Browse Source

Data download pipeline

Petra Lamborn 4 years ago
parent
commit
444647a8d5
3 changed files with 16 additions and 1 deletions
  1. 5
    0
      .gitignore
  2. 6
    0
      download.R
  3. 5
    1
      expl.R

+ 5
- 0
.gitignore View File

@@ -47,3 +47,8 @@ Session.vim
47 47
 # auto-generated tag files
48 48
 tags
49 49
 
50
+# ---> Project-specific
51
+# large data files
52
+disaggregated-crash-data.zip
53
+finaldata_201809.csv
54
+crashdata.Rdata

+ 6
- 0
download.R View File

@@ -0,0 +1,6 @@
1
+# Dowload data
2
+download.file("https://nzta.govt.nz/assets/Safety/docs/disaggregated-crash-data.zip",
3
+              "disaggregated-crash-data.zip")
4
+unzip("disaggregated-crash-data.zip", "finaldata_201809.csv")
5
+dat <- read.csv("finaldata_201809.csv")
6
+save(dat, file = "crashdata.Rdata")

+ 5
- 1
expl.R View File

@@ -1,5 +1,9 @@
1 1
 # Exploration on data
2 2
 
3
-dat <- read.csv(unzip("disaggregated-crash-data.zip", "finaldata_201809.csv"))
3
+# Load data from Rdata file
4
+load("crashdata.Rdata")
5
+
6
+# Alternative way to load data
7
+#dat <- read.csv("finaldata_201809.csv")
4 8
 
5 9
 str(dat)