learning_to_program_with_gdeltr2.r

### Code for Introduction to Programming with gdeltr2
## asbcllc.com/blog/2017/august/intro_to_programming_with_gdeltr2/index.html

# Package Install ---------------------------------------------------------
install.packages("devtools")
install.packages("purrr")

library(purrr)

packages_to_install <-
	c("dplyr", "rlang", "tidyr", "stringr", "lubridate", "purrrlyr", "plotly", "wordcloud2",
		"readr","tidyr", "ggplot2",  "tidyverse", "tibble", "hrbrthemes",
		"ggthemes", "jsonlite")

purrr::map(packages_to_install, install.packages)

# github install ----------------------------------------------------------


## Install from github

devtools::install_github("hafen/trelliscopejs")
devtools::install_github("jbkunst/highcharter")
devtools::install_github("abresler/gdeltr2")

# strings -----------------------------------------------------------------


### Start

## Strings

"My Text" == 'My Text'

"My Text" == 'my text'

# Objects -----------------------------------------------------------------


### Objects

my_favorite_team <-
  "Brooklyn Nets"

favoriteNBAPlayerEver <-
  "Mitch Richmond"

my_favorite_team

favoriteNBAPlayerEver

my_family <-
  c("Alex", "Liz", "Chase", "Theo")
their_type <-
  c("Adult", "Adult", "Toy Poodle", "Baby")

their_age <-
  c(33, 32, 2, 0)

my_family
their_type
their_age

all_objects <- c(my_family, their_type,their_age)
all_objects

# Data Frames -------------------------------------------------------------


## Data Frame
library(dplyr)
df_bresler_family <-
  data_frame(name = my_family, type = their_type, age = their_age)

df_bresler_family
View(df_bresler_family)

### Working with the API

# api ---------------------------------------------------------------------


library(gdeltr2)

## Terms
sports_terms <-
	c('"Brooklyn Nets"', "Caris LeVert", '"Kyrie Irving" Trade', '"Luka Doncic"',
	  'NBA "Draft Prospect"', '"Jarrett Allen"')

political_terms <-
	c('"Bill Perkins"', '"New York City" "City Counsel"')

finance_real_estate_terms <-
  c("Eastdil", "Condo Bubble", '"JBG Smith"', '"CPPIB"', "Anbang",
    "WeWork", '"Goldman Sachs"' , 'Blackstone "Real Estate"')

other_terms <-
	c("Supergoop", '"LNG"', 'Maryland "High School Football"',
	  '"Jared Kushner"', '"Eddie Huang"')

my_terms <-
  c(sports_terms, political_terms, finance_real_estate_terms, other_terms)



# domains -----------------------------------------------------------------



news_domains <-
  c("nypost.com", "washingtonpost.com", "wsj.com", "gothamgazette.com")

sports_domains <-
  c("espn.com", "netsdaily.com")

finance_real_estate_domains <-
  c("realdeal.com", "zerohedge.com", "institutionalinvestor.com", 'pionline.com',
    "curbed.com", "archdaily.com")

random_domains <-
  c("tmz.com", "snopes.com", "alphr.com", "oilprice.com")

my_domains <-
  c(news_domains, sports_domains, finance_real_estate_domains, random_domains)


# GKG ---------------------------------------------------------------------


df_gkg <-
  get_gdelt_codebook_ft_api(code_book = "gkg")

my_themes <-
  c("ECON_WORLDCURRENCIES_CHINESE_YUAN", # stories about china's currency -- god way to find stories about china's economy
    "ECON_BUBBLE", # articles about economic bubble
    "TAX_FNCACT_BROKER", # articles about brokers of things
    "ECON_HOUSING_PRICES", # articls about housing prices
    "ECON_BITCOIN", # articles about bitcoin
    "ELECTION_FRAUD", # articles about election fraud
    "SOC_POINTSOFINTEREST_GOVERNMENT_BUILDINGS", # articles about government buildings
    "WB_1277_BANKRUPTCY_AND_LIQUIDATION", # articles about bankruptcy
    "WB_639_REPRODUCTIVE_MATERNAL_AND_CHILD_HEALTH", # articles about pregnancy and child health
    "WB_2151_CHILD_DEVELOPMENT", # articles about child development
    "TAX_FNCACT_BUILDER" # articles about builders
  )

set.seed(1234)

random_themes <-
  df_gkg %>% pull(idGKGTheme) %>% sample(3)

my_themes <-
  c(my_themes, random_themes)

# OCR ---------------------------------------------------------------------


my_ocr <-
  c(
    "Brooklyn Nets",
    "Panerai",
    "Four Seasons",
    "NBA",
    "Goldman Sachs",
    "Philadelphia Eagles",
    "Supergoop",
    "Boston Celtics",
    "Big Baller Brand",
    "BBB",
    "Boston Properties"
  )


# imagetags ---------------------------------------------------------------

df_imagetags <-
  get_gdelt_codebook_ft_api(code_book = "imagetags")

View(df_imagetags)

my_image_tags <-
  c("Toy Poodle", "poodle", "commercial building", "basketball player", "supermodel")



# Image Web ---------------------------------------------------------------

df_imageweb <-
  get_gdelt_codebook_ft_api(code_book = "imageweb")

View(df_imageweb)

my_image_web <-
  c("Jared Kushner", "Empire State Building", "New York City", "Ivanka Trump",
    "Tesla Model 3", "Jeremy Lin", "NBA", "Brooklyn Nets"
  )

# other_parameters --------------------------------------------------------


my_timespan <-
  "5 days"

df_countries <-
  get_gdelt_codebook_ft_api(code_book = "countries")

View(df_countries)

my_trelliscope_parameters <-
  list(
  rows = 1,
  columns = 2,
  path = NULL
)

# Artlist -----------------------------------------------------------------
get_data_ft_v2_api(
  terms = my_terms,
  domains = my_domains,
  images_web_tag = my_image_web,
  images_tag = my_image_tags,
  images_ocr = my_ocr,
  gkg_themes = my_themes,
  modes = c("Artlist"),
  timespans = my_timespan,
  trelliscope_parameters = my_trelliscope_parameters
)
trelliscopeImage
# Timeline  -----------------------------------------------------------------
get_data_ft_v2_api(
  terms = my_terms,
  domains = my_domains,
  images_web_tag = my_image_web,
  images_tag = my_image_tags,
  images_ocr = my_ocr,
  gkg_themes = my_themes,
  modes = c("TimelineVolInfo"),
  timespans = "12 Weeks",
  trelliscope_parameters = my_trelliscope_parameters
)
trelliscopeHighcharter

# wordclouds --------------------------------------------------------------


get_data_ft_v2_api(
  terms = my_terms,
  domains = my_domains,
  images_web_tag = my_image_web,
  images_tag = my_image_tags,
  images_ocr = my_ocr,
  gkg_themes = my_themes,
  modes = c("WordCloudEnglish", "WordCloudTheme", "WordCloudImageTags", "WordCloudImageWebTags"),
  timespans = "2 weeks",
  trelliscope_parameters = list(
    rows = 1,
    columns = 1,
    path = NULL
  )
)
trelliscopeWordcloud