Cynthia Hester HW3

Data_Wrangling_HW3.Rmd

@@ -0,0 +1,193 @@
+---
+title: "Homework Three"
+description: Basic Data Wrangling
+author:
+  - name: Cynthia Hester 
+
+date: 10-09-2021
+output: 
+  distill::distill_article:
+   self_contained: no
+draft: yes    
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+library(stringr)
+library(tidyverse)
+library(readr)
+library(here)
+```
+
+
+
+
+
+## Introduction
+
+Let's start with what the heck is data wrangling? You can wrangle cattle, but wrangling data? Yes! After data is imported or read into the RStudio environment it needs to be maneuvered before it can be used for visualization or modeling.
+
+
+## First Steps
+
+
+First, I am going to import data into R- In this case the Railroad_2012 data set which is a CSV file. While this is an already cleaned data set, it can still provide insight.
+
+
+
+```{r}
+library(readr)
+railroad_2012_clean_county <- read_csv("_data/railroad_2012_clean_county.csv")
+View(railroad_2012_clean_county)
+```
+
+
+
+The railroad data set was checked out, starting with the **head** and **tail** functions, which displayed the first 5 and last 5 rows of the data set.
+
+
+
+```{r}
+head(railroad_2012_clean_county,5)   
+tail(railroad_2012_clean_county,5)
+```
+
+
+________________________________________________________________________________
+Then using **colnames** which takes a look at column names of the data set.
+
+
+
+```{r}
+colnames(railroad_2012_clean_county)
+```
+
+
+________________________________________________________________________________
+The  **glimpse**  function which is part of the dplyr package which provides a synopsis of data was used.
+
+
+
+```{r}
+glimpse(railroad_2012_clean_county)   
+```
+
+________________________________________________________________________________
+
+The  **pivot_wider** function was used to make the data set more manageable and readable, as well as filling in missing values from n/a to 0.
+
+
+
+```{r}
+railroad_2012_clean_county %>%
+  pivot_wider(names_from = state, values_from = total_employees,values_fill = 0)
+```  
+________________________________________________________________________________
+
+
+## Next step - Some Data Wrangling
+
+
+I was interested in the railroad county that had the most employees so I started with the **arrange** function which ranked the number of employees in descending order.It shows, not surprisingly that Cook county in Illinois had the most number of employees.
+
+
+```{r}
+arrange(railroad_2012_clean_county,desc(total_employees))
+```
+
+
+The **arrange** function was also used to display the *total_employees* column.
+
+
+
+```{r}
+arrange(railroad_2012_clean_county,total_employees)
+```
+
+________________________________________________________________________________
+
+I was interested if there were any **na** values in the railroad data set. It shows there were none. Which makes sense because this was a clean data set.
+
+
+
+```{r}
+ railroad_2012_clean_county %>%
+  is.na() %>% 
+  sum()
+```
+________________________________________________________________________________
+
+The **select** function was used to determine the number of rows. In this data set there were 2930 rows.
+
+
+
+```{r}
+select(railroad_2012_clean_county)
+```
+
+
+The **select** function separates the *state* column from the rest of the data set.
+
+
+
+```{r}
+select(railroad_2012_clean_county,state)
+```
+________________________________________________________________________________
+
+The **filter** function was used to determine which rail stations had fewer than 2 employees. Yeah,I was curious about this. It turns out there were 145 stations with less than 2 employees.
+
+
+
+```{r}
+filter(railroad_2012_clean_county,total_employees < 2)
+```
+
+
+
+
+I was curious about the number of stations that had less than or equal to 2 employees, so I created a new object called *subset_employees*, that utilized the pipe operator, **group_by** function,and **filter** function to determine the stations with less than or equal to 2 employees.
+
+
+
+```{r}
+subset_employees<-railroad_2012_clean_county %>% 
+  group_by(total_employees) %>% 
+  filter(total_employees<=2)
+subset_employees
+
+```
+
+________________________________________________________________________________
+
+
+The **summarise** function was used to learn what the mean of the total employees in all states. As it turns out the mean was 87.17816.
+
+
+
+```{r}
+railroad_2012_clean_county %>% 
+  summarise(mean(total_employees))
+```
+________________________________________________________________________________  
+
+
+In this block  the **rename function** was used to change one of the column names, *from total_rail_ employees* to *number_of_employees*. This comes in handy if a column needs to be renamed.
+
+
+
+```{r}
+data<-railroad_2012_clean_county
+data<-rename(data,number_of_rail_employees = total_employees)
+data
+```
+
+
+
+
+
+_______________________________________________________________________________
+By doing this assignment I learned about the power of the tidyverse,which contains the dplyr package. A lot of insight can be gleaned from the railroad dataset with these tools,such as business, and municipal forcasting. For instance, stations with the fewest employees, such as the examples used of  2 or less could be analyzed for either expansion or closure depending on the geographic proximity to other local stations,jobs and housing.   
+
+
+

Reading_in_data_HW2.Rmd

@@ -0,0 +1,124 @@
+---
+title: "Homework_2 "
+description: Reading in Data
+
+author:
+  - name: Cynthia Hester
+
+date: 09-29-2021
+output: 
+  distill::distill_article:
+
+    self_contained: no
+draft: yes  
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = FALSE)
+```
+
+## Reading in the first data set
+
+Reading in or importing data files to RStudio is a necessary step to gain access to any files that are needed for cleaning or tidying. After imported data is cleaned, it is then more suitable for exploration.
+
+
+As we know data formats are not homogeneous,and come in many different flavors. So,whether data is in **CSV, SPSS,XLSX,SAS,TXT,STATA,or HTML** as well as many other formats, there is usually R package to read in the data.
+
+
+The first data set I will read in is from the included R package "Data Sets". It is the *MTCars* (MotorTrend) dataset which was extracted from the 1974 Motor Trend US magazine, and comprises fuel consumption as well as 10 aspects of automotive design and performance for 32 cars (1973-74).
+
+
+
+**This R chunk loads in the data sets package and provides a summary of the statistics for the *mtcars* data set**
+
+```{r}
+library(datasets)
+summary(mtcars)
+
+```
+
+
+
+
+**This R chunk uses an alternative to the *summary* function called *Skim*. *Skim* provides a comprehensive overview of the *mtcars* data set as well as providing a visualization of the  data in the rows represented by histograms.**
+
+
+```{r}
+library(skimr)
+skim(mtcars)
+```
+
+
+
+
+
+**This R chunk exemplifies the granularity of the *Skim* package by selecting specific columns to summarize.**
+
+
+```{r}
+skim(mtcars,hp,wt)
+```
+
+
+
+
+
+**This R chunk provides the column names of the *mtcars* dataset using the colnames() function.**
+
+```{r}
+colnames(mtcars)
+```
+
+
+
+
+
+**This R chuck introduces the *dim()* function provides information on the dimensions of the data set,which shows this data array to have 32 rows and 11 columns.**
+
+```{r}
+dim(mtcars)
+```
+
+
+
+
+**This R chunk shows a generic visualization of the *mtcars* object using the *plot()* function.**
+```{r}
+plot(mtcars)
+```
+
+
+
+## The Second Data Set comes from the course csv file eggs_tidy. 
+
+I wanted to try reading data in from an external data set, that used the csv format.
+
+
+**This first R chunk reads in the eggs tidy csv data**
+
+```{r}
+library(readr)
+eggs_tidy <- read_csv("_data/eggs_tidy.csv")
+```
+
+
+**Summarizes the eggs_tidy data set**
+```{r}
+summary(eggs_tidy)
+```
+
+
+
+**Summarizes data set using the skim function**
+```{r}
+skim(eggs_tidy)
+```
+
+**This chunk uses the *tibble function* which provides a more comprehensive and readable  data frame**
+
+```{r}
+library(tibble)
+as_tibble(eggs_tidy)
+```
+
+