Skip to content

[natural-language-processing] Gonzalo Álvarez #520

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
gonalvarez05 wants to merge 5 commits into
base: master
Choose a base branch
from
Open

[natural-language-processing] Gonzalo Álvarez #520

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c76904c
lab-started
gonalvarez05 Mar 26, 2021
dc3b9e8
challenge-1 completed
gonalvarez05 Mar 29, 2021
db1aedb
challenge 1 completed
gonalvarez05 Mar 29, 2021
3033648
challenge 2 ongoing
gonalvarez05 Mar 30, 2021
a3425b2
challenge 2 ongoing
gonalvarez05 Mar 31, 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
Binary file added module-3/natural-language-processing/training.1600000.processed.noemoticon.csv.zip
View file
Open in desktop
Binary file not shown.
6 changes: 6 additions & 0 deletions module-3/natural-language-processing/your-code/Untitled.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 4
}
210 changes: 196 additions & 14 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 @@ -66,9 +66,29 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ironhack s q website is'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def clean_up(s):\n",
" \"\"\"\n",
Expand All @@ -79,7 +99,17 @@
"\n",
" Returns:\n",
" A string that has been cleaned up.\n",
" \"\"\""
" \n",
" \"\"\"\n",
" \n",
" remove_url= re.sub('http://[\\w]+\\.\\w+', '', s)\n",
" remove_num= re.sub('\\d+', '', remove_url)\n",
" remove_num=remove_num.lower()\n",
" new_string= re.sub('[^a-z0-9]', ' ', remove_num).strip() \n",
" \n",
" return new_string\n",
"\n",
"clean_up(\"@Ironhack's- Q website 776-is http://ironhack.com [(2018)]\") "
]
},
{
Expand All @@ -101,7 +131,38 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] /Users/gonzaloalvarez/nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import nltk\n",
"from nltk import word_tokenize\n",
"nltk.download('punkt')\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -114,7 +175,32 @@
"\n",
" Returns:\n",
" A list of words as the result of tokenization.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" return word_tokenize(s)\n",
"\n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ironhack', 's', 'q', 'website', 'is']"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenize('ironhack s q website is')"
]
},
{
Expand Down Expand Up @@ -145,9 +231,51 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] /Users/gonzaloalvarez/nltk_data...\n",
"[nltk_data] Package wordnet is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from nltk.stem import WordNetLemmatizer\n",
"lemmatizer= WordNetLemmatizer()\n",
"nltk.download('wordnet')\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['run', 'ran', 'change', 'changed', 'gonzo', 'wash', 'wa']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def stem_and_lemmatize(l):\n",
" \"\"\"\n",
Expand All @@ -158,7 +286,13 @@
"\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\n",
"\n",
"stem_and_lemmatize(['run', 'ran', 'change', 'changed', 'gonzo', 'wash', 'was'])"
]
},
{
Expand All @@ -176,9 +310,50 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 8,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] /Users/gonzaloalvarez/nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from nltk.corpus import stopwords\n",
"nltk.download('stopwords')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['I', 'wa', 'running', 'bleeding']"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def remove_stopwords(l):\n",
" \"\"\"\n",
Expand All @@ -189,7 +364,14 @@
"\n",
" Returns:\n",
" A list of strings after stop words are removed.\n",
" \"\"\""
" \"\"\"\n",
" \n",
" lemmatize= [lemmatizer.lemmatize(t) for t in l]\n",
" no_stops= [t for t in lemmatize if t not in stopwords.words('english')]\n",
" \n",
" return no_stops\n",
"\n",
"remove_stopwords(['I', 'was', 'running', 'and', 'then', 'they', 'are', 'over', 'here', 'bleeding'])"
]
},
{
Expand All @@ -204,9 +386,9 @@
],
"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 +400,9 @@
"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