Data/Top_health_spending at main · khaylheb99/Data · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

df = pd.read_csv('C:\\Users\\KAY\\Documents\\Data Science\\Datasets\\World Bank Indicators.csv') #bringing in the dataset to be used
df
df.shape
df.info

Late = ['2010-07-01']
filt= df['Date'].isin(Late)

df[filt]
try:
    latest = df[filt]
    print (latest)
except TypeError as e:
    print (e)
    print ('None object')

Recent = (df['Date'] == '01/07/2010')   #getting the newest available data from the dataset
Recent=df[Recent]

Recent.shape
pd.set_option('display.max_column', 20)   #displaying the full data
pd.set_option('display.max_row', 214)
Recent

#Have to remove the commas before changing the datatype from string to floats

Recent['Transit: Railways, (million passenger-km)'] = Recent['Transit: Railways, (million passenger-km)'].str.replace(',', '', case= False)
Recent['Business: Mobile phone subscribers'] = Recent['Business: Mobile phone subscribers'].str.replace(',', '', case= False)
Recent['Health: Health expenditure per capita (current US$)'] = Recent['Health: Health expenditure per capita (current US$)'].str.replace(',', '', case= False)
Recent['Population: Total (count)'] = Recent['Population: Total (count)'].str.replace(',', '', case= False)
Recent['Population: Urban (count)'] = Recent['Population: Urban (count)'].str.replace(',', '', case= False)
Recent['Finance: GDP (current US$)'] = Recent['Finance: GDP (current US$)'].str.replace(',', '', case= False)
Recent['Finance: GDP per capita (current US$)'] = Recent['Finance: GDP per capita (current US$)'].str.replace(',', '', case= False)


#changing datatype to floats

Recent['Population: Total (count)'] = Recent['Population: Total (count)'].astype(float)
Recent['Population: Urban (count)'] = Recent['Population: Urban (count)'].astype(float)
Recent['Population: Ages 0-14 (% of total)'] = Recent['Population: Ages 0-14 (% of total)'].astype(float)
Recent['Transit: Railways, (million passenger-km)'] = Recent['Transit: Railways, (million passenger-km)'].astype(float)
Recent['Business: Mobile phone subscribers'] = Recent['Business: Mobile phone subscribers'].astype(float)
Recent['Transit: Passenger cars (per 1,000 people)'] = Recent['Transit: Passenger cars (per 1,000 people)'].astype(float)
Recent['Business: Internet users (per 100 people)'] = Recent['Business: Internet users (per 100 people)'].astype(float)
Recent['Health: Mortality, under-5 (per 1,000 live births)'] = Recent['Health: Mortality, under-5 (per 1,000 live births)'].astype(float)
Recent['Health: Health expenditure per capita (current US$)'] = Recent['Health: Health expenditure per capita (current US$)'].astype(float)
Recent['Health: Health expenditure, total (% GDP)'] = Recent['Health: Health expenditure, total (% GDP)'].astype(float)
Recent['Population:: Birth rate, crude (per 1,000)'] = Recent['Population:: Birth rate, crude (per 1,000)'].astype(float)
Recent['Finance: GDP (current US$)'] = Recent['Finance: GDP (current US$)'].astype(float)
Recent['Finance: GDP per capita (current US$)'] = Recent['Finance: GDP per capita (current US$)'].astype(float)

Recent.sort_values(by='Population: Total (count)', ascending = False).tail(20)

Recent.to_excel('C:\\Users\\KAY\\Documents\\Data Science\\Datasets\\Latest co.xlsx')  #exporting to excel file format

Top_health = Recent.sort_values(by=['Health: Health expenditure per capita (current US$)'], ascending = False).head(50)
Top_health
#creating a new table to show the top 50 spenders on healthcare

country = Top_health['Country Name'].head(10)
health_fund = Top_health['Health: Health expenditure per capita (current US$)'].head(10)
#plotting a barhistogram to visualize and compare the top 10 healthcare spenders

plt.style.use('seaborn-dark-palette')
plt.barh(country,health_fund, color = 'g')
plt.title('Top health fundings')
plt.xlabel('country')
plt.ylabel('health_fund')

plt.tight_layout()

plt.show()