lab

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

library(ggplot2)
library(readr)
overall_usage <- read_csv("overall_usage.csv")

## Parsed with column specification:
## cols(
##   cohort = col_character(),
##   event_name = col_integer(),
##   user_id = col_integer(),
##   post_id = col_integer(),
##   extra_info = col_integer(),
##   time = col_integer(),
##   device_type = col_integer(),
##   time_started = col_integer()
## )

######## FIGURE 1
ggplot(overall_usage, aes(x= cohort, y =event_name)) + geom_bar(stat = 'identity', aes(fill = cohort)) + coord_cartesian(ylim =c(270000,300000)) + ggtitle('FIGURE 1')

Including Plots

You can also embed plots, for example:

user_activity <- read_csv("user_activity.csv")

## Warning: Missing column names filled in: 'X1' [1]

## Parsed with column specification:
## cols(
##   X1 = col_integer(),
##   cohort = col_character(),
##   event_name = col_character(),
##   user_id = col_character(),
##   post_id = col_integer(),
##   extra_info = col_integer(),
##   time = col_integer(),
##   device_type = col_integer(),
##   time_started = col_integer()
## )

user_activity$cohort = as.factor(user_activity$cohort)
#user_activity$event_name = log(user_activity$event_name)
#######
ggplot(user_activity, aes(event_name)) +geom_density(aes(color = cohort, alpha = .25)) + coord_cartesian(xlim = c(0, 300)) + ggtitle('FIGURE 2')

#+ facet_wrap(~cohort)

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

ggplot(user_activity, aes(event_name)) +geom_density(aes(color = cohort)) + coord_cartesian(xlim = c(0, 300)) + facet_wrap(~cohort)  + ggtitle('FIGURE 3')

#+ facet_wrap(~cohort)

data= read_csv('group_activity.csv')

## Warning: Missing column names filled in: 'X1' [1]

## Parsed with column specification:
## cols(
##   X1 = col_integer(),
##   cohort = col_character(),
##   event_name = col_character(),
##   user_id = col_character(),
##   post_id = col_integer(),
##   extra_info = col_integer(),
##   time = col_integer(),
##   device_type = col_integer(),
##   time_started = col_integer()
## )

ggplot(data, aes(x=event_name, y = post_id)) + geom_boxplot(aes(fill = event_name)) + facet_wrap(~cohort) + coord_cartesian(ylim=c(0,50)) + ggtitle('FIGURE 4')

library(foreign)
#install.packages('nnet')
library(nnet)
data_full = read_csv('data.csv')

## Warning: Missing column names filled in: 'X1' [1]

## Parsed with column specification:
## cols(
##   X1 = col_integer(),
##   cohort = col_character(),
##   event_name = col_character(),
##   user_id = col_character(),
##   post_id = col_character(),
##   extra_info = col_character(),
##   time = col_datetime(format = ""),
##   device_type = col_character(),
##   time_started = col_datetime(format = ""),
##   device = col_character()
## )

data_sample=data_full[sample(nrow(data_full), nrow(data_full)*.5), ]
test <- multinom(event_name ~ factor(cohort) + factor(extra_info) + factor(device), data = data_sample)

## # weights:  30 (18 variable)
## initial  value 934189.579111 
## iter  10 value 500468.241879
## iter  20 value 411701.037625
## iter  30 value 386515.856333
## final  value 386503.563413 
## converged

coef = summary(test)$coefficients
#table(data_sample$extra_info)
graph = data.frame(t(coef))
graph$names = row.names(graph)
graph  =graph[c(2:7, 9),1:3]

ggplot(graph, aes(x=names, y=Heart)) + geom_bar(stat = 'identity', aes(fill = names)) + coord_cartesian(ylim = c(-.2,.2)) + ggtitle('FIGURE 5')

ggplot(graph, aes(x=names, y=Whisper.Created)) + geom_bar(stat = 'identity', aes(fill = names))+ coord_cartesian(ylim = c(-.2,.2)) + ggtitle('FIGURE 6')

coef

##                 (Intercept) factor(cohort)B factor(cohort)C
## Heart            -0.9402028      0.03599948   -0.0005164111
## Whisper Created   8.7480892      0.95713441    0.7471708825
##                 factor(cohort)D factor(cohort)E factor(cohort)F
## Heart                 -0.126933     -0.01869487      0.00792366
## Whisper Created        1.026889      0.48621474      1.56561709
##                 factor(extra_info)top-level factor(extra_info)undefined
## Heart                              2.991407                   0.8671575
## Whisper Created                    2.307160                 -21.0845206
##                 factor(device)ios
## Heart                  -0.1341333
## Whisper Created         1.3001537

z <- summary(test)$coefficients/summary(test)$standard.errors
#z
p <- (1 - pnorm(abs(z), 0, 1)) * 2
p

##                 (Intercept) factor(cohort)B factor(cohort)C
## Heart             0.1186478    0.0001091292       0.9558588
## Whisper Created   0.0000000    0.1524312638       0.2511411
##                 factor(cohort)D factor(cohort)E factor(cohort)F
## Heart                  0.000000      0.04444419      0.38920563
## Whisper Created        0.133297      0.44188497      0.02700969
##                 factor(extra_info)top-level factor(extra_info)undefined
## Heart                            0.08126519                   0.1500756
## Whisper Created                  0.13436863                   0.0000000
##                 factor(device)ios
## Heart                 0.000000000
## Whisper Created       0.006890041

#p
#test <- multinom(prog2 ~ ses + write, data = ml)