Module: Daru::IO

Defined in:
lib/daru/io/io.rb

Class Method Summary collapse

Class Method Details

.dataframe_write_csv(dataframe, path, opts = {}) ⇒ Object


105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
# File 'lib/daru/io/io.rb', line 105

def dataframe_write_csv dataframe, path, opts={}
  options = {
    converters: :numeric
  }.merge(opts)

  writer = ::CSV.open(path, 'w', options)
  writer << dataframe.vectors.to_a

  dataframe.each_row do |row|
    if options[:convert_comma]
      writer << row.map { |v| v.to_s.gsub('.', ',') }
    else
      writer << row.to_a
    end
  end

  writer.close
end

.dataframe_write_excel(dataframe, path, opts = {}) ⇒ Object


44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
# File 'lib/daru/io/io.rb', line 44

def dataframe_write_excel dataframe, path, opts={}
  book   = Spreadsheet::Workbook.new
  sheet  = book.create_worksheet
  format = Spreadsheet::Format.new :color => :blue, :weight => :bold

  sheet.row(0).concat(dataframe.vectors.to_a.map(&:to_s)) # Unfreeze strings
  sheet.row(0).default_format = format
  i = 1
  dataframe.each_row do |row|
    sheet.row(i).concat(row.to_a)
    i += 1
  end

  book.write(path)
end

.dataframe_write_sql(ds, dbh, table) ⇒ Object


144
145
146
147
148
149
150
# File 'lib/daru/io/io.rb', line 144

def dataframe_write_sql ds, dbh, table
  require 'dbi'
  query = "INSERT INTO #{table} ("+ds.vectors.to_a.join(",")+") VALUES ("+((["?"]*ds.vectors.size).join(","))+")"
  sth   =  dbh.prepare(query)
  ds.each_row { |c| sth.execute(*c.to_a) }
  return true
end

.from_csv(path, opts = {}) ⇒ Object

Functions for loading/writing CSV files


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
# File 'lib/daru/io/io.rb', line 62

def from_csv path, opts={}
  opts[:col_sep]           ||= ','
  opts[:converters]        ||= :numeric

  daru_options = opts.keys.inject({}) do |hash, k|
    if [:clone, :order, :index, :name].include?(k)
      hash[k] = opts[k]
      opts.delete k
    end

    hash
  end

  # Preprocess headers for detecting and correcting repetition in 
  # case the :headers option is not specified.
  unless opts[:headers]
    csv = ::CSV.open(path, 'rb', opts)
    yield csv if block_given?

    csv_as_arrays = csv.to_a
    headers       = csv_as_arrays[0].recode_repeated.map(&:to_sym)
    csv_as_arrays.delete_at 0
    csv_as_arrays = csv_as_arrays.transpose

    hsh = {}
    headers.each_with_index do |h, i|
      hsh[h] = csv_as_arrays[i]
    end
  else
    opts[:header_converters] ||= :symbol
    
    csv = ::CSV.read(path, 'rb',opts)
    yield csv if block_given?

    hsh = {}
    csv.by_col.each do |col_name, values|
      hsh[col_name] = values
    end
  end

  Daru::DataFrame.new(hsh,daru_options)
end

.from_excel(path, opts = {}) ⇒ Object

Functions for loading/writing Excel files.


24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
# File 'lib/daru/io/io.rb', line 24

def from_excel path, opts={}
  opts = {
    :worksheet_id => 0,
  }.merge opts

  worksheet_id = opts[:worksheet_id]
  book         = Spreadsheet.open path
  worksheet    = book.worksheet worksheet_id
  headers      = worksheet.row(0).recode_repeated.map(&:to_sym)

  df = Daru::DataFrame.new({})
  headers.each_with_index do |h,i|
    col = worksheet.column(i).to_a
    col.delete_at 0
    df[h] = col
  end

  df
end

.from_plaintext(filename, fields) ⇒ Object

Loading data from plain text files


154
155
156
157
158
159
160
161
162
163
164
165
# File 'lib/daru/io/io.rb', line 154

def from_plaintext filename, fields
  ds = Daru::DataFrame.new({}, order: fields)
  fp = File.open(filename,"r")
  fp.each_line do |line|
    row = Daru::IOHelpers.process_row(line.strip.split(/\s+/),[""])
    next if row == ["\x1A"]
    ds.add_row(row)
  end
  ds.update
  fields.each { |f| ds[f].rename f }
  ds
end

.from_sql(dbh, query) ⇒ Object

Loading/writing from SQL databases


126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
# File 'lib/daru/io/io.rb', line 126

def from_sql dbh, query
  require 'dbi'
  sth     = dbh.execute(query)
  vectors = {}
  fields  = []
  sth.column_info.each do |c|
    vectors[c[:name]] = Daru::Vector.new([])
    vectors[c[:name]].rename c[:name]
    fields.push(c[:name].to_sym)
  end
  ds=Daru::DataFrame.new(vectors,order: fields)
  sth.fetch do |row|
    ds.add_row(row.to_a)
  end
  ds.update
  ds
end

.load(filename) ⇒ Object


174
175
176
177
178
179
180
181
182
# File 'lib/daru/io/io.rb', line 174

def load filename
  if File.exist? filename
    o = false
    File.open(filename, 'r') { |fp| o = Marshal.load(fp) }
    o
  else
    false
  end
end

.save(klass, filename) ⇒ Object

Loading and writing Marshalled DataFrame/Vector


168
169
170
171
172
# File 'lib/daru/io/io.rb', line 168

def save klass, filename
  fp = File.open(filename, 'w')
  Marshal.dump(klass, fp)
  fp.close
end