Aeronautical Development 1\n",
+      "Development Establishment 1\n",
+      "Establishment of 1\n",
+      "of the 3\n",
+      "the Defence 2\n",
+      "Defence Research 2\n",
+      "Research and 1\n",
+      "and Development 1\n",
+      "Development Organisation 1\n",
+      "Organisation ( 1\n",
+      "( by 1\n",
+      "by Press 1\n",
+      "Press Information 1\n",
+      "Information Bureau 1\n",
+      "Bureau , 1\n",
+      ", Government 1\n",
+      "Government of 1\n",
+      "of India 1\n",
+      "India ) 1\n",
+      ") as 1\n",
+      "as a 1\n",
+      "a scientist 1\n",
+      "scientist after 1\n",
+      "after becoming 1\n",
+      "becoming a 1\n",
+      "a member 1\n",
+      "member of 1\n",
+      "Research & 1\n",
+      "& Development 1\n",
+      "Development Service 1\n",
+      "Service ( 1\n",
+      "( DRDS 1\n",
+      "DRDS ) 1\n",
+      ") . 1\n",
+      ". He 1\n",
+      "He started 1\n",
+      "started his 1\n",
+      "his career 1\n",
+      "career by 1\n",
+      "by designing 1\n",
+      "designing a 1\n",
+      "a small 1\n",
+      "small hovercraft 1\n",
+      "hovercraft , 1\n",
+      ", but 1\n",
+      "but remained 1\n",
+      "remained unconvinced 1\n",
+      "unconvinced by 1\n",
+      "by his 1\n",
+      "his choice 1\n",
+      "choice of 1\n",
+      "a job 1\n",
+      "job at 1\n",
+      "at DRDO.alam 1\n",
+      "DRDO.alam was 1\n",
+      "was invited 1\n",
+      "invited by 1\n",
+      "by Raja 1\n",
+      "Raja Ramanna 1\n",
+      "Ramanna to 1\n",
+      "to witness 1\n",
+      "witness the 1\n",
+      "the country 1\n",
+      "country 's 1\n",
+      "'s first 1\n",
+      "first nuclear 1\n",
+      "nuclear test 1\n",
+      "test Smiling 1\n",
+      "Smiling Buddha 1\n",
+      "Buddha as 1\n",
+      "as the 1\n",
+      "the representative 1\n",
+      "representative of 1\n",
+      "of TBRL 1\n",
+      "TBRL , 1\n",
+      ", even 1\n",
+      "even though 1\n",
+      "though he 1\n",
+      "he had 1\n",
+      "had not 1\n",
+      "not participated 1\n",
+      "participated in 1\n",
+      "in its 1\n",
+      "its development. 1\n",
+      "development. In 1\n",
+      "In the 1\n",
+      "the 1970s 1\n",
+      "1970s , 1\n",
+      "Kalam also 1\n",
+      "also directed 1\n",
+      "directed two 1\n",
+      "two projects 1\n",
+      "projects , 1\n",
+      ", Project 1\n",
+      "Project Devil 1\n",
+      "Devil and 1\n",
+      "and Project 1\n",
+      "Project Valiant 1\n",
+      "Valiant , 1\n",
+      ", which 1\n",
+      "which sought 1\n",
+      "sought to 1\n",
+      "to develop 1\n",
+      "develop ballistic 1\n",
+      "ballistic missiles 1\n",
+      "missiles from 1\n",
+      "from the 1\n",
+      "the technology 1\n",
+      "technology of 1\n",
+      "the successful 1\n",
+      "successful SLV 1\n",
+      "SLV programme 1\n",
+      "\n",
+      "The pair with the max frequency: of a\n",
+      "ORGANIZATION --> MadrasInstitute\n",
+      "GPE --> Technology\n",
+      "PERSON --> Kalam\n",
+      "ORGANIZATION --> AeronauticalDevelopment\n",
+      "ORGANIZATION --> DefenceResearch\n",
+      "ORGANIZATION --> DevelopmentOrganisation\n",
+      "PERSON --> PressInformationBureau\n",
+      "GPE --> India\n",
+      "ORGANIZATION --> Defence\n",
+      "ORGANIZATION --> DevelopmentService\n",
+      "ORGANIZATION --> DRDS\n",
+      "PERSON --> RajaRamanna\n",
+      "PERSON --> Buddha\n",
+      "ORGANIZATION --> TBRL\n",
+      "PERSON --> Kalam\n",
+      "PERSON --> ProjectDevil\n",
+      "PERSON --> ProjectValiant\n",
+      "ORGANIZATION --> SLV\n"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "from nltk.tokenize import TreebankWordTokenizer\n",
+    "\n",
+    "# Read the text file\n",
+    "with open(\"nlp.txt\") as f:\n",
+    "    text = f.read()\n",
+    "\n",
+    "# Tokenize the text\n",
+    "tokenizer = TreebankWordTokenizer()\n",
+    "tokens = tokenizer.tokenize(text)\n",
+    "\n",
+    "# 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",
+    "# 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",
+    "# 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",
+    " \n",
+    "# Apply part-of-speech tagging to the tokens\n",
+    "tagged = nltk.pos_tag(tokens)\n",
+    " \n",
+    "# Apply named entity recognition to the tagged words\n",
+    "entities = nltk.chunk.ne_chunk(tagged)\n",
+    "\n",
+    "# Print the entities found in the text\n",
+    "for entity in entities:\n",
+    "    if hasattr(entity, 'label') and entity.label() == 'ORGANIZATION':\n",
+    "        print(entity.label(),'-->', ''.join(c[0] for c in entity))\n",
+    "    elif hasattr(entity, 'label') and entity.label() == 'GPE':\n",
+    "        print(entity.label(), '-->',''.join(c[0] for c in entity))\n",
+    "    elif hasattr(entity, 'label') and entity.label() == 'PERSON':\n",
+    "        print(entity.label(), '-->',''.join(c[0] for c in entity))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "1dae5fb5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ORGANIZATION --> MadrasInstitute\n",
+      "GPE --> Technology\n",
+      "ORGANIZATION --> AeronauticalDevelopment\n",
+      "ORGANIZATION --> DefenceResearch\n",
+      "ORGANIZATION --> DevelopmentOrganisation\n",
+      "PERSON --> PressInformationBureau\n",
+      "GPE --> India\n",
+      "ORGANIZATION --> DefenceResearchDevelopmentService\n",
+      "ORGANIZATION --> DRDOalam\n",
+      "PERSON --> RajaRamanna\n",
+      "PERSON --> Buddha\n",
+      "ORGANIZATION --> TBRL\n",
+      "PERSON --> Kalam\n",
+      "PERSON --> ProjectDevil\n",
+      "PERSON --> ProjectValiant\n",
+      "ORGANIZATION --> SLV\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import nltk\n",
+    "from nltk.tokenize import TreebankWordTokenizer\n",
+    "from nltk.stem import PorterStemmer\n",
+    "f=open(\"nlp.txt\",'r')\n",
+    "tk=TreebankWordTokenizer()\n",
+    "new_string = re.sub(r'[^\\w\\s]', '', f.read())\n",
+    "val=tk.tokenize(new_string)\n",
+    "tagged=nltk.pos_tag(val)\n",
+    "entities=nltk.chunk.ne_chunk(tagged)\n",
+    "\n",
+    "for entity in entities:\n",
+    "    if hasattr(entity, 'label') and entity.label() == 'ORGANIZATION':\n",
+    "        print(entity.label(),'-->', ''.join(c[0] for c in entity))\n",
+    "    elif hasattr(entity, 'label') and entity.label() == 'GPE':\n",
+    "        print(entity.label(), '-->',''.join(c[0] for c in entity))\n",
+    "    elif hasattr(entity, 'label') and entity.label() == 'PERSON':\n",
+    "        print(entity.label(), '-->',''.join(c[0] for c in entity))\n",
+    "f.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "6d384b4b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('Allon', 'Bacuth'),\n",
+       " ('Ashteroth', 'Karnaim'),\n",
+       " ('Ben', 'Ammi'),\n",
+       " ('En', 'Mishpat'),\n",
+       " ('Jegar', 'Sahadutha'),\n",
+       " ('Salt', 'Sea'),\n",
+       " ('Whoever', 'sheds'),\n",
+       " ('appoint', 'overseers'),\n",
+       " ('aromatic', 'resin'),\n",
+       " ('cutting', 'instrument')]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "from nltk.collocations import *\n",
+    "bigram_measures = nltk.collocations.BigramAssocMeasures()\n",
+    "trigram_measures = nltk.collocations.TrigramAssocMeasures()\n",
+    "fourgram_measures = nltk.collocations.QuadgramAssocMeasures()\n",
+    "finder = BigramCollocationFinder.from_words(\n",
+    "nltk.corpus.genesis.words('english-web.txt'))\n",
+    "finder.nbest(bigram_measures.pmi, 10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "662bc8cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('olive', 'leaf', 'plucked'),\n",
+       " ('rider', 'falls', 'backward'),\n",
+       " ('sewed', 'fig', 'leaves'),\n",
+       " ('yield', 'royal', 'dainties'),\n",
+       " ('during', 'mating', 'season'),\n",
+       " ('Salt', 'Sea', ').'),\n",
+       " ('Sea', ').', 'Twelve'),\n",
+       " ('Their', 'hearts', 'failed'),\n",
+       " ('Valley', ').', 'Melchizedek'),\n",
+       " ('doing', 'forced', 'labor')]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "from nltk.collocations import *\n",
+    "bigram_measures = nltk.collocations.BigramAssocMeasures()\n",
+    "trigram_measures = nltk.collocations.TrigramAssocMeasures()\n",
+    "fourgram_measures = nltk.collocations.QuadgramAssocMeasures()\n",
+    "finder = TrigramCollocationFinder.from_words(nltk.corpus.genesis.words('english-web.txt'))\n",
+    "finder.nbest(bigram_measures.pmi, 10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35309f2c",
+   "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/AIDS CN NLP/NLP/NLP 2/Lab03(parse-tree)/nlp.txt

@@ -0,0 +1 @@
+After graduating of a Madras Institute of Technology in 1960, Kalam of a Aeronautical Development Establishment of the Defence Research and Development Organisation (by Press Information Bureau, Government of India) as a scientist after becoming a member of the Defence Research & Development Service (DRDS). He started his career by designing a small hovercraft, but remained unconvinced by his choice of a job at DRDO.alam was invited by Raja Ramanna to witness the country's first nuclear test Smiling Buddha as the representative of TBRL, even though he had not participated in its development. In the 1970s, Kalam also directed two projects, Project Devil and Project Valiant, which sought to develop ballistic missiles from the technology of the successful SLV programme