rer145

library(gutenbergr)
library(stringr)

# search for the EXACT name of the novel title
gutenberg_works(title=='Dracula')

# search for the EXACT author's name (Last Name, First Name)
gutenberg_works(author=='Stoker, Bram')

# search for the word 'Frankenstein' in the title column

rer145

library(dplyr)
library(tidytext)
library(janeaustenr)

# Using dplyr and janeaustenr, get the contents of 'Sense & Sensibility'
sns<-austen_books()
sns<-sns%>%
  filter(book=='Sense & Sensibility')

head(sns)

rer145

library(dplyr)
library(tidytext)
library(janeaustenr)

# Using dplyr and janeaustenr, get the contents of 'Sense & Sensibility'
sns<-austen_books()
sns<-sns%>%
  filter(book=='Sense & Sensibility')

head(sns)

rer145

library(dplyr)
library(Lahman)
library(ggplot2)

# Get all the teams from 1980 and how many home runs they hit
df<-Teams %>%
  filter(yearID==1980) %>%
  select(name, HR) %>%
  arrange(HR)

rer145

library(Lahman)
library(dplyr)
library(ggplot2)
library(ggiraph)

# Get all teams from 1980 and the number of home runs hit
df<-Teams %>%
  filter(yearID == 1980) %>%
  select(name, HR) %>%
  arrange(HR)

rer145

library(dplyr)
library(stringr)

deaths<-read.csv("z_KoreanConflict.csv", header=TRUE, stringsAsFactors=FALSE)

rer145

library(dplyr)
library(ggplot2)
library(stringr)
library(lubridate)

# First grab the data and filter out the bad data in INCIDENT_DATE (see https://gist.github.com/rer145/68b75131d7e2d89adc53b1f8d75ab294)
deaths<-read.csv("KoreanConflict.csv", header=TRUE, stringsAsFactors=FALSE)

regEx = "^\\d{8}$"

rer145

library(dplyr)
library(stringr)

deaths<-read.csv("z_KoreanConflict.csv", header=TRUE, stringsAsFactors=FALSE)

# We want to make sure all data in INCIDENT_DATE is correct
# A quick investigation shows the data in a YYYYMMDD format, but some fields are empty
# A simple regular expression can just check for 8 digits
regEx = "^\\d{8}$"

rer145

library(dplyr)
library(tidytext)
library(gutenbergr)
library(ggplot2)

# Get our data, the text of Frankenstein
dracula<-gutenberg_download(345)

# Remove the gutenberg_id field since we don't need it
dracula$gutenberg_id<-NULL

rer145

import os.path

def input_file_prompt():
    """ () -> string

    Precondition: none

    This function returns back a filename that the user wants to read data from. It also checks to see
    if the file already exists and if not, informs the users and prompts them to try again.