Module: Prophet::Diagnostics

Defined in:
lib/prophet/diagnostics.rb

Class Method Summary collapse

Class Method Details

.coverage(df, w) ⇒ Object 



341
342
343
344
345
346
347
 
# File 'lib/prophet/diagnostics.rb', line 341

def self.coverage(df, w)
  is_covered = (df["y"] >= df["yhat_lower"]) & (df["y"] <= df["yhat_upper"])
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "coverage" => is_covered})
  end
  rolling_mean_by_h(is_covered.to(:float), df["horizon"], w, "coverage")
end

.cross_validation(model, horizon:, period: nil, initial: nil, cutoffs: nil) ⇒ Object 



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
59
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
 
# File 'lib/prophet/diagnostics.rb', line 31

def self.cross_validation(model, horizon:, period: nil, initial: nil, cutoffs: nil)
  if model.history.nil?
    raise Error, "Model has not been fit. Fitting the model provides contextual parameters for cross validation."
  end

  df = model.history.dup
  horizon = timedelta(horizon)

  predict_columns = ["ds", "yhat"]
  if model.uncertainty_samples
    predict_columns.concat(["yhat_lower", "yhat_upper"])
  end

  # Identify largest seasonality period
  period_max = 0.0
  model.seasonalities.each do |_, s|
    period_max = [period_max, s[:period]].max
  end
  seasonality_dt = timedelta("#{period_max} days")

  if cutoffs.nil?
    # Set period
    period = period.nil? ? 0.5 * horizon : timedelta(period)

    # Set initial
    initial = initial.nil? ? [3 * horizon, seasonality_dt].max : timedelta(initial)

    # Compute Cutoffs
    cutoffs = generate_cutoffs(df, horizon, initial, period)
  else
    # add validation of the cutoff to make sure that the min cutoff is strictly greater than the min date in the history
    if cutoffs.min <= df["ds"].min
      raise Error, "Minimum cutoff value is not strictly greater than min date in history"
    end
    # max value of cutoffs is <= (end date minus horizon)
    end_date_minus_horizon = df["ds"].max - horizon
    if cutoffs.max > end_date_minus_horizon
      raise Error, "Maximum cutoff value is greater than end date minus horizon, no value for cross-validation remaining"
    end
    initial = cutoffs[0] - df["ds"].min
  end

  # Check if the initial window
  # (that is, the amount of time between the start of the history and the first cutoff)
  # is less than the maximum seasonality period
  if initial < seasonality_dt
    msg = "Seasonality has period of #{period_max} days "
    msg += "which is larger than initial window. "
    msg += "Consider increasing initial."
    # logger.warn(msg)
  end

  predicts = cutoffs.map { |cutoff| single_cutoff_forecast(df, model, cutoff, horizon, predict_columns) }

  # Combine all predicted DataFrame into one DataFrame
  predicts.reduce(Rover::DataFrame.new) { |memo, v| memo.concat(v) }
end

.deepcopy(value) ⇒ Object 



167
168
169
170
171
172
173
174
175
 
# File 'lib/prophet/diagnostics.rb', line 167

def self.deepcopy(value)
  if value.is_a?(Hash)
    value.to_h { |k, v| [deepcopy(k), deepcopy(v)] }
  elsif value.is_a?(Array)
    value.map { |v| deepcopy(v) }
  else
    value.dup
  end
end

.generate_cutoffs(df, horizon, initial, period) ⇒ Object 



3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
 
# File 'lib/prophet/diagnostics.rb', line 3

def self.generate_cutoffs(df, horizon, initial, period)
  # Last cutoff is 'latest date in data - horizon' date
  cutoff = df["ds"].max - horizon
  if cutoff < df["ds"].min
    raise Error, "Less data than horizon."
  end
  result = [cutoff]
  while result[-1] >= df["ds"].min + initial
    cutoff -= period
    # If data does not exist in data range (cutoff, cutoff + horizon]
    if !(((df["ds"] > cutoff) & (df["ds"] <= cutoff + horizon)).any?)
      # Next cutoff point is 'last date before cutoff in data - horizon'
      if cutoff > df["ds"].min
        closest_date = df[df["ds"] <= cutoff].max["ds"]
        cutoff = closest_date - horizon
      end
      # else no data left, leave cutoff as is, it will be dropped.
    end
    result << cutoff
  end
  result = result[0...-1]
  if result.length == 0
    raise Error, "Less data than horizon after initial window. Make horizon or initial shorter."
  end
  # logger.info("Making #{result.length} forecasts with cutoffs between #{result[-1]} and #{result[0]}")
  result.reverse
end

.mae(df, w) ⇒ Object 



309
310
311
312
313
314
315
 
# File 'lib/prophet/diagnostics.rb', line 309

def self.mae(df, w)
  ae = (df["y"] - df["yhat"]).abs
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "mae" => ae})
  end
  rolling_mean_by_h(ae, df["horizon"], w, "mae")
end

.mape(df, w) ⇒ Object 



317
318
319
320
321
322
323
 
# File 'lib/prophet/diagnostics.rb', line 317

def self.mape(df, w)
  ape = ((df["y"] - df["yhat"]) / df["y"]).abs
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "mape" => ape})
  end
  rolling_mean_by_h(ape, df["horizon"], w, "mape")
end

.mdape(df, w) ⇒ Object 



325
326
327
328
329
330
331
 
# File 'lib/prophet/diagnostics.rb', line 325

def self.mdape(df, w)
  ape = ((df["y"] - df["yhat"]) / df["y"]).abs
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "mdape" => ape})
  end
  rolling_median_by_h(ape, df["horizon"], w, "mdape")
end

.mse(df, w) ⇒ Object 



295
296
297
298
299
300
301
 
# File 'lib/prophet/diagnostics.rb', line 295

def self.mse(df, w)
  se = (df["y"] - df["yhat"]) ** 2
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "mse" => se})
  end
  rolling_mean_by_h(se, df["horizon"], w, "mse")
end

.performance_metrics(df, metrics: nil, rolling_window: 0.1, monthly: false) ⇒ Object 



177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/prophet/diagnostics.rb', line 177

def self.performance_metrics(df, metrics: nil, rolling_window: 0.1, monthly: false)
  valid_metrics = ["mse", "rmse", "mae", "mape", "mdape", "smape", "coverage"]
  if metrics.nil?
    metrics = valid_metrics
  end
  if (!df.include?("yhat_lower") || !df.include?("yhat_upper")) && metrics.include?("coverage")
    metrics.delete("coverage")
  end
  if metrics.uniq.length != metrics.length
    raise ArgumentError, "Input metrics must be a list of unique values"
  end
  if !Set.new(metrics).subset?(Set.new(valid_metrics))
    raise ArgumentError, "Valid values for metrics are: #{valid_metrics}"
  end
  df_m = df.dup
  if monthly
    raise Error, "Not implemented yet"
    # df_m["horizon"] = df_m["ds"].dt.to_period("M").astype(int) - df_m["cutoff"].dt.to_period("M").astype(int)
  else
    df_m["horizon"] = df_m["ds"] - df_m["cutoff"]
  end
  df_m.sort_by! { |r| r["horizon"] }
  if metrics.include?("mape") && df_m["y"].abs.min < 1e-8
    # logger.info("Skipping MAPE because y close to 0")
    metrics.delete("mape")
  end
  if metrics.length == 0
    return nil
  end
  w = (rolling_window * df_m.shape[0]).to_i
  if w >= 0
    w = [w, 1].max
    w = [w, df_m.shape[0]].min
  end
  # Compute all metrics
  dfs = {}
  metrics.each do |metric|
    dfs[metric] = send(metric, df_m, w)
  end
  res = dfs[metrics[0]]
  metrics.each do |metric|
    res_m = dfs[metric]
    res[metric] = res_m[metric]
  end
  res
end

.prophet_copy(m, cutoff = nil) ⇒ Object 



115
116
117
118
119
120
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
 
# File 'lib/prophet/diagnostics.rb', line 115

def self.prophet_copy(m, cutoff = nil)
  if m.history.nil?
    raise Error, "This is for copying a fitted Prophet object."
  end

  if m.specified_changepoints
    changepoints = m.changepoints
    if !cutoff.nil?
      # Filter change points '< cutoff'
      last_history_date = m.history["ds"][m.history["ds"] <= cutoff].max
      changepoints = changepoints[changepoints < last_history_date]
    end
  else
    changepoints = nil
  end

  # Auto seasonalities are set to False because they are already set in
  # m.seasonalities.
  m2 = m.class.new(
    growth: m.growth,
    n_changepoints: m.n_changepoints,
    changepoint_range: m.changepoint_range,
    changepoints: changepoints,
    yearly_seasonality: false,
    weekly_seasonality: false,
    daily_seasonality: false,
    holidays: m.holidays,
    seasonality_mode: m.seasonality_mode,
    seasonality_prior_scale: m.seasonality_prior_scale,
    changepoint_prior_scale: m.changepoint_prior_scale,
    holidays_prior_scale: m.holidays_prior_scale,
    mcmc_samples: m.mcmc_samples,
    interval_width: m.interval_width,
    uncertainty_samples: m.uncertainty_samples
  )
  m2.extra_regressors = deepcopy(m.extra_regressors)
  m2.seasonalities = deepcopy(m.seasonalities)
  m2.country_holidays = deepcopy(m.country_holidays)
  m2
end

.rmse(df, w) ⇒ Object 



303
304
305
306
307
 
# File 'lib/prophet/diagnostics.rb', line 303

def self.rmse(df, w)
  res = mse(df, w)
  res["rmse"] = res.delete("mse").map { |v| Math.sqrt(v) }
  res
end

.rolling_mean_by_h(x, h, w, name) ⇒ Object 



224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
 
# File 'lib/prophet/diagnostics.rb', line 224

def self.rolling_mean_by_h(x, h, w, name)
  # Aggregate over h
  df = Rover::DataFrame.new({"x" => x, "h" => h})
  df2 = df.group("h").sum("x").inner_join(df.group("h").count).sort_by { |r| r["h"] }
  xs = df2["sum_x"]
  ns = df2["count"]
  hs = df2["h"]

  trailing_i = df2.length - 1
  x_sum = 0
  n_sum = 0
  # We don't know output size but it is bounded by len(df2)
  res_x = [nil] * df2.length

  # Start from the right and work backwards
  (df2.length - 1).downto(0) do |i|
    x_sum += xs[i]
    n_sum += ns[i]
    while n_sum >= w
      # Include points from the previous horizon. All of them if still
      # less than w, otherwise weight the mean by the difference
      excess_n = n_sum - w
      excess_x = excess_n * xs[i] / ns[i]
      res_x[trailing_i] = (x_sum - excess_x) / w
      x_sum -= xs[trailing_i]
      n_sum -= ns[trailing_i]
      trailing_i -= 1
    end
  end

  res_h = hs[(trailing_i + 1)..-1]
  res_x = res_x[(trailing_i + 1)..-1]

  Rover::DataFrame.new({"horizon" => res_h, name => res_x})
end

.rolling_median_by_h(x, h, w, name) ⇒ Object 



260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
 
# File 'lib/prophet/diagnostics.rb', line 260

def self.rolling_median_by_h(x, h, w, name)
  # Aggregate over h
  df = Rover::DataFrame.new({"x" => x, "h" => h})
  grouped = df.group("h")
  df2 = grouped.count.sort_by { |r| r["h"] }
  hs = df2["h"]

  res_h = []
  res_x = []
  # Start from the right and work backwards
  i = hs.length - 1
  while i >= 0
    h_i = hs[i]
    xs = df[df["h"] == h_i]["x"].to_a

    next_idx_to_add = (h == h_i).to_numo.cast_to(Numo::UInt8).argmax - 1
    while xs.length < w && next_idx_to_add >= 0
      # Include points from the previous horizon. All of them if still
      # less than w, otherwise just enough to get to w.
      xs << x[next_idx_to_add]
      next_idx_to_add -= 1
    end
    if xs.length < w
      # Ran out of points before getting enough.
      break
    end
    res_h << hs[i]
    res_x << Rover::Vector.new(xs).median
    i -= 1
  end
  res_h.reverse!
  res_x.reverse!
  Rover::DataFrame.new({"horizon" => res_h, name => res_x})
end

.single_cutoff_forecast(df, model, cutoff, horizon, predict_columns) ⇒ Object 



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
 
# File 'lib/prophet/diagnostics.rb', line 89

def self.single_cutoff_forecast(df, model, cutoff, horizon, predict_columns)
  # Generate new object with copying fitting options
  m = prophet_copy(model, cutoff)
  # Train model
  history_c = df[df["ds"] <= cutoff]
  if history_c.shape[0] < 2
    raise Error, "Less than two datapoints before cutoff. Increase initial window."
  end
  m.fit(history_c, **model.fit_kwargs)
  # Calculate yhat
  index_predicted = (df["ds"] > cutoff) & (df["ds"] <= cutoff + horizon)
  # Get the columns for the future dataframe
  columns = ["ds"]
  if m.growth == "logistic"
    columns << "cap"
    if m.logistic_floor
      columns << "floor"
    end
  end
  columns.concat(m.extra_regressors.keys)
  columns.concat(m.seasonalities.map { |_, props| props[:condition_name] }.compact)
  yhat = m.predict(df[index_predicted][columns])
  # Merge yhat(predicts), y(df, original data) and cutoff
  yhat[predict_columns].merge(df[index_predicted][["y"]]).merge(Rover::DataFrame.new({"cutoff" => [cutoff] * yhat.length}))
end

.smape(df, w) ⇒ Object 



333
334
335
336
337
338
339
 
# File 'lib/prophet/diagnostics.rb', line 333

def self.smape(df, w)
  sape = (df["y"] - df["yhat"]).abs / ((df["y"].abs + df["yhat"].abs) / 2)
  if w < 0
    return Rover::DataFrame.new({"horizon" => df["horizon"], "smape" => sape})
  end
  rolling_mean_by_h(sape, df["horizon"], w, "smape")
end

.timedelta(value) ⇒ Object 



156
157
158
159
160
161
162
163
164
165
 
# File 'lib/prophet/diagnostics.rb', line 156

def self.timedelta(value)
  if value.is_a?(Numeric)
    # ActiveSupport::Duration is a numeric
    value
  elsif (m = /\A(\d+(\.\d+)?) days\z/.match(value))
    m[1].to_f * 86400
  else
    raise Error, "Unknown time delta"
  end
end