Skip to content

[natural-language-processing] Sara Hernández #535

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

[natural-language-processing] Sara Hernández #535

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
803f5e0
lab-started
ssarahreyes Apr 5, 2021
902046e
lab-finished
ssarahreyes Apr 7, 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
159 changes: 147 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 +66,16 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import re "
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -79,7 +88,42 @@
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" s_clean = re.sub(r'https?:\\/\\/.*[\\r\\n]*', '', s) # deleting the url\n",
" s_clean = re.sub(r'\\#|\\@|\\d|\\-|\\'|\\,|\\[|\\]', ' ', s_clean) # deleting special characters\n",
" \n",
" return s_clean.lower() #lowercase to ML"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"sentence = '''@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\")'''"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' ironhack s q website is '"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sentence_clean = clean_up(sentence)\n",
"sentence_clean"
]
},
{
Expand All @@ -101,7 +145,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -114,7 +158,32 @@
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" s_list = re.split(r' ', s)\n",
" s_list_withiout_empty_strings = [s for s in s_list if s != '']\n",
" \n",
" return s_list_withiout_empty_strings"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 's', 'q', 'website', 'is']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenize(sentence_clean)"
]
},
{
Expand Down Expand Up @@ -145,7 +214,27 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"import nltk"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import nltk\n",
"from nltk.stem import WordNetLemmatizer\n",
"lemmatizer = WordNetLemmatizer()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -158,7 +247,11 @@
"\n",
" Returns:\n",
" A list of strings after being stemmed and lemmatized.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" lemmatize = [lemmatizer.lemmatize(t) for t in l]\n",
" \n",
" return lemmatize"
]
},
{
Expand All @@ -176,7 +269,16 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from nltk.corpus import stopwords"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -189,7 +291,40 @@
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" \"\"\"\n",
" lemmatize = stem_and_lemmatize(l)\n",
" stop_words= [t for t in lemmatize if t not in stopwords.words('english')]\n",
" \n",
" return stop_words"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"list_words = ['I', 'saw', 'the', 'life', 'inside', 'your', 'eyes']"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['I', 'saw', 'life', 'inside', 'eye']"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"remove_stopwords(list_words)"
]
},
{
Expand All @@ -204,9 +339,9 @@
],
"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 +353,9 @@
"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