0. Loading Libraries

import pandas as pd
from dfply import *
from plotnine import *
import ssl

1. Data Loading

## adding below ssl line as it is giving ssl error locally in my machine
ssl._create_default_https_context = ssl._create_unverified_context

polling=pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2024/2024-01-16/polling_places.csv")
polling.head()

	election_date	state	county_name	jurisdiction	jurisdiction_type	precinct_id	precinct_name	polling_place_id	location_type	name	address	notes	source	source_date	source_notes
0	2020-11-03	AL	AUTAUGA	AUTAUGA	county	NaN	AUTAUGAVILLE VOL FIRE DEPT	NaN	election_day	AUTAUGAVILLE VOL FIRE DEPT	2610 HIGHWAY 14 W, AUTAUGAVILLE, AL 36003	NaN	ORR	2020-10-21	NaN
1	2020-11-03	AL	AUTAUGA	AUTAUGA	county	NaN	BILLINGSLEY COMMUNITY CENTER	NaN	election_day	BILLINGSLEY COMMUNITY CENTER	2159 COUNTY RD 37, BILLINGSLEY, AL 36006	NaN	ORR	2020-10-21	NaN
2	2020-11-03	AL	AUTAUGA	AUTAUGA	county	NaN	BOONE'S CHAPEL	NaN	election_day	BOONE'S CHAPEL	2301 COUNTY RD 66, PRATTVILLE, AL 36067	NaN	ORR	2020-10-21	NaN
3	2020-11-03	AL	AUTAUGA	AUTAUGA	county	NaN	BOOTH VOL FIRE DEPT	NaN	election_day	BOOTH VOL FIRE DEPT	1701 COUNTY ROAD 10, BOOTH, AL 36008	NaN	ORR	2020-10-21	NaN
4	2020-11-03	AL	AUTAUGA	AUTAUGA	county	NaN	CAMELLIA BAPTIST CH	NaN	election_day	CAMELLIA BAPTIST CH	201 WOODVALE ROAD, PRATTVILLE, AL 36067	NaN	ORR	2020-10-21	NaN

2. Data Transformation

polling['year'] = polling['election_date'].apply(lambda x: int(x.split('-')[0]))

polling_summary = (polling >> group_by(X.year) >> summarize(count=n(X.year)) )

3. Plotting

(polling_summary >> 
 ggplot(aes(x = 'year', y = 'count')) + 
 geom_line() + theme_minimal() + 
 labs (
     x = "Year", 
     y = "No. of Polling Places",
     title = "Count of Polling Places",
     subtitle = "2012 to 2020"
 ) 
)