R Notebook

library(ggplot2)

cyl.am <- ggplot(mtcars, aes(x = factor(cyl), fill = factor(am)))

#position = "stack" is default
cyl.am + geom_bar()

cyl.am + 
  geom_bar(position = "fill") 

# Dodging - principles of similarity and proximity
cyl.am +
  geom_bar(position = "dodge")

val = c("#E41A1C", "#377EB8")
lab = c("Manual", "Automatic")
cyl.am +
  geom_bar(position = "dodge") +
  scale_x_discrete("Cylinders") + 
  scale_y_continuous("Numbers") +
  scale_fill_manual("Transmission", 
                    values = val,
                    labels = lab) 

mtcars$group <- 0
ggplot(mtcars, aes(x = mpg, y = group)) + geom_point()

# Change the y aesthetic limits
ggplot(mtcars, aes(x = mpg, y = group)) + geom_point() + geom_jitter() + scale_y_continuous(limits = c(-2,2))

# Basic scatter plot: wt on x-axis and mpg on y-axis; map cyl to col
ggplot(mtcars, aes(x = wt, y = mpg, col = cyl)) + geom_point(size = 4)

# Hollow circles - an improvement
ggplot(mtcars, aes(x = wt, y = mpg, col = cyl)) + geom_point(shape = 1, size = 4 )

# Add transparency - very nice
ggplot(mtcars, aes(x = wt, y = mpg, col = cyl)) + geom_point( size = 4, alpha = 0.6)

head(iris)

ggplot(iris, aes(x = Sepal.Width, fill = Species)) + geom_histogram(aes(binwidth = 0.2))

Ignoring unknown aesthetics: binwidth

  
ggplot(iris, aes(x = Sepal.Width, fill = Species)) + geom_histogram(aes(y = ..density..), binwidth = 0.1)

ggplot(iris, aes(x = Sepal.Width, fill = Species)) + geom_histogram(binwidth = 0.1, position = "fill") 

ggplot(iris, aes(x = Sepal.Width, fill = Species)) + geom_histogram(binwidth = 0.1, position = "dodge")

# Make a univariate histogram
ggplot(mtcars, aes(mpg)) +
  geom_histogram()

# Change the bin width to 1
ggplot(mtcars, aes(mpg)) +
  geom_histogram(binwidth = 1)

# Change the y aesthetic to density
ggplot(mtcars, aes(mpg)) +
  geom_histogram(aes(y=..density..), binwidth = 1)

# Custom color code
myBlue <- "#377EB8"
# Change the fill color to myBlue
ggplot(mtcars, aes(mpg)) +
  geom_histogram(aes(y = ..density..),
                 binwidth = 1, fill = myBlue)

# Draw a bar plot of cyl, filled according to am
ggplot(mtcars, aes(x= cyl, fill = factor(am))) + geom_bar()

# Change the position argument to stack
ggplot(mtcars, aes(x= cyl, fill = factor(am))) + geom_bar(position = "stack")

# Change the position argument to fill
ggplot(mtcars, aes(x= cyl, fill = factor(am))) + geom_bar(position = "fill")

# Change the position argument to dodge
ggplot(mtcars, aes(x= cyl, fill = factor(am))) + geom_bar(position = "dodge")

# Draw a bar plot of cyl, filled according to am
ggplot(mtcars, aes(x = cyl, fill = factor(am))) + geom_bar()

# Change the position argument to "dodge"
ggplot(mtcars, aes(x = cyl, fill = factor(am))) + geom_bar(position = "dodge")

# Define posn_d with position_dodge()
posn_d <- position_dodge(width = 0.2)
# Change the position argument to posn_d
ggplot(mtcars, aes(x = cyl, fill = factor(am))) + geom_bar(position = posn_d)

# Use posn_d as position and adjust alpha to 0.6
ggplot(mtcars, aes(x = cyl, fill = factor(am))) + geom_bar(position = posn_d, alpha = 0.6)

#API key
saved_cfg <- data.world::save_config("eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJwcm9kLXVzZXItY2xpZW50OmNocmlzaXllciIsImlzcyI6ImFnZW50OmNocmlzaXllcjo6Zjk1YzVlYTEtZTBiZS00NTU5LTg5MjItYWVkODg4Nzc3NjBkIiwiaWF0IjoxNDk1ODQ2MDQ1LCJyb2xlIjpbInVzZXJfYXBpX3dyaXRlIiwidXNlcl9hcGlfcmVhZCJdLCJnZW5lcmFsLXB1cnBvc2UiOnRydWV9.hMhCmAcXhD3DqJbp5L0JJF9xRfJsMZf-oPSkyxmC5D07tJhNAn-mzPPa4kSVKD65mUuktHwglgUGkJPZoNORVg")
library(data.world)
library(tidyverse)
# Datasets are identified by their URL
df <- read.csv("https://query.data.world/s/5s3rdju1vng0j5ij7675hcpto",header=T);
head(df)

# List tables
data_list <- data.world::query(
  qry_sql("SELECT * FROM Tables"),
  dataset = drugs_ds)
# data_list is a tbl_df with two columns: tableID and tableName.
data_list$tableName

 [1] "FDA_NDC_Product"             "Data"                        "Methods"                    
 [4] "Variables"                   "Pharma_Lobby"                "atc-codes"                  
 [7] "companies_drugs_keyed"       "drug_list"                   "drug_uses"                  
[10] "drugdata_clean"              "drugnames_withclasses"       "lobbying_keyed"             
[13] "manufacturers_drugs_cleaned" "meps_full_2014"              "spending-2011"              
[16] "spending-2012"               "spending-2013"               "spending-2014"              
[19] "spending-2015"               "spending_all_top100"         "usp_drug_classification"    

data_list$tableId

 [1] "FDA_NDC_Product.csv/FDA_NDC_Product"                                      
 [2] "Medicare_Drug_Spending_PartD_All_Drugs_YTD_2015_12_06_2016.xlsx/Data"     
 [3] "Medicare_Drug_Spending_PartD_All_Drugs_YTD_2015_12_06_2016.xlsx/Methods"  
 [4] "Medicare_Drug_Spending_PartD_All_Drugs_YTD_2015_12_06_2016.xlsx/Variables"
 [5] "Pharma_Lobby.csv/Pharma_Lobby"                                            
 [6] "atc-codes.csv/atc-codes"                                                  
 [7] "companies_drugs_keyed.csv/companies_drugs_keyed"                          
 [8] "drug_list.json/drug_list"                                                 
 [9] "drug_uses.csv/drug_uses"                                                  
[10] "drugdata_clean.csv/drugdata_clean"                                        
[11] "drugnames_withclasses.csv/drugnames_withclasses"                          
[12] "lobbying_keyed.csv/lobbying_keyed"                                        
[13] "manufacturers_drugs_cleaned.csv/manufacturers_drugs_cleaned"              
[14] "meps_full_2014.zip/meps_full_2014/meps_full_2014.csv/meps_full_2014"      
[15] "spending-2011.csv/spending-2011"                                          
[16] "spending-2012.csv/spending-2012"                                          
[17] "spending-2013.csv/spending-2013"                                          
[18] "spending-2014.csv/spending-2014"                                          
[19] "spending-2015.csv/spending-2015"                                          
[20] "spending_all_top100.csv/spending_all_top100"                              
[21] "usp_drug_classification.csv/usp_drug_classification"                      

get_year <- function(yr) {
  data.world::query(qry_sql(paste0("SELECT * FROM `spending-", yr, "`")),
                    dataset = drugs_ds)[,-1] %>%
    ## First column is a row number; don"t need that
    mutate(year = yr)
}
# Read in and combine all years' data
spend <- map_df(2011:2015, get_year)
head(spend)

# Add a row for each generic with overall summaries of each variable ----------
spend_overall <- spend %>%
  group_by(drugname_generic, year) %>%
  summarise(
    claim_count = sum(claim_count, na.rm = TRUE),
    total_spending = sum(total_spending, na.rm = TRUE),
    user_count = sum(user_count, na.rm = TRUE),
    unit_count = sum(unit_count, na.rm = TRUE),
    user_count_non_lowincome = sum(user_count_non_lowincome, na.rm = TRUE),
    user_count_lowincome = sum(user_count_lowincome, na.rm = TRUE)
  ) %>%
  mutate(
    total_spending_per_user = total_spending / user_count,
    drugname_brand = "ALL BRAND NAMES",
    ## Add NA values for variables that are brand-specific
    unit_cost_wavg = NA,
    out_of_pocket_avg_lowincome = NA,
    out_of_pocket_avg_non_lowincome = NA
  ) %>%
  ungroup()
# Select top 100 generics by number of users across all five years ------------
by_user_top100 <- group_by(spend_overall, drugname_generic) %>%
  summarise(total_users = sum(user_count, na.rm = TRUE)) %>%
  arrange(desc(total_users)) %>%
  slice(1:100)
# For top 100 generics, add ALL BRAND NAMES rows to by-brand-name rows --------
spend_all_top100 <- bind_rows(spend, spend_overall) %>%
  filter(drugname_generic %in% by_user_top100$drugname_generic) %>%
  arrange(drugname_generic)
head(spend_all_top100)

library(dplyr)
df <- read.csv("https://query.data.world/s/7ezifc8eqig9vdazaoa1noecv",header=T)
df$arrival_date <- as.Date(df$arrival_date, format = "%m/%d/%Y")
df$departure_date <- as.Date(df$departure_date, format = "%m/%d/%Y")
df$ArrivalYear <- format(as.Date(df$arrival_date, format="%Y/%m/%d"),"%Y")
df$ArrivalYear <- as.integer(df$ArrivalYear)
head(df)

dim(df)

[1] 48237     8

whowentwhere <- df  %>% filter(grepl("Russia", country)) %>% select(name, country, ArrivalYear) %>% arrange(desc(name)) 
head(whowentwhere)

dim(whowentwhere)

[1] 673   3

whowentwhere1 <-  whowentwhere %>% filter(ArrivalYear >= 2012) %>% 
 group_by(name,country, ArrivalYear) %>% 
 summarise(n= n()) %>% arrange(desc(name))
whowentwhere1

ggplot(whowentwhere1, aes(ArrivalYear, fill = factor(name))) + geom_bar()

whowentwhere2 <-  whowentwhere %>% 
 group_by(name) %>% 
 summarise(n= n()) %>% arrange(desc(n))
whowentwhere2

PanAm <- df %>%  filter(grepl("Weldon",name)) %>% filter(grepl("Russia", country)) %>% arrange(desc(departure_date))
dim(PanAm)

[1] 22  8

PanAm

PanAm$ArrivalYear <- format(as.Date(PanAm$arrival_date, format="%Y/%m/%d"),"%Y")
head(PanAm)

xyz <- ggplot(PanAm, aes(x = ArrivalYear, fill = factor(country))) + geom_bar() + theme(legend.position='null') + ggtitle("Weldon in Russia")
xyz

abc <- df %>%  filter(grepl("Weldon",name))  %>% arrange(desc(departure_date))
ggplot(abc, aes(x = ArrivalYear, fill = factor(country))) + geom_bar() + ggtitle("Weldon")

Legend Issues

Weldon

yz <- ggplot(PanAm, aes(x = ArrivalYear, fill = factor(country))) + geom_bar() + theme(legend.position='bottom') +
  theme(legend.title=element_blank())
yz 

library(gridExtra)
g_legend<-function(a.gplot){
    tmp <- ggplot_gtable(ggplot_build(a.gplot))
    leg <- which(sapply(tmp$grobs, function(x) x$name) == "guide-box")
    legend <- tmp$grobs[[leg]]
    legend
}
legend <- g_legend(yz)
grid.arrange(legend, yz+ theme(legend.position = 'none'), 
    ncol=2, nrow=1, widths=c(1/6,5/6))

Nunes

PanAm <- df %>%  filter(grepl("nunes",name)) %>% filter(grepl("Russia", country))%>% arrange(desc(departure_date))
PanAm$ArrivalYear <- format(as.Date(PanAm$arrival_date, format="%Y/%m/%d"),"%Y")
PanAm

Dana Rohrabacher

PanAm <- whowentwhere %>%  filter(grepl("Rohr",name)) %>% filter(grepl("Russia", country))%>% arrange(desc(ArrivalYear))
PanAm

#PanAm$ArrivalYear <- format(as.Date(PanAm$arrival_date, format="%Y/%m/%d"),"%Y")
xyz <- ggplot(PanAm, aes(x = ArrivalYear, fill = factor(country))) + geom_bar() 
# + theme(legend.position='null')
xyz