library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(rvest)

## Loading required package: xml2

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

library(ggplot2)

Get the data: First, get the filepath of your message file. Then, choose which friend you want to analyze data with. I just used CTRL + F to find the friend and then used that file path (it so happens that this friend was number 691).

If you wanted to analyze all of your messages to everyone, you could loop through all of your friends and use that data instead.

url <- "facebook-jhovde-2018/html/messages.htm"
raw <- read_html(url)

# this is the list of people I had messages with
people <- raw %>%
  html_nodes("div.contents a") %>% 
  html_text %>% 
  data_frame()

# making html session

session <- html_session("file:///Users/josephhovde/RProjects/facebook-jhovde-2018/messages/691.html")

# iterating through them
friend <- read_html("facebook-jhovde-2018/messages/691.html")

# used the great SelectorGadget chrome plugin to find the html node I wanted ("span.meta")
friend_df <- friend %>%
  html_nodes("span.meta") %>% 
  html_text() %>% 
  data_frame()

# reformatting the dates. This takes some patience.

friend_df <- friend_df %>% 
  rename(moment = ".")

friend_df <- friend_df %>%
  separate(moment, c("weekday", "monthday", "yeartime"), ",")

friend_df <- friend_df %>%
  separate(yeartime, c("year", "time"), "at")


# group by year

friend_df %>% 
  group_by(year) %>% 
  summarise(n = n()) %>% 
  ggplot(aes(x = year, y = n)) +
  geom_col(aes(fill = year))

# group by day of week
friend_df %>% 
  group_by(weekday) %>% 
  summarise(n = n()) %>% 
  ggplot(aes(x = reorder(weekday, n), y = n)) +
  geom_col(aes(fill = weekday))

# trim exces whitespace
friend_df$time <- trimws(friend_df$time)
friend_df$monthday <- trimws(friend_df$monthday)

friend_df <- friend_df %>% 
  separate(time, c("time", "timezone"), " ")

# separate month and day of month

friend_df <- friend_df %>% 
  separate(monthday, c("month", "day"), " ")

# putting it in day month year

friend_df <- friend_df %>% 
  mutate(dmy = paste(day, month, year, sep = " "))

# getting the dates properly formatted. This was harder to figure out than it should have been

friend_df$dmy <- as_date(x = friend_df$dmy, format = "%d %B %Y")

Now that I have the dates properly formatted, I do some analysis to check out the change of messages over time. I use the cut() function which can breka your dates into weeks, months etc; it was new to me and is very useful.

# This is a chart of number of messages per day. Can see patterns but it's too granular.

friend_df %>% 
  group_by(dmy) %>% 
  summarise(n = n()) %>% 
  arrange(dmy) %>% 
  ggplot(aes(x = dmy, y = n)) +
    geom_col()

# This cuts the data up by week. Very useful!

friend_df$week <- as.Date(cut(friend_df$dmy, breaks = "week"))

friend_df %>% 
  group_by(week) %>% 
  summarise(n = n()) %>% 
  arrange(week) %>% 
  ggplot(aes(x = week, y = n)) +
    geom_col()

# same thing, cutting by month

friend_df$month_cut <- as.Date(cut(friend_df$dmy, breaks = "month"))

# chart of monthly messages over time

friend_df %>% 
  group_by(month_cut) %>% 
  summarise(n = n()) %>% 
  arrange(month_cut) %>% 
  ggplot(aes(x = month_cut, y = n)) +
  geom_col() +
  scale_x_date(date_breaks = "1 year") +
  labs(title = "Facebook Messages Exchanged Over Time",
       subtitle = "With One Friend Since 2012",
       x = "Date",
       y = "Number of FB Messages Exchanged") +
  theme(axis.text.x = element_text(angle = 70, hjust = 1),
        panel.background = element_rect(fill = "lightblue"),
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank())