Class: EasyML::Data::Preprocessor::SimpleImputer

Inherits:
Object
  • Object
show all
Defined in:
lib/easy_ml/data/preprocessor/simple_imputer.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(strategy: "mean", path: nil, attribute: nil, options: {}, &block) ⇒ SimpleImputer

Returns a new instance of SimpleImputer.



12
13
14
15
16
17
18
19
20
21
22
23
24
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 12

def initialize(strategy: "mean", path: nil, attribute: nil, options: {}, &block)
  @strategy = strategy.to_sym
  @path = path
  @attribute = attribute
  @options = options || {}
  apply_defaults
  load
  @statistics ||= {}
  deep_symbolize_keys!
  return unless block_given?

  instance_eval(&block)
end

Instance Attribute Details

#attribute ⇒ Object

Returns the value of attribute attribute.



10
11
12
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 10

def attribute
  @attribute
end

#options ⇒ Object

Returns the value of attribute options.



10
11
12
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 10

def options
  @options
end

#path ⇒ Object

Returns the value of attribute path.



10
11
12
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 10

def path
  @path
end

#statistics ⇒ Object (readonly)

Returns the value of attribute statistics.



9
10
11
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 9

def statistics
  @statistics
end

#strategy ⇒ Object

Returns the value of attribute strategy.



10
11
12
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 10

def strategy
  @strategy
end

Instance Method Details

#apply_defaults ⇒ Object 



30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 30

def apply_defaults
  @options[:date_column] ||= "CREATED_DATE"

  if strategy == :categorical
    @options[:categorical_min] ||= 25
  elsif strategy == :custom
    itself = ->(col) { col }
    @options[:fit] ||= itself
    @options[:transform] ||= itself
  end
end

#cleanup ⇒ Object 



134
135
136
137
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 134

def cleanup
  @statistics = {}
  FileUtils.rm(file_path) if File.exist?(file_path)
end

#deep_symbolize_keys! ⇒ Object 



26
27
28
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 26

def deep_symbolize_keys!
  @statistics = @statistics.deep_symbolize_keys
end

#file_path ⇒ Object 



128
129
130
131
132
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 128

def file_path
  raise "Need both attribute and path to save/load statistics" unless attribute.present? && path.to_s.present?

  File.join(path, "statistics.json")
end

#fit(x, df = nil) ⇒ Object 



42
43
44
45
46
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
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 42

def fit(x, df = nil)
  x = validate_input(x)

  fit_values = case @strategy
               when :mean
                 fit_mean(x)
               when :median
                 fit_median(x)
               when :ffill
                 fit_ffill(x, df)
               when :most_frequent
                 fit_most_frequent(x)
               when :categorical
                 fit_categorical(x)
               when :constant
                 fit_constant(x)
               when :clip
                 fit_no_op(x)
               when :today
                 fit_no_op(x)
               when :one_hot
                 fit_no_op(x)
               when :custom
                 fit_custom(x)
               else
                 raise ArgumentError, "Invalid strategy: #{@strategy}"
               end || {}

  @statistics[attribute] ||= {}
  @statistics[attribute][@strategy] = fit_values.merge!(original_dtype: x.dtype)
  save
  self
end

#fit_custom(x) ⇒ Object 



189
190
191
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 189

def fit_custom(x)
  x
end

#load ⇒ Object 



155
156
157
158
159
160
161
162
163
164
165
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 155

def load
  return unless File.exist?(file_path)

  all_statistics = JSON.parse(File.read(file_path))
  attribute_stats = all_statistics[@attribute]

  return unless attribute_stats

  @statistics = deserialize_statistics(attribute_stats)
  deep_symbolize_keys!
end

#save ⇒ Object 



139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 139

def save
  FileUtils.mkdir_p(File.dirname(file_path))

  all_statistics = (File.exist?(file_path) ? JSON.parse(File.read(file_path)) : {}).deep_symbolize_keys

  deep_symbolize_keys!

  serialized = serialize_statistics(@statistics)
  all_statistics[attribute] = {} unless all_statistics.key?(attribute)
  all_statistics[attribute][@strategy] = serialized[attribute.to_sym][@strategy.to_sym]

  File.open(file_path, "w") do |file|
    file.write(JSON.pretty_generate(all_statistics))
  end
end

#should_transform_categorical?(val) ⇒ Boolean

Returns:

  • (Boolean) 


167
168
169
170
171
172
173
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 167

def should_transform_categorical?(val)
  values = @statistics.dig(:categorical, :value) || {}
  min_ct = options[:categorical_min] || 25
  allowed_values = values.select { |_v, c| c >= min_ct }

  allowed_values.keys.map(&:to_s).exclude?(val)
end

#should_transform_custom?(x) ⇒ Boolean

Returns:

  • (Boolean) 


193
194
195
196
197
198
199
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 193

def should_transform_custom?(x)
  if options.key?(:should_transform)
    options[:should_transform].call(x)
  else
    should_transform_default?(x)
  end
end

#transform(x) ⇒ Object 



76
77
78
79
80
81
82
83
84
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 76

def transform(x)
  check_is_fitted

  if x.is_a?(Polars::Series)
    transform_polars(x)
  else
    transform_dense(x)
  end
end

#transform_categorical(val) ⇒ Object 



175
176
177
178
179
180
181
182
183
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 175

def transform_categorical(val)
  return "other" if val.nil?

  values = @statistics.dig(:categorical, :value) || {}
  min_ct = options[:categorical_min] || 25
  allowed_values = values.select { |_v, c| c >= min_ct }.keys.map(&:to_s)

  allowed_values.include?(val.to_s) ? val.to_s : "other"
end

#transform_custom(x) ⇒ Object 



201
202
203
204
205
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 201

def transform_custom(x)
  raise "Transform required" unless options.key?(:transform)

  options[:transform].call(x)
end

#transform_polars(x) ⇒ Object 



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 86

def transform_polars(x)
  result = case @strategy
           when :mean, :median, :ffill, :most_frequent, :constant
             x.fill_null(@statistics[@strategy][:value])
           when :clip
             min = options["min"] || 0
             max = options["max"] || 1_000_000_000_000
             if x.null_count != x.len
               x.clip(min, max)
             else
               x
             end
           when :categorical
             allowed_values = @statistics.dig(:categorical, :value).select do |_k, v|
               v >= options[:categorical_min]
             end.keys.map(&:to_s)
             if x.null_count == x.len
               x.fill_null(transform_categorical(nil))
             else
               x.apply do |val|
                 allowed_values.include?(val) ? val : transform_categorical(val)
               end
             end
           when :today
             x.fill_null(transform_today(nil))
           when :custom
             if x.null_count == x.len
               x.fill_null(transform_custom(nil))
             else
               x.apply do |val|
                 should_transform_custom?(val) ? transform_custom(val) : val
               end
             end
           else
             raise ArgumentError, "Unsupported strategy for Polars::Series: #{@strategy}"
           end

  # Cast the result back to the original dtype
  original_dtype = @statistics.dig(@strategy, :original_dtype)
  original_dtype ? result.cast(original_dtype) : result
end

#transform_today(_val) ⇒ Object 



185
186
187
 
# File 'lib/easy_ml/data/preprocessor/simple_imputer.rb', line 185

def transform_today(_val)
  EST.now.beginning_of_day
end