import pandas as pd
import numpy as np
import seaborn as sns
from statsmodels.graphics.mosaicplot import mosaic
import matplotlib.pyplot as plt
%matplotlib inline
df = pd.read_csv("datasets_600600_1109547_hospital_beds_per_india_v1.csv")
df.iloc[30:31,7:8] = (df.iloc[30:31,7:8]/1000)
df
country | state | county | lat | lng | type | measure | beds | population | year | source | source_url | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | IN | AN | NaN | 11.740100 | 92.658600 | TOTAL | 1000HAB | 2.825081 | 380520 | 2016 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
1 | IN | AP | NaN | 15.912900 | 79.740000 | TOTAL | 1000HAB | 0.436072 | 53060000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
2 | IN | AR | NaN | 28.218000 | 94.727800 | TOTAL | 1000HAB | 1.427893 | 1683600 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
3 | IN | AS | NaN | 26.200600 | 92.937600 | TOTAL | 1000HAB | 0.497753 | 34438756 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
4 | IN | BR | NaN | 25.096100 | 85.313100 | TOTAL | 1000HAB | 0.094838 | 122988691 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
5 | IN | CH | NaN | 30.733300 | 76.779400 | TOTAL | 1000HAB | 3.305227 | 1136382 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
6 | IN | CT | NaN | 21.278700 | 81.866100 | TOTAL | 1000HAB | 0.333759 | 28200000 | 2016 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
7 | IN | DN | NaN | 20.180900 | 73.016900 | TOTAL | 1000HAB | 1.501793 | 412174 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
8 | IN | DD | NaN | 20.428300 | 72.839700 | TOTAL | 1000HAB | 0.815190 | 294410 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
9 | IN | DL | NaN | 28.704100 | 77.102500 | TOTAL | 1000HAB | 0.927110 | 26300000 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
10 | IN | GA | NaN | 15.299300 | 74.124000 | TOTAL | 1000HAB | 1.996611 | 1508556 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
11 | IN | GJ | NaN | 22.258700 | 71.192400 | TOTAL | 1000HAB | 0.296420 | 68052000 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
12 | IN | HR | NaN | 29.058800 | 76.085600 | TOTAL | 1000HAB | 0.396725 | 28332000 | 2016 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
13 | IN | HP | NaN | 31.104800 | 77.173400 | TOTAL | 1000HAB | 1.699184 | 7297034 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
14 | IN | JK | NaN | 33.778200 | 76.576200 | TOTAL | 1000HAB | 0.509006 | 14324000 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
15 | IN | JH | NaN | 23.610200 | 85.279900 | TOTAL | 1000HAB | 0.298536 | 36122977 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
16 | IN | KA | NaN | 15.317300 | 75.713900 | TOTAL | 1000HAB | 1.031376 | 67600000 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
17 | IN | KL | NaN | 10.850500 | 76.271100 | TOTAL | 1000HAB | 1.018546 | 37312000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
18 | IN | LD | NaN | 8.295441 | 73.048973 | TOTAL | 1000HAB | 3.614458 | 83000 | 2016 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
19 | IN | MP | NaN | 22.973400 | 78.656900 | TOTAL | 1000HAB | 0.390610 | 79634400 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
20 | IN | MH | NaN | 19.751500 | 75.713900 | TOTAL | 1000HAB | 0.433412 | 118700000 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
21 | IN | MN | NaN | 24.663700 | 93.906300 | TOTAL | 1000HAB | 0.492069 | 2900000 | 2014 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
22 | IN | ML | NaN | 25.467000 | 91.366200 | TOTAL | 1000HAB | 1.284438 | 3470000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
23 | IN | MZ | NaN | 23.164500 | 92.937600 | TOTAL | 1000HAB | 1.322517 | 1510000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
24 | IN | NL | NaN | 26.158400 | 94.562400 | TOTAL | 1000HAB | 0.643836 | 2920000 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
25 | IN | OR | NaN | 20.951700 | 85.098500 | TOTAL | 1000HAB | 0.402674 | 45990000 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
26 | IN | PY | NaN | 11.941600 | 79.808300 | TOTAL | 1000HAB | 2.605109 | 1370000 | 2016 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
27 | IN | PB | NaN | 31.147100 | 75.341200 | TOTAL | 1000HAB | 0.599285 | 29924000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
28 | IN | RJ | NaN | 27.023800 | 74.217900 | TOTAL | 1000HAB | 0.621999 | 75649600 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
29 | IN | SK | NaN | 27.533000 | 88.512200 | TOTAL | 1000HAB | 2.427396 | 642664 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
30 | IN | TN | NaN | 11.127100 | 78.656900 | TOTAL | 1000HAB | 0.971725 | 79788 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
31 | IN | TG | NaN | 18.112400 | 79.019300 | TOTAL | 1000HAB | 0.536375 | 39120000 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
32 | IN | TR | NaN | 23.940800 | 91.988200 | TOTAL | 1000HAB | 1.206473 | 3671032 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
33 | IN | UP | NaN | 26.846700 | 80.946200 | TOTAL | 1000HAB | 0.344954 | 221073168 | 2017 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
34 | IN | UT | NaN | 30.066800 | 79.019300 | TOTAL | 1000HAB | 0.832877 | 10220000 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
35 | IN | WB | NaN | 22.986800 | 87.855000 | TOTAL | 1000HAB | 0.834920 | 94100000 | 2015 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
36 | IN | IN | NaN | 20.593700 | 78.962900 | TOTAL | 1000HAB | 0.527706 | 1353000000 | 2018 | nhp | http://www.cbhidghs.nic.in/showfile.php?lid=1147 |
df.dropna(axis = 1,inplace = True)
df.drop(['source','source_url','type','measure'],axis = 'columns',inplace = True)
df1 = np.split(df,[36],axis = 0)
india_states = df1[0]
india = df1[1]
india_states # india_states as dataframe
country | state | lat | lng | beds | population | year | |
---|---|---|---|---|---|---|---|
0 | IN | AN | 11.740100 | 92.658600 | 2.825081 | 380520 | 2016 |
1 | IN | AP | 15.912900 | 79.740000 | 0.436072 | 53060000 | 2017 |
2 | IN | AR | 28.218000 | 94.727800 | 1.427893 | 1683600 | 2018 |
3 | IN | AS | 26.200600 | 92.937600 | 0.497753 | 34438756 | 2017 |
4 | IN | BR | 25.096100 | 85.313100 | 0.094838 | 122988691 | 2018 |
5 | IN | CH | 30.733300 | 76.779400 | 3.305227 | 1136382 | 2018 |
6 | IN | CT | 21.278700 | 81.866100 | 0.333759 | 28200000 | 2016 |
7 | IN | DN | 20.180900 | 73.016900 | 1.501793 | 412174 | 2018 |
8 | IN | DD | 20.428300 | 72.839700 | 0.815190 | 294410 | 2015 |
9 | IN | DL | 28.704100 | 77.102500 | 0.927110 | 26300000 | 2015 |
10 | IN | GA | 15.299300 | 74.124000 | 1.996611 | 1508556 | 2018 |
11 | IN | GJ | 22.258700 | 71.192400 | 0.296420 | 68052000 | 2018 |
12 | IN | HR | 29.058800 | 76.085600 | 0.396725 | 28332000 | 2016 |
13 | IN | HP | 31.104800 | 77.173400 | 1.699184 | 7297034 | 2017 |
14 | IN | JK | 33.778200 | 76.576200 | 0.509006 | 14324000 | 2018 |
15 | IN | JH | 23.610200 | 85.279900 | 0.298536 | 36122977 | 2015 |
16 | IN | KA | 15.317300 | 75.713900 | 1.031376 | 67600000 | 2018 |
17 | IN | KL | 10.850500 | 76.271100 | 1.018546 | 37312000 | 2017 |
18 | IN | LD | 8.295441 | 73.048973 | 3.614458 | 83000 | 2016 |
19 | IN | MP | 22.973400 | 78.656900 | 0.390610 | 79634400 | 2018 |
20 | IN | MH | 19.751500 | 75.713900 | 0.433412 | 118700000 | 2015 |
21 | IN | MN | 24.663700 | 93.906300 | 0.492069 | 2900000 | 2014 |
22 | IN | ML | 25.467000 | 91.366200 | 1.284438 | 3470000 | 2017 |
23 | IN | MZ | 23.164500 | 92.937600 | 1.322517 | 1510000 | 2017 |
24 | IN | NL | 26.158400 | 94.562400 | 0.643836 | 2920000 | 2015 |
25 | IN | OR | 20.951700 | 85.098500 | 0.402674 | 45990000 | 2018 |
26 | IN | PY | 11.941600 | 79.808300 | 2.605109 | 1370000 | 2016 |
27 | IN | PB | 31.147100 | 75.341200 | 0.599285 | 29924000 | 2017 |
28 | IN | RJ | 27.023800 | 74.217900 | 0.621999 | 75649600 | 2018 |
29 | IN | SK | 27.533000 | 88.512200 | 2.427396 | 642664 | 2017 |
30 | IN | TN | 11.127100 | 78.656900 | 0.971725 | 79788 | 2017 |
31 | IN | TG | 18.112400 | 79.019300 | 0.536375 | 39120000 | 2017 |
32 | IN | TR | 23.940800 | 91.988200 | 1.206473 | 3671032 | 2018 |
33 | IN | UP | 26.846700 | 80.946200 | 0.344954 | 221073168 | 2017 |
34 | IN | UT | 30.066800 | 79.019300 | 0.832877 | 10220000 | 2015 |
35 | IN | WB | 22.986800 | 87.855000 | 0.834920 | 94100000 | 2015 |
india #india as dataframe
country | state | lat | lng | beds | population | year | |
---|---|---|---|---|---|---|---|
36 | IN | IN | 20.5937 | 78.9629 | 0.527706 | 1353000000 | 2018 |
st = india_states['state']
pop = india_states['population']
plt.figure(figsize=(7,9))
plt.xlabel("States")
plt.ylabel("Population")
plt.title("Population Per State")
plt.bar(st,pop,width=0.9,align='center')
plt.subplots_adjust(bottom=0.15)
plt.xticks(st,rotation =-90)
plt.show()
byyear = india_states.groupby('year')
byear = byyear[['beds','population']].sum()
by_year = byear.reset_index()
by_year
year | beds | population | |
---|---|---|---|
0 | 2014 | 0.492069 | 2900000 |
1 | 2015 | 4.785881 | 288657387 |
2 | 2016 | 9.775132 | 58365520 |
3 | 2017 | 11.138245 | 427927410 |
4 | 2018 | 12.784920 | 482650435 |
plt.figure(figsize=(9,3))
plt.subplot(121)
plt.xlabel("Year")
plt.ylabel("Beds Capacity")
plt.title("No.of Beds/year")
plt.plot(by_year.year,by_year.beds,linewidth =3)
plt.subplot(122)
plt.title("Population/year")
plt.xlabel("Year")
plt.ylabel("Population (10^8)")
plt.plot(by_year.year,by_year.population,'b')
plt.xticks(by_year["year"].tolist())
plt.subplots_adjust(wspace=0.3)
plt.grid()
plt.show()
top = india_states.iloc[[19,4,20,33,35]]
top_five = top[['state','beds','year']].reset_index(drop = True)
top_five
state | beds | year | |
---|---|---|---|
0 | MP | 0.390610 | 2018 |
1 | BR | 0.094838 | 2018 |
2 | MH | 0.433412 | 2015 |
3 | UP | 0.344954 | 2017 |
4 | WB | 0.834920 | 2015 |
sns.barplot(x = 'state',y = 'beds',data=top_five,hue = 'year',palette="Reds_d").set_title('Bed capacity in top five States of india')
plt.xlabel("States")
plt.ylabel("Bed Capacity (per 1000HAB)")
plt.show()
stat = india_states[['beds','population']]
stat.corr()
beds | population | |
---|---|---|
beds | 1.000000 | -0.493583 |
population | -0.493583 | 1.000000 |
statistics = byyear.describe()
bed_stat = statistics['beds'].fillna(statistics['beds']['std'].mean())
bed_stat
count | mean | std | min | 25% | 50% | 75% | max | |
---|---|---|---|---|---|---|---|---|
year | ||||||||
2014 | 1.0 | 0.492069 | 0.821742 | 0.492069 | 0.492069 | 0.492069 | 0.492069 | 0.492069 |
2015 | 7.0 | 0.683697 | 0.236024 | 0.298536 | 0.538624 | 0.815190 | 0.833899 | 0.927110 |
2016 | 5.0 | 1.955026 | 1.499177 | 0.333759 | 0.396725 | 2.605109 | 2.825081 | 3.614458 |
2017 | 11.0 | 1.012568 | 0.639181 | 0.344954 | 0.517064 | 0.971725 | 1.303478 | 2.427396 |
2018 | 12.0 | 1.065410 | 0.912585 | 0.094838 | 0.399658 | 0.826688 | 1.446368 | 3.305227 |
pop_stat = statistics['population'].fillna(statistics['population']['std'].mean())
pop_stat
count | mean | std | min | 25% | 50% | 75% | max | |
---|---|---|---|---|---|---|---|---|
year | ||||||||
2014 | 1.0 | 2.900000e+06 | 4.180366e+07 | 2900000.0 | 2900000.0 | 2900000.0 | 2900000.0 | 2900000.0 |
2015 | 7.0 | 4.123677e+07 | 4.681670e+07 | 294410.0 | 6570000.0 | 26300000.0 | 65111488.5 | 118700000.0 |
2016 | 5.0 | 1.167310e+07 | 1.515474e+07 | 83000.0 | 380520.0 | 1370000.0 | 28200000.0 | 28332000.0 |
2017 | 11.0 | 3.890249e+07 | 6.333505e+07 | 79788.0 | 2490000.0 | 29924000.0 | 38216000.0 | 221073168.0 |
2018 | 12.0 | 4.022087e+07 | 4.190817e+07 | 412174.0 | 1639839.0 | 30157000.0 | 69951400.0 | 122988691.0 |
x = [i for i in range(2014,2019,1)]
y = [i for i in range(0,13,2)]
plt.xlabel('Year')
plt.ylabel('Value')
plt.title("Lineplot representation of bed's statistics")
plt.plot(x,bed_stat['count'],label = 'count',marker='o', linewidth=3,mfc = 'k')
plt.plot(x,bed_stat['mean'],label = 'mean',marker='o', linewidth=3,)
plt.plot(x,bed_stat['std'],label = 'std',marker='o', linewidth=3)
plt.plot(x,bed_stat['min'],label = 'min',marker='o',linestyle = ':', linewidth=3)
plt.plot(x,bed_stat['50%'],label = '50%',marker='o', linewidth=3)
plt.plot(x,bed_stat['max'],label = 'max',marker='o',linestyle = '--', linewidth=3)
plt.legend(loc = 'best')
plt.xticks(x)
plt.grid(alpha = 0.5)
plt.show()
x = [i for i in range(2014,2019,1)]
#y = [i for i in range(0,1,0)]
plt.xlabel('Year')
plt.ylabel('Value (In 10^8)')
plt.title("Lineplot representation of Population statistics")
plt.plot(x,pop_stat['count'],label = 'count',marker='o',linewidth=3)
plt.plot(x,pop_stat['mean'],label = 'mean',marker='o',linewidth=3)
plt.plot(x,pop_stat['std'],label = 'std',marker='o',linewidth=3)
plt.plot(x,pop_stat['min'],label = 'min',marker='o',linestyle = ':', linewidth=3)
plt.plot(x,pop_stat['50%'],label = '50%',marker='o', linewidth=3)
plt.plot(x,pop_stat['max'],label = 'max',marker='o',linestyle = '--', linewidth=3)
plt.legend(loc = 'best')
plt.xticks(x)
plt.grid(alpha = 0.5)
plt.show()
udf = pd.read_csv("datasets_600600_1109547_hospital_beds_USA_v1.csv",na_values={'beds':'0'})
udf
country | state | county | lat | lng | type | measure | beds | population | year | source | source_url | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | US | AK | aleutians east | 63.588753 | -154.493062 | ICU | 1000HAB | NaN | 3338 | 2019 | khn | https://khn.org/news/as-coronavirus-spreads-wi... |
1 | US | AK | aleutians west | 63.588753 | -154.493062 | ICU | 1000HAB | NaN | 5784 | 2019 | khn | https://khn.org/news/as-coronavirus-spreads-wi... |
2 | US | AK | anchorage | 63.588753 | -154.493062 | ACUTE | 1000HAB | 2.182916 | 298225 | 2018 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
3 | US | AK | anchorage | 63.588753 | -154.493062 | ICU | 1000HAB | 0.244782 | 298225 | 2019 | khn | https://khn.org/news/as-coronavirus-spreads-wi... |
4 | US | AK | anchorage | 63.588753 | -154.493062 | OTHER | 1000HAB | 0.191131 | 298225 | 2019 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
5708 | US | WY | uinta | 43.075968 | -107.290284 | ACUTE | 1000HAB | 2.023316 | 20758 | 2018 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
5709 | US | WY | uinta | 43.075968 | -107.290284 | ICU | 1000HAB | 0.289045 | 20758 | 2019 | khn | https://khn.org/news/as-coronavirus-spreads-wi... |
5710 | US | WY | uinta | 43.075968 | -107.290284 | PSYCHIATRIC | 1000HAB | 8.815878 | 20758 | 2018 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
5711 | US | WY | washakie | 43.075968 | -107.290284 | ICU | 1000HAB | 2.181025 | 8253 | 2018 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
5712 | US | WY | weston | 43.075968 | -107.290284 | ICU | 1000HAB | 1.686104 | 7117 | 2018 | arcgis | https://services1.arcgis.com/Hp6G80Pky0om7QvQ/... |
5713 rows × 12 columns
udf.drop(['measure','source','source_url'],axis = 1,inplace = True)
udf.rename(columns={'county':'city'} ,inplace = True)
udf.dropna(inplace=True)
udf.reset_index(drop = True,inplace = True)
udf
country | state | city | lat | lng | type | beds | population | year | |
---|---|---|---|---|---|---|---|---|---|
0 | US | AK | anchorage | 63.588753 | -154.493062 | ACUTE | 2.182916 | 298225 | 2018 |
1 | US | AK | anchorage | 63.588753 | -154.493062 | ICU | 0.244782 | 298225 | 2019 |
2 | US | AK | anchorage | 63.588753 | -154.493062 | OTHER | 0.191131 | 298225 | 2019 |
3 | US | AK | anchorage | 63.588753 | -154.493062 | PSYCHIATRIC | 0.938888 | 298225 | 2018 |
4 | US | AK | bethel | 63.588753 | -154.493062 | ICU | 2.060478 | 17957 | 2018 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
4690 | US | WY | uinta | 43.075968 | -107.290284 | ACUTE | 2.023316 | 20758 | 2018 |
4691 | US | WY | uinta | 43.075968 | -107.290284 | ICU | 0.289045 | 20758 | 2019 |
4692 | US | WY | uinta | 43.075968 | -107.290284 | PSYCHIATRIC | 8.815878 | 20758 | 2018 |
4693 | US | WY | washakie | 43.075968 | -107.290284 | ICU | 2.181025 | 8253 | 2018 |
4694 | US | WY | weston | 43.075968 | -107.290284 | ICU | 1.686104 | 7117 | 2018 |
4695 rows × 9 columns
print('BED CAPACITY IN EVERY CITY OF USA (PER STATE)'.center(140,"*"))
bystate = udf.loc[:,('state','city','beds','year','population')].groupby('state')
state_list = list(udf['state'].unique())
for a,b, in bystate:
state_list = list(udf['state'].unique())
fig = plt.figure(figsize=(6,6))
bycity = bystate.get_group(str(a)).groupby('city')
bed_city = bycity.sum().head(10).reset_index()
plt.xlabel("city")
plt.ylabel("beds")
plt.title(str(a))
plt.bar(bed_city.city,bed_city.beds,width=0.9,align='center')
plt.xticks(bed_city.city,rotation =90)
plt.show()
***********************************************BED CAPACITY IN EVERY CITY OF USA (PER STATE)************************************************
sns.lmplot(x ='population',y ='beds',data=udf,hue='year',palette="Set1",legend_out=False)
plt.title('Beds capacity (2012-2020) ')
plt.show()
sp = bystate.mean().reset_index()
plt.figure(figsize=(15,5))
ax = sns.scatterplot(x="state", y='beds', hue="year",data=sp)
ax.set_title('Bed capacities per state for diffrent durations')
plt.xticks(sp['state'])
plt.show()
bytype = udf.loc[:,('type','beds')].groupby('type')
bp = bytype.mean().reset_index()
plt.figure(figsize = (10, 6))
ax = sns.barplot(x='type',y='beds',data=bp,ci='sd')
#plt.setp(ax.artists, alpha=.5, linewidth=2, edgecolor="k")
ax.set_title("Barplot for bed capacity in USA")
plt.yticks(fontsize = 12)
plt.xticks(rotation=45,fontsize = 12)
plt.show()
plt.figure(figsize=(6,6))
sns.lineplot(x= 'year',y = 'beds',hue='type',data=udf,palette="Set1", lw=2,style='type',estimator=None)
plt.title("Lineplot for types of beds in USA")
plt.legend(loc='upper left')
plt.grid(alpha=0.5)
plt.show()
sns.heatmap(udf[['beds','population']].corr(),annot=True)
plt.title("CORRELATION")
plt.show()
stt = udf[['beds','population']].describe().T
stt
count | mean | std | min | 25% | 50% | 75% | max | |
---|---|---|---|---|---|---|---|---|
beds | 4695.0 | 2.004897 | 3.315337 | 0.01622 | 0.283027 | 1.135538 | 2.694095 | 9.046635e+01 |
population | 4695.0 | 204881.866454 | 503932.932795 | 1084.00000 | 24307.500000 | 58480.000000 | 176423.000000 | 1.010572e+07 |
stt_india = india_states[['beds','population']].describe()
stt_india_bed = stt_india.iloc[:,:1].reset_index()
ind = pd.Series(['india']*8,name="country")
bed_conty = pd.concat([stt_india_bed,ind],axis=1)
bystate = udf.loc[:,('state','beds','population')].groupby('state')
stt_usa = bystate.sum().describe()
stt_usa_bed =stt_usa.iloc[:,:1].reset_index()
ind = pd.Series(['USA']*8,name="country")
bed_conty_1 = pd.concat([stt_usa_bed,ind],axis=1)
final_comp = pd.concat([bed_conty,bed_conty_1])
plt.title("Beds capacity between india and USA ")
sns.lineplot(x='index',y='beds',hue='country',data=final_comp)
plt.show()
Although, their is a count difference in states of two countries, We come to the conclusion that in 2018-19, USA has more bed capacity than india.The maxima and minima for both the countries are differing a lot. Thus, their is a need to fill this gap for the betterment of future.