Method: EasyML::Data::Preprocessor::SimpleImputer#transform_polars

Defined in:
lib/easy_ml/data/preprocessor/simple_imputer.rb

#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