Skip to content

Instantly share code, notes, and snippets.

View mmmayo13's full-sized avatar

Matthew Mayo mmmayo13

View GitHub Profile
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body
style="
background-color: #ffffff;
font-family: arial, verdana, tahoma;
font-size: 14px;
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>KDnuggets Weekly Digest</title>
</head>
<body style="background-color:#FFFFFF; font-family:arial,verdana,tahoma; font-size:14px;">
<table style="border:0px; border-collapse:collapse; width:680px; margin-left:auto; margin-right:auto;">
<td>
<!-- Header -->
<table style="width:100%; border-collapse:collapse;">
from math import sqrt, floor
import numpy as np
def random(ds, k, random_state=42):
"""
Create random cluster centroids.
Parameters
----------
from collections import Counter
from string import punctuation
from sklearn.feature_extraction.stop_words import ENGLISH_STOP_WORDS as stop_words
import spacy
def count_words(tokens):
word_counts = {}
for token in tokens:
if token not in stop_words and token not in punctuation and token is not '\n':
if token not in word_counts.keys():