Abstract

The present document shows a data set from the Electric Vehicles Population in cities and counties throughout the states of the US over the period 1997 – 2023 (present). Over this period, the industry of Electric Vehicles (EV) in the United States has undergone a transformative journey across cities and counties. In the late 1990s, EVs were largely experimental and niche, with limited presence in select urban areas. However, as technological advancements, environmental considerations, and government incentives gained momentum, the EV population began a notable ascent. In the early 2000s, there was a significant increase in the industry. Starting the mid 2010s and so on, the EV population was observed, with major metropolitan areas leading the charge. By 2023, EV popularity in the United Stated, had become more widespread, reflecting a comprehensive shift towards sustainable transportation practices across diverse urban and suburban areas.

Introduction to the Data

The evolution of Electric Vehicles in the United States has grown over the last years. We found a dataset where we can see this increase from 1997 – 2023 (present), where over this period, cities and counties across the nation have played a pivotal role in shaping the trajectory of electric vehicle adoption. This dataset can be found on Kaggle, where the author, Utkarsh Singh, a Junior Data Scientist at Travee.AI explains about this increase in the Electric Vehicle industry, where the last time it was updated was 7 months ago.

glimpse(EV_Pop)
## Rows: 124,716
## Columns: 17
## $ VIN..1.10.                                        <chr> "5YJ3E1EB4L", "5YJ3E…
## $ County                                            <chr> "Yakima", "San Diego…
## $ City                                              <chr> "Yakima", "San Diego…
## $ State                                             <chr> "WA", "CA", "OR", "W…
## $ Postal.Code                                       <int> 98908, 92101, 97404,…
## $ Model.Year                                        <int> 2020, 2019, 2021, 20…
## $ Make                                              <chr> "TESLA", "TESLA", "V…
## $ Model                                             <chr> "MODEL 3", "MODEL 3"…
## $ Electric.Vehicle.Type                             <chr> "Battery Electric Ve…
## $ Clean.Alternative.Fuel.Vehicle..CAFV..Eligibility <chr> "Clean Alternative F…
## $ Electric.Range                                    <int> 322, 220, 22, 289, 1…
## $ Base.MSRP                                         <int> 0, 0, 0, 0, 0, 0, 0,…
## $ Legislative.District                              <int> 14, NA, NA, 14, 1, 3…
## $ DOL.Vehicle.ID                                    <int> 127175366, 266614659…
## $ Vehicle.Location                                  <chr> "POINT (-120.56916 4…
## $ Electric.Utility                                  <chr> "PACIFICORP", "", ""…
## $ X2020.Census.Tract                                <dbl> 53077000904, 6073005…

Reorder and remove columns

EV_Pop <- EV_Pop %>% select('Electric.Vehicle.Type', 'VIN..1.10.',  'Model.Year', 'Make', 'Model', 'County', 'City', 'State','Electric.Range')

Changing column names

EV_Pop <- EV_Pop %>% rename(EV_Type='Electric.Vehicle.Type', Vin='VIN..1.10.')

Calculated age of the car

EV_Pop <- EV_Pop %>% mutate(CarAge = 2023 - Model.Year)

First steps to binning car age

Breaks <- c(0,9,18,27)
Labels <- c("New", "Mid", "Old")

Binning Car Age

EV_Pop$Age_Bin <- cut(EV_Pop$CarAge,breaks=Breaks,labels=Labels)

Created new dataset - NewEV_Pop

NewEV_Pop <- subset(EV_Pop, subset = ! (EV_Pop$'Electric.Range'==0))

Scatter Plot

NewEV_Pop %>% ggplot(aes(CarAge,Electric.Range))+geom_point()+geom_smooth(method = "lm",colour="blue")+labs(title= "Relationship between Age & Range", x="Age", y="Range")

Graph Slope

cor(NewEV_Pop$CarAge,NewEV_Pop$'Electric.Range')
## [1] -0.1707202

#Created a tab so we can visualize the data in an easier way

model<- lm(NewEV_Pop$'Electric.Range'~ NewEV_Pop$CarAge, data=NewEV_Pop)

Business Questions

  1. What are the key factors influencing the adoption of electric vehicles in different regions? What seems to be the most common state electric vehicles appear to be in?

  2. What are the demographic factors that correlate with higher electric vehicle adoption, how can businesses use this information to target specific customer segments?

  3. How does the availability and accessibility of charging infrastructure impact the adoption of electric vehicles and what opportunities does this present for businesses in the charging industry?

  4. How do consumers perceive the environmental benefits of electric vehicles, how can businesses effectively communicate these advantages in their marketing efforts?

Analysis

Found the correlation between the car age and the electric range. The slope resulted in -0.1707202. This is a weak negative correlation. Created a model to easier visualize this data, including the slope and y intercept. This allowed us to plug in these values and utilize the regression model to find the output and dependent variable.

Conclusion

In conclusion, the evolution of Electric Vehicles in the United States, showcases a significant upward trend from 1997 to 2023. The integral role played by cities and counties in shaping this trajectory is evident. The observed negative correlation of -0.1707202 between electric range and age underscores the dynamic nature of technological advancements within the Electric Vehicle industry. As stakeholders continue to collaborate, these insights will be crucial in sustaining the positive shift towards widespread electric vehicle adoption. Ongoing monitoring and analysis of such datasets will be pivotal in steering the future of sustainable transportation.