Skip to content

[lab-nlp] Javier Sanchez Camacho #50

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

[lab-nlp] Javier Sanchez Camacho #50

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
91 changes: 81 additions & 10 deletions your-code/challenge-1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,9 +66,30 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"import nltk"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ironhack s q website is'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def clean_up(s):\n",
" \"\"\"\n",
Expand All @@ -79,7 +100,14 @@
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" \"\"\"\n",
" string = re.sub(r'http\\S+', '', s)\n",
" return re.sub('[^A-Za-z]+', ' ', string).lower().strip()\n",
" \n",
"test = \"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\"\n",
"\n",
"test_string = clean_up(test)\n",
"test_string"
]
},
{
Expand All @@ -101,9 +129,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 's', 'q', 'website', 'is']"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def tokenize(s):\n",
" \"\"\"\n",
Expand All @@ -114,7 +153,11 @@
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" \"\"\"\n",
" return nltk.word_tokenize(s)\n",
"\n",
"test_string = tokenize(test_string)\n",
"test_string"
]
},
{
Expand Down Expand Up @@ -145,11 +188,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Nope, something went wrong, I'll use another set of words\n",
"\n",
"import nltk\n",
"from nltk.stem import PorterStemmer, WordNetLemmatizer\n",
"\n",
"def stem_and_lemmatize(l):\n",
" \n",
" \"\"\"\n",
" Perform stemming and lemmatization on a list of words.\n",
"\n",
Expand All @@ -158,7 +207,17 @@
"\n",
" Returns:\n",
" A list of strings after being stemmed and lemmatized.\n",
" \"\"\""
" \"\"\"\n",
" ps = nltk.PorterStemmer()\n",
" lemmatizer = nltk.WordNetLemmatizer()\n",
" l2 = []\n",
" \n",
" for w in l:\n",
" s = ps.stem(w)\n",
" s = lemmatizer.lemmatize(s)\n",
" l2 += [s]\n",
" \n",
" return l2\n"
]
},
{
Expand All @@ -176,7 +235,16 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"from nltk.corpus import stopwords"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -189,7 +257,10 @@
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" \"\"\"\n",
" stop_words = stopwords.words('english')\n",
"\n",
" return [w for w in l if w not in stop_words]"
]
},
{
Expand Down Expand Up @@ -218,7 +289,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.10.9"
}
},
"nbformat": 4,
Expand Down
Loading