R 筆記

2019-11-10 20:08:49

字體：大中小

來源：轉載

供稿：網友

begin note

調用命令：r CMD BATCH D:/RWORKSPACE/CMD_TEST.R （注意 CMD BATCH 都要大寫）

ls(): 列出所有的變量名稱

ls(pattern ='v'): 根據pattern匹配

rm('xxx') 刪除變量

rm(list=ls()) 刪除所有的變量> ls()character(0)

集合轉數組：

> vector1 <- c(5,9,3)> vector2 <- c(10,11,12,13,14,15)> column.names <- c("COL1","COL2","COL3")> row.names <- c("ROW1","ROW2","ROW3")> matrix.names <- c("Matrix1","Matrix2")> result <- array(c(vector1,vector2),dim=c(3,3,2),dimnames = list(column.names,row.names,matrix.names))> PRint(result), , Matrix1 ROW1 ROW2 ROW3COL1 5 10 13COL2 9 11 14COL3 3 12 15, , Matrix2 ROW1 ROW2 ROW3COL1 5 10 13COL2 9 11 14COL3 3 12 15

> # Print the third row of the second matrix of the array.> print(result[3,,2])ROW1 ROW2 ROW3 3 12 15 > > # Print the element in the 1st row and 3rd column of the 1st matrix.> print(result[1,3,1])[1] 13> > # Print the 2nd Matrix.> print(result[,,2]) ROW1 ROW2 ROW3COL1 5 10 13COL2 9 11 14COL3 3 12 15數組的操作：

# Create two vectors of different lengths.vector1 <- c(5,9,3)vector2 <- c(10,11,12,13,14,15)# Take these vectors as input to the array.array1 <- array(c(vector1,vector2),dim=c(3,3,2))# Create two vectors of different lengths.vector3 <- c(9,1,0)vector4 <- c(6,0,11,3,14,1,2,6,9)array2 <- array(c(vector1,vector2),dim=c(3,3,2))# create matrices from these arrays.matrix1 <- array1[,,2]matrix2 <- array2[,,2]# Add the matrices.result <- matrix1+matrix2print(result)# Create two vectors of different lengths.vector1 <- c(5,9,3)vector2 <- c(10,11,12,13,14,15)# Take these vectors as input to the array.new.array <- array(c(vector1,vector2),dim=c(3,3,2))print(new.array)# Use apply to calculate the sum of the rows across all the matrices.計算所有矩陣每行的和result <- apply(new.array, c(1), sum)print(result)# Create a vector as input.data <- c("East","West","East","North","North","East","West","West","West","East","North")print(data)print(is.factor(data))# Apply the factor function.factor_data <- factor(data)print(factor_data)print(is.factor(factor_data))#判斷是否是factor  , true# Create the vectors for data frame.height <- c(132,151,162,139,166,147,122)weight <- c(48,49,66,53,67,52,40)gender <- c("male","male","female","female","male","female","male")# Create the data frame.input_data <- data.frame(height,weight,gender)print(input_data)# Test if the gender column is a factor.  a row of data frame is a factor, like thisprint(is.factor(input_data$gender))# Print the gender column so see the levels.print(input_data$gender)data <- c("East","West","East","North","North","East","West","West","West","East","North")# Create the factorsfactor_data <- factor(data)print(factor_data)# Apply the factor function with required order of the level. 改變了level的順序new_order_data <- factor(factor_data,levels = c("East","West","North"))print(new_order_data)gl(n, k, labels)以下是所使用的參數的說明：
n 是一個整數來給出級別數k 是一個整數給出重復的數量labels 為所得到的因子級別標簽的向量。示例
v <- gl(3, 4, labels = c("Tampa", "Seattle","Boston"))print(v)
創建數據幀
# Create the data frame.emp.data <- data.frame(	emp_id = c (1:5), 	emp_name = c("Rick","Dan","Michelle","Ryan","Gary"),	salary = c(623.3,515.2,611.0,729.0,843.25), 	start_date = as.Date(c("2012-01-01","2013-09-23","2014-11-15","2014-05-11","2015-03-27")),	stringsAsFactors=FALSE			)# Print the data frame.			print(emp.data) 
str(emp.data)print(summary(emp.data))  # Extract Specific columns.提取數據幀的列result <- data.frame(emp.data$emp_name,emp.data$salary)print(result)result <- emp.data[1:2,]#提取數據的前兩行和所有的列print(result)result <- emp.data[c(3,5),c(2,4)]# 提取3， 5 行的第2,4 列的數據print(result)# Add the "dept" coulmn.添加列emp.data$dept <- c("IT","Operations","IT","HR","Finance")v <- emp.dataprint(v)
# Create the first data frame.emp.data <- data.frame(	emp_id = c (1:5), 	emp_name = c("Rick","Dan","Michelle","Ryan","Gary"),	salary = c(623.3,515.2,611.0,729.0,843.25), 	start_date = as.Date(c("2012-01-01","2013-09-23","2014-11-15","2014-05-11","2015-03-27")),	dept=c("IT","Operations","IT","HR","Finance"),	stringsAsFactors=FALSE			)# Create the second data frame， 添加行記錄emp.newdata <- 	data.frame(	emp_id = c (6:8), 	emp_name = c("Rasmi","Pranab","Tusar"),	salary = c(578.0,722.5,632.8), 	start_date = as.Date(c("2013-05-21","2013-07-30","2014-06-17")),	dept = c("IT","Operations","Fianance"),	stringsAsFactors=FALSE				)# Bind the two data frames.emp.finaldata <- rbind(emp.data,emp.newdata)print(emp.finaldata)install.packages(file_name_with_path, repos = NULL, type="source")# Install the package named "xml", 安裝packageinstall.packages("E:/XML_3.98-1.3.zip", repos = NULL, type="source")
# Create vector objects.city <- c("Tampa","Seattle","Hartford","Denver")state <- c("FL","WA","CT","CO")zipcode <- c(33602,98104,06161,80294)# Combine above three vectors into one data frame. cbind is column bind 行的結列addresses <- cbind(city,state,zipcode)# Print a header.cat("# # # # The First data frame/n") # Print the data frame.print(addresses)# Create another data frame with similar columnsnew.address <- data.frame(   city = c("Lowry","Charlotte"),   state = c("CO","FL"),   zipcode = c("80230","33949"),   stringsAsFactors=FALSE)# Print a header.cat("# # # The Second data frame/n") # Print the data frame.print(new.address)# Combine rows form both the data frames. rbind is row bind 結合行all.addresses <- rbind(addresses,new.address)# Print a header.cat("# # # The combined data frame/n") # Print the result.print(all.addresses)
melt and cast 
熔化和轉換
R語言編程的最有趣的地方是關于改變多個步驟中的數據的形狀來獲得所希望的形狀。用來做這種函數被稱為 melt() 和 cast()。
我們認為數據集被稱為 ships 出現在庫被稱為 "MASS".
library(MASS)print(ships)當我們上面的代碼執行時，它產生以下結果：
   type year period service incidents1     A   60     60     127         02     A   60     75      63         03     A   65     60    1095         34     A   65     75    1095         45     A   70     60    1512         6..........................8     A   75     75    2244        119     B   60     60   44882        3910    B   60     75   17176        2911    B   65     60   28609        58........................17    C   60     60    1179         118    C   60     75     552         119    C   65     60     781         0........................融化數據
現在，我們融化數據需要組織其轉換類型(type), 并且 year 到多行以外的所有列。
molten.ships <- melt(ships, id = c("type","year"))print(molten.ships)當我們上面的代碼執行時，它產生以下結果：
    type year  variable value1      A   60    period    602      A   60    period    753      A   65    period    604      A   65    period    75........................9      B   60    period    6010     B   60    period    7511     B   65    period    6012     B   65    period    7513     B   70    period    60......................41     A   60   service   12742     A   60   service    6343     A   65   service  1095......................70     D   70   service  120871     D   75   service     072     D   75   service  205173     E   60   service    4574     E   60   service     075     E   65   service   789......................101    C   70 incidents     6102    C   70 incidents     2103    C   75 incidents     0104    C   75 incidents     1105    D   60 incidents     0106    D   60 incidents     0......................轉換數據
我們可以轉化數據轉換成在創建每種類型的 ships 每年的匯總的新形式。它是通過使用 case()函數。
recasted.ship <- cast(molten.ships, type+year~variable,sum)print(recasted.ship)當我們上面的代碼執行時，它產生以下結果：
   type year period service incidents1     A   60    135     190         02     A   65    135    2190         73     A   70    135    4865        244     A   75    135    2244        115     B   60    135   62058        686     B   65    135   48979       1117     B   70    135   20163        568     B   75    135    7117        189     C   60    135    1731         210    C   65    135    1457         111    C   70    135    2731         812    C   75    135     274         113    D   60    135     356         014    D   65    135     480         015    D   70    135    1557        1316    D   75    135    2051         417    E   60    135      45         018    E   65    135    1226        1419    E   70    135    3318        1720    E   75    135     542         1
讀一個CSV文件
以下是 read.csv()函數的一個簡單的例子，它讀取在當前工作目錄的可用的 CSV 文件：
data <- read.csv("input.csv")print(data)data <- read.csv("input.csv")#分析data的行列情況print(is.data.frame(data))print(ncol(data))print(nrow(data))# Get the person detail having max salary. 求最高工資記錄的具體情況retval <- subset(data, salary == max(salary))print(retval)
# Create a data frame.data <- read.csv("input.csv")info <- subset(data, salary > 600 & dept == "IT")#工資大于600 并且是IT部門的員工print(info)# Create a data frame.data <- read.csv("input.csv")retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))#生日大于2014-1-1日print(retval)# Load the packages required to read XML files.library("XML")library("methods")# Convert the input xml file to a data frame.xmldataframe <- xmlToDataFrame("input.xml")#加載xml里面的數據print(xmldataframe)# Load the package required to read JSON files.library("rjson")# Give the input file name to the function.result <- fromJSON(file="input.json")# Print the result.print(result)# Load the package required to read JSON files.library("rjson")# Give the input file name to the function.result <- fromJSON(file="input.json")# Convert JSON file to a data frame.json_data_frame <- as.data.frame(result)#json字符類型 到frame 幀print(json_data_frame)# Create a connection Object to MySQL database.# We will connect to the sampel database named "sakila" that comes with MySql installation. mysqlconnection = dbConnect(MySQL(), user='root', passWord='', dbname='sakila', host='localhost')# List the tables available in this database. dbListTables(mysqlconnection)# Query the "actor" tables to get all the rows.輸入sqlresult = dbSendQuery(mysqlconnection, "select * from actor")# Store the result in a R data frame object. n=5 is used to fetch first 5 rows.現在查詢的條數data.frame = fetch(result, n=5)print(data.fame)# Create the function. 找到向量中出現次數最多的元素getmode <- function(v) {	uniqv <- unique(v)	uniqv[which.max(tabulate(match(v, uniqv)))]}# Create the vector with numbers.v <- c(2,1,2,3,1,2,3,4,1,5,5,3,2,3)# Calculate the mode using the user function. result <- getmode(v)print(result)K線圖：
library(quantmod)sse<-getSymbols('^SSEC', from='2015-1-1',to=Sys.Date(), src='yahoo')SSEC.m <- to.monthly(SSEC)tail(SSEC.m)candleChart(SSEC.m,theme = 'white')