Scott Hoover githoov

Director of Analytics at Snowflake

githoov / trial_time_to_close.R

Created April 14, 2016 15:12

	# load data
	durations <- read.csv(file = "~/Downloads/trial_durations.csv", header = TRUE)
	names(durations) <- c("id", "month", "duration", "won")

	# summary of time to close by closed won
	summary.df <- ddply(durations, .(month, won), summarize, median_duration = median(duration))

	# time to close
	ggplot(durations, aes(x = month, y = duration, colour = won)) + geom_boxplot() + ggtitle("Trials: Time to Close") + xlab("Time") + ylab("Time to Close (Days)")

githoov / cadence_over_time.R

Last active April 13, 2016 18:30

	# load data
	df <- read.csv(file = "~/Downloads/cadence.csv", header = TRUE)
	names(df) <- c("id", "month", "in_trial", "topic", "number_of_chats", "median_time_to_reply", "iqr")

	# create a summary table for inspection
	summary.df <- ddply(na.omit(subset(df, number_of_chats > 5)), .(month), summarize, cadence = median(median_time_to_reply), spread = median(iqr))

	# plot median of medians over time
	ggplot(na.omit(subset(df, number_of_chats > 5)), aes(x = month, y = median_time_to_reply)) + stat_summary(fun.data = mean_cl_normal)

githoov / discourse_and_chats.R

Last active April 12, 2016 20:23

	# input queries
	# tickets: https://metanew.looker.com/x/CQ9zcpw
	# discourse views: https://metanew.looker.com/x/yYf3CPH

	# load data
	tickets <- read.csv(file = "~/Downloads/ticket_topics.csv", header = TRUE)
	articles <- read.csv(file = "~/Downloads/discourse_topics.csv", header = TRUE)

	# rename columns
	names(tickets) <- c("week", "topic", "chats")

githoov / user_growth.R

Created April 12, 2016 03:33

	# preliminaries
	# using pinger
	# 2014 (control): https://metanew.looker.com/sql/cb77dv2thvbrxd
	# 2015 (treat): https://metanew.looker.com/sql/xqttksqxp3qgrn
	# using license
	# 2014 (control): https://metanew.looker.com/sql/fm8hgny7f9yrkh
	# 2015 (treat): https://metanew.looker.com/sql/rq2sxqkwqmc7z2

	# read in 2014 and 2015 data sets
	Y2014 <- read.csv(file = "~/Downloads/sql_runner_fm8hgny7f9yrkh_2016-04-09_05-37-37.csv", header = TRUE)

githoov / zendesk_chat_events.yaml

Last active February 22, 2016 06:49

Zendesk Chat Events

githoov / view_definitions.yml

Created January 7, 2016 21:23

Redshift View Definitions

githoov / recent_data_load.yml

Created January 7, 2016 21:21

Redshift Recent Data Loads

	- explore: data_loads
	hidden: true
	- view: data_loads
	derived_table:
	sql: \|
	select replace(regexp_substr(filename, '//[a-zA-Z0-9\-]+/'), '/', '') as root_bucket
	, case
	when replace(regexp_substr(filename, '//[a-zA-Z0-9\-]+/'), '/', '') = 'snowplow-looker-emr-out'
	then 'snowplow'
	else regexp_replace(regexp_substr(filename, '/[a-zA-Z0-9\\-\\_]+\\.[a-zA-Z]{3,4}'), '(/\|[0-9]{2,})', '')

githoov / load_errors.yml

Created January 7, 2016 21:19

Redshift Load Errors

	- explore: etl_errors
	label: 'ETL Errors'
	hidden: true
	- view: etl_errors
	derived_table:
	sql: \|
	select distinct errors.starttime as error_time
	, detail.filename as file_name
	, errors.err_reason
	from stl_loaderror_detail as detail, stl_load_errors as errors

githoov / table_skew.yml

Created January 7, 2016 21:18

Redshift Table Skew

githoov / db_space.yml

Created January 7, 2016 21:17

Redshift Cluster Disk Utilization