us_expl_data_analysis.Rmd

---
title: "U.S. Exploratory Data Analysis"
author: "Joseph Lavicka"
date: "`r Sys.Date()`"
output: pdf_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(
	echo = TRUE,
	message = FALSE,
	warning = FALSE
)
```

# packages 

```{r}
library(tidyverse)
```

# explore ACLED dataset

```{r}

acled <- read_csv("../data/acled_us/2012-01-01-2022-11-30-United_States.csv")

acled %>% 
  group_by(event_type) %>% 
  summarise(n = n()) %>% 
  arrange(desc(n)) %>% 
  ggplot(aes(x = reorder(event_type, -n), y = n)) +
  geom_bar(stat = 'identity', fill = "black", color = "black", alpha = .5) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  xlab("Event Type") +
  ylab("Log of Count") +
  ggtitle("Count of Event Type") +
  scale_y_log10()

acled %>% 
  group_by(sub_event_type) %>% 
  summarise(n = n()) %>% 
  arrange(desc(n)) %>% 
  ggplot(aes(x = reorder(sub_event_type, -n), y = n)) +
  geom_bar(stat = 'identity', fill = "black", color = "black", alpha = .5) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  xlab("Sub-Event Type") +
  ylab("Log of Count") +
  ggtitle("Count of Sub-Event Type") +
  scale_y_log10()

acled %>% 
  group_by(admin1) %>% 
  summarise(n = n()) %>% 
  arrange(desc(n)) %>% 
  ggplot(aes(x = reorder(admin1, -n), y = n)) +
  geom_bar(stat = 'identity', fill = "black", color = "black", alpha = .5) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  xlab("State") +
  ylab("Count") +
  ggtitle("Count of Events by State")

acled %>% 
  group_by(fatalities) %>% 
  summarise(n = n()) %>% 
  arrange(fatalities) %>% 
  ggplot(aes(y = n, x = fatalities)) +
  geom_point() +
  scale_y_log10() +
  scale_x_log10() +
  stat_smooth(method = lm, formula = (y ~ poly(x, 2)), se = FALSE) +
  theme_bw() +
  xlab("Log of Event Fatalities") +
  ylab("Log of Count") +
  ggtitle("Fatalities per Event")

acled %>% 
  select(event_date, event_type) %>% 
  mutate(event_date = lubridate::dmy(event_date)) %>% 
  group_by(date = lubridate::floor_date(event_date, 'month'), event_type) %>% 
  summarise(n = n()) %>%   
  ggplot(aes(x = date, y = n, color = event_type)) +
  geom_point() +
  geom_smooth(method = lm, se = FALSE) +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  scale_y_log10() +
  scale_color_discrete(name = "Event Type") +
  ylab("Count") +
  xlab("Date")

acled %>% 
  group_by(admin1, admin2) %>% 
  summarise(n = n()) %>% 
  arrange(desc(n))
```

# explore final dataset

```{r}
final <- read_csv("../data/final.csv")

dim(final)

summary(final)

str(final)

sum(is.na(final))
```