noshot 0.1.0__py3-none-any.whl

noshot/data/AIDS CN NLP/NLP/NLP 2/Lab02(stemming)/test.txt

@@ -0,0 +1 @@
+India is a diverse land of cultures languages and traditions It is known for its rich history and heritage The country has a vast landscape with mountains rivers and deserts The people of India are friendly and hospitable Indian cuisine is famous for its spices and flavors The country has a thriving film industry known as Bollywood India's festivals like Diwali and Holi are celebrated with enthusiasm India's contribution to science technology and literature is significant Overall India is a nation of beauty and diversity

noshot/data/AIDS CN NLP/NLP/NLP 2/Lab02(stemming)/tokenizing.ipynb

@@ -0,0 +1,272 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "501b401b-6f80-49b9-b496-0851d73c3b3e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['Details', 'are', 'important', 'but', 'don’t', 'be', 'obsessed', 'with', 'examples,', 'illustrations,', 'and', 'so', 'on.', 'You', 'just', 'need', 'to', 'get', 'a', 'hang', 'of', 'the', 'main', 'point', 'and', 'not', 'the', 'examples.', 'Comprehending', 'the', 'overall', 'flow', 'and', 'structure', 'will', 'help', 'you', 'analyze', 'and', 'answer', 'the', 'questions', 'flow', 'and', 'flow', 'and', 'analyze', 'and', 'analyze', 'and', 'comprehending', 'with', 'examples']\n"
+     ]
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "txt=\"Details are important but don’t be obsessed with examples, illustrations, and so on. You just need to get a hang of the main point and not the examples. Comprehending the overall flow and structure will help you analyze and answer the questions flow and flow and analyze and analyze and comprehending with examples\"\n",
+    "words = word_tokenize(txt)\n",
+    "print(words)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "430f6338-3f42-45fc-8740-83804def3d58",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Details': 1, 'are': 1, 'important': 1, 'but': 1, 'don’t': 1, 'be': 1, 'obsessed': 1, 'with': 2, 'examples,': 1, 'illustrations,': 1, 'and': 8, 'so': 1, 'on.': 1, 'You': 1, 'just': 1, 'need': 1, 'to': 1, 'get': 1, 'a': 1, 'hang': 1, 'of': 1, 'the': 4, 'main': 1, 'point': 1, 'not': 1, 'examples.': 1, 'Comprehending': 1, 'overall': 1, 'flow': 3, 'structure': 1, 'will': 1, 'help': 1, 'you': 1, 'analyze': 3, 'answer': 1, 'questions': 1, 'comprehending': 1, 'examples': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "dict = {}\n",
+    "for word in words:\n",
+    "    dict[word]=dict.setdefault(word,0)+1\n",
+    "print(dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d7d2357-6d27-4685-bd03-37e14da9ad9e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "6c2b8d4b-52c4-4c8d-a3b4-2526c90ccd57",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Details  :  0.02631578947368421\n",
+      "are  :  0.02631578947368421\n",
+      "important  :  0.02631578947368421\n",
+      "but  :  0.02631578947368421\n",
+      "don’t  :  0.02631578947368421\n",
+      "be  :  0.02631578947368421\n",
+      "obsessed  :  0.02631578947368421\n",
+      "with  :  0.05263157894736842\n",
+      "examples,  :  0.02631578947368421\n",
+      "illustrations,  :  0.02631578947368421\n",
+      "and  :  0.21052631578947367\n",
+      "so  :  0.02631578947368421\n",
+      "on.  :  0.02631578947368421\n",
+      "You  :  0.02631578947368421\n",
+      "just  :  0.02631578947368421\n",
+      "need  :  0.02631578947368421\n",
+      "to  :  0.02631578947368421\n",
+      "get  :  0.02631578947368421\n",
+      "a  :  0.02631578947368421\n",
+      "hang  :  0.02631578947368421\n",
+      "of  :  0.02631578947368421\n",
+      "the  :  0.10526315789473684\n",
+      "main  :  0.02631578947368421\n",
+      "point  :  0.02631578947368421\n",
+      "not  :  0.02631578947368421\n",
+      "examples.  :  0.02631578947368421\n",
+      "Comprehending  :  0.02631578947368421\n",
+      "overall  :  0.02631578947368421\n",
+      "flow  :  0.07894736842105263\n",
+      "structure  :  0.02631578947368421\n",
+      "will  :  0.02631578947368421\n",
+      "help  :  0.02631578947368421\n",
+      "you  :  0.02631578947368421\n",
+      "analyze  :  0.07894736842105263\n",
+      "answer  :  0.02631578947368421\n",
+      "questions  :  0.02631578947368421\n",
+      "comprehending  :  0.02631578947368421\n",
+      "examples  :  0.02631578947368421\n"
+     ]
+    }
+   ],
+   "source": [
+    "t=len(dict)\n",
+    "for word,prob in dict.items():\n",
+    "    print(word,' : ',prob/t)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "1fcfc1ff-e00a-4f37-bf40-6a11288eaa1c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Details  :  1\n",
+      "are  :  1\n",
+      "important  :  1\n",
+      "but  :  1\n",
+      "don’t  :  1\n",
+      "be  :  1\n",
+      "obsessed  :  1\n",
+      "examples,  :  1\n",
+      "illustrations,  :  1\n",
+      "so  :  1\n",
+      "on.  :  1\n",
+      "You  :  1\n",
+      "just  :  1\n",
+      "need  :  1\n",
+      "to  :  1\n",
+      "get  :  1\n",
+      "a  :  1\n",
+      "hang  :  1\n",
+      "of  :  1\n",
+      "main  :  1\n",
+      "point  :  1\n",
+      "not  :  1\n",
+      "examples.  :  1\n",
+      "Comprehending  :  1\n",
+      "overall  :  1\n",
+      "structure  :  1\n",
+      "will  :  1\n",
+      "help  :  1\n",
+      "you  :  1\n",
+      "answer  :  1\n",
+      "questions  :  1\n",
+      "comprehending  :  1\n",
+      "examples  :  1\n"
+     ]
+    }
+   ],
+   "source": [
+    "for w,f in dict.items():\n",
+    "    if(f==1):\n",
+    "        print(w, ' : ', 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "1e90382a-0f29-4ed4-988b-d2b158d5c521",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "53\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(words))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "f70b3b62-173a-4bf8-9c4e-b8e8e150250f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['Detailsare', 'areimportant', 'importantbut', 'butdon’t', 'don’tbe', 'beobsessed', 'obsessedwith', 'withexamples,', 'examples,illustrations,', 'illustrations,and', 'andso', 'soon.', 'on.You', 'Youjust', 'justneed', 'needto', 'toget', 'geta', 'ahang', 'hangof', 'ofthe', 'themain', 'mainpoint', 'pointand', 'andnot', 'notthe', 'theexamples.', 'examples.Comprehending', 'Comprehendingthe', 'theoverall', 'overallflow', 'flowand', 'andstructure', 'structurewill', 'willhelp', 'helpyou', 'youanalyze', 'analyzeand', 'andanswer', 'answerthe', 'thequestions', 'questionsflow', 'flowand', 'andflow', 'flowand', 'andanalyze', 'analyzeand', 'andanalyze', 'analyzeand', 'andcomprehending', 'comprehendingwith', 'withexamples', 'examples']\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(len(words)-1):\n",
+    "    words[i]+=words[i+1]\n",
+    "print(words)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "e85089d4-6608-48a6-ad7f-c3e443396491",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Detailsare': 1, 'areimportant': 1, 'importantbut': 1, 'butdon’t': 1, 'don’tbe': 1, 'beobsessed': 1, 'obsessedwith': 1, 'withexamples,': 1, 'examples,illustrations,': 1, 'illustrations,and': 1, 'andso': 1, 'soon.': 1, 'on.You': 1, 'Youjust': 1, 'justneed': 1, 'needto': 1, 'toget': 1, 'geta': 1, 'ahang': 1, 'hangof': 1, 'ofthe': 1, 'themain': 1, 'mainpoint': 1, 'pointand': 1, 'andnot': 1, 'notthe': 1, 'theexamples.': 1, 'examples.Comprehending': 1, 'Comprehendingthe': 1, 'theoverall': 1, 'overallflow': 1, 'flowand': 3, 'andstructure': 1, 'structurewill': 1, 'willhelp': 1, 'helpyou': 1, 'youanalyze': 1, 'analyzeand': 3, 'andanswer': 1, 'answerthe': 1, 'thequestions': 1, 'questionsflow': 1, 'andflow': 1, 'andanalyze': 2, 'andcomprehending': 1, 'comprehendingwith': 1, 'withexamples': 1, 'examples': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "pair={}\n",
+    "for w in words:\n",
+    "    if w not in pair:\n",
+    "        pair[w]=1\n",
+    "    else:\n",
+    "        pair[w]+=1\n",
+    "print(pair)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "de8b5406-67b0-4084-bc8f-661d8fc34de7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "flowand  :  3\n"
+     ]
+    }
+   ],
+   "source": [
+    "max=0\n",
+    "for w in pair:\n",
+    "    count=pair[w]\n",
+    "    if(count>max):\n",
+    "        max=count\n",
+    "        most=w\n",
+    "print(most,' : ',max)"
+   ]
+  }
+ ],
+ "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)/collocation.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6d49579f",
+   "metadata": {},
+   "source": [
+    "## Exp 4\n",
+    "\n",
+    "Code credits - [Mudit Golchha](https://github.com/mudit2004/NLP)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "25e2b36e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<head><title>Not Acceptable!</title></head><body><h1>Not Acceptable!</h1><p>An appropriate representation of the requested resource could not be found on this server. This error was generated by Mod_Security.</p></body></html>\n"
+     ]
+    }
+   ],
+   "source": [
+    "#SETTING THE TEXT FROM A URL\n",
+    "import requests\n",
+    "url = 'https://coffeeshopstartups.com/how-to-start-a-coffee-shop-blog/'\n",
+    "\n",
+    "# CREATE REQUEST\n",
+    "x = requests.get(url)\n",
+    "\n",
+    "#CONVERT REQUEST TO STRING\n",
+    "text = x.text\n",
+    "\n",
+    "#PRINT\n",
+    "print(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "ada9929d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['coffee', 'has', 'been', 'forever', 'been', 'close', 'to', 'my', 'heart', 'if', 'you', 'ask', 'me', 'i', 'don', '’', 't', 'really', 'remember', 'when', 'exactly', 'i', 'fell', 'in', 'love', 'but', 'i', 'just', 'did', 'the', 'aroma', 'the', 'taste', 'the', 'flavour', 'everything', 'is', 'so', 'therapeutic', 'i', 'am', 'sure', 'like', 'me', 'you', 'have', 'wondered', 'what', 'is', 'about', 'coffee', 'that', 'we', 'love', 'so', 'much', 'like', 'how', 'is', 'it', 'even', 'possible', 'to', 'love', 'coffee', 'so', 'muchmy', 'love', 'for', 'coffee', 'extends', 'far', 'back', 'atleast', 'a', 'decade', 'back', 'when', 'i', 'used', 'to', 'sip', 'some', 'coffee', 'here', 'and', 'there', 'it', 'then', 'grew', 'into', 'a', 'weekly', 'saturday', 'morning', 'tradition', 'almost', 'when', 'my', 'friends', 'would', 'either', 'come', 'over', 'to', 'my', 'place', 'or', 'we', 'would', 'all', 'go', 'out', 'meet', 'at', 'a', 'coffee', 'shop', 'and', 'nonchalantly', 'order', 'for', 'the', 'beverage', 'of', 'our', 'choice', '–', 'coffee', 'my', 'love', 'for', 'coffee', 'has', 'developed', 'over', 'the', 'years', 'but', 'has', 'grown', 'more', 'than', 'ever', 'especially', 'in', 'the', 'past', 'few', 'years', 'i', 'know', 'it', 'may', 'seem', 'kind', 'of', 'silly', 'to', 'some', 'to', 'love', 'something', 'like', 'a', 'beverage', 'as', 'much', 'as', 'i', 'do', 'but', 'then', 'again', 'it', '’', 's', 'more', 'than', 'just', 'a', '“', 'simple', 'beverage', '”', 'to', 'meyou', 'see', 'now', 'that', 'i', 'think', 'about', 'it', 'i', 'feel', 'there', 'is', 'no', 'smell', 'i', 'love', 'waking', 'up', 'to', 'than', 'a', 'fresh', 'brewed', 'cup', 'of', 'coffee', 'i', 'think', 'there', 'is', 'just', 'something', 'so', 'inviting', 'about', 'the', 'smell', 'of', 'coffee', 'that', 'makes', 'me', 'feel', 'so', 'ready', 'i', 'mean', 'it', '’', 's', 'almost', 'like', 'it', 'makes', 'me', 'feel', 'renewed', 'i', 'actually', 'love', 'the', 'aroma', 'of', 'coffee', 'so', 'much', 'that', 'i', 'even', 'have', 'coffee', 'scented', 'perfumes', 'that', 'i', 'use', 'of', 'course', 'there', 'is', 'the', 'taste', 'that', 'i', 'truly', 'adore', 'it', 'was', 'never', 'something', 'that', 'i', 'had', 'to', 'acquire', 'so', 'to', 'speak', 'i', 'appreciate', 'the', 'taste', 'of', 'coffee', 'without', 'any', 'cream', 'or', 'sugar', 'quite', 'franklyi', 'don', '’', 't', 'know', 'why', 'am', 'i', 'getting', 'into', 'the', 'tiny', 'details', 'about', 'its', 'aroma', 'or', 'taste', 'in', 'this', 'piece', 'of', 'blog', 'post', 'but', 'i', 'totally', 'feel', 'i', 'just', 'get', 'lost', 'when', 'it', 'comes', 'to', 'either', 'talking', 'about', 'coffee', 'or', 'penning', 'down', 'about', 'the', 'subjectat', 'the', 'end', 'of', 'it', 'all', 'i', 'would', 'want', 'to', 'say', 'one', 'simple', 'thing', '–', 'when', 'you', 'appreciate', 'coffee', 'for', 'more', 'than', 'the', 'caffeine', 'it', 'provides', 'that', '’', 's', 'when', 'you', 'truly', 'begin', 'to', 'love', 'coffee', 'that', '’', 's', 'when', 'you', 'realize', 'you', 'have', 'a', 'heart', 'of', 'coffee…']\n"
+     ]
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "import string\n",
+    "\n",
+    "#setting string\n",
+    "text = 'Coffee has been forever been close to my heart. If you ask me, I don’t really remember when exactly I fell in love, but I just did. The aroma, the taste, the flavour, everything is so therapeutic. I am sure, like me, you have wondered what is about coffee that we love so much? Like, how is it even possible to love coffee so much?My love for coffee extends far back, atleast a decade back when I used to sip some coffee here and there. It then grew into a weekly Saturday morning tradition almost, when my friends would either come over to my place or we would all go out, meet at a coffee shop and nonchalantly order for the beverage of our choice – coffee. My love for coffee has developed over the years, but has grown more than ever, especially, in the past few years. I know it may seem kind of silly to some to love something like a beverage as much as I do, but then again, it’s more than just a “simple beverage” to me.You see, now that I think about it, I feel, there is no smell I love waking up to than a fresh brewed cup of coffee. I think, there is just something so inviting about the smell of coffee that makes me feel so ready; I mean, it’s almost like it makes me feel renewed. I actually love the aroma of coffee so much that I even have coffee scented perfumes that I use! Of course, there is the taste that I truly adore, it was never something that I had to acquire, so to speak. I appreciate the taste of coffee without any cream or sugar, quite frankly.I don’t know why am I getting into the tiny details about its aroma or taste in this piece of blog post, but I totally feel, I just get lost when it comes to either talking about coffee or penning down about the subject.At the end of it all, I would want to say one simple thing – when you appreciate coffee for more than the caffeine it provides, that’s when you truly begin to love coffee. That’s when you realize, you have a heart of coffee…'\n",
+    "\n",
+    "#preparing the string\n",
+    "translating = str.maketrans('', '', string.punctuation)\n",
+    "cleaned_text = text.translate(translating)\n",
+    "token = word_tokenize(cleaned_text.lower())\n",
+    "\n",
+    "#printing the token\n",
+    "print(token)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "9c58ac9b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "hasbeen->1  beenforever->1  foreverbeen->1  beenclose->1  closeto->1  myheart->1  heartif->1  ifyou->1  youask->1  askme->1  mei->1  idon->1  treally->1  reallyremember->1  rememberwhen->1  whenexactly->1  exactlyi->1  ifell->1  fellin->1  inlove->1  lovebut->1  justdid->1  didthe->1  aromathe->1  tastethe->1  theflavour->1  flavoureverything->1  everythingis->1  isso->1  sotherapeutic->1  therapeutici->1  iam->1  amsure->1  surelike->1  likeme->1  meyou->1  havewondered->1  wonderedwhat->1  whatis->1  isabout->1  thatwe->1  welove->1  loveso->1  muchlike->1  likehow->1  howis->1  isit->1  iteven->1  evenpossible->1  possibleto->1  somuchmy->1  muchmylove->1  coffeeextends->1  extendsfar->1  farback->1  backatleast->1  atleasta->1  adecade->1  decadeback->1  backwhen->1  wheni->1  iused->1  usedto->1  tosip->1  sipsome->1  somecoffee->1  coffeehere->1  hereand->1  andthere->1  thereit->1  itthen->1  thengrew->1  grewinto->1  intoa->1  aweekly->1  weeklysaturday->1  saturdaymorning->1  morningtradition->1  traditionalmost->1  almostwhen->1  whenmy->1  myfriends->1  friendswould->1  wouldeither->1  eithercome->1  comeover->1  overto->1  myplace->1  placeor->1  orwe->1  wewould->1  wouldall->1  allgo->1  goout->1  outmeet->1  meetat->1  ata->1  acoffee->1  coffeeshop->1  shopand->1  andnonchalantly->1  nonchalantlyorder->1  orderfor->1  forthe->1  thebeverage->1  beverageof->1  ofour->1  ourchoice->1  choice–->1  –coffee->1  coffeemy->1  mylove->1  hasdeveloped->1  developedover->1  overthe->1  theyears->1  yearsbut->1  buthas->1  hasgrown->1  grownmore->1  thanever->1  everespecially->1  especiallyin->1  inthe->1  thepast->1  pastfew->1  fewyears->1  yearsi->1  iknow->1  knowit->1  itmay->1  mayseem->1  seemkind->1  kindof->1  ofsilly->1  sillyto->1  tosome->1  someto->1  lovesomething->1  somethinglike->1  likea->1  abeverage->1  beverageas->1  asmuch->1  muchas->1  asi->1  ido->1  dobut->1  butthen->1  thenagain->1  againit->1  smore->1  thanjust->1  justa->1  a“->1  “simple->1  simplebeverage->1  beverage”->1  ”to->1  tomeyou->1  meyousee->1  seenow->1  nowthat->1  thinkabout->1  aboutit->1  iti->1  ifeel->1  feelthere->1  isno->1  nosmell->1  smelli->1  ilove->1  lovewaking->1  wakingup->1  upto->1  tothan->1  thana->1  afresh->1  freshbrewed->1  brewedcup->1  cupof->1  coffeei->1  thinkthere->1  isjust->1  justsomething->1  somethingso->1  soinviting->1  invitingabout->1  thesmell->1  smellof->1  thatmakes->1  feelso->1  soready->1  readyi->1  imean->1  meanit->1  salmost->1  almostlike->1  likeit->1  itmakes->1  feelrenewed->1  renewedi->1  iactually->1  actuallylove->1  lovethe->1  aromaof->1  muchthat->1  ieven->1  evenhave->1  havecoffee->1  coffeescented->1  scentedperfumes->1  perfumesthat->1  iuse->1  useof->1  ofcourse->1  coursethere->1  isthe->1  tastethat->1  itruly->1  trulyadore->1  adoreit->1  itwas->1  wasnever->1  neversomething->1  somethingthat->1  ihad->1  hadto->1  toacquire->1  acquireso->1  soto->1  tospeak->1  speaki->1  iappreciate->1  appreciatethe->1  tasteof->1  coffeewithout->1  withoutany->1  anycream->1  creamor->1  orsugar->1  sugarquite->1  quitefranklyi->1  franklyidon->1  tknow->1  knowwhy->1  whyam->1  ami->1  igetting->1  gettinginto->1  intothe->1  thetiny->1  tinydetails->1  detailsabout->1  aboutits->1  itsaroma->1  aromaor->1  ortaste->1  tastein->1  inthis->1  thispiece->1  pieceof->1  ofblog->1  blogpost->1  postbut->1  itotally->1  totallyfeel->1  feeli->1  justget->1  getlost->1  lostwhen->1  whenit->1  itcomes->1  comesto->1  toeither->1  eithertalking->1  talkingabout->1  coffeeor->1  orpenning->1  penningdown->1  downabout->1  thesubjectat->1  subjectatthe->1  theend->1  endof->1  ofit->1  itall->1  alli->1  iwould->1  wouldwant->1  wantto->1  tosay->1  sayone->1  onesimple->1  simplething->1  thing–->1  –when->1  youappreciate->1  appreciatecoffee->1  coffeefor->1  formore->1  thanthe->1  thecaffeine->1  caffeineit->1  itprovides->1  providesthat->1  youtruly->1  trulybegin->1  beginto->1  yourealize->1  realizeyou->1  havea->1  aheart->1  heartof->1  ofcoffee…->1  coffeehas->2  tomy->2  don’->2  ’t->2  buti->2  ijust->2  thearoma->2  youhave->2  aboutcoffee->2  somuch->2  lovecoffee->2  coffeeso->2  lovefor->2  forcoffee->2  it’->2  ithink->2  aboutthe->2  makesme->2  mefeel->2  that’->2  swhen->2  thetaste->3  coffeethat->3  tolove->3  morethan->3  thereis->3  whenyou->3  ’s->4  ofcoffee->4  thati->5  "
+     ]
+    }
+   ],
+   "source": [
+    "#FINDING THE FREQ NOW OF PAIRS OF WORDS\n",
+    "Elements_count = {}\n",
+    "for i in range(len(token)):\n",
+    "    if(i != len(token)-1):\n",
+    "        a = token[i]+token[i+1]\n",
+    "        if a in Elements_count:\n",
+    "            Elements_count[a] += 1\n",
+    "        else:\n",
+    "            Elements_count[a] = 1\n",
+    "            \n",
+    "#SORTING THE DICTIONARY\n",
+    "sorted_dict = dict(sorted(Elements_count .items(), key=lambda item: item[1]))\n",
+    "\n",
+    "#PRINTING THE DICTIONARY\n",
+    "for key, value in sorted_dict.items():\n",
+    "   print(f\"{key}->{value}\",end='  ')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "b1faa524",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The number of times 'i' has come: 22\n"
+     ]
+    }
+   ],
+   "source": [
+    "#NOW FINDING HOW MANY TIMES 'i' HAS COME\n",
+    "i_count = 0\n",
+    "for j in range(len(token)):\n",
+    "    if token[j] == 'i':\n",
+    "        i_count +=1\n",
+    "print(\"The number of times \\'i\\' has come:\",i_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "59d0d270",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The number of times 'that' has come: 9\n"
+     ]
+    }
+   ],
+   "source": [
+    "#SIMILARLY FINDING FOR 'that'\n",
+    "that_count = 0\n",
+    "for j in range(len(token)):\n",
+    "    if token[j] == 'that':\n",
+    "        that_count +=1\n",
+    "print(\"The number of times \\'that\\' has come:\",that_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "bdfb07a2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total count of toekn : 389\n"
+     ]
+    }
+   ],
+   "source": [
+    "#TOTAL NUMBER OF WORDS\n",
+    "total_count = len(token)\n",
+    "print(\"Total count of toekn :\",total_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "62562a76",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The null hypothesis is : 0.0013084766820203409\n",
+      "The observed is : 0.012853470437017995\n",
+      "The value of t-test is : 17.71528322212498\n",
+      "Since the confidence level id 0.005 and  17.71528322212498 > 3.169 , we can reject it and Hence it is a collocation\n"
+     ]
+    }
+   ],
+   "source": [
+    "import math\n",
+    "\n",
+    "#T-TEST FOR 'thati'\n",
+    "Null_hypothesis = (i_count/total_count)*(that_count/total_count)\n",
+    "print(\"The null hypothesis is :\",Null_hypothesis)\n",
+    "observed = (5/total_count)\n",
+    "print(\"The observed is :\", observed)\n",
+    "\n",
+    "t_test = (observed-Null_hypothesis)/(math.sqrt(math.pow(observed,2)/total_count))\n",
+    "print(\"The value of t-test is :\",t_test)\n",
+    "\n",
+    "print(\"Since the confidence level id 0.005 and \",t_test,'>',\"3.169 , we can reject it and Hence it is a collocation\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "04396255",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5\n",
+      "4\n",
+      "17\n",
+      "362\n"
+     ]
+    }
+   ],
+   "source": [
+    "#NOW HYPOTHESIS TEST\n",
+    "thati_count = 0\n",
+    "that_other_count = 0\n",
+    "other_i_count = 0\n",
+    "other_count = 0\n",
+    "\n",
+    "for j in range(len(token)):\n",
+    "    if(j< len(token)-1):\n",
+    "        if(token[j] == 'that' and token[j+1] == 'i'):\n",
+    "            thati_count +=1\n",
+    "        elif(token[j] == 'that' and token[j+1] != 'i'):\n",
+    "            that_other_count += 1\n",
+    "        elif(token[j] != 'that' and token[j+1] == 'i'):\n",
+    "            other_i_count += 1\n",
+    "        elif(token[j] != 'that' and token[j+1] != 'i'):\n",
+    "            other_count += 1\n",
+    "            \n",
+    "#PRINTING\n",
+    "print(thati_count)\n",
+    "print(that_other_count) \n",
+    "print(other_i_count)\n",
+    "print(other_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "35ec04f5",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The value of that i : 0.5089974293059126\n",
+      "The value of that other : 0.09254498714652956\n",
+      "The value of other i : 0.961439588688946\n",
+      "The value of other : 362.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "#PRINTING\n",
+    "print(\"The value of that i :\",(i_count*that_count)/total_count)\n",
+    "print(\"The value of that other :\",(that_count*that_other_count)/total_count)\n",
+    "print(\"The value of other i :\",(i_count*other_i_count)/total_count)\n",
+    "print(\"The value of other :\",(other_count*total_count)/total_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "2f6a88f4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "i =(i_count*that_count)/total_count\n",
+    "j = (that_count*that_other_count)/total_count\n",
+    "k =(i_count*other_i_count)/total_count\n",
+    "l = (other_count*total_count)/total_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "de862f55",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The hypothesis test is : 472.158941601101\n"
+     ]
+    }
+   ],
+   "source": [
+    "#NOW x^2\n",
+    "a = math.pow(thati_count-i,2)/i\n",
+    "b = math.pow(that_other_count-j,2)/j\n",
+    "c = math.pow(other_i_count-k,2)/k\n",
+    "d = math.pow(other_count-l,2)/l\n",
+    "hypothesis =a+b+c+d\n",
+    "print(\"The hypothesis test is :\",hypothesis)"
+   ]
+  }
+ ],
+ "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
+}