Skip to content
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

Jump to bottom

lab_bag_of_words [Ernesto Moreno] #1

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

lab_bag_of_words [Ernesto Moreno] #1

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
98 changes: 75 additions & 23 deletions your-code/main.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -25,13 +25,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"corpus = []\n",
"\n",
"# Write your code here"
"# Write your code here\n",
"import re\n",
"import pandas as pd\n",
"data=[pd.read_csv(d) for d in docs]\n",
"data=pd.concat(data,axis=0)\n",
"data=list(data)\n",
"for i in range(len(data)):\n",
" corpus.append((data[i][:-1].lower())) "
]
},
{
Expand All @@ -43,10 +49,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack is cool', 'i love ironhack', 'i am a student at ironhack']\n"
]
}
],
"source": [
"print(corpus)"
]
},
{
"cell_type": "markdown",
Expand Down Expand Up @@ -84,13 +100,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"bag_of_words = []\n",
"\n",
"# Write your code here"
"# Write your code here\n",
"dummy=[re.split(r' ',i) for i in corpus]\n",
"for i in dummy:\n",
" for j in i:\n",
" if j not in bag_of_words:\n",
" bag_of_words.append(j)"
]
},
{
Expand All @@ -104,10 +124,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['ironhack', 'is', 'cool', 'i', 'love', 'am', 'a', 'student', 'at']\n"
]
}
],
"source": [
"print(bag_of_words)"
]
},
{
"cell_type": "markdown",
Expand All @@ -118,13 +148,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"term_freq = []\n",
"\n",
"# Write your code here"
"# Write your code here\n",
"i=0\n",
"dummy=[re.split(r' ',phrase) for phrase in corpus]\n",
"for phrase in corpus:\n",
" term_freq.append([])\n",
" for word in bag_of_words:\n",
" aux=0\n",
" for dum in dummy[i]:\n",
" if word==dum:\n",
" term_freq[i].append(1) \n",
" aux=1\n",
" if aux==0:\n",
" term_freq[i].append(0)\n",
" i=i+1"
]
},
{
Expand All @@ -138,10 +180,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 1, 1, 1, 1]]\n"
]
}
],
"source": [
"print(term_freq)"
]
},
{
"cell_type": "markdown",
Expand Down Expand Up @@ -169,7 +221,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
"version": "3.8.8"
}
},
"nbformat": 4,
Expand Down