Skip to content

[lab-nlp] Bruno #62

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
Bruno2391 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[lab-nlp] Bruno #62

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
178 changes: 172 additions & 6 deletions your-code/challenge-1.ipynb → your-code/[challenge-1] Bruno.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 61,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -82,6 +82,95 @@
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import nltk \n",
"from nltk.stem import WordNetLemmatizer\n",
"from nltk.corpus import stopwords\n",
"from sklearn.feature_extraction.text import CountVectorizer\n",
"#from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from nltk.tokenize import word_tokenize \n",
"from nltk.stem import PorterStemmer, LancasterStemmer, SnowballStemmer"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] C:\\Users\\btdjf\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n",
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\btdjf\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n",
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\btdjf\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package omw-1.4 to\n",
"[nltk_data] C:\\Users\\btdjf\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package omw-1.4 is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nltk.download('stopwords')\n",
"nltk.download('wordnet')\n",
"nltk.download('punkt') \n",
"nltk.download('omw-1.4')"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ironhack s q website is\n"
]
}
],
"source": [
"import re\n",
"\n",
"text = \"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\\\")\"\n",
"\n",
"def clean_up(text):\n",
" # removing URLs\n",
" text = re.sub(r\"http\\S+|www\\S+|https\\S+\", \"\", text)\n",
" # removing special characters\n",
" text = re.sub(r\"[^a-zA-Z ]+\", \" \", text)\n",
" # converting to lowercase\n",
" text = text.lower()\n",
" # Remove extra whitespaces\n",
" text = re.sub(r\"\\s+\", \" \", text)\n",
" return text.strip()\n",
"\n",
"print(clean_up(text))"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand All @@ -101,7 +190,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -117,6 +206,28 @@
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 's', 'q', 'website', 'is']\n"
]
}
],
"source": [
"text = \"ironhack s q website is\"\n",
"\n",
"def tokenize(text):\n",
" return word_tokenize(text)\n",
"\n",
"print(tokenize(text))"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -145,7 +256,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -161,6 +272,37 @@
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 's', 'q', 'websit', 'is']\n"
]
}
],
"source": [
"words = ['ironhack', 's', 'q', 'website', 'is']\n",
"\n",
"def stem_and_lemmatize(words):\n",
" stemmer = PorterStemmer()\n",
" lemmatizer = WordNetLemmatizer()\n",
" stemmed_and_lemmatized = []\n",
"\n",
" for word in words:\n",
" stemmed_word = stemmer.stem(word)\n",
" lemmatized_word = lemmatizer.lemmatize(stemmed_word)\n",
" stemmed_and_lemmatized.append((lemmatized_word))\n",
"\n",
" return stemmed_and_lemmatized\n",
"\n",
"print(stem_and_lemmatize(words))"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand All @@ -176,7 +318,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 69,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -192,6 +334,30 @@
" \"\"\""
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 'websit']\n"
]
}
],
"source": [
"words = ['ironhack', 's', 'q', 'websit', 'is']\n",
"\n",
"def remove_stopwords(words):\n",
" stop_words = set(stopwords.words('english'))\n",
" filtered_words = [word for word in words if word not in stop_words and len(word) > 1]\n",
" return filtered_words\n",
"\n",
"print(remove_stopwords(words))\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand All @@ -204,7 +370,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -218,7 +384,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.11.5"
}
},
"nbformat": 4,
Expand Down
Loading