Module: TopStmtToR

Includes:
BlockToRSupport
Defined in:
lib/statsailr/block_to_r/sts_block_to_r.rb,
lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb

Class Method Summary collapse

Class Method Details

.create_function(blk) ⇒ Object 



9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
 
# File 'lib/statsailr/block_to_r/sts_block_to_r.rb', line 9

def self.create_function( blk )
  r_func = nil
  case blk.command
  when /^(\w+)$/
    method_to_create_r_function = "create_r_func_for_" + $1.downcase
    if respond_to? method_to_create_r_function
      r_func = send( method_to_create_r_function , blk.opts)
    else
      raise "#{method_to_create_r_function} cannot be found. Unknown top level command: #{blk.command}"
    end
  else
    raise "Invalid TOPLEVEL command name: " + blk.command
  end
  puts "The following options are not used in " + blk.command + " : " + blk.opts.keys.join(" ") if ! blk.opts.empty?
  return r_func
end

.create_r_func_for_getwd(opts) ⇒ Object 



163
164
165
166
167
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 163

def self.create_r_func_for_getwd(opts)
  puts "Current working directory"
  r_func = RBridge.create_function_call( "print", {"x" => RBridge.create_function_call( "getwd" , {} )})
  return r_func
end

.create_r_func_for_read(opts) ⇒ Object 



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
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 60

def self.create_r_func_for_read(opts)
  case
  when builtin_data_name = opts["builtin"] # builtin
    opts.delete("builtin"); opts.delete("file")
    puts "Built-in dataset becomes available using data(): #{builtin_data_name.to_s}"
    r_func = RBridge.create_function_call( "data" , {"" => RBridge.create_strvec([ builtin_data_name.to_s ])} )
  when file_path = opts["file"] # csv
    opts.delete("builtin"); opts.delete("file")
    if type = opts["type"]
      opts.delete("type")
      case type.downcase
      when "rds"
        r_func = read_rds(file_path, opts)
      when "rdata"
        r_func = read_rda(file_path, opts)
      when "csv"
        r_func = read_csv(file_path, opts)
      else
        raise "TOPLEVEL READ statement currently supports rds(single r object), rdata or csv for type option. #{type} is specified."
      end
    else
      case file_path
      when /\.(rds)$/i  # i is option to ignore cases
        r_func = read_rds(file_path, opts)
      when /\.(rdata|rda)$/i
        r_func = read_rda(file_path, opts)
      when /\.csv$/i
        r_func = read_csv(file_path, opts)
      else
        raise "TOP level READ statement tried to idenfity file type from 'file=' option, but failed. File name preferably ends with .rds, .RData(.rdata) or .csv, or specify file type."
      end
    end
  else
    raise "TOPLEVEL READ statement requires 'builtin=' or 'file=' option."
  end
end

.create_r_func_for_save(opts) ⇒ Object 



121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 121

def self.create_r_func_for_save(opts)
  if opts["file"]
    file_path = opts["file"]
  else
    raise "TOPLEVEL SAVE statement require 'file=' option. 'type=' option is optional when file extension matches file type."
  end
  if opts["type"]
    type = opts["type"].downcase
  end
  opts.delete("file"); opts.delete("type")

  if ! opts.empty?
    dataset_to_save = opts.filter(){|k,v| v.nil? }.keys
    dataset_to_save.each{|elem|
      opts.delete(elem)
    }
  else
    raise "Dataset should be specified"
  end

  case type
  when "rds"
    r_func = save_rds(dataset_to_save, file_path)
  when "rdata"
    r_func = save_rda(dataset_to_save, file_path)
  when "csv"
    r_func = save_csv(dataset_to_save, file_path)
  else
    case file_path
    when /\.rds$/i
      r_func = save_rds(dataset_to_save, file_path)
    when /\.(rda|rdata)$/i
      r_func = save_rda(dataset_to_save, file_path)
    when /\.csv$/i
      r_func = save_csv(dataset_to_save, file_path)
    else
      raise "TOP level SAVE statement tried to idenfity file type from file option, but failed. File name preferably ends with .rds, .rda (.rdata) or .csv, or specify file type."
    end
  end
  return r_func
end

.create_r_func_for_setwd(opts) ⇒ Object 



169
170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 169

def self.create_r_func_for_setwd(opts)
  opts.select!(){|k,v| v.nil? }
  if opts.empty?
    raise "SETWD requires String keyword that specifies directory to which working diretory moves."
  end

  puts "Setting new working directory"
  dir_path = opts.keys[0]
  opts.delete(dir_path)
  r_func = RBridge.create_function_call( "setwd" , {"dir" => RBridge.create_strvec([dir_path])} )
  return r_func
end

.read_csv(data_path, opts) ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 28

def self.read_csv(data_path, opts)
  opt_hash = {}
  if header = opts["header"]
    opts.delete("header")
    opt_hash = {"header" => RBridge.create_lglvec([header]) }
  else
    opt_hash = {"header" => RBridge.create_lglvec([true]) }
  end

  available_opts = ["sep","na.strings","skip"]

  opts.filter!(){|k,v|
    if available_opts.include?(k)
      opt_hash[k] = RBridge.create_vec( [v] )
    end
    ! available_opts.include?(k)
  }

  if as_name = opts["as"]
    opts.delete("as")
    puts "Read #{data_path} using read.csv(), which uses #{as_name} for dataset name."
    read_func = RBridge.create_function_call( "read.csv" , {"file" => RBridge.create_strvec([data_path])}.merge(opt_hash) )
    r_func = RBridge.create_assign_function( as_name.to_s , read_func )
  else
    basename = File.basename(data_path, File.extname(data_path))
    as_name = basename.gsub(/\s/, '_').downcase
    puts "Read #{data_path} using read.csv(), which uses #{as_name} for dataset name (created from filename)."
    read_func = RBridge.create_function_call( "read.csv" , {"file" => RBridge.create_strvec([data_path])}.merge(opt_hash) )
    r_func = RBridge.create_assign_function( as_name , read_func )
  end
end

.read_rda(data_path, opts) ⇒ Object 



18
19
20
21
22
23
24
25
26
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 18

def self.read_rda(data_path, opts)
  if as_name = opts["as"]
    opts.delete("as")
    puts "Read #{data_path} using laod(), which does not rename object when importing. 'as' option is ignored."
  end

  r_func = RBridge.create_function_call( "load" , {"file" => RBridge.create_strvec([data_path])} )
  return(r_func)
end

.read_rds(data_path, opts) ⇒ Object 



2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 2

def self.read_rds(data_path, opts)
  if as_name = opts["as"]
    opts.delete("as")
    puts "Read #{data_path} using readRDS(), which uses #{as_name} for dataset name."
    read_func = RBridge.create_function_call( "readRDS" , {"file" => RBridge.create_strvec([data_path])} )
    r_func = RBridge.create_assign_function( as_name.to_s , read_func )
  else
    basename = File.basename(data_path, File.extname(data_path))
    as_name = basename.gsub(/\s/, '_').downcase
    puts "Read #{data_path} using readRDS(), which uses #{as_name} for dataset name (created from filename)."
    read_func = RBridge.create_function_call( "readRDS" , {"file" => RBridge.create_strvec([data_path])} )
    r_func = RBridge.create_assign_function( as_name , read_func )
  end
  return(r_func)
end

.save_csv(r_var, data_path) ⇒ Object 



111
112
113
114
115
116
117
118
119
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 111

def self.save_csv(r_var, data_path)
  puts "SAVE #{data_path} using write.csv()"
  if(r_var.size != 1)
    puts "Only one dataset can be specified. Others are ignored."
  end
  r_var = r_var[0]
  save_csv_func = RBridge.create_function_call( "write.csv" , {"x" => RBridge::SymbolR.new(r_var).to_r_symbol, "file" => RBridge.create_strvec([data_path])} )
  return save_csv_func
end

.save_rda(r_var, data_path) ⇒ Object 



106
107
108
109
110
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 106

def self.save_rda(r_var, data_path)
  puts "SAVE #{data_path} using save()"
  save_rds_func = RBridge.create_function_call( "save" , {"" => RBridge::create_strvec(r_var), "file" => RBridge.create_strvec([data_path])} )
  return save_rds_func
end

.save_rds(r_var, data_path) ⇒ Object 



97
98
99
100
101
102
103
104
105
 
# File 'lib/statsailr/block_to_r/top_stmt/top_stmt_to_r_func.rb', line 97

def self.save_rds(r_var, data_path)
  puts "SAVE #{data_path} using saveRDS()"
  if(r_var.size != 1)
    puts "Only one dataset can be specified. Others are ignored."
  end
  r_var = r_var[0]
  save_rds_func = RBridge.create_function_call( "saveRDS" , {"object" => RBridge::SymbolR.new(r_var).to_r_symbol, "file" => RBridge.create_strvec([data_path])} )
  return save_rds_func
end