Skip to content

[lab-nlp] Joao Soares #49

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
JMpCS wants to merge 1 commit into
base: master
Choose a base branch
from
+1,349 −54
Open

[lab-nlp] Joao Soares #49

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
175 changes: 134 additions & 41 deletions your-code/challenge-1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,20 +66,46 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 69,
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"from nltk.tokenize import word_tokenize"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [],
"source": [
"def clean_up(s):\n",
" \"\"\"\n",
" Cleans up numbers, URLs, and special characters from a string.\n",
"\n",
" Args:\n",
" s: The string to be cleaned up.\n",
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" s = re.sub(r'http\\S+', ' ', s)\n",
" s = re.sub(r'[^\\w\\s]+|\\d+', ' ', s)\n",
" s = s.strip()\n",
" s = re.sub(r'\\s+', ' ', s)\n",
" \n",
" return s.lower()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ironhack s q website is\n"
]
}
],
"source": [
"s = \"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\\\")\"\n",
"clean_sentence = clean_up(s)\n",
"print(clean_sentence)"
]
},
{
Expand All @@ -101,20 +127,40 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 72,
"metadata": {},
"outputs": [],
"source": [
"from nltk.tokenize import word_tokenize"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
"def tokenize(s):\n",
" \"\"\"\n",
" Tokenize a string.\n",
"\n",
" Args:\n",
" s: String to be tokenized.\n",
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" return word_tokenize(s)"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 's', 'q', 'website', 'is']\n"
]
}
],
"source": [
"text = 'ironhack s q website is'\n",
"tokens = tokenize(text)\n",
"print(tokens)"
]
},
{
Expand Down Expand Up @@ -145,20 +191,42 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
"from nltk.stem import SnowballStemmer, WordNetLemmatizer"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
"def stem_and_lemmatize(l):\n",
" \"\"\"\n",
" Perform stemming and lemmatization on a list of words.\n",
"\n",
" Args:\n",
" l: A list of strings.\n",
"\n",
" Returns:\n",
" A list of strings after being stemmed and lemmatized.\n",
" \"\"\""
" stemmer = SnowballStemmer('english')\n",
" lemmatizer = WordNetLemmatizer()\n",
" stems = [stemmer.stem(l) for l in l]\n",
" lemmas = [lemmatizer.lemmatize(l) for l in l]\n",
" return stems, lemmas"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(['@', 'i', 'r', 'o', 'n', 'h', 'a', 'c', 'k', \"'\", 's', '-', '#', 'q', ' ', 'w', 'e', 'b', 's', 'i', 't', 'e', ' ', '7', '7', '6', '-', 'i', 's', ' ', 'h', 't', 't', 'p', ':', '/', '/', 'i', 'r', 'o', 'n', 'h', 'a', 'c', 'k', '.', 'c', 'o', 'm', ' ', '[', '(', '2', '0', '1', '8', ')', ']', '\"', ')'], ['@', 'I', 'r', 'o', 'n', 'h', 'a', 'c', 'k', \"'\", 's', '-', '#', 'Q', ' ', 'w', 'e', 'b', 's', 'i', 't', 'e', ' ', '7', '7', '6', '-', 'i', 's', ' ', 'h', 't', 't', 'p', ':', '/', '/', 'i', 'r', 'o', 'n', 'h', 'a', 'c', 'k', '.', 'c', 'o', 'm', ' ', '[', '(', '2', '0', '1', '8', ')', ']', '\"', ')'])\n"
]
}
],
"source": [
"print(stem_and_lemmatize(s))"
]
},
{
Expand All @@ -176,20 +244,40 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 78,
"metadata": {},
"outputs": [],
"source": [
"from nltk.corpus import stopwords"
]
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
"def remove_stopwords(l):\n",
" \"\"\"\n",
" Remove English stopwords from a list of strings.\n",
"\n",
" Args:\n",
" l: A list of strings.\n",
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" stop_words = set(stopwords.words('english'))\n",
" filtered_words = [l for l in l if l not in stop_words]\n",
" return filtered_words"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['@', 'I', 'r', 'n', 'h', 'c', 'k', \"'\", '-', '#', 'Q', ' ', 'w', 'e', 'b', 'e', ' ', '7', '7', '6', '-', ' ', 'h', 'p', ':', '/', '/', 'r', 'n', 'h', 'c', 'k', '.', 'c', ' ', '[', '(', '2', '0', '1', '8', ')', ']', '\"', ')']\n"
]
}
],
"source": [
"print(remove_stopwords(s))"
]
},
{
Expand Down Expand Up @@ -218,7 +306,12 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.10.7"
},
"vscode": {
"interpreter": {
"hash": "721db305ef1fd1fc91cdf20e400af694a949fe540ac5f48c160f31c7e384879d"
}
}
},
"nbformat": 4,
Expand Down
Loading