s445887/KWT-2024
1
0
Fork 0
forked from bfijalkowski/KWT-2024
Code Pull Requests Activity

Labs

Browse Source
This commit is contained in:
potato 2024-04-15 21:46:15 +02:00
parent 71ca3b66ed
commit e5ed49b0b0
3 changed files with 286 additions and 163 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

111
lab/lab_01.ipynb
View File

@ -82,7 +82,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 5,
"id": "compact-trinidad", "id": "compact-trinidad",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -92,7 +92,7 @@
"['Press the ENTER button']" "['Press the ENTER button']"
] ]
}, },
"execution_count": 3, "execution_count": 5,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -119,7 +119,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 6,
"id": "exposed-daniel", "id": "exposed-daniel",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -139,7 +139,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 7,
"id": "serial-velvet", "id": "serial-velvet",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -149,7 +149,7 @@
"['Press the ENTER button', 'Press the ENTER key']" "['Press the ENTER button', 'Press the ENTER key']"
] ]
}, },
"execution_count": 5, "execution_count": 7,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -176,17 +176,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 11,
"id": "every-gibson", "id": "every-gibson",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"[]" "['Press the ENTER button', 'Press the ENTER key']"
] ]
}, },
"execution_count": 6, "execution_count": 11,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -213,13 +213,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 9,
"id": "protected-rings", "id": "protected-rings",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " return [entry[1] for entry in translation_memory if entry[0].lower() == sentence.lower()]"
] ]
}, },
{ {
@ -232,17 +232,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 13,
"id": "severe-alloy", "id": "severe-alloy",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "['Press the ENTER button', 'Press the ENTER key']"
] ]
}, },
"execution_count": 18, "execution_count": 13,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -261,13 +261,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 12,
"id": "structural-diesel", "id": "structural-diesel",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import re\n",
"\n",
"def remove_punctuation(sentence):\n",
" return re.sub(r'[^\\w\\s]', '', sentence)\n",
"\n",
"\n",
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " return [entry[1] for entry in translation_memory\n",
" if entry[0].lower() == remove_punctuation(sentence.lower())]"
] ]
}, },
{ {
@ -280,17 +287,17 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 27,
"id": "brief-senegal", "id": "brief-senegal",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"''" "['System restart required']"
] ]
}, },
"execution_count": 12, "execution_count": 27,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -317,13 +324,26 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 26,
"id": "mathematical-customs", "id": "mathematical-customs",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import re\n",
"\n",
"def remove_punctuation(sentence):\n",
" return re.sub(r'[^\\w\\s]', '', sentence)\n",
"\n",
"\n",
"def tm_lookup(sentence):\n", "def tm_lookup(sentence):\n",
" return ''" " values = []\n",
" for entry in translation_memory:\n",
" key = set(entry[0].lower().split())\n",
" mod_sentence = set(remove_punctuation(sentence.lower()).split())\n",
" remainder = list(key - mod_sentence)\n",
" if len(remainder) <= 1:\n",
" values.append(entry[1])\n",
" return values"
] ]
}, },
{ {
@ -344,7 +364,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 42,
"id": "humanitarian-wrong", "id": "humanitarian-wrong",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -362,7 +382,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 43,
"id": "located-perception", "id": "located-perception",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,17 +394,31 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 44,
"id": "3437b88b",
"metadata": {},
"outputs": [],
"source": [
"glossary = [('komputer', 'computer'), ('przycisk', 'button'), ('drukarka', 'printer')]\n",
"\n",
"def glossary_lookup(sentence):\n",
" sentence_words = sentence.split()\n",
" return [entry for entry in glossary if entry[0] in sentence_words]"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "advised-casting", "id": "advised-casting",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"[('przycisk', 'button'), ('drukarka', 'printer')]" "[('drukarka', 'printer'), ('przycisk', 'button')]"
] ]
}, },
"execution_count": 17, "execution_count": 51,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -406,7 +440,7 @@
"id": "defensive-fifteen", "id": "defensive-fifteen",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Operacja split w pierwszej linijce funkcji moze zostac uznana za stala. Biorac pod uwage ze lista krotek zawierajaca glosariusz musi byc przejrzana za kazdym razem cala, jak i caly string – skomplikowaność obliczen bedzie wynosic O(n*m)."
] ]
}, },
{ {
@ -419,13 +453,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 48,
"id": "original-tunisia", "id": "original-tunisia",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" return ''" " sentence_words = [ element.lower() for element in sentence.split()]\n",
" return [entry for entry in glossary if entry[0].lower() in sentence_words]"
] ]
}, },
{ {
@ -438,13 +473,27 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 49,
"id": "f69a873a",
"metadata": {},
"outputs": [],
"source": [
"glossary = [('komputer', 'computer'), ('przycisk', 'button'), ('drukarka', 'printer')]\n",
"glossary = { k:v for k,v in glossary}\n",
"translated_words = list(glossary.keys())"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "adolescent-semiconductor", "id": "adolescent-semiconductor",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def glossary_lookup(sentence):\n", "def glossary_lookup(sentence):\n",
" return ''" " words = sentence.split()\n",
" \n",
" return [(word, glossary[word]) for word in words if word in translated_words]"
] ]
} }
], ],
@ -467,7 +516,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.11.0"
}, },
"subtitle": "1. Podstawowe techniki wspomagania tłumaczenia", "subtitle": "1. Podstawowe techniki wspomagania tłumaczenia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

111
lab/lab_02.ipynb
View File

@ -67,7 +67,9 @@
" ('Sprawdź ustawienia sieciowe', 'Check the network settings'),\n", " ('Sprawdź ustawienia sieciowe', 'Check the network settings'),\n",
" ('Drukarka jest wyłączona', 'The printer is switched off'),\n", " ('Drukarka jest wyłączona', 'The printer is switched off'),\n",
" ('Wymagane ponowne uruchomienie komputera', 'System restart required')\n", " ('Wymagane ponowne uruchomienie komputera', 'System restart required')\n",
" ]" " ]\n",
"\n",
"translation_memory = { k:v for k,v in translation_memory}"
] ]
}, },
{ {
@ -86,7 +88,11 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def ice_lookup(sentence, prev_sentence, next_sentence):\n", "def ice_lookup(sentence, prev_sentence, next_sentence):\n",
" return []" " s_t = translation_memory.get(sentence, False)\n",
" p_s = translation_memory.get(prev_sentence, False)\n",
" n_s = translation_memory.get(next_sentence, False)\n",
" if s_t and p_s and n_s:\n",
" return s_t "
] ]
}, },
{ {
@ -141,7 +147,7 @@
"id": "graduate-theorem", "id": "graduate-theorem",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Nie jest to poprawna funkcja dystansu fuzzy match. Warunki 1,3,4 sa spelnione. 2 warunek jest nie spełniony poniewaz odleglosc pomiedzy dwoma zdaniami/slowami o tej samej dlugosci ale innych znakach bedzie rowna zero."
] ]
}, },
{ {
@ -179,7 +185,7 @@
"id": "metallic-leave", "id": "metallic-leave",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Tak, jest to poprawna funkcja dystansu. Wszystkie warunki sa spelnione."
] ]
}, },
{ {
@ -201,12 +207,54 @@
"### Ćwiczenie 5: Czy dystans Levenshteina jest poprawną funkcją dystansu? Uzasadnij krótko swoją odpowiedź sprawdzając każdy z warunków." "### Ćwiczenie 5: Czy dystans Levenshteina jest poprawną funkcją dystansu? Uzasadnij krótko swoją odpowiedź sprawdzając każdy z warunków."
] ]
}, },
{
"cell_type": "code",
"execution_count": 22,
"id": "79e4deef",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from Levenshtein import distance as levenshtein_distance\n",
"\n",
"# warunek 1\n",
"levenshtein_distance(\"smthn\", \"nothin\")\n",
"# Output: 3\n",
"# zawsze nieujemne\n",
"\n",
"# warunek 2\n",
"levenshtein_distance(\"and\", \"and\")\n",
"# Output: 0\n",
"# dwa takie same zdania ktore sa w odleglosci 0 od siebie\n",
"\n",
"# warunek 3\n",
"levenshtein_distance(\"zombie\", \"mombie\") == levenshtein_distance(\"mombie\", \"zombie\")\n",
"# Output: True\n",
"# zamiennosc zdan\n",
"\n",
"# warunek 4\n",
"x,y,z = 'zombie', 'glombie', 'mombie'\n",
"levenshtein_distance(x,y) + levenshtein_distance(y,z) >= levenshtein_distance(x,z)\n",
"#Output: True\n",
"# miara każdej odleglosci musi być mniejsza lub równa sumie miar dwóch pozostałych"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "bibliographic-stopping", "id": "bibliographic-stopping",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Tak jest poprawną funkcją dystansu."
] ]
}, },
{ {
@ -223,7 +271,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 7,
"id": "secondary-wrist", "id": "secondary-wrist",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -233,7 +281,7 @@
"2" "2"
] ]
}, },
"execution_count": 5, "execution_count": 7,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -254,7 +302,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 8,
"id": "associate-tuner", "id": "associate-tuner",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -273,7 +321,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 9,
"id": "focal-pathology", "id": "focal-pathology",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -283,7 +331,7 @@
"0.9166666666666666" "0.9166666666666666"
] ]
}, },
"execution_count": 7, "execution_count": 9,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -294,7 +342,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 10,
"id": "roman-ceiling", "id": "roman-ceiling",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -304,7 +352,7 @@
"0.9428571428571428" "0.9428571428571428"
] ]
}, },
"execution_count": 8, "execution_count": 10,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -315,7 +363,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 11,
"id": "invisible-cambodia", "id": "invisible-cambodia",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -325,7 +373,7 @@
"0.631578947368421" "0.631578947368421"
] ]
}, },
"execution_count": 9, "execution_count": 11,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -344,14 +392,43 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 12,
"id": "genetic-cradle", "id": "genetic-cradle",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def fuzzy_lookup(sentence, threshold):\n", "def fuzzy_lookup(sentence, threshold):\n",
" return []" " return [ v for k,v in translation_memory.items() if levenshtein_similarity(sentence, k) > threshold ]"
] ]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "2e72b54a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Press the ENTER button', 'System restart required']"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fuzzy_lookup('Spróbuj wyłączyć i włączyć komputer', 0.25)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1f15316",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {
@ -373,7 +450,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.11.0"
}, },
"subtitle": "2. Zaawansowane użycie pamięci tłumaczeń", "subtitle": "2. Zaawansowane użycie pamięci tłumaczeń",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",

227
lab/lab_03.ipynb
View File

@ -63,7 +63,9 @@
"id": "diverse-sunglasses", "id": "diverse-sunglasses",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Odpowiedź:" "Odpowiedź: Narzędzie DeepL: https://www.deepl.com/translator\n",
"\n",
"przetłumaczyło tekst \"prowadnice szaf metalowych\" na \"metal cabinet slides\""
] ]
}, },
{ {
@ -87,6 +89,16 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 1,
"id": "8f6b6fa9",
"metadata": {},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "loving-prince", "id": "loving-prince",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -110,7 +122,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"id": "bound-auction", "id": "bound-auction",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -128,13 +140,40 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 4,
"id": "cognitive-cedar", "id": "cognitive-cedar",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def terminology_lookup():\n", "count_dictionary = {}\n",
" return []" "\n",
"def terminology_lookup(text, tags):\n",
" return [(tag, [[m.start(), m.end()] \n",
" for m in re.finditer(tag, text)])\n",
" for tag in tags if tag in text]\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9fe3b66f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('program', [[14, 21], [291, 298], [468, 475], [516, 523], [533, 540]]),\n",
" ('application', [[80, 91], [164, 175], [322, 333]])]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"terminology_lookup(text, dictionary)"
] ]
}, },
{ {
@ -161,116 +200,74 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 6,
"id": "tribal-attention", "id": "7b7b7569",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
" \n", "Requirement already satisfied: spacy in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (3.7.4)\n",
"for\n", "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (3.0.12)\n",
"all\n", "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (1.0.5)\n",
"Java\n", "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (1.0.10)\n",
"programmer\n", "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (2.0.8)\n",
":\n", "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (3.0.9)\n",
"this\n", "Requirement already satisfied: thinc<8.3.0,>=8.2.2 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (8.2.3)\n",
"section\n", "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (1.1.2)\n",
"explain\n", "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (2.4.8)\n",
"how\n", "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (2.0.10)\n",
"to\n", "Requirement already satisfied: weasel<0.4.0,>=0.1.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (0.3.4)\n",
"compile\n", "Requirement already satisfied: typer<0.10.0,>=0.3.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (0.9.4)\n",
"and\n", "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (6.4.0)\n",
"run\n", "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (4.66.2)\n",
"a\n", "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (2.31.0)\n",
"swing\n", "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (2.7.0)\n",
"application\n", "Requirement already satisfied: jinja2 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (3.1.3)\n",
"from\n", "Requirement already satisfied: setuptools in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (65.5.0)\n",
"the\n", "Requirement already satisfied: packaging>=20.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (24.0)\n",
"command\n", "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (3.3.0)\n",
"line\n", "Requirement already satisfied: numpy>=1.19.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from spacy) (1.26.4)\n",
".\n", "Requirement already satisfied: annotated-types>=0.4.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.6.0)\n",
"for\n", "Requirement already satisfied: pydantic-core==2.18.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (2.18.1)\n",
"information\n", "Requirement already satisfied: typing-extensions>=4.6.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (4.11.0)\n",
"on\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.3.2)\n",
"compile\n", "Requirement already satisfied: idna<4,>=2.5 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.7)\n",
"and\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2.2.1)\n",
"run\n", "Requirement already satisfied: certifi>=2017.4.17 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2024.2.2)\n",
"a\n", "Requirement already satisfied: blis<0.8.0,>=0.7.8 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from thinc<8.3.0,>=8.2.2->spacy) (0.7.11)\n",
"swing\n", "Requirement already satisfied: confection<1.0.0,>=0.0.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from thinc<8.3.0,>=8.2.2->spacy) (0.1.4)\n",
"application\n", "Requirement already satisfied: click<9.0.0,>=7.1.1 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from typer<0.10.0,>=0.3.0->spacy) (8.1.7)\n",
"use\n", "Requirement already satisfied: cloudpathlib<0.17.0,>=0.7.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from weasel<0.4.0,>=0.1.0->spacy) (0.16.0)\n",
"NetBeans\n", "Requirement already satisfied: MarkupSafe>=2.0 in /Users/potoato/.pyenv/versions/3.11.0/lib/python3.11/site-packages (from jinja2->spacy) (2.1.5)\n",
"IDE\n", "\n",
",\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.3\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
"see\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
"Running\n", ]
"Tutorial\n", }
"Examples\n", ],
"in\n", "source": [
"NetBeans\n", "!pip install spacy"
"IDE\n", ]
".\n", },
"the\n", {
"compilation\n", "cell_type": "code",
"instruction\n", "execution_count": 8,
"work\n", "id": "tribal-attention",
"for\n", "metadata": {},
"all\n", "outputs": [
"swing\n", {
"program\n", "ename": "OSError",
"—\n", "evalue": "[E050] Can't find model 'en_core_web_sm'. It doesn't seem to be a Python package or a valid path to a data directory.",
"applet\n", "output_type": "error",
",\n", "traceback": [
"as\n", "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"well\n", "\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
"as\n", "Cell \u001b[0;32mIn[8], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mspacy\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m nlp \u001b[38;5;241m=\u001b[39m \u001b[43mspacy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43men_core_web_sm\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4\u001b[0m doc \u001b[38;5;241m=\u001b[39m nlp(text)\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m token \u001b[38;5;129;01min\u001b[39;00m doc:\n",
"application\n", "File \u001b[0;32m~/.pyenv/versions/3.11.0/lib/python3.11/site-packages/spacy/__init__.py:51\u001b[0m, in \u001b[0;36mload\u001b[0;34m(name, vocab, disable, enable, exclude, config)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload\u001b[39m(\n\u001b[1;32m 28\u001b[0m name: Union[\u001b[38;5;28mstr\u001b[39m, Path],\n\u001b[1;32m 29\u001b[0m \u001b[38;5;241m*\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 34\u001b[0m config: Union[Dict[\u001b[38;5;28mstr\u001b[39m, Any], Config] \u001b[38;5;241m=\u001b[39m util\u001b[38;5;241m.\u001b[39mSimpleFrozenDict(),\n\u001b[1;32m 35\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Language:\n\u001b[1;32m 36\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Load a spaCy model from an installed package or a local path.\u001b[39;00m\n\u001b[1;32m 37\u001b[0m \n\u001b[1;32m 38\u001b[0m \u001b[38;5;124;03m name (str): Package name or model path.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[38;5;124;03m RETURNS (Language): The loaded nlp object.\u001b[39;00m\n\u001b[1;32m 50\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m---> 51\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mutil\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_model\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 52\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 53\u001b[0m \u001b[43m \u001b[49m\u001b[43mvocab\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvocab\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 54\u001b[0m \u001b[43m \u001b[49m\u001b[43mdisable\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdisable\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 55\u001b[0m \u001b[43m \u001b[49m\u001b[43menable\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43menable\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 56\u001b[0m \u001b[43m \u001b[49m\u001b[43mexclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 57\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 58\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
".\n", "File \u001b[0;32m~/.pyenv/versions/3.11.0/lib/python3.11/site-packages/spacy/util.py:472\u001b[0m, in \u001b[0;36mload_model\u001b[0;34m(name, vocab, disable, enable, exclude, config)\u001b[0m\n\u001b[1;32m 470\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m OLD_MODEL_SHORTCUTS:\n\u001b[1;32m 471\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIOError\u001b[39;00m(Errors\u001b[38;5;241m.\u001b[39mE941\u001b[38;5;241m.\u001b[39mformat(name\u001b[38;5;241m=\u001b[39mname, full\u001b[38;5;241m=\u001b[39mOLD_MODEL_SHORTCUTS[name])) \u001b[38;5;66;03m# type: ignore[index]\u001b[39;00m\n\u001b[0;32m--> 472\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIOError\u001b[39;00m(Errors\u001b[38;5;241m.\u001b[39mE050\u001b[38;5;241m.\u001b[39mformat(name\u001b[38;5;241m=\u001b[39mname))\n",
"here\n", "\u001b[0;31mOSError\u001b[0m: [E050] Can't find model 'en_core_web_sm'. It doesn't seem to be a Python package or a valid path to a data directory."
"be\n",
"the\n",
"step\n",
"-PRON-\n",
"need\n",
"to\n",
"follow\n",
":\n",
"install\n",
"the\n",
"late\n",
"release\n",
"of\n",
"the\n",
"Java\n",
"SE\n",
"platform\n",
",\n",
"if\n",
"-PRON-\n",
"have\n",
"not\n",
"already\n",
"do\n",
"so\n",
".\n",
"create\n",
"a\n",
"program\n",
"that\n",
"use\n",
"Swing\n",
"component\n",
".\n",
"compile\n",
"the\n",
"program\n",
".\n",
"run\n",
"the\n",
"program\n",
".\n"
] ]
} }
], ],
@ -302,7 +299,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": null,
"id": "surgical-demonstration", "id": "surgical-demonstration",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -337,7 +334,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": null,
"id": "superb-butterfly", "id": "superb-butterfly",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -356,7 +353,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": null,
"id": "acting-tolerance", "id": "acting-tolerance",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -374,7 +371,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"id": "eight-redhead", "id": "eight-redhead",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -393,7 +390,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": null,
"id": "monetary-mambo", "id": "monetary-mambo",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -422,7 +419,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.10" "version": "3.11.0"
}, },
"subtitle": "3. Terminologia", "subtitle": "3. Terminologia",
"title": "Komputerowe wspomaganie tłumaczenia", "title": "Komputerowe wspomaganie tłumaczenia",