Ll

-- coding: utf-8 --

"""model.ipynb

Automatically generated by Colaboratory.

Original file is located at https://colab.research.google.com/drive/1hA9Xz_VjzMVj66qS_j3A5dKcGkAfScKM """

pip install pycaret

from scipy import stats

import numpy as np

import pandas as pd

import pickle

import matplotlib.pyplot as plt

create fictitious data set

simple_life_dataset = pd.DataFrame({'Age':[0, 60], 'Life Expectancy':[90, 30]}) simple_life_dataset.head()

import numpy as np from scipy import stats slope, intercept, r_value, p_value, std_err = stats.linregress(simple_life_dataset['Age'],simple_life_dataset['Life Expectancy']) print('intercept: ', intercept) print('slope: ', slope)

np.ceil(slope * 20 + intercept)

fig, axes = plt.subplots(figsize=(5,5)) x = [0,20,60] y = [90, 70, 30] axes.plot(x,y, color='blue', linestyle='--', marker='o') fig.suptitle('Life Expectancy') axes.set_xlabel('age') axes.set_xlim([-5,100]) axes.set_ylabel('life_expectancy') axes.set_ylim([0,100]) plt.grid() plt.show()

load WHO longevity data

http://apps.who.int/gho/data/node.main.688

who_list = pd.read_csv('/content/drive/MyDrive/WHOSIS_000001,WHOSIS_000015.csv')

save a local copy of the data set for our Flask prototype later on

who_list.to_csv('WHOSIS_000001,WHOSIS_000015.csv')

Keep only useful features fix case display of country text

who_list = who_list[['GHO (DISPLAY)', 'YEAR (CODE)' , 'COUNTRY (DISPLAY)', 'SEX (DISPLAY)', 'Numeric']] who_list['COUNTRY (DISPLAY)'] = [ctry.title() for ctry in who_list['COUNTRY (DISPLAY)'].values]

print a few rows

who_list[who_list['COUNTRY (DISPLAY)']=='France'].head(10)

country = 'United States Of America' sex = 'Male'

pull latest entries for birth and 60 years for a country and gender

sub_set = who_list[who_list['COUNTRY (DISPLAY)'].str.startswith(country, na=False)] sub_set = sub_set[sub_set['SEX (DISPLAY)'] == sex]

sort by year in descending order to work with the latest read

sub_set = sub_set.sort_values('YEAR (CODE)', ascending=False) sub_set_birth = sub_set[sub_set['GHO (DISPLAY)'] == 'Life expectancy at birth (years)'] sub_set_60 = sub_set[sub_set['GHO (DISPLAY)'] == 'Life expectancy at age 60 (years)'] print('sub_set_birth:') print(sub_set_birth.head(5)) print('sub_set_60:') print(sub_set_60.head(5))

create data set with both points as shown in first example

lf_at_birth = sub_set_birth['Numeric'].values[0] lf_at_60 = sub_set_60['Numeric'].values[0]

let's organize our data and plot

age = [0,60] life_expectancy = [lf_at_birth, lf_at_60] fig, axes = plt.subplots(figsize=(5,5)) x = age y = life_expectancy axes.plot(x,y, color='blue', linestyle='--', marker='o') fig.suptitle('Life Expectancy') axes.set_xlabel('age') axes.set_xlim([-5,100]) axes.set_ylabel('life expectancy') axes.set_ylim([0,100]) plt.grid() plt.show()

model

slope, intercept, r_value, p_value, std_err = stats.linregress(age, life_expectancy) print('intercept: ', intercept) print('slope: ', slope)

predict life expectancy for an 49-year-old male in the USA:

np.ceil(slope * 49 + intercept)

def get_life_expectancy(age, country, sex): # pull latest entries for birth and 60 years sub_set = who_list[who_list['COUNTRY (DISPLAY)'].str.startswith(country, na=False)] sub_set = sub_set[sub_set['SEX (DISPLAY)'] == sex] sub_set = sub_set.sort_values('YEAR (CODE)', ascending=False) sub_set_birth = sub_set[sub_set['GHO (DISPLAY)'] == 'Life expectancy at birth (years)'] sub_set_60 = sub_set[sub_set['GHO (DISPLAY)'] == 'Life expectancy at age 60 (years)']

# not all combinations exsits so check that we have data for both
if len(sub_set_birth['Numeric']) > 0 and len(sub_set_60['Numeric']) > 0:
    # create data set with both points as shown in first example
    lf_at_birth = sub_set_birth['Numeric'].values[0]
    lf_at_60 = sub_set_60['Numeric'].values[0]

    # model
    slope, intercept, r_value, p_value, std_err = stats.linregress([0,60],[lf_at_birth, lf_at_60])

    # predict for the age variable
    return(np.ceil(slope * age + intercept))
else:
    return None

list(set(who_list['COUNTRY (DISPLAY)']))[0:10]

test the function out using a 22-year-old Japanese female:

get_life_expectancy(22, 'Japan', 'Female')

get_life_expectancy(22,'Pakistan','Female')

get_life_expectancy(21,'India','Male')

missing_values_count = who_list.isnull().sum()

print(missing_values_count)

get_life_expectancy(80,'Pakistan','Female')

pickle.dump(get_life_expectancy,open('model.pkl','wb'))

model=pickle.load(open('model.pkl','rb'))