csgallego

#We start by opening the file drug12q4 (4th quaterly report from the year 2012) that lists the number or complaints for each drug. The information is separated by dollar signs so we add a separator. We noticed that there was a problem with one quotation mark and we solve this problem by adding quote.
drug12q4 = read.csv("aers_ascii_2012q4/ascii/drug12q4.txt",sep="$",as.is=TRUE,quote="")

#We want to look at all the drugs that are a form of Yaz/Yasmin/Ocella (they might be under different names)
Yaz12q4 = grepl("(^yaz.*)|(^yasm.*)|(^ocel.*)|(^safy*)|(beyaz)",drug12q4$DRUGNAME,ignore.case=TRUE)

#We create a table of Yaz12q4.
table(drug12q4$DRUGNAME[Yaz12q4])

#We sum to see how many complaints there were against Yaz/Yasmin/Ocella in the 4th quarter of 2012.

csgallego

visitee=paste(visits$visitee_namefirst,visits$visite_namelast)
visitee=tolower(iconv(visitee,to=“UTF-8”)
tail(sort(table(visitee)), 30)

csgallego

z = strptime(visits$APPT_START_DATE,format="%m/%d/%Y %H:%M”)
class(z)
head(visits$APPT_START_DATE)
visits$APPT_START_DATE[z$year < 0]
gsub("/13 ","/2013 ",visits$APPT_START_DATE)
visits$CAPPT_START_DATE = gsub("/13 ","/2013 ",visits$APPT_START_DATE)
z = strptime(visits$CAPPT_START_DATE,format="%m/%d/%Y %H:%M”)
is.na(z)
sum(is.na(z))
visits$CAPPT_START_DATE[is.na(z)]

csgallego

#I am creating “POTUS” that gives me every visitors who visited the President of the United States.
POTUS=visits[visitee==“potus ”,]

#I’m marking sure I include all the versions of POTUS possible:
POTUS = visits[ tolower(visits$visitee_namefirst) == "potus" | tolower(visits$visitee_namelast) == "potus"  ,]

#We created a subsrting of those who visited POTUS on June 5th:
substr(POTUS$APPT_START_DATE, 1,5)

#Let’s make a histogram:

csgallego

#We created a subsrting of those who visited POTUS on June 5th:
POTUS[paste(POTUS$time$mon+1,POTUS$time$mday)=="6 5”,]

#Let’s look at only the full names:
POTUS[paste(POTUS$time$mon+1,POTUS$time$mday)=="6 5",c("NAMEFIRST","NAMELAST”)]

#Let’s look at only the 4 first columns: 
POTUS[paste(POTUS$time$mon+1,POTUS$time$mday)=="6 5",1:4]

#We want to add the “column” description which gives us interesting information (it is the column 27):

csgallego

#U01358 and U01402 are big events, they are not related to the NSA revelations. Let’s at all the other UIN and see who they correspond to.

subset(June5,UIN=="U01627”)
#U01627 is the band for the event mention earlier, it is said in the description. 

[I am checking if the UIN are given in increasing order:
POTUS$UIN[order(POTUS$time)]
unique(POTUS$UIN[order(POTUS$time)])
sort(table(visits$UIN))
This helps us find out that they are]

csgallego

#We look at the 2012Q3 data
demo12Q3 = read.csv("aers_ascii_2012q3/ascii/DEMO12Q3.TXT",sep="$",as.is=TRUE,quote="")
drug12Q3 = read.csv("aers_ascii_2012q3/ascii/DRUG12Q3.TXT",sep="$",as.is=TRUE,quote="")

#We need to list the case numers in the demo file, by using the drug file so we merge the two dataframes.
data12Q3 = merge(demo12Q3,drug12Q3,by="ISR")

#We now want to list the column "CASE" associated with the "DRUGNAME" Yaz/Yasmin
yaz12Q3 = grepl("(^yaz.*)|(^yasm.*)|(^ocel.*)|(^safy*)|(beyaz)",data12Q3$DRUGNAME,ignore.case=TRUE)
xyaz12Q3 = data12Q3[yaz12Q3,]

csgallego

#We start by opening the file drug12q4 (4th quaterly report from the year 2012) that lists the number or complaints for each drug. The information is separated by dollar signs so we add a separator. We noticed that there was a problem with one quotation mark and we solve this problem by adding quote.
drug12q4 = read.csv("aers_ascii_2012q4/ascii/drug12q4.txt",sep="$",as.is=TRUE,quote="")

#We want to look at all the drugs that are a form of Yaz/Yasmin/Ocella (they might be under different names)
Yaz12q4 = grepl("(^yaz.*)|(^yasm.*)|(^ocel.*)|(^safy*)|(beyaz)",drug12q4$DRUGNAME,ignore.case=TRUE)

#We create a table of Yaz12q4.
table(drug12q4$DRUGNAME[Yaz12q4])

#We sum to see how many complaints there were against Yaz/Yasmin/Ocella in the 4th quarter of 2012.

csgallego

#Cleaning the dates of the White House visitor logs

z = strptime(visits$APPT_START_DATE,format="%m/%d/%Y %H:%M") 
class(z)
head(visits$APPT_START_DATE)
visits$APPT_START_DATE[z$year < 0]
gsub("/13 ","/2013 ",visits$APPT_START_DATE)
visits$CAPPT_START_DATE = gsub("/13 ","/2013 ",visits$APPT_START_DATE)
z = strptime(visits$CAPPT_START_DATE,format="%m/%d/%Y %H:%M")
is.na(z)

csgallego

#We create vector named "visitee"
visitee=paste(visits$visitee_namefirst,visits$visite_namelast) 
visitee=tolower(iconv(visitee,to=“UTF-8”) 
tail(sort(table(visitee)), 30)

#I am creating “POTUS” that gives me every visitors who visited the President of the United States
POTUS=visits[visitee==“potus ”,]

#I’m making sure I include all the versions of POTUS possible
POTUS = visits[ tolower(visits$visitee_namefirst) == "potus" | tolower(visits$visitee_namelast) == "potus" ,]