Class: Datasets::EStatJapan::StatsData

Inherits:
Dataset
  • Object
show all
Defined in:
lib/datasets/e-stat-japan.rb

Overview

wrapper class for e-Stat API service

Instance Attribute Summary collapse

Attributes inherited from Dataset

#metadata

Instance Method Summary collapse

Methods inherited from Dataset

#clear_cache!, #to_table

Constructor Details

#initialize(id, app_id: nil, areas: nil, categories: nil, times: nil, skip_levels: [1], hierarchy_selection: 'child', skip_nil_column: true, skip_nil_row: false, time_range: nil) ⇒ StatsData

generate accessor instance for e-Stat API's endpoint getStatsData. for detail spec : https://www.e-stat.go.jp/api/api-info/e-stat-manual

Examples:

stats_data = Datasets::EStatJapan::StatsData.new(
  "0000020201", # A Population and household (key name: Ａ　人口・世帯)
  categories: ["A1101"], # Population (key name: A1101_人口総数)
  areas: ["01105", "01106"], # Toyohira-ku Sapporo-shi Hokkaido, Minami-ku Sapporo-shi Hokkaido
  times: ["1981100000", "1982100000"],
  hierarchy_selection: 'child',
  skip_child_area: true,
  skip_nil_column: true,
  skip_nil_row: false,
)


57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/datasets/e-stat-japan.rb', line 57

def initialize(id,
               app_id: nil,
               areas: nil, categories: nil, times: nil,
               skip_levels: [1],
               hierarchy_selection: 'child',
               skip_nil_column: true,
               skip_nil_row: false,
               time_range: nil)
  @app_id = app_id || fetch_app_id
  if @app_id.nil? || @app_id.empty?
    raise ArgumentError, 'Please set app_id via `Datasets::EStatJapan.configure` method, environment var `ESTATJAPAN_APP_ID` or keyword argument `:app_id`'
  end

  super()

  @api_version = '3.0'
  @base_url = "https://api.e-stat.go.jp/rest/#{@api_version}/app/json/getStatsData"
  @metadata.id = "e-stat-japan-#{@api_version}"
  @metadata.name = "e-Stat API #{@api_version}"
  @metadata.url = @base_url
  @metadata.licenses = ["CC-BY-4.0"]
  @metadata.description = "e-Stat API #{@api_version}"

  @id = id
  @areas = areas
  @categories = categories
  @times = times
  @skip_levels = skip_levels
  case hierarchy_selection
  when 'child' then
    @skip_child_area = false
    @skip_parent_area = true
  when 'parent' then
    @skip_child_area = true
    @skip_parent_area = false
  else # 'both'
    @skip_child_area = false
    @skip_parent_area = false
  end
  @skip_nil_column = skip_nil_column
  @skip_nil_row = skip_nil_row
  @time_range = time_range

  @url = generate_url
  option_hash = Digest::MD5.hexdigest(@url.to_s)
  base_name = "e-stat-japan-#{option_hash}.json"
  @data_path = cache_dir_path + base_name
  @loaded = false
end

Instance Attribute Details

#app_id ⇒ Object

Returns the value of attribute app_id.



32
33
34
 
# File 'lib/datasets/e-stat-japan.rb', line 32

def app_id
  @app_id
end

#id ⇒ Object

Returns the value of attribute id.



32
33
34
 
# File 'lib/datasets/e-stat-japan.rb', line 32

def id
  @id
end

Instance Method Details

#areas ⇒ Object 



141
142
143
144
 
# File 'lib/datasets/e-stat-japan.rb', line 141

def areas
  load_data
  @areas
end

#columns ⇒ Object 



151
152
153
154
 
# File 'lib/datasets/e-stat-japan.rb', line 151

def columns
  load_data
  @columns
end

#each ⇒ Object

fetch data records from Remote API

Examples:

indices = []
rows = []
map_id_name = {}
estat.each do |record|
  # Select Hokkaido prefecture only
  next unless record.id.to_s.start_with? '01'
  indices << record.id
  rows << record.values
  map_id_name[record.id] = record.name
end


121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/datasets/e-stat-japan.rb', line 121

def each
  return to_enum(__method__) unless block_given?

  load_data

  # create rows
  @areas.each do |a_key, a_value|
    rows = []
    @time_tables.reject { |_key, x| x[:skip] }.each do |st_key, _st_value|
      row = @columns.reject { |_key, x| x[:skip] }.map do |c_key, _c_value|
        @indexed_data.dig(st_key, a_key, c_key)
      end
      rows << row
    end
    next if @skip_nil_row && rows.flatten.count(nil).positive?

    yield Record.new(a_key, a_value['@name'], rows.flatten)
  end
end

#schema ⇒ Object 



156
157
158
159
 
# File 'lib/datasets/e-stat-japan.rb', line 156

def schema
  load_data
  @schema
end

#time_tables ⇒ Object 



146
147
148
149
 
# File 'lib/datasets/e-stat-japan.rb', line 146

def time_tables
  load_data
  @time_tables
end