xccds

library(treemap)
data <- read.csv('d:/sheet1.csv',T)
tmPlot(data,
       index=c("item", "subitem"),
       vSize="time1206",
       vColor="time1106",
       type="comp",
       title='苹果公司财务报表可视化',
       palette='RdBu')

xccds

library(treemap)
data <- read.csv('d:/olympic.csv',T)
tmPlot(data,
       index=c("sports", "events"),
       vSize="gold",
       vColor="china",
       type="value",
       title='中国奥运金牌分布',
       fontsize.labels=13,
       lowerbound.cex.labels=0.7, 

xccds

# 数据读入
data <- read.csv('qq.csv',T,stringsAsFactors=F)
data <- data[-nrow(data),] # 最后一行有问题，删除

library(stringr)
library(plyr)
library(lubridate)
library(ggplot2)
library(reshape2)
library(igraph)

xccds

# Example from Survival Analysis- A Self-Learning Text, Third Edition 

library(survival)
addicts <- read.table('ADDICTS.txt',T)
names(addicts) <- c('id','clinic','status', 'survt','prison','dose')

# 1. 估计生存函数，观察不同组间的区别

# 建立生存对象
Surv(addicts$survt,addicts$status==1)

xccds

# 原始文件读入
txt <- readLines('txtdm.txt')
ignore = ",|:|!|'"
stopwords = c('and','edition','for','in','little','of','the','to')
txt <- tolower(txt)

# 文档分词
doc <- strsplit(txt,' ')
# 去除常用词和标点
doc <- lapply(doc,function(x)gsub(ignore,'',x))

xccds

# 加载库
import numpy as np
import pandas as pd
from ggplot import *

# 生成二维随机游走数据
def walk(n):
    NS = randint(0,2,size=n)
    WE = 1 - NS
    xstep = np.random.choice([1,-1],size=n,replace=True) * WE

xccds

rem2 <- function (){
  library(nlme)
  a0 <- 9.9
  a1 <- 2
  # 对6个人重复测量多次
  ni <- c(12, 13, 14, 15, 16, 13)
  nyear <- length(ni)
  set.seed(205)
  # 构造x值
  xx <- matrix(rep(0, length=max(ni) * nyear),

xccds

# Data generation of Random Intercept and slope model
a0 <- 9.9
a1 <- 2
n <- c(12, 13, 14, 15, 16, 13)
npeople <- length(n)
set.seed(1)
si <- rnorm(npeople, mean = 0, sd = 0.5) # random slope
x <- matrix(rep(0, length = max(n) * npeople),
             ncol = npeople)
for (i in 1:npeople){

xccds

# 广义混合效应模型
glme <- function (){
  library(lme4)
  set.seed(820)
  ni <- c(12, 13, 14, 15, 16, 13, 11, 17, 13, 16)
  ndset <- length(ni)
  xx <- matrix(rep(0, length = max(ni) * ndset),
               ncol = ndset)
  bbi <- rnorm(ndset, mean = 0, sd = 1)
  for (ii in 1:ndset){

xccds

# 基于《统计模拟和R实现》一书例子
import numpy as np
from numpy import random as rm
import pandas as pd

def simulation(T=4200):
    t = 0;nA =0;nD=0;n=0;A=[];D=[];N=[];S=[]
    tA = rm.exponential(10,1) # 客来时间
    tD = inf  # 客走时间
    while True: