library(REmap)
head(chinaIphone)
chinaIphone
remapC(chinaIphone)

mapNames("河南")
set.seed(123)
henan = data.frame(country = mapNames("河南"), value = sample(17))
remapC(henan, maptype = "河南",color = "skyblue")

park = read.csv('park_result.csv')
geodata = data.frame(park$lon, park$lat, park$park)

pointData = data.frame(park$park, color = 'red')


remapC(henan, maptype = "河南",color = "skyblue",
       markPointData = pointData,
       markPointTheme = markPointControl(symbol = "pin",
                                         symbolSize = 5,
                                         effect = F),
       geoData = geodata)

library(maptools) 
china_map<-readShapePoly("bou2_4p.shp") 
plot(china_map, axes=F, border="gray") 


class(china_map) 

	[1] "SpatialPolygonsDataFrame" 

china_map@data

plot(china_map,col = gray(924:0/924));

china_map@data

library(rgdal)

china_map1<- readOGR(".", "bou2_4p") 
  # OGR data source with driver: ESRI Shapefile 
  # Source: ".", layer: "bou2_4p" 
  # with 925 features and 7 fields 
  # Feature type: wkbPolygon with 2 dimensions 

 plot(china_map1, axes=F, border="gray") 

 china_map1@data

library(PBSmapping)
china_map2 <- importShapefile("bou2_4p",readDBF=FALSE) 
str(china_map2)#看数据集的属性 
plotPolys(china_map2) 

library(shapefiles)
china_map3 <- read.shapefile("bou2_4p") 

library(REmap)
city_vec = c("北京","Shanghai","广州")
get_city_coord("Shanghai")
	[1] 121.45950  31.21004

get_geo_position (city_vec)
              lon       lat     city
    1  121.459503 31.210037 Shanghai
    12 116.413554 39.911013     北京
    21 113.270793 23.135308     广州

remapC(data,
       maptype = ‘china’,
      color = c(‘#1e90ff’,’#f0ffff’),
      theme = get_theme("Bright"),
      title = "",
      subtitle = "",
      mindata = NA,
      maxdata = NA,
      # mark Line & point
      markLineData = NA,
      markPointData = NA,
      markLineTheme = markLineControl(),
      markPointTheme = markPointControl(),
      geoData = NA)

head(chinaIphone)
remapC(chinaIphone)
remapC(chinaIphone,
      color = 'orange')
## 颜色改为白色到橘红色
remapC(chinaIphone,
      color = c('orange','red'))

data = data.frame(country = mapNames("world"),
                   value = sample(178)+200)
head(data)
remapC(data,maptype = "world",color = 'skyblue')

mapNames(‘西藏’)

data = data.frame(country = mapNames('西藏'),
                   value = sample(7)+200)
head(data)
remapC(data,maptype = '西藏',color = 'skyblue')

remapC(chinaIphone,
        title = "remapC实例地图",
        theme = get_theme("none",backgroundColor = "#fff",
                          titleColor = "#1b1b1b",
                          pointShow = T),
        max = 2000)

remapB(center = c(104.114129,37.550339),
       zoom = 5,
       color = "Bright",
       title = "",
       subtitle = "",
       # mark Line & point
       markLineData = NA,
       markPointData = NA,
       markLineTheme = markLineControl(),
       markPointTheme = markPointControl(),
       geoData = NA)

library(devtools)
install_github('lchiffon/REmap')
library(REmap)

remapB()
remapB(color = "Blue")
remapB(color = "pink")

remapB(get_city_coord("北京"),zoom = 12)

remapB(title = "Bmap迁徙图示例",
        color = "Blue",
    	markLineData = demoC)

markLineControl(symbolSize = c(2,4),
      smoothness = 0.2,
      effect = T,
      lineWidth = 1,
      lineType = ‘solid’,
      color = "Random") 

remapB(title = "Remap:  百度迁徙模拟",
       color = "Blue",
       markLineData = demoC,
       markLineTheme = markLineControl(symbolSize = c(0,0),
                                       lineWidth = 10,
                                       lineType = ‘dashed’))

get_geo_position(c("Beijing","Shanghai","Guangzhou"))

       lon      lat      city
1 116.4232 39.91528   Beijing
2 121.5221 31.30477  Shanghai
3 113.2684 23.12980 Guangzhou

remapB(title = "Remap:  百度迁徙模拟",
       color = "Blue",
       markPointData = demoC[,2])

markPointControl(symbol = ‘emptyCircle’,
                  symbolSize = "Random",
                  effect = T,
                  effectType = ‘scale’,
                  color = "Random")

remap(mapdata, title = "", subtitle = "",
      theme =get_theme("Dark"))

library(REmap)
set.seed(125)
origin = rep("北京",10)
destination = c("上海","广州","大连","南宁","南昌","拉萨","长春","包头","重庆","常州")
dat = data.frame(origin,destination)
out = remap(dat,title = "REmap实例数据",subtitle = "theme:Dark")
plot(out)

get_theme(theme = "Dark", lineColor = "Random",
  backgroundColor = "#1b1b1b", titleColor = "#fff",
  borderColor = "rgba(100,149,237,1)", regionColor = "#1b1b1b")

## 默认模板: Bright
## default theme:"Bright"
set.seed(125)
out = remap(dat,title = "REmap实例数据",subtitle = "theme:Bright",
            theme = get_theme("Bright"))
plot(out)

out = remap(dat,title = "REmap实例数据",subtitle = "theme:Bright",
            theme = get_theme("None",
                              lineColor = "orange",
                              backgroundColor = "#FFC1C1",
                              titleColor = "#1b1b1b",
                              regionColor = "#ADD8E6"))
plot(out)

<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <title>Document</title>
</head>

<body>
</body>
<!--插入JavaScript代码-->
<script type="text/javascript">
console.log('Hello Wold')
</script>

</html>

<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <title>Document</title>
    <!--引入外部JavaScript文件-->
    <style type="text/css">out.js</style>
</head>

<body>
</body>
</html>

colors()
x <- seq(0, 2*pi, len = 51)
plot(x, sin(x), type = "o", pch = 21, col = colors()[552])

plot(x, sin(x), type = "o", pch = 21, col = 'red')

plot(x, sin(x), type = "o", pch = 21, col = '#FF0000')

palette()
	# [1] "black"   "red"     "green3"  "blue"    "cyan"    "magenta" "yellow" 
	# [8] "gray"

palette(c("red","green","blue","yellow","cyan"))

palette("default")

rgb(red, green, blue, alpha, names = NULL, maxColorValue = 1)

pie(rep(1, times = 1000), labels = "", col = rainbow(1000), border = rainbow(1000))

pie(rep(1, times = 1000), labels = "", col = heat.colors(1000), border = heat.colors(1000))

pie(rep(1, times = 1000), labels = "", col = terrain.colors(1000), border = terrain.colors(1000))

pie(rep(1, times = 1000), labels = "", col = topo.colors(1000), border = topo.colors(1000))

pie(rep(1, times = 1000), labels = "", col = cm.colors(1000), border = cm.colors(1000))

display.brewer.all(type = "seq")

barplot(rep(1,6),col=brewer.pal(9, "YlOrRd")[3:8])

display.brewer.all(type = "div")

barplot(rep(1,6),col=brewer.pal(11, "BrBG")[3:8])

display.brewer.all(type = "qual")

# 加载需要的R包
library(RMySQL)
library(data.table)

# 读取数据
movie = fread('data/douban_movie_clean.txt', sep = '^', encoding = 'UTF-8')


movie = data.frame(movie)
head(movie)

## 连接数据库
conn <- dbConnect(RMySQL::MySQL(), username="root", password= '123456', host="localhost", port=3306, dbname = 'study')

# 查看MySQL连接实例信息
summary(conn, verbose = TRUE)
# 查看数据库的表
dbListTables(conn)

# 建表并插入数据
dbWriteTable(conn,"movie", movie, overwrite = T)

# 设置数据库的连接信息
dbSendQuery(conn,'SET NAMES gbk')

# 读取数据库信息到R中
mysql=dbGetQuery(conn,"select * from movie")

## 关闭连接
dbDisconnect(conn)

# 加载需要的R包
library(rvest)
library(rjson)
library(stringr)
library(dplyr)

# 读取数据
url = 'https://movie.douban.com/j/search_tags?type=movie'
web <- read_html(url,encoding="UTF-8")

# 找出电影的不同类型
tags <- web %>% html_nodes('p') %>% html_text() %>% fromJSON()
tag = tags$tags

basicurl<-"https://movie.douban.com/j/search_subjects?type=movie&tag="

# 爬取不同类型电影函数
WebSpider = function(m){
  i = 0
  # 存放每个类型电影的结果
  result = data.frame()
  while(1){
    #Sys.sleep(runif(1,1,2)) # 限制两次爬虫运行的时间
    url = str_c(basicurl,m,'&sort=recommend&page_limit=20&page_start=', i)
    
    web<-read_html(url,encoding="UTF-8")
    
    # 提取不同页的电影数据，并把数据格式由json转化list
    movies.inf = web %>% html_nodes("p") %>% html_text() %>% fromJSON()
    
    # 转化为数据格式为数据框
    temp = do.call("rbind",movies.inf$subjects)
    
    # 合并每个类型所有页的电影数据
    result = rbind(result, temp)
    if(is.null(temp)){
      print(i);break} else{
        i = i + 1} 
  }
  
  # 在数据中添加电影分类
  result$tags = m
  # 合并不同类型的电影数据
  return(result)
}

# 存放所有类型的电影
movies <- data.frame()

# 爬取所有类型的电影
for(j in 1:length(tag)){
  movies <- rbind(movies, WebSpider(tag[j]))}

# 转化列表中的每一项为字符型
movies.df = lapply(movies, as.character)

# 去除重复的电影
movies.unique = movies.df %>% tbl_df() %>% distinct(id, .keep_all = T)

# 写出数据
write.csv(movies.unique, file = 'data/douban_movies_unique_R.csv', row.names = F)

library(rvest)
web = read_html('http://xukuang.github.io/blog/images', encoding = 'UTF-8')
web %>% html_nodes('div.tag-list label') %>% html_text() # 该命令执行后，显示一下结果说明运行成功
	#  [1] "\n            热门\n            "    
	#  [2] "\n            最新\n            "    
	#  [3] "\n            经典\n            "    
	#  [4] "\n            可播放\n            "  
	#  [5] "\n            豆瓣高分\n            "
	#  [6] "\n            冷门佳片\n            "
	#  [7] "\n            华语\n            "    
	#  [8] "\n            欧美\n            "    
	#  [9] "\n            韩国\n            "    
	# [10] "\n            日本\n            "    
	# [11] "\n            动作\n            "    
	# [12] "\n            喜剧\n            "    
	# [13] "\n            爱情\n            "    
	# [14] "\n            科幻\n            "    
	# [15] "\n            悬疑\n            "    
	# [16] "\n            恐怖\n            "    
	# [17] "\n            动画\n            "    

{name:value}

[collection, collection]

{
    "table1": {
        "time": "130911",
        "data": {
            "code": [
                "TF1312",
                "TF1403",
                "TF1406"
            ],
            "rt_time": [
                130911,
                130911,
                130911
            ]
        }
    },
    "table2": {
        "time": "130911",
        "data": {
            "contract": [
                "TF1312",
                "TF1312",
                "TF1403"
            ],
            "jtid": [
                99,
                65,
                21
            ]
        }
    }
}

[
{
     "text":"This is the text","color":"dark_red","bold":"true","strikethough":"true","clickEvent":
          {"action":"open_url","value":"zh.wikipedia.org"},
     "hoverEvent":
          {"action":"show_text","value":
               {"extra":"something"}
          }
},
{
     "translate":"item.dirt.name","color":"blue","italic":"true"
}
]

library(rjson)
json_data1 <- fromJSON(file ="example1.json")
json_data1
	# $firstName
	# [1] "John"
	# 
	# $lastName
	# [1] "Smith"
	# 
	# $sex
	# [1] "male"
	# 
	# $age
	# [1] 25
	# 
	# $address
	# $address$streetAddress
	# [1] "21 2nd Street"
	# 
	# $address$city
	# [1] "New York"
	# 
	# $address$state
	# [1] "NY"
	# 
	# $address$postalCode
	# [1] "10021"
	# 
	# $phoneNumber
	# $phoneNumber[[1]]
	# $phoneNumber[[1]]$type
	# [1] "home"
	# 
	# $phoneNumber[[1]]$number
	# [1] "212 555-1234"
	# 
	# $phoneNumber[[2]]
	# $phoneNumber[[2]]$type
	# [1] "fax"

	# $phoneNumber[[2]]$number
	# [1] "646 555-4567"

json_data2 <- fromJSON(file ="example2.json")
json_data2

	# [[1]]
	# [[1]]$text
	# [1] "This is the text"
	# 
	# [[1]]$color
	# [1] "dark_red"
	# 
	# [[1]]$bold
	# [1] "true"
	# 
	# [[1]]$strikethough
	# [1] "true"
	# 
	# [[1]]$clickEvent
	# [[1]]$clickEvent$action
	# [1] "open_url"
	# 
	# [[1]]$clickEvent$value
	# [1] "zh.wikipedia.org"
	#  
	# [[1]]$hoverEvent
	# [[1]]$hoverEvent$action
	# [1] "show_text"
	# 
	# [[1]]$hoverEvent$value
	# [[1]]$hoverEvent$value$extra
	# [1] "something"
	#
	# [[2]]
	# [[2]]$translate
	# [1] "item.dirt.name"
	# 
	# [[2]]$color
	# [1] "blue"
	# 
	# [[2]]$italic
	# [1] "true"

json_data1 <- fromJSON(paste(readLines("example1.json"), collapse=""))
json_data2 <- fromJSON(paste(readLines("example2.json"), collapse=""))

json_str<-toJSON(json_data2)
json_str
	# [1] "[{\"text\":\"This is the text\",\"color\":\"dark_red\",\"bold\":\"true\",\"strikethough\":\"true\",\"clickEvent\":{\"action\":\"open_url\",\"value\":\"zh.wikipedia.org\"},\"hoverEvent\":{\"action\":\"show_text\",\"value\":{\"extra\":\"something\"}}},{\"translate\":\"item.dirt.name\",\"color\":\"blue\",\"italic\":\"true\"}]"
cat(json_str)
	# [{"text":"This is the text","color":"dark_red","bold":"true","strikethough":"true","clickEvent":{"action":"open_url","value":"zh.wikipedia.org"},"hoverEvent":{"action":"show_text","value":{"extra":"something"}}},{"translate":"item.dirt.name","color":"blue","italic":"true"}]

writeLines(json_str1, "result1.json")
writeLines(json_str2, "result2.json")

library(rjson)

fdlist <- fromJSON(file = 'data.JSON')
fdlist

fdm <- matrix(unlist(fdlist),ncol=4,byrow=T)
fddf <- data.frame(fdm)
head(fddf)

# 加载需要的R包
library(stringr)
library(dplyr)

# 读取数据
# 这里文件内容是中文，采用的UTF-8格式，所以对encoding进行限制
fw = readLines('data/xyj.txt', encoding = 'UTF-8') # 文件xyz.txt的4020行分别存入到了一个长度为4020的向量中

# 数据预处理和计算
# 去除向量中每个元素的开始和结尾的空格
fw.real = str_trim(fw)
# 去除向量中为空的元素
fw.real = fw.real[!fw.real == '']
# 对向量中每个字符进行拆分
fw.list = str_split(fw.real, '') # 结果是数据类型为列表
# 将数据的类型由列表转化为数据框
single = data.frame(ch = do.call('c',fw.list))
# 统计每个字出现的次数，并按次数由高到底排列
result = single %>% group_by(ch) %>% summarise(num = n()) %>% arrange(desc(num))

# 写出数据
# 在windows系统下，R写出的数据文件默认为gbk的编码方式
write.csv(result, 'data/result_r.csv', row.names = F)
# 通过参数fileEncoding，将R写出的数据文件设置为UTF-8的编码方式
write.csv(result, 'data/result_r_utf8.csv', row.names = F,fileEncoding = 'UTF-8')

# 加载需要的R包
library(tidytext)
library(dplyr)
library(stringr)

# 读取数据
# 这里文件内容是中文，采用的UTF-8格式，所以对encoding进行限制
fw = readLines('data/xyj.txt', encoding = 'UTF-8') # 文件xyz.txt的4020行分别存入到了一个长度为4020的向量中

# 数据预处理和计算
# 去除向量中每个元素的开始和结尾的空格
fw.real = str_trim(fw)

# 方案二，不需要去除向量中为空的元素
# fw.real = fw.real[!fw.real == '']

# 统计每个字出现的次数，并按次数由高到底排列
result = fw_df %>%
  unnest_tokens(ch, text, token = 'characters') %>% group_by(ch) %>% summarise(num = n()) %>% arrange(desc(num))

# 写出数据
# 在windows系统下，R写出的数据文件默认为gbk的编码方式
write.csv(result, 'data/result_r.csv', row.names = F)
# 通过参数fileEncoding，将R写出的数据文件设置为UTF-8的编码方式
write.csv(result, 'data/result_r_utf8.csv', row.names = F,fileEncoding = 'UTF-8')

# 找出出现次数大于5000的非标点符号字符
# 结果中result的ch列的因子水平按出现次数排序
result = result  %>%
  filter(!ch %in% c('，', '。', '：', '“', '”', '！') & num > 5000) %>% mutate(ch = reorder(ch, num))

# 出图
 ggplot(result, aes(x = ch, y = num)) +
  geom_bar(stat = "identity", fill = 'red') +
  xlab(NULL) + ylab('次数') + coord_flip()