Skip to content

Instantly share code, notes, and snippets.

View bh1995's full-sized avatar

Bjørn Hansen bh1995

2 followers · 0 following
View GitHub Profile
@bh1995
bh1995 / gist:c9742e7dd58c8ffe5d0316f67462bdeb
Last active September 23, 2023 12:19
Credit Card Checker Challenge Project
// All valid credit card numbers
const valid1 = [4, 5, 3, 9, 6, 7, 7, 9, 0, 8, 0, 1, 6, 8, 0, 8];
const valid2 = [5, 5, 3, 5, 7, 6, 6, 7, 6, 8, 7, 5, 1, 4, 3, 9];
const valid3 = [3, 7, 1, 6, 1, 2, 0, 1, 9, 9, 8, 5, 2, 3, 6];
const valid4 = [6, 0, 1, 1, 1, 4, 4, 3, 4, 0, 6, 8, 2, 9, 0, 5];
const valid5 = [4, 5, 3, 9, 4, 0, 4, 9, 6, 7, 8, 6, 9, 6, 6, 6];
// All invalid credit card numbers
const invalid1 = [4, 5, 3, 2, 7, 7, 8, 7, 7, 1, 0, 9, 1, 7, 9, 5];
const invalid2 = [5, 7, 9, 5, 5, 9, 3, 3, 9, 2, 1, 3, 4, 6, 4, 3];
@bh1995
bh1995 / index.html
Created September 5, 2023 11:38
CSS Cheat Sheet
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>CSS Cheat Sheet</title>
<link rel="stylesheet" href="styles.css" />
</head>
<body>
<header>
@bh1995
bh1995 / Loading ECG data from .h5 format
Last active July 25, 2021 09:01
import h5py
# load af data
path = 'af_save_path' # for ex. '/content/drive/MyDrive/ecg_data_full/af_full.h5'
h5f = h5py.File(path,'r')
af_array = h5f['af_tot'][:]
h5f.close()
# load normal data
path = 'normal_save_path' # for ex. '/content/drive/MyDrive/ecg_data_full/normal_full.h5'
h5f = h5py.File(path,'r')
normal_array = h5f['normal_tot'][:]
@bh1995
bh1995 / word_score
Last active January 13, 2021 22:27
import re
# Number of reviews to use
N_total = 32261216
# Set word occurence lower threshold (must occur in 0.5 percent of the number of reviews)
N_limit = 0.005 * N_total
score_threshold = 90
comments_cleaned = reviews_with_score_df\
.select(['comments', 'mean_score'])\
.limit(N_total)\
@bh1995
bh1995 / filtering words
Created January 13, 2021 22:11
# Filter all reviews
listings_score_only_df = listings_df.select(['id', 'review_scores_rating']).cache()
listings_score_only_df = listings_score_only_df.withColumn('id',
listings_score_only_df['id'].cast(IntegerType()))
listings_score_only_df = listings_score_only_df.filter(col('id').isNotNull())
listings_score_only_df = listings_score_only_df.withColumn('review_scores_rating',
listings_score_only_df['review_scores_rating'].cast(IntegerType()))
listings_score_only_df = listings_score_only_df.filter(col('review_scores_rating').isNotNull())
listings_score_only_df = listings_df.select(['id', 'review_scores_rating']).cache()
@bh1995
bh1995 / spark_session
Created January 13, 2021 17:49
# create the Spark session
conf = SparkConf().set("spark.ui.port", "4050")
sc = pyspark.SparkContext(conf=conf)
spark = SparkSession.builder.getOrCreate()
@bh1995
bh1995 / seasonal_trend
Created January 12, 2021 21:22
beijing_popularity_month = beijing_popularity.groupBy(f.month(beijing_popularity["date"]).alias("month")).count().sort("month", ascending=True)
beijing_popularity_month_pd = beijing_popularity_month.toPandas()
num = len(beijing_popularity_month_pd)*4
c = [i for i in range(0,num,4)]
plt.figure(figsize=(10,4))
plt.bar(c, beijing_popularity_month_pd['count'],width=3, align='center', alpha=0.5)
plt.xticks(c,beijing_popularity_month_pd["month"])
plt.ylabel('Popularity')
plt.xlabel('Month')
plt.title('The Popularity of Beijing by month')
@bh1995
bh1995 / beijing_popularity
Created January 12, 2021 20:59
beijing_popularity_sql = """SELECT a.date, b.city,b.neighbourhood_cleansed
FROM reviews_df a
LEFT JOIN listings_df2 b
on a.listing_id = b.id
WHERE b.city='Beijing'
ORDER BY date ASC;
"""
beijing_popularity = spark.sql(beijing_popularity_sql).cache()
beijing_popularity_pd = beijing_popularity.toPandas()
# plot
@bh1995
bh1995 / beijing_listing_price_filter
Created January 12, 2021 20:30
lowPrice = 2000
beijing_price_pd = beijing_price.filter(beijing_price["price"]<lowPrice).toPandas()
# plot
plt.figure(figsize = [16,7])# set figuresize
plt.hist(beijing_price_low_pd['price'],bins = 50,alpha = 0.5,color = 'red',edgecolor = 'white', linewidth = 1.2)
plt.xlabel('price',size = 15)
plt.ylabel('count',size = 15)
plt.title('Histogram of Bei Jing price distribution of below 2000$ price',size = 15)
plt.show()
@bh1995
bh1995 / beijing_listing_price
Created January 12, 2021 20:22
beijing_price_sql = """SELECT price1 as price
FROM listings_df2
WHERE city = 'Beijing'
"""
beijing_price = spark.sql(beijing_price_sql).cache()
beijing_price_pd = beijing_price.toPandas()
# plot
plt.figure(figsize = [16,7])# set figuresize
plt.hist(beijing_price_pd['price'],bins = 50,alpha = 0.5,color = 'red',edgecolor = 'white', linewidth = 1.2)
plt.xlabel('price',size = 15)