Dixhom

"""
advantages over normal tqdm:

1. progress can be checked more in detail.
   a progress bar comes with a number at the end "########6".
   This means the last portion is done 60%.
2. The total number of iteration can be changed.
   `obj.total_count = new_count`

"""

Dixhom

int base_year = 1970;
// cumulative days of the year for each month
int daysCumsum[] = {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365};
char* dayOfTheWeek[] = {"Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"};


int getLeapYear(int year) {
    // get num leap years from the year 1
    int div4 = year / 4;
    int div100 = year / 100;

Dixhom

def getLeapYear(year):
    # get num leap years from the year 1
    div4 = year // 4
    div100 = year // 100
    div400 = year // 400
    # number of leap years until `year`
    return div4 - div100 + div400

def isLeapYear(year):
    # whether `year` is a leap year

Dixhom

import requests
from bs4 import BeautifulSoup

url = "https://mansion-market.com/mansions/categories/brands"
r = requests.get(url)
soup = BeautifulSoup(r.content, "html.parser")
# be careful, select() returns a list.
[a.text for a in soup.select('div.article_list')[0].select('li')]

Dixhom

# About:
# - This code reads import statements from python scripts and creates a requirements_txt.

# Caveats:
# - Sometimes library names in pip and python scripts are different. e.g.) pip install scikit-learn vs import sklearn. The users need to fix the name by themselves.

# Todo:
# - Prepare a conversion table between the library names in pip and python scripts and create the requirements.txt properly.

import pkg_resources

Dixhom

n = 8
div = 10**n
for i in range(10**(n-1), 10**n):
    if (i * i) % div == i:
        print(i)
        
# 2: 25, 76    
# 3: 376, 625
# 4: 9376
# 5: 90625

Dixhom

class Rational:
	"""
	a class to handle rational numbers
	"""
	def __init__(self, num, denom=1):
		self.num = num # numerator
		self.denom = denom # denominator
		
	def __gcd(self,u,v):
		"""

Dixhom

# pip install PyQRCode
# pip install pypng

import pyqrcode
import re

def create_qr_code(value=None, 
                    error='L', 
                    version=1, 
                    mode='binary', 

Dixhom

What is this?

This is a verification to confirm whether a tree based machine learning model causes multicollinearity. This is purely out of my curiosity. I just wondered if multicollinearity takes place in a tree based model and aggravates its performance. If it does, it means one needs to remove correlated features before building models.

Method

I artificially generated three datasets, obtained scores with lightgbm and k-fold cross validation and compared the finals scores.

1. dataset 1: 10 informative features (useful features for prediction)
2. dataset 2: 10 informative features + 10 features with random values

Dixhom

from tqdm import tqdm

"""
This is a script to solve a math problem.

The number from 1 to 4 will be placed in each cell of a 4 x 4 board. 
Each number must appear only once in each row and column of the board. 
How many possible numbers of cases are there?

This script is extended to solve the problem with 2^power instead of 4.