-
Notifications
You must be signed in to change notification settings - Fork 2
/
quarto.qmd
204 lines (176 loc) · 4.26 KB
/
quarto.qmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
---
title: "Web traffic"
format: html
editor_options:
chunk_output_type: console
execute:
echo: false
warning: false
error: false
---
This report uses the
[Cybersyn Web Traffic Foundation](https://app.snowflake.com/marketplace/listing/GZTSZ290BUX5L/cybersyn-web-traffic-foundation-experimental)
data to compare web traffic metrics between a select domains.
## Connect to Data
We start by connecting to the `CYBERSYN` schema in snowflake,
filtering the domains,
and tidying the data.
```{r}
library(tidyverse)
library(DBI)
library(dbplyr)
library(gt)
library(gtExtras)
library(odbc)
# Connect to the database
conn <-
DBI::dbConnect(
odbc::snowflake(),
warehouse = "DEVREL_WH_LARGE",
database = "WEB_TRAFFIC_FOUNDATION_EXPERIMENTAL",
schema = "CYBERSYN"
)
# connect to tables/views
timeseries <- tbl(conn, "WEBTRAFFIC_SYNDICATE_TIMESERIES")
attributes <- tbl(conn, "WEBTRAFFIC_SYNDICATE_ATTRIBUTES")
# Standardize column names
timeseries <- timeseries |> rename_with(str_to_lower)
attributes <- attributes |> rename_with(str_to_lower)
# Join to make complete table
timeseries <-
timeseries |>
left_join(
attributes,
by = join_by(variable, variable_name)
)
```
```{r}
top_domains <-
c(
"youtube.com",
"google.com",
"facebook.com",
"tiktok.com",
"instagram.com",
"airbnb.com",
"vrbo.com",
"lyft.com",
"uber.com"
)
timeseries <-
timeseries |>
filter(domain_id %in% top_domains) |>
select(domain_id, date, measure, value)
```
```{r}
timeseries <-
timeseries |>
pivot_wider(names_from = measure, values_from = value) |>
rename_with(str_to_lower)
```
The resulting `timeseries` data will look like this:
```{r}
timeseries
```
## Visualize Page Views with `{ggplot2}`
Here we will compare the page views between `airbnb.com` and `vrbo.com`.
```{r}
domains <- c("airbnb.com", "vrbo.com")
timeseries |>
filter(domain_id %in% domains) |>
ggplot(aes(date, pageviews, color = domain_id)) +
geom_line() +
scale_y_log10() +
theme_minimal() +
theme(legend.position = "bottom") +
labs(
x = "",
y = "",
color = "",
title = "Pageviews"
)
```
## Compare Metrics in a Table with `{gt}`
Here we compare page views, number of users, and number of sessions
across all our selected domains, again highlighting airbnb.com and vrbo.com.
```{r}
comparison <-
timeseries |>
group_by(domain_id) |>
summarize(
across(
c("pageviews", "users", "sessions"),
\(x) median(x, na.rm = TRUE),
.names = "avg_{.col}"
),
.groups = "drop"
) |>
arrange(desc(avg_pageviews))
```
```{r}
comparison |>
gt(rowname_col = "domain_id") |>
fmt_number(scale_by = 1e-6) |>
cols_label(
avg_pageviews = "Pageviews",
avg_users = "Users",
avg_sessions = "Sessions"
) |>
gt_highlight_rows(
rows = (domain_id == "airbnb.com"),
fill = "#ffce67"
) |>
gt_highlight_rows(
rows = (domain_id == "vrbo.com"),
fill = "#78c2ad"
)
```
## Marketing
There are 2 main ratios used in marketing:
- content engagement: page views to users
- repeat rates and website usage: sessions to users
We also calculate the page views per session for all our domains.
```{r}
marketing <- timeseries |>
mutate(
pageviews_per_user = pageviews / users, # content engagement
sessions_per_user = sessions / users, # repeat rates and website
pageviews_per_session = pageviews / sessions
) |>
select(-pageviews, -users, -sessions) |>
pivot_longer(
c(pageviews_per_user, sessions_per_user, pageviews_per_session)
)
```
```{r}
marketing |>
ggplot() +
geom_line(aes(x = date, y = value, color = name)) +
facet_wrap(vars(domain_id), scales = "free_y") +
labs(
title = "Marketing Metric Ratios Over Time"
) +
scale_color_manual(
breaks = c(
"pageviews_per_session",
"pageviews_per_user",
"sessions_per_user"
),
labels = c(
'Views / Session',
"Content Engagement (views/user)",
"Repeats and Usage (sessions/user)"
),
values = c('#1b9e77', '#d95f02', '#7570b3')
) +
theme_minimal() +
theme(
legend.position = "bottom",
legend.title = element_blank(),
axis.title.x = element_blank(),
axis.title.y = element_blank()
) +
guides(
color = guide_legend(ncol = 2, nrow = 2, byrow = TRUE)
)
```