shuozhang1985

#Dataset description
library(plyr); library(dplyr)
library(ggplot2)
setwd("~/Desktop/student")
d1_mat=read.csv("student-mat.csv", sep=';', header=T, stringsAsFactors = F)
d2_por=read.csv("student-por.csv", sep=';', header = T, stringsAsFactors = F)
data=merge(d1_mat,d2_por,by=c("school", "sex", "age", "address", "famsize", 
                              "Pstatus","Medu", "Fedu", "Mjob", "Fjob", "reason",
                              "nursery", "internet"))
summary(data)

shuozhang1985

library(plotly)
library(dplyr)
library(ggmap)
library(map)
library(googleVis)
library(ggplot2)
library(leaflet)
library(lattice)
library(plyr)
library(Rmisc)

shuozhang1985

device_data=read.csv('./data/phonedata.csv', header=T, stringsAsFactors = F)
device_map=dplyr::filter(device_data, !is.na(longitude), !is.na(latitude), !is.na(group))%>%
  dplyr::filter(longitude>=73, longitude<136, latitude>=4, latitude<54)
  N=nrow(device_map)
agegroup=rep(0, N)
for (i in 1:N){
  if (device_map$age[i]<=26){
    agegroup[i]='post-90s'
  }
  else if (device_map$age[i]>26&device_map$age[i]<=36){

shuozhang1985

app_data=read.csv('./data/appmap.csv', header=T, stringsAsFactors = F)
#str(app_data)

app_map=dplyr::filter(app_data, !is.na(longitude), !is.na(latitude), !is.na(group))%>%
  dplyr::filter(longitude>=73, longitude<136, latitude>=4, latitude<54)
#str(app_map)
N1=nrow(app_map)
agegroup1=rep(0, N1)
for (i in 1:N1){
  if (app_map$age[i]<=26){

shuozhang1985

library(dplyr)
library(wordcloud)
library(RColorBrewer)
library(shinythemes)

device_data=read.csv('./data/phonedata.csv', header=T, stringsAsFactors = F)
#str(device_data)
device_map=dplyr::filter(device_data, !is.na(longitude), !is.na(latitude), !is.na(group))%>%
  dplyr::filter(longitude>=73, longitude<136, latitude>=4, latitude<54)
#str(device_map)

shuozhang1985

library(shiny)
library(shinydashboard)
library(dplyr)
library(leaflet)
library(googleVis)
library(plotly)
library(wordcloud)
library(RColorBrewer)
library(shinythemes)

shuozhang1985

library(shiny)
library(dplyr)
library(leaflet)
library(ggplot2)
library(plotly)
library(googleVis)
library(wordcloud)
library(RColorBrewer)
library(shinythemes)

shuozhang1985

setwd("~/Desktop/web scraping")
library(ggplot2)
library(data.table)
library(dygraphs)
library(dplyr)
swimming=read.csv('swimming.txt', header=T, stringsAsFactors = F)
nrow(swimming)
View(swimming)
summary(swimming)
ss=swimming%>%

shuozhang1985

from bs4 import BeautifulSoup
import urllib2
web='http://www.sports-reference.com/olympics/summer/2012/'
req = urllib2.Request(web)
page = urllib2.urlopen(req)
soup = BeautifulSoup(page, "lxml")
table = soup.find("div", { "class" : "table_container" })
cells=[]
for row in table.findAll("tr"):
    result = row.findAll("td")

shuozhang1985

setwd("~/Desktop/web scraping")
library(dplyr)
library(ggplot2)
library(dygraphs)
library(plotly)

event=read.csv('gender2.txt', header=T, stringsAsFactors = F, sep=',')
nrow(event)
View(event)
#length(event$Event)