{ "cells": [ { "cell_type": "markdown", "id": "1f41de4f", "metadata": { "id": "1f41de4f" }, "source": [ "# Wprowadzenie do NLP w Pythonie\n", "- Tokenizacja, Lematyzacja i stemming\n", "- Embedding\n", "- Podobieństwo cosinusowe\n", "- Gra słowa: Ciepło - Zimno\n", "\n" ] }, { "cell_type": "markdown", "source": [], "metadata": { "id": "uhWUmrthslFf" }, "id": "uhWUmrthslFf" }, { "cell_type": "markdown", "source": [ "## 1. Tokenizacja, lematyzacja, stemming" ], "metadata": { "id": "-i50vfsGsN4o" }, "id": "-i50vfsGsN4o" }, { "cell_type": "code", "execution_count": null, "id": "4613333a", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "4613333a", "outputId": "11b31106-b285-44db-d5d2-fe7edf8f0729" }, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n", "[nltk_data] Unzipping tokenizers/punkt_tab.zip.\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "Zdania: ['NLP to skrót od Natural Language Processing!', 'Po polsku to Przetwarzanie Języka Naturalnego']\n", "Tokeny: ['NLP', 'to', 'skrót', 'od', 'Natural', 'Language', 'Processing', '!', 'Po', 'polsku', 'to', 'Przetwarzanie', 'Języka', 'Naturalnego']\n" ] } ], "source": [ "#Biblioteka NLTK\n", "import nltk\n", "from nltk.tokenize import word_tokenize, sent_tokenize\n", "nltk.download('punkt_tab')\n", "\n", "text = \"NLP to skrót od Natural Language Processing! Po polsku to Przetwarzanie Języka Naturalnego\"\n", "print(\"Zdania:\", sent_tokenize(text))\n", "print(\"Tokeny:\", word_tokenize(text))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "f37f6bc5", "metadata": { "id": "f37f6bc5", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "041991be-ebdb-4878-d9cc-874da5dbc596" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Word Lemma Stem \n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package wordnet to /root/nltk_data...\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "running run run \n", "ran run ran \n", "easily easily easili \n", "easy easy easi \n", "studied study studi \n", "studying study studi \n", "studies study studi \n" ] } ], "source": [ "from nltk.stem import WordNetLemmatizer, SnowballStemmer\n", "lemmatizer = WordNetLemmatizer()\n", "stemmer = SnowballStemmer(\"english\")\n", "nltk.download('wordnet')\n", "\n", "words = [\"running\", \"ran\", \"easily\", \"easy\", \"studied\",\"studying\",\"studies\"]\n", "print(\"{:<10} {:<10} {:<10}\".format(\"Word\", \"Lemma\", \"Stem\"))\n", "for w in words:\n", " print(\"{:<10} {:<10} {:<10}\".format(w, lemmatizer.lemmatize(w, pos='v'), stemmer.stem(w)))\n" ] }, { "cell_type": "markdown", "source": [ "## 2. Embedding - słowa na wektory" ], "metadata": { "id": "mab1LD_ulnbQ" }, "id": "mab1LD_ulnbQ" }, { "cell_type": "code", "source": [ "# Usuń wszystkie wersje scipy i numpy\n", "!pip uninstall -y scipy numpy -q\n", "\n", "# Zainstaluj konkretne wersje zgodne z gensim\n", "!pip install numpy==1.26.4 scipy==1.12.0 --no-deps --force-reinstall --no-cache-dir -q\n", "\n", "# Zainstaluj gensim w wersji 4.3.2 – stabilna i zgodna\n", "!pip install gensim==4.3.2 --no-deps --force-reinstall --no-cache-dir -q" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "jf5WMwkVqmuF", "outputId": "0d3de262-2b1d-461c-d5cc-b1da1620221c" }, "id": "jf5WMwkVqmuF", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m20.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.3/18.3 MB\u001b[0m \u001b[31m253.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.4/38.4 MB\u001b[0m \u001b[31m250.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m26.7/26.7 MB\u001b[0m \u001b[31m239.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h" ] } ] }, { "cell_type": "code", "source": [ "import os\n", "print(\"Restartuję runtime\")\n", "os.kill(os.getpid(), 9)\n" ], "metadata": { "id": "UhU-IVuKqnpn" }, "id": "UhU-IVuKqnpn", "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Tylko sprawdzenie wersji\n", "import scipy\n", "print(\"✅ SciPy version:\", scipy.__version__) # powinno dać 1.12.0\n", "\n", "# Test ładowania modelu GloVe\n", "import gensim\n", "from gensim.downloader import load\n", "\n", "print(\"Ładowanie modelu GloVe...\")\n", "model = load(\"glove-wiki-gigaword-100\")\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "X9PoIIBzqquo", "outputId": "2916c4e9-d046-4d9c-8872-ed56066c916e" }, "id": "X9PoIIBzqquo", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "✅ SciPy version: 1.12.0\n", "Ładowanie modelu GloVe...\n", "[==================================================] 100.0% 128.1/128.1MB downloaded\n" ] } ] }, { "cell_type": "code", "source": [ "print(\"dog →\", model[\"dog\"][:10])\n", "print(\"dogs →\", model[\"dogs\"][:10])\n", "print(\"cat →\", model[\"cat\"][:10])\n", "print(\"music →\", model[\"music\"][:10])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "noRSUNABL0gN", "outputId": "88a775e7-9a7e-4d61-8a78-06ee12c96946" }, "id": "noRSUNABL0gN", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "dog → [ 0.30817 0.30938 0.52803 -0.92543 -0.73671 0.63475 0.44197 0.10262\n", " -0.09142 -0.56607]\n", "dogs → [ 0.37861 0.30269 0.27838 -0.92052 -0.79141 0.75824 0.12946 0.28971\n", " -0.38836 -0.39586]\n", "cat → [ 0.23088 0.28283 0.6318 -0.59411 -0.58599 0.63255 0.24402\n", " -0.14108 0.060815 -0.7898 ]\n", "music → [ 0.12705 0.37253 0.23076 -0.10727 1.4273 0.7799 -0.055009\n", " -0.18909 -0.42828 0.28443 ]\n" ] } ] }, { "cell_type": "code", "source": [ "slowo = input(\"Wpisz dowolne angielskie słowo: \").lower()\n", "\n", "if slowo in model:\n", " print(f\"Najbardziej podobne słowa do '{slowo}' to:\")\n", " podobne = model.most_similar(slowo, topn=5)\n", " for s, podobienstwo in podobne:\n", " print(f\"{s} (podobieństwo: {podobienstwo:.2f})\")\n", "else:\n", " print(\"To słowo nie istnieje w modelu. Spróbuj inne!\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "NPF3RugvKnRI", "outputId": "e6872492-7cfa-4254-90c5-f14bf1270ca1" }, "id": "NPF3RugvKnRI", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Wpisz dowolne angielskie słowo: hospital\n", "Najbardziej podobne słowa do 'hospital' to:\n", "clinic (podobieństwo: 0.81)\n", "medical (podobieństwo: 0.78)\n", "hospitals (podobieństwo: 0.77)\n", "nursing (podobieństwo: 0.71)\n", "hospitalized (podobieństwo: 0.69)\n" ] } ] }, { "cell_type": "markdown", "id": "50821d9e", "metadata": { "id": "50821d9e" }, "source": [ "## 3. Podobieństwo cosinusowe" ] }, { "cell_type": "code", "execution_count": null, "id": "b8036f26", "metadata": { "id": "b8036f26", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "fcd1b0d0-58d2-48d4-9a86-255ebada376b" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Podobieństwo 'dog' vs 'cat': 0.8798075\n", "Podobieństwo 'dog' vs 'century': 0.12041345\n" ] } ], "source": [ "from sklearn.metrics.pairwise import cosine_similarity\n", "def cos_sim(a, b):\n", " return cosine_similarity([a], [b])[0][0]\n", "print(\"Podobieństwo 'dog' vs 'cat':\", cos_sim(model['dog'], model['cat']))\n", "print(\"Podobieństwo 'dog' vs 'century':\", cos_sim(model['dog'], model['century']))" ] }, { "cell_type": "markdown", "id": "79ddbb2c", "metadata": { "id": "79ddbb2c" }, "source": [ "## 4. Gra: Ciepło–Zimno" ] }, { "cell_type": "code", "source": [ "import random\n", "\n", "# Zakładamy, że model i cos_sim są już załadowane:\n", "# model = load(\"glove-wiki-gigaword-50\")\n", "# def cos_sim(a, b): return cosine_similarity([a], [b])[0][0]\n", "\n", "vocab = [w for w in model.index_to_key if w.isalpha() and len(w) > 3]\n", "target = random.choice(vocab)\n", "\n", "print(\"Zgadnij słowo (angielskie). Wpisz 'exit' by zakończyć.\")\n", "\n", "last_sim = None\n", "wrong_guesses = 0\n", "hint_progress = 0 # ile liter ma zostać pokazanych jako podpowiedź\n", "\n", "while True:\n", " guess = input(\">>> \").lower().strip()\n", "\n", " if guess == 'exit':\n", " print(\"Koniec gry. Słowo to:\", target)\n", " break\n", "\n", " if guess == target:\n", " print(\"Brawo! Zgadłeś/-aś!\")\n", " break\n", "\n", " if guess not in model:\n", " print(\"Nie znam tego słowa.\")\n", " continue\n", "\n", " sim = cos_sim(model[guess], model[target])\n", "\n", " if last_sim is None:\n", " print(f\"Podobieństwo: {sim:.4f}\")\n", " else:\n", " print(\"Ciepło!\" if sim > last_sim else \"Zimno!\", f\"(sim = {sim:.4f})\")\n", "\n", " last_sim = sim\n", " wrong_guesses += 1\n", "\n", " # Podpowiedź po 3. błędach i dalej\n", " if wrong_guesses >= 3:\n", " hint_progress = min(wrong_guesses - 2, len(target)) # nie wyjść poza długość słowa\n", " hint = target[:hint_progress] + \"_\" * (len(target) - hint_progress)\n", " print(f\"Podpowiedź: {hint}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "THBz6Iu5gn2a", "outputId": "dbf41de4-ef46-4e15-b7b6-5162568f643f" }, "id": "THBz6Iu5gn2a", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Zgadnij słowo (angielskie). Wpisz 'exit' by zakończyć.\n", ">>> exit\n", "Koniec gry. Słowo to: menzah\n" ] } ] }, { "cell_type": "markdown", "source": [ "#### Wersja kodu z wbudowaną listą angielskich słówek na poziomie A2" ], "metadata": { "id": "XOpQRfIvlIiK" }, "id": "XOpQRfIvlIiK" }, { "cell_type": "code", "source": [ "\n", "# Lista słów A2\n", "a2_words = {\n", " \"ability\", \"able\", \"about\", \"above\", \"accident\", \"activity\", \"actor\", \"actress\", \"add\", \"address\", \"adult\",\n", " \"advice\", \"aeroplane\", \"afraid\", \"after\", \"afternoon\", \"again\", \"against\", \"age\", \"ago\", \"agree\", \"air\",\n", " \"airport\", \"album\", \"all\", \"all right\", \"almost\", \"along\", \"already\", \"alright\", \"also\", \"always\", \"amazing\",\n", " \"ambulance\", \"amount\", \"and\", \"angry\", \"animal\", \"another\", \"answer\", \"any\", \"anybody\", \"anyone\", \"anything\",\n", " \"anywhere\", \"apartment\", \"apple\", \"April\", \"area\", \"arm\", \"around\", \"arrive\", \"art\", \"article\", \"artist\",\n", " \"as\", \"ask\", \"at\", \"aunt\", \"autumn\", \"away\", \"baby\", \"back\", \"bad\", \"bag\", \"bake\", \"ball\", \"banana\", \"band\",\n", " \"bank\", \"bar\", \"base\", \"baseball\", \"basket\", \"basketball\", \"bath\", \"bathroom\", \"be\", \"bean\", \"bear\", \"beautiful\",\n", " \"because\", \"become\", \"bed\", \"bedroom\", \"beer\", \"before\", \"begin\", \"behind\", \"believe\", \"bell\", \"below\", \"best\",\n", " \"better\", \"between\", \"bicycle\", \"big\", \"bike\", \"bill\", \"bird\", \"birthday\", \"black\", \"blond\", \"blog\", \"blue\",\n", " \"board\", \"boat\", \"body\", \"boil\", \"book\", \"boot\", \"bored\", \"boring\", \"both\", \"bottle\", \"box\", \"boy\", \"boyfriend\",\n", " \"bread\", \"break\", \"breakfast\", \"bring\", \"brother\", \"brown\", \"build\", \"building\", \"bus\", \"business\", \"busy\",\n", " \"but\", \"butter\", \"buy\", \"by\", \"bye\", \"cafe\", \"cake\", \"call\", \"camera\", \"can\", \"cannot\", \"cap\", \"capital\", \"car\",\n", " \"card\", \"care\", \"careful\", \"carefully\", \"carry\", \"cat\", \"CD\", \"cent\", \"center\", \"century\", \"certainly\", \"chair\",\n", " \"change\", \"chart\", \"cheap\", \"check\", \"cheese\", \"chicken\", \"child\", \"chocolate\", \"choose\", \"cinema\", \"city\",\n", " \"class\", \"classmate\", \"classroom\", \"clean\", \"clear\", \"clearly\", \"climb\", \"clock\", \"close\", \"clothes\", \"cloud\",\n", " \"club\", \"coat\", \"coffee\", \"cold\", \"college\", \"color\", \"come\", \"common\", \"company\", \"compare\", \"complete\",\n", " \"computer\", \"concert\", \"conversation\", \"cook\", \"cooker\", \"cooking\", \"cool\", \"correct\", \"cost\", \"could\",\n", " \"country\", \"course\", \"cousin\", \"cow\", \"cream\", \"create\", \"cricket\", \"cross\", \"crown\", \"cry\", \"cup\", \"customer\",\n", " \"cut\", \"dad\", \"dance\", \"dancer\", \"dancing\", \"dangerous\", \"dark\", \"date\", \"daughter\", \"day\", \"dear\", \"decide\",\n", " \"deep\", \"delicious\", \"describe\", \"description\", \"design\", \"desk\", \"dictionary\", \"die\", \"different\", \"difficult\",\n", " \"dinner\", \"dirty\", \"discuss\", \"discussion\", \"dish\", \"do\", \"doctor\", \"dog\", \"dollar\", \"door\", \"down\", \"draw\",\n", " \"dream\", \"dress\", \"drink\", \"drive\", \"driver\", \"during\", \"each\", \"ear\", \"early\", \"east\", \"easy\", \"eat\", \"egg\",\n", " \"eighteen\", \"eighty\", \"either\", \"elephant\", \"eleven\", \"email\", \"end\", \"engine\", \"enjoy\", \"enough\", \"enter\",\n", " \"environment\", \"eraser\", \"euro\", \"even\", \"evening\", \"event\", \"ever\", \"every\", \"everybody\", \"everyone\",\n", " \"everything\", \"everywhere\", \"exam\", \"example\", \"excited\", \"exciting\", \"exercise\", \"expensive\", \"explain\",\n", " \"extra\", \"eye\", \"face\", \"fact\", \"fall\", \"family\", \"famous\", \"far\", \"farm\", \"farmer\", \"fast\", \"fat\", \"father\",\n", " \"favorite\", \"feel\", \"feeling\", \"festival\", \"few\", \"field\", \"fifteen\", \"fifth\", \"fifty\", \"fill\", \"film\",\n", " \"final\", \"find\", \"fine\", \"finger\", \"finish\", \"fire\", \"first\", \"fish\", \"five\", \"flat\", \"flight\", \"floor\",\n", " \"flower\", \"fly\", \"follow\", \"food\", \"foot\", \"football\", \"for\", \"forget\", \"form\", \"four\", \"fourteen\", \"free\",\n", " \"Friday\", \"friend\", \"friendly\", \"from\", \"front\", \"fruit\", \"full\", \"fun\", \"funny\", \"future\", \"game\", \"garden\",\n", " \"geography\", \"get\", \"gift\", \"girl\", \"girlfriend\", \"give\", \"glass\", \"glasses\", \"go\", \"good\", \"goodbye\",\n", " \"grandfather\", \"grandmother\", \"grape\", \"great\", \"green\", \"group\", \"grow\", \"guess\", \"guitar\", \"hair\", \"half\",\n", " \"hall\", \"hamburger\", \"hand\", \"happen\", \"happy\", \"hard\", \"hat\", \"hate\", \"have\", \"he\", \"head\", \"health\", \"healthy\",\n", " \"hear\", \"heart\", \"hello\", \"help\", \"her\", \"here\", \"hi\", \"high\", \"history\", \"hobby\", \"hold\", \"holiday\", \"home\",\n", " \"homework\", \"hope\", \"horse\", \"hospital\", \"hot\", \"hotel\", \"hour\", \"house\", \"how\", \"hundred\", \"hungry\", \"hurry\",\n", " \"hurt\", \"husband\", \"I\", \"ice\", \"ice cream\", \"idea\", \"if\", \"important\", \"improve\", \"in\", \"include\", \"information\",\n", " \"interested\", \"interesting\", \"internet\", \"into\", \"invite\", \"island\", \"it\", \"its\", \"jacket\", \"jam\", \"job\", \"join\",\n", " \"journey\", \"juice\", \"jump\", \"just\", \"keep\", \"key\", \"kick\", \"kid\", \"kill\", \"kind\", \"kitchen\", \"know\", \"language\",\n", " \"large\", \"last\", \"late\", \"later\", \"laugh\", \"lazy\", \"learn\", \"leave\", \"left\", \"leg\", \"lemon\", \"lesson\", \"let\",\n", " \"letter\", \"library\", \"lie\", \"life\", \"light\", \"like\", \"line\", \"lion\", \"listen\", \"little\", \"live\", \"long\", \"look\",\n", " \"lose\", \"lot\", \"love\", \"low\", \"lunch\", \"machine\", \"magazine\", \"main\", \"make\", \"man\", \"many\", \"map\", \"market\",\n", " \"married\", \"match\", \"matter\", \"may\", \"maybe\", \"me\", \"meal\", \"mean\", \"meat\", \"medicine\", \"meet\", \"meeting\",\n", " \"member\", \"message\", \"meter\", \"midnight\", \"milk\", \"million\", \"minute\", \"miss\", \"mistake\", \"model\", \"modern\",\n", " \"moment\", \"money\", \"monkey\", \"month\", \"moon\", \"more\", \"morning\", \"most\", \"mother\", \"mountain\", \"mouse\",\n", " \"mouth\", \"move\", \"movie\", \"much\", \"mum\", \"museum\", \"music\", \"must\", \"my\", \"name\", \"narrow\", \"national\",\n", " \"nature\", \"near\", \"neck\", \"need\", \"negative\", \"never\", \"new\", \"news\", \"newspaper\", \"next\", \"nice\", \"night\",\n", " \"no\", \"noise\", \"noisy\", \"north\", \"nose\", \"not\", \"note\", \"nothing\", \"now\", \"number\", \"nurse\", \"object\",\n", " \"ocean\", \"of\", \"off\", \"offer\", \"office\", \"often\", \"oh\", \"oil\", \"old\", \"on\", \"one\", \"only\", \"open\", \"or\",\n", " \"orange\", \"order\", \"other\", \"our\", \"out\", \"outside\", \"over\", \"own\", \"page\", \"paint\", \"pair\", \"paper\",\n", " \"parent\", \"park\", \"part\", \"partner\", \"party\", \"pass\", \"past\", \"pen\", \"pencil\", \"people\", \"pepper\", \"perfect\",\n", " \"person\", \"pet\", \"phone\", \"photo\", \"photograph\", \"photographer\", \"physics\", \"picture\", \"piece\", \"pig\", \"pilot\",\n", " \"pink\", \"pizza\", \"place\", \"plane\", \"plant\", \"plastic\", \"plate\", \"play\", \"player\", \"please\", \"plenty\", \"pocket\",\n", " \"police\", \"polite\", \"pool\", \"poor\", \"pop\", \"popular\", \"possible\", \"post\", \"postcard\", \"potato\", \"pound\",\n", " \"practice\", \"prefer\", \"prepare\", \"present\", \"pretty\", \"print\", \"problem\", \"program\", \"project\", \"pull\",\n", " \"purple\", \"push\", \"put\", \"quarter\", \"question\", \"quick\", \"quiet\", \"radio\", \"rain\", \"rainy\", \"read\", \"ready\",\n", " \"real\", \"really\", \"receive\", \"red\", \"remember\", \"repeat\", \"report\", \"rest\", \"restaurant\", \"return\", \"rice\",\n", " \"ride\", \"right\", \"river\", \"road\", \"room\", \"run\", \"sad\", \"safe\", \"salad\", \"salt\", \"same\", \"sandwich\", \"Saturday\",\n", " \"save\", \"say\", \"school\", \"science\", \"scientist\", \"score\", \"sea\", \"season\", \"seat\", \"second\", \"see\", \"sell\",\n", " \"send\", \"sentence\", \"September\", \"seven\", \"seventeen\", \"seventy\", \"several\", \"shake\", \"shall\", \"shampoo\",\n", " \"share\", \"she\", \"sheep\", \"shirt\", \"shoe\", \"shop\", \"shopping\", \"short\", \"should\", \"shoulder\", \"show\", \"sick\",\n", " \"side\", \"sign\", \"silver\", \"similar\", \"simple\", \"since\", \"sing\", \"singer\", \"sister\", \"sit\", \"six\", \"sixteen\",\n", " \"sixty\", \"size\", \"skate\", \"skateboard\", \"ski\", \"skirt\", \"sky\", \"sleep\", \"slow\", \"small\", \"smile\", \"snow\",\n", " \"so\", \"soap\", \"soccer\", \"social\", \"some\", \"somebody\", \"someone\", \"something\", \"sometimes\", \"son\", \"song\",\n", " \"soon\", \"sorry\", \"sound\", \"soup\", \"south\", \"space\", \"speak\", \"special\", \"spell\", \"spend\", \"sport\", \"spring\",\n", " \"stand\", \"star\", \"start\", \"station\", \"stay\", \"steak\", \"still\", \"stomach\", \"stop\", \"store\", \"story\", \"straight\",\n", " \"strange\", \"street\", \"strong\", \"student\", \"study\", \"stupid\", \"style\", \"subject\", \"success\", \"sugar\", \"summer\",\n", " \"sun\", \"Sunday\", \"supermarket\", \"sure\", \"surprise\", \"swim\", \"swimming\", \"table\", \"take\", \"talk\", \"tall\", \"tape\",\n", " \"taste\", \"taxi\", \"tea\", \"teach\", \"teacher\", \"team\", \"tell\", \"ten\"\n", "}\n", "\n", "# Filtrowanie słów obecnych w modelu\n", "vocab = [w for w in a2_words if w in model.key_to_index]\n", "target = random.choice(vocab)\n", "\n", "print(\"Zgadnij słowo. Wpisz 'exit', by zakończyć.\")\n", "\n", "# Funkcja podobieństwa\n", "def cos_sim(a, b):\n", " return cosine_similarity([a], [b])[0][0]\n", "\n", "# Zmienna pomocnicza\n", "last_sim = None\n", "wrong_guesses = 0\n", "hint_progress = 0\n", "\n", "# Główna pętla gry\n", "while True:\n", " guess = input(\">>> \").lower().strip()\n", "\n", " if guess == 'exit':\n", " print(\"Koniec gry. Szukane słowo to:\", target)\n", " break\n", "\n", " if guess == target:\n", " print(\"Brawo! Zgadłeś/-aś słowo!\")\n", " break\n", "\n", " if guess not in model:\n", " print(\"Nie znam tego słowa.\")\n", " continue\n", "\n", " sim = cos_sim(model[guess], model[target])\n", "\n", " if last_sim is None:\n", " print(f\"Podobieństwo: {sim:.4f}\")\n", " else:\n", " print(\"Ciepło!\" if sim > last_sim else \"Zimno!\", f\"(sim = {sim:.4f})\")\n", "\n", " last_sim = sim\n", " wrong_guesses += 1\n", "\n", " if wrong_guesses >= 3:\n", " hint_progress = min(wrong_guesses - 2, len(target))\n", " hint = target[:hint_progress] + \"_\" * (len(target) - hint_progress)\n", " print(f\"Podpowiedź: {hint}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-gNBVYfspdyG", "outputId": "851b3daa-8947-4439-8161-f6ad97e9cbaf", "collapsed": true }, "id": "-gNBVYfspdyG", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Zgadnij słowo. Wpisz 'exit', by zakończyć.\n", ">>> hospital\n", "🔎 Podobieństwo: 0.3231\n", ">>> cat\n", "Zimno! (sim = 0.2823)\n", ">>> car\n", "Ciepło! (sim = 0.3315)\n", "Podpowiedź: s_____\n", ">>> sun\n", "Ciepło! (sim = 0.5008)\n", "Podpowiedź: sp____\n", ">>> sunglasses\n", "Zimno! (sim = 0.0757)\n", "Podpowiedź: spr___\n", ">>> spring\n", "Brawo! Zgadłeś/-aś słowo!\n" ] } ] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" } }, "nbformat": 4, "nbformat_minor": 5 }