rcsmit

# Read a PDF and convert it to an XLS
# Tested on Bijlage B - Wob-deelbesluit 'Vaccinaties en medicatie oktober 2020'

# Not tested 100%

# inspired by https://x.com/Transparangst/status/1906717209423974689


def read_directly_from_pdf():
    # read a file 

rcsmit

import pandas as pd
import numpy as np
import math


import numpy as np
import matplotlib.pyplot as plt

def binary_search_steps(target, max_num):
    """Simulate binary search and return number of steps needed"""

rcsmit

import pandas as pd
import streamlit as st
import plotly.graph_objects as go
import matplotlib.pyplot as plt

# stacked range bar chart
# as proposed by https://www.youtube.com/watch?v=5zBg9pH_6bE

# by Rene Smit (@rcsmit), with help from Github Co Pilot (GPT 4o)

rcsmit

# We berekenen de sterfte in 2020-2024 aan de hand van de sterftekansen per leeftijdsgroep (5jr, Eurostats) in 2019 en 
# de bevolkingsgrootte in 2020-2024(CBS) 
# Naar aanleiding van https://twitter.com/PeeNee2/status/1855384448478609656

import pandas as pd

# Load the data from CSV files
sterfte_df = pd.read_csv("https://raw.githubusercontent.com/rcsmit/COVIDcases/refs/heads/main/input/sterfte_eurostats_NL.csv")
bevolking_df = pd.read_csv("https://raw.githubusercontent.com/rcsmit/COVIDcases/refs/heads/main/input/bevolking_leeftijd_NL.csv", delimiter=";")
sterfte_df['jaar'] = sterfte_df['TIME_PERIOD'].str[:4].astype(int)

rcsmit

import numpy as np
from scipy.integrate import odeint
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D

rcsmit

import os
import time
import streamlit as st
from PIL import Image, ExifTags
from io import BytesIO
import pytesseract
import re
import os

# based on https://www.youtube.com/watch?v=RPN-HxvAQnQ

rcsmit

def get_data_eurostat():
    """Get from Eurostat : Deaths by week, sex and 5-year age group
    Data from https://ec.europa.eu/eurostat/databrowser/product/view/demo_r_mwk_05?lang=en
    https://ec.europa.eu/eurostat/databrowser/bookmark/fbd80cd8-7b96-4ad9-98be-1358dd80f191?lang=en
    https://ec.europa.eu/eurostat/api/dissemination/sdmx/2.1/dataflow/ESTAT/DEMO_R_MWK_05/1.0?references=descendants&detail=referencepartial&format=sdmx_2.1_generic&compressed=true
   
    Returns:
        df: dataframe with weekly mortality in 5 year tranches

                                DATAFLOW        LAST UPDATE freq     age sex  ... OBS_VALUE OBS_FLAG   age_sex  jaar weeknr

rcsmit

import pandas as pd
import streamlit as st
import plotly.graph_objects as go
import numpy as np
import statsmodels.api as sm

// output: https://twitter.com/rcsmit/status/1800539585841344854

def test():
 

rcsmit

# recreating https://twitter.com/NateB_Panic/status/1636811443612860417/photo/1

import numpy as np
import plotly
import plotly.graph_objects as go
import numpy as np

p_values = [0.01, 0.05,0.1,0.2, 0.3, 0.5]  # set the values of p
x = np.arange(0, 30, 1)  # generate an array of x values from 0 to 10

rcsmit

""" A script to calculate the loss or gain after x months working in a year with a montly salary of y
    This calculation is a simplification

    Goal is to learn to work with OOP and make the script pythonic as much as possible.  

    TODO : calculate the total capital after z years, with taking inflation in account

Returns:
    A dataframe like this: