Module: Daru::IO

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

Defined Under Namespace

Classes: SqlDataSource

Class Method Summary collapse

Class Method Details

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



104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
# File 'lib/daru/io/io.rb', line 104

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



135
136
137
138
139
140
141
# File 'lib/daru/io/io.rb', line 135

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_activerecord(relation, *fields) ⇒ Object

Load dataframe from AR::Relation

Parameters:

  • relation (ActiveRecord::Relation)

    A relation to be used to load the contents of dataframe

Returns:

  • A dataframe containing the data in the given relation



148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
# File 'lib/daru/io/io.rb', line 148

def from_activerecord(relation, *fields)
  if fields.empty?
    records = relation.map do |record|
      record.attributes.symbolize_keys
    end
    return Daru::DataFrame.new(records)
  else
    fields = fields.map(&:to_sym)
  end

  vectors = Hash[*fields.map { |name|
    [
      name,
      Daru::Vector.new([]).tap {|v| v.rename name }
    ]
  }.flatten]

  Daru::DataFrame.new(vectors, order: fields).tap do |df|
    relation.pluck(*fields).each do |record|
      df.add_row(Array(record))
    end
    df.update
  end
end

.from_csv(path, opts = {}) ⇒ Object

Functions for loading/writing CSV files



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
# File 'lib/daru/io/io.rb', line 61

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
    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



175
176
177
178
179
180
181
182
183
184
185
186
# File 'lib/daru/io/io.rb', line 175

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(db, query) ⇒ Object

Execute a query and create a data frame from the result

Parameters:

  • dbh (DBI::DatabaseHandle)

    A DBI connection to be used to run the query

  • query (String)

    The query to be executed

Returns:

  • A dataframe containing the data resulting from the query



130
131
132
133
# File 'lib/daru/io/io.rb', line 130

def from_sql(db, query)
  require 'daru/io/sql_data_source'
  SqlDataSource.make_dataframe(db, query)
end

.load(filename) ⇒ Object



195
196
197
198
199
200
201
202
203
# File 'lib/daru/io/io.rb', line 195

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



189
190
191
192
193
# File 'lib/daru/io/io.rb', line 189

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