Class: Wads::Stats

Inherits:
Object
  • Object
show all
Defined in:
lib/wads/data_structures.rb

Overview

Stats allows you to maintain sets of data values, identified by a key, or data set name. You can then use Stats methods to get the count, average, sum, or percentiles for these keys.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(name) ⇒ Stats

Returns a new instance of Stats.



82
83
84
85
# File 'lib/wads/data_structures.rb', line 82

def initialize(name)
    @name = name
    @data = {}
end

Instance Attribute Details

#dataObject

Returns the value of attribute data.



80
81
82
# File 'lib/wads/data_structures.rb', line 80

def data
  @data
end

#nameObject

Returns the value of attribute name.



79
80
81
# File 'lib/wads/data_structures.rb', line 79

def name
  @name
end

Instance Method Details

#add(key, value) ⇒ Object



87
88
89
90
91
92
93
94
95
96
# File 'lib/wads/data_structures.rb', line 87

def add(key, value)
    data_set = @data[key]
    if data_set
        data_set << value
    else
        data_set = []
        data_set << value
        @data[key] = data_set
    end     
end

#average(key) ⇒ Object



120
121
122
123
124
125
126
127
# File 'lib/wads/data_structures.rb', line 120

def average(key)
    data_set = @data[key]
    if data_set
        return (sum(key) / count(key)).round(5)
    else
        return 0
    end
end

#count(key) ⇒ Object



102
103
104
105
106
107
108
109
# File 'lib/wads/data_structures.rb', line 102

def count(key)
    data_set = @data[key]
    if data_set
        return data_set.size
    else
        return 0
    end
end

#display_countsObject



235
236
237
238
239
240
241
242
# File 'lib/wads/data_structures.rb', line 235

def display_counts
    puts "#{pad(@name, 20)}   Value"
    puts "#{'-' * 20}   #{'-' * 10}"
    @data.keys.each do |key|
        #data_set = @data[key]
        puts "#{pad(key, 20)}   #{count(key)}"
    end
end

#halfway(b, e) ⇒ Object



159
160
161
162
163
# File 'lib/wads/data_structures.rb', line 159

def halfway(b, e)
    d = e - b
    m = b + (d / 2).to_i
    m
end

#increment(key) ⇒ Object



98
99
100
# File 'lib/wads/data_structures.rb', line 98

def increment(key)
    add(key, 1)
end

#keysObject



244
245
246
# File 'lib/wads/data_structures.rb', line 244

def keys 
    @data.keys 
end

#max(key) ⇒ Object



138
139
140
141
142
143
144
145
# File 'lib/wads/data_structures.rb', line 138

def max(key)
    data_set = @data[key]
    if data_set
        return data_set.max
    else
        return 0
    end
end

#min(key) ⇒ Object



129
130
131
132
133
134
135
136
# File 'lib/wads/data_structures.rb', line 129

def min(key)
    data_set = @data[key]
    if data_set
        return data_set.min
    else
        return 0
    end
end

#most_common(key) ⇒ Object



202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
# File 'lib/wads/data_structures.rb', line 202

def most_common(key)
    value_counts = {}
    data_set = @data[key]
    data_set.each do |data|
        c = value_counts[data]
        if c.nil?
            value_counts[data] = 1
        else
            value_counts[data] = value_counts[data] + 1
        end
    end
    
    largest_count = 0
    largest_key = "none"
    value_counts.keys.each do |key|
        key_count = value_counts[key]
        if key_count > largest_count
            largest_count = key_count
            largest_key = key
        end
    end
    largest_key
end

#pad(str, size, left_align = false) ⇒ Object



226
227
228
229
230
231
232
233
# File 'lib/wads/data_structures.rb', line 226

def pad(str, size, left_align = false)
    str = str.to_s
    if left_align
        str[0, size].ljust(size, ' ')
    else
        str[0, size].rjust(size, ' ')
    end
end

#percentile(key, pct) ⇒ Object



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
# File 'lib/wads/data_structures.rb', line 165

def percentile(key, pct)
    data_set = @data[key]
    if data_set
        sorted_data_set = data_set.sort
        pct_index = (data_set.length - 1).to_f * pct
        mod = pct_index.modulo(1.0)
        adj = pct_index
        if mod > 0.9
            adj = pct_index.ceil
        elsif mod < 0.1
            adj = pct_index.floor
        else
            # We want halfway between the two indices
            low = pct_index.floor
            high = pct_index.ceil
            if low < 0
                low = 0
            end
            if high > data_set.size - 1
                high = data_set.size - 1
            end
            result = halfway(sorted_data_set[low], sorted_data_set[high])
            return result
        end
        
        if adj < 0
            adj = 0
        elsif adj > data_set.size - 1
            adj = data_set.size - 1
        end
        result = sorted_data_set[adj]
        return result
    else
        return 0
    end
end

#report(report_keys = keys) ⇒ Object



248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
# File 'lib/wads/data_structures.rb', line 248

def report(report_keys = keys)
    puts "#{pad(@name, 10)}#{SPACER}#{pad('Count', 7)}#{SPACER}#{pad('Min', VALUE_WIDTH)}#{SPACER}#{pad('Avg', VALUE_WIDTH)}#{SPACER}#{pad('StdDev', VALUE_WIDTH)}#{SPACER}#{pad('Max', VALUE_WIDTH)}#{SPACER}| #{pad('p1', VALUE_WIDTH)}#{SPACER}#{pad('p10', VALUE_WIDTH)}#{SPACER}#{pad('p50', VALUE_WIDTH)}#{SPACER}#{pad('p90', VALUE_WIDTH)}#{SPACER}#{pad('p99', VALUE_WIDTH)}"
    puts "#{'-' * 10}#{SPACER}#{'-' * 7}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}| #{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}#{SPACER}#{'-' * VALUE_WIDTH}"
    if report_keys.nil?
        report_keys = @data.keys
    end
    report_keys.each do |key|
        data_set = @data[key]
        m1 = min(key).round(5)
        a = average(key).round(5)
        sd = std_dev(key).round(5)
        m2 = max(key).round(5)
        p1 = percentile(key, 0.01).round(5)
        p10 = percentile(key, 0.1).round(5)
        p50 = percentile(key, 0.5).round(5)
        p90 = percentile(key, 0.90).round(5)
        p99 = percentile(key, 0.99).round(5)
        puts "#{pad(key, 10)}#{SPACER}#{pad(count(key), 7)}#{SPACER}#{pad(m1, VALUE_WIDTH)}#{SPACER}#{pad(a, VALUE_WIDTH)}#{SPACER}#{pad(sd, VALUE_WIDTH)}#{SPACER}#{pad(m2, VALUE_WIDTH)}#{SPACER}| #{pad(p1, VALUE_WIDTH)}#{SPACER}#{pad(p10, VALUE_WIDTH)}#{SPACER}#{pad(p50, VALUE_WIDTH)}#{SPACER}#{pad(p90, VALUE_WIDTH)}#{SPACER}#{pad(p99, VALUE_WIDTH)}"
    end
    
end

#sample_variance(key) ⇒ Object



147
148
149
150
151
152
153
# File 'lib/wads/data_structures.rb', line 147

def sample_variance(key)
    data_set = @data[key]
    return 0 unless data_set
    m = average(key)
    s = data_set.inject(0.0){|accum, i| accum +(i-m)**2 }
    s/(data_set.length - 1).to_f
end

#std_dev(key) ⇒ Object



155
156
157
# File 'lib/wads/data_structures.rb', line 155

def std_dev(key)
    Math.sqrt(sample_variance(key))
end

#sum(key) ⇒ Object



111
112
113
114
115
116
117
118
# File 'lib/wads/data_structures.rb', line 111

def sum(key)
    data_set = @data[key]
    if data_set
        return data_set.inject(0.to_f){|sum,x| sum + x }
    else
        return 0
    end
end