Skip to content

[natural-language-processing] Álvaro Castilla #544

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
CastillaAlvaro wants to merge 2 commits into
base: master
Choose a base branch
from
Open

[natural-language-processing] Álvaro Castilla #544

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
138f876
lab-started
CastillaAlvaro Apr 24, 2021
809e693
lab-finished
CastillaAlvaro Apr 24, 2021
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
238 changes: 226 additions & 12 deletions module-3/natural-language-processing/your-code/challenge-1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"s = \"\"\"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\")\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -79,7 +97,34 @@
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" url = re.sub('http://[\\\\w]+\\\\.\\\\w+', '', s)\n",
" numbers = re.sub('\\\\d+', '', url).lower()\n",
" new_string = re.sub('[^a-z0-9]', ' ', numbers).strip()\n",
" \n",
" return new_string"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ironhack s q website is'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_string = clean_up(s)\n",
"new_string"
]
},
{
Expand All @@ -101,7 +146,37 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to /home/usuario/nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import nltk\n",
"from nltk import word_tokenize\n",
"nltk.download('punkt')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -114,7 +189,29 @@
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" return word_tokenize(new_string)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 's', 'q', 'website', 'is']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenize(new_string)"
]
},
{
Expand Down Expand Up @@ -145,7 +242,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"from nltk.stem import PorterStemmer\n",
"porter = PorterStemmer()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -158,7 +265,58 @@
"\n",
" Returns:\n",
" A list of strings after being stemmed and lemmatized.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" return [porter.stem(i) for i in l]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"l = ['ironhack', 's', 'q', 'website', 'is']"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['token', 'token', 'token']"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stem_and_lemmatize(['token', 'tokenize', 'tokenization'])"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 's', 'q', 'websit', 'is']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stem_and_lemmatize(l)"
]
},
{
Expand All @@ -176,7 +334,37 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] /home/usuario/nltk_data...\n",
"[nltk_data] Unzipping corpora/stopwords.zip.\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from nltk.corpus import stopwords\n",
"nltk.download('stopwords')"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -189,7 +377,33 @@
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" lemma = [porter.stem(i) for i in l]\n",
" stop_wds = [i for i in lemma if i not in stopwords.words('english')]\n",
" \n",
" return stop_wds\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 'q', 'websit']"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"remove_stopwords(l)"
]
},
{
Expand All @@ -204,9 +418,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python [conda env:ironhack_env]",
"language": "python",
"name": "python3"
"name": "conda-env-ironhack_env-py"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -218,9 +432,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}
Loading