tmasjc

library(httr)
library(dplyr)

# Find out which cities are being covered in China
china <- "https://api.openaq.org/v1/cities?country=CN"
china_df <- GET(china) %>% content("parsed") %>% `[[`('results') %>% bind_rows()

# Main interest
cities <- c("Beijing", "Shanghai", "Guangzhou")
china_df %>% filter(city %in% cities)

tmasjc

# Mon Feb 12 16:48:40 2018 ------------------------------

library(tidyverse)
library(wbstats)
set.seed(1234)

# GDP per capita
gdp <- wb(indicator = "NY.GDP.PCAP.CD") %>% as.tibble()
skimr::skim(gdp)

tmasjc

library(tidyverse)
library(rvest)

# basic parameter
baseURL <- "https://openaq-data.s3.amazonaws.com/"
startDate <- as.Date("2015-07-01")
endDate <- as.Date("2018-04-01")

# from url endpoints
filenames <- paste0(seq.Date(from = startDate, to = endDate, by = "day"), ".csv")

tmasjc

library(tidyverse)

# read raw data
raw <- read_csv("~/Documents/Gitlab/wuhanzflog.csv")
skimr::skim(raw)


# Clean Up Data -----------------------------------------------------------

dat <- raw %>%

tmasjc

Checklist

-	Does the project contain R script?
-	Does the project contain data?
-	Does the project contain a test script?
-	Do the scripts contain proper comments?
-	Is the project organised in proper structure? 
-	Do the scripts follow R style guide?
		http://style.tidyverse.org/
-	Does the README display the project structure?

tmasjc

# using Alt + A as prefix
unbind C-b
set -g prefix M-a
bind-key M-a send prefix

# reopen last window
unbind /
bind / last-window

# split panes using | and -

tmasjc

# Mon Apr 23 10:44:54 2018 ------------------------------

# make dummy data frame with 1s and NAs
vec <- purrr::map(1:3, ~c(1, NA) %>% rep(times = 5) %>% sample()) 
names(vec) <- paste0("Col_", 1:3)
df <- vec %>% as.data.frame()
df

# Extra column
df <- df %>% bind_cols(lettrs = letters[1:nrow(df)])

tmasjc

# Tue Apr 24 01:21:14 2018 ------------------------------
library(tidyverse)

# Simulate some samples ---------------------------------------------------

dat <- data_frame(
  col_a = rep(c(letters[1:3], NA), 5) %>% sample(),
  col_aa = col_a %>% sample(),
  col_n = rep(c(1:3, NA), 5) %>% sample()
)

tmasjc

library(mongolite)
library(dplyr)

# connect to database
con <- mongo(collection = "relet_price", db = "bizops", url ="mongodb://localhost", verbose = TRUE)

# some random id based on datetime
gen_id <- function(){
    c <- gsub("(\\:|\\-|\\s)", "", as.character(Sys.time()))
    strsplit(c, "") %>% 

tmasjc

library(tidyverse)

set.seed(1122)

vecs <- lapply(X = 1:2, function(x) rep(c(1, 2, 3), times = 10) %>% sample() %>% head(10))
names(vecs) <- paste0("col_", 1:2)
dat <- vecs %>% as.data.frame()
dat

# Which col has repeated value more than 3 appearances?