Module: Punk::Dataset
- Defined in:
- lib/punks/dataset/dataset.rb
Class Method Summary collapse
Class Method Details
.read(path) ⇒ Object
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
# File 'lib/punks/dataset/dataset.rb', line 47 def self.read( path ) rows = [] ## check if path include wildcard (*) ## e.g. './datasets/punks/*.csv' if path.index( '*' ) ## allow glob to read multiple files - keep? why? why not? #=> ["./datasets/punks/0-999.csv", # "./datasets/punks/1000-1999.csv", # "./datasets/punks/2000-2999.csv", # "./datasets/punks/3000-3999.csv", # "./datasets/punks/4000-4999.csv", # "./datasets/punks/5000-5999.csv", # "./datasets/punks/6000-6999.csv", # "./datasets/punks/7000-7999.csv", # "./datasets/punks/8000-8999.csv", # "./datasets/punks/9000-9999.csv"] datasets = Dir.glob( path ) datasets.each do |dataset| rows += read_csv( dataset ) end else ## "vanilla" (single) datafile rows += read_csv( path ) end # puts " #{rows.size} rows(s)" #=> 10000 rows(s) ### wrap in punk struct for easier access punks = rows.map { |row| Metadata.parse( row ) } punks end |