dprep-exercises-2023-02-16

exercises.Rmd

---
title: "dPrep Tutorial"
output: html_document
date: "2023-02-16"
---

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

## Exercises

### Exercise 1: Conditionals

```{r, echo=FALSE}
# Initialization of the data
x <- c(10, 20, NA, 5, 3, 100)

# 1) all values equal to 10

# indexing which one is 10
x==10
# wrapping it into a which statement --> to get index NUMBERS
which(x==10)
# using it on x as an index vector
x[which(x==10)]

# 2) all values not equal to 10
x!=10
which(x!=10)
x[which(x!=10)]

x[x!=10]
x[which(x!=10)]

# 3) values larger than 20
x[which(x>20)]

# 4) values larger than 20
x[which(x<10)]

# 5) counting number of missing values

# (remember to build code gradually)

is.na(x)
data.frame(x, is.na(x))

# one solution: summing up
sum(is.na(x))

# second solution
which(is.na(x)) # which items are missing? # the third!
length(which(is.na(x)))

# 6) all values larger than 20 OR missing values

larger_than_20 = x > 20
is_na = is.na(x)
combined = larger_than_20 | is_na

data.frame(x, larger_than_20,
           is_na,
           combined)

x[combined]
# 7) &

first = x > 5
second = x < 20
combination = first & second

data.frame(x, first, second, combination)

x[combination] # w/ NAs
x[which(combination)] # without NAs

```

## Exercise 2: Controls

```{r}
download.file("https://raw.githubusercontent.com/hannesdatta/course-dprep/master/content/docs/modules/week4/regional-global-daily-latest.csv", "streams.csv")
library(tidyverse)
streams <- read_csv('streams.csv', skip=1, n_max = Inf)
```

```{r warning=FALSE}
download.file("https://raw.githubusercontent.com/hannesdatta/course-dprep/master/content/docs/modules/week4/regional-global-daily-latest.csv", "streams.csv")
library(tidyverse)

prototype = F

nrows = Inf

if (prototype==T) nrows = 100

streams <- read_csv('streams.csv', skip=1, n_max = nrows)

nrow(streams)
```

```{r}
# another (less optimal solution)

prototype = T

if (prototype==T) {
  streams <- read_csv('streams.csv', skip=1, n_max = 100) } else {
  streams <- read_csv('streams.csv', skip=1,  
                      n_max = Inf)
  }

nrow(streams)


```

```{r}
urls = c('http://data.insideairbnb.com/spain/catalonia/barcelona/2022-12-11/visualisations/listings.csv',
         'http://data.insideairbnb.com/spain/catalonia/barcelona/2022-09-10/visualisations/listings.csv',
         'http://data.insideairbnb.com/spain/catalonia/barcelona/2022-06-07/visualisations/listings.csv')

for (url in urls) {
  filename = paste(gsub('[^a-zA-Z]', '', url), '.csv') # keep only letter
  filename = gsub('httpdatainsideairbnbcom', '', filename) # wipe httpdatainsideairbnbcom from filename
  download.file(url, destfile = filename) # download file
}
```

### Use a lapply loop to load data sets

```{r}
urls = c('http://data.insideairbnb.com/spain/catalonia/barcelona/2022-12-11/visualisations/listings.csv',
         'http://data.insideairbnb.com/spain/catalonia/barcelona/2022-09-10/visualisations/listings.csv',
         'http://data.insideairbnb.com/spain/catalonia/barcelona/2022-06-07/visualisations/listings.csv')

datasets = lapply(urls, read_csv)

final_data = bind_rows(datasets)
```

#### very very bad solution
```{r}

datasets1 = read_csv('http://data.insideairbnb.com/spain/catalonia/barcelona/2022-12-11/visualisations/listings.csv')
datasets2 = read_csv('http://data.insideairbnb.com/spain/catalonia/barcelona/2022-09-10/visualisations/listings.csv')

nrow(datasets1)
nrow(datasets2)

```

## Exploration

```{r}

final_data %>% count()


```



```