Skip to content

[lab-nlp] Felipe de Ávila Granja DA/May Lisbon #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
FelipeAvila2 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[lab-nlp] Felipe de Ávila Granja DA/May Lisbon #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
162 changes: 149 additions & 13 deletions your-code/challenge-1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ironhack s q website is \n"
]
}
],
"source": [
"import re\n",
"\n",
"def clean_up(s):\n",
" \"\"\"\n",
" Cleans up numbers, URLs, and special characters from a string.\n",
Expand All @@ -79,7 +89,14 @@
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" element = re.sub('http://.+', '', s)\n",
" element = re.sub('@|-|#|\\'', ' ', element)\n",
" return (re.sub('\\d+',' ',element)).lower()\n",
" \n",
"string = \"\"\"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\")\"\"\"\n",
"print(clean_up(string))"
]
},
{
Expand All @@ -101,10 +118,31 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Unzipping tokenizers\\punkt.zip.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 's', 'q', 'website', 'is']\n"
]
}
],
"source": [
"import nltk\n",
"from nltk.tokenize import word_tokenize\n",
"nltk.download('punkt')\n",
"\n",
"def tokenize(s):\n",
" \"\"\"\n",
" Tokenize a string.\n",
Expand All @@ -114,7 +152,13 @@
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" \"\"\"\n",
"\n",
" return word_tokenize(s)\n",
" \n",
"string = clean_up(string)\n",
"token = tokenize(string)\n",
"print(token)"
]
},
{
Expand Down Expand Up @@ -145,10 +189,57 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 41,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package averaged_perceptron_tagger to\n",
"[nltk_data] C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package averaged_perceptron_tagger is already up-to-\n",
"[nltk_data] date!\n"
]
},
{
"data": {
"text/plain": [
"['the',\n",
" 'wonderful',\n",
" 'tokenization',\n",
" 'be',\n",
" 'colourfull',\n",
" 'in',\n",
" 'housekeep',\n",
" 'forever']"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from nltk.stem import WordNetLemmatizer\n",
"from nltk.stem import PorterStemmer\n",
"nltk.download('wordnet')\n",
"from nltk.corpus import wordnet\n",
"\n",
"nltk.download('averaged_perceptron_tagger')\n",
"\n",
"def get_wordnet_pos(word):\n",
" tag = nltk.pos_tag([word])[0][1][0].upper() # gets first letter of POS categorization\n",
" tag_dict = {\"J\": wordnet.ADJ, \n",
" \"N\": wordnet.NOUN,\n",
" \"V\": wordnet.VERB,\n",
" \"R\": wordnet.ADV}\n",
" return tag_dict.get(tag, wordnet.NOUN) # get returns second argument if first key does not exist\n",
"\n",
"\n",
"def stem_and_lemmatize(l):\n",
" \"\"\"\n",
" Perform stemming and lemmatization on a list of words.\n",
Expand All @@ -158,7 +249,19 @@
"\n",
" Returns:\n",
" A list of strings after being stemmed and lemmatized.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" lem = WordNetLemmatizer()\n",
" lemmatized = [lem.lemmatize(w,get_wordnet_pos(w)) for w in l]\n",
" \n",
" ps = PorterStemmer()\n",
" stemmed = [ps.stem(w) for w in l]\n",
" \n",
" return stemmed, lemmatized\n",
"\n",
"sentence1, sentence2 = stem_and_lemmatize(['the','wonderful','tokenization','is','colourfull','in','housekeeping','forever'])\n",
"\n",
"sentence2"
]
},
{
Expand All @@ -176,10 +279,33 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 42,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"['wonderful', 'tokenization', 'colourfull', 'housekeep', 'forever']"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from nltk.corpus import stopwords\n",
"nltk.download('stopwords')\n",
"\n",
"def remove_stopwords(l):\n",
" \"\"\"\n",
" Remove English stopwords from a list of strings.\n",
Expand All @@ -189,7 +315,17 @@
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" filtered_sentence = []\n",
" \n",
" for w in l:\n",
" if w not in stopwords.words('english'):\n",
" filtered_sentence.append(w)\n",
" \n",
" return filtered_sentence\n",
"\n",
"remove_stopwords(sentence2)"
]
},
{
Expand Down Expand Up @@ -218,7 +354,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.8.5"
}
},
"nbformat": 4,
Expand Down
Loading