In [1]:

    

library(data.table)


    

In [2]:

    

library(ggplot2)


    

In [3]:

    

library(dplyr)


    

    




Attaching package: ‘dplyr’

The following objects are masked from ‘package:data.table’:

    between, first, last

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

In [4]:

    

options(scipen=999)


    

In [5]:

    

sample_human_revision_session_data <- data.table(read.table("~/Desktop/human_events.tsv", header=TRUE, sep="\t"))


    

In [6]:

    

sample_human_revision_session_data$updated_timestamp <- as.POSIXct(as.character(sample_human_revision_session_data$timestamp), format='%Y%m%d%H%M%S', origin='1970-01-01')


    

In [7]:

    

sample_human_revision_session_data$updated_previous_timestamp <- as.POSIXct(as.character(sample_human_revision_session_data$prev_timestamp), format='%Y%m%d%H%M%S', origin='1970-01-01')


    

In [8]:

    

sample_human_revision_session_data$time_difference <- as.numeric(sample_human_revision_session_data$updated_timestamp - sample_human_revision_session_data$updated_previous_timestamp)


    

In [9]:

    

sample_human_revision_session_data$log_time_difference <- log10(sample_human_revision_session_data$time_difference + 1)


    

    




Warning message in eval(expr, envir, enclos):
“NaNs produced”

In [10]:

    

attach(sample_human_revision_session_data)


    

In [20]:

    

sample_human_revision_session_data_mean = summarize(group_by(sample_human_revision_session_data[prev_timestamp != 'NULL' & session_events >= 10 & time_difference >= 0,], user, session_start), edit_in_session = n(), mean_time_difference = mean(time_difference))


    

In [21]:

    

head(sample_human_revision_session_data_mean)


    

    






user
session_start
edit_in_session
mean_time_difference

	
1             
20140727151034
12            
117.2500      
	
1             
20141122224009
 9            
391.4444      
	
1             
20150304141053
23            
963.2174      
	
1             
20150304231604
16            
832.3125      
	
1             
20150305231129
19            
485.1579      
	
1             
20150308203934
25            
422.0000      

In [22]:

    

sample_human_revision_session_data_mean[mean_time_difference < 10, group := "group1"]


    

    




Error in `:=`(group, "group1"): Check that is.data.table(DT) == TRUE. Otherwise, := and `:=`(...) are defined for use in j, once only and in particular ways. See help(":=").
Traceback:

1. sample_human_revision_session_data_mean[mean_time_difference < 
 .     10, `:=`(group, "group1")]
2. `[.grouped_df`(sample_human_revision_session_data_mean, mean_time_difference < 
 .     10, `:=`(group, "group1"))
3. NextMethod()
4. `[.tbl_df`(sample_human_revision_session_data_mean, mean_time_difference < 
 .     10, `:=`(group, "group1"))
5. check_names_df(j, x)
6. `:=`(group, "group1")
7. stop("Check that is.data.table(DT) == TRUE. Otherwise, := and `:=`(...) are defined for use in j, once only and in particular ways. See help(\":=\").")

In [ ]: