apoorv74

packages_required <- c("ckanr","stringr","dplyr","DT","listviewer","ggplot2", "purrr","glue")
lapply(packages_required, require, character.only=TRUE)

org_url <- "https://openbudgetsindia.org/"
ckanr::ckanr_setup(url = org_url)
org_connect <- ckanr::src_ckan(url = org_url)

### Check connection
ckanr::ckan_version()

apoorv74

library(readr)
library(dplyr)

# Change These
file_path <- "~/Downloads/budget_changelog_2020/changelog_2.csv"
file_export_path <- "~/Downloads/budget_changelog_2020/changelog_updated.csv"

changelog <- read_csv(
  file_path,
  col_types = cols(

apoorv74

library(rvest)
library(readr)

# This file needs to be read as text. 
x <- readr::read_file("~/Downloads/Chandigarh.xls")

# Every file will have a table, the way it is structured in this sample. We just want to extract this table and convert it to a data frame
# Check and clean the file as per the structure of the original one. Headers and Rows need to be adjusted.
y <- x %>% read_html() %>% html_table(fill = TRUE)
z <- y[[1]]

apoorv74

html_master <- c()
for(i in 1:3){
pmjay_hospt <- 'https://hospitals.pmjay.gov.in/Search/empnlWorkFlow.htm'
req_params <- list("actionFlag"=  'ViewRegisteredHosptlsNew',
                   "search"=  'Y',
                   "appReadOnly"= 'Y',
                   "pageNo"=  i,
                   "searchState"= 23,
                   "searchDistrict"=  411,
                   "searchHospType"=  -1,

apoorv74

Comparison with other Nations:

• US - No overarching data protection framework but Sector wise laws - GLB - provisions for collection and use of financial data
• EU - GDPR (Replaces the Data Protection Directive of 1995) - Technology and Sector agnostic

Current state in India - SPD Rules were issued under Section 43A of the IT Act -

• Against negligence in implementing and maintaining reasonable security practices and procedures while dealing with sensitive personal data or infoirmation

Entities:

apoorv74

Datasets:

• Uber Movememt Data - https://movement.uber.com/
• NYC trip record - http://www.nyc.gov/html/tlc/html/about/trip_record_data.shtml

Repos:

apoorv74

args <- commandArgs(trailingOnly = TRUE)

library(ggplot2)
library(ggflags)

bg_color = '#5A8E38'


# Declaring constants -----------------------------------------------------

apoorv74

#!/usr/bin/env Rscript
args = commandArgs(trailingOnly = TRUE)


# What is this: A script that assists in following best practices when starting a new project
# What are these best practices:
# - Creating a project is the first step, managing individual scripts is a mess
# - Always have a git setup at the root of the project
# - A README.md file for documentation
# - A .gitignore file for ignoring files and directories, remember .DS_Store

apoorv74

convert <- function(x) {
  map <- c("\\[:alpha:\\]" = "a-zA-Z", "\\[:digit:\\]" = "0-9")
  for (i in seq_along(map)) {
    x <- gsub(names(map)[[i]], map[[i]], x)
  }
  x
}
convert("[[:alpha:]](?:(?:[[:digit:]]){1,2}(?:[[:alpha:]]){1,2})(?:(?:[[:digit:]]){6,7})")
#> [1] "[a-zA-Z](?:(?:[0-9]){1,2}(?:[a-zA-Z]){1,2})(?:(?:[0-9]){6,7})"

apoorv74

library(plotflow)
library(reports)

## make a folder to store the pdfs
folder(deleteMe)

## paste the paths to pdfs together in one string w/ spaces
plotflow:::mergePDF(
  in.file=paste(file.path("deleteMe", dir("deleteMe")), collapse=" "),
  file="merged.pdf"