prophet-rb 0.3.0 → 0.4.0

data/lib/prophet/forecaster.rb

@@ -386,6 +386,12 @@ module Prophet
 
     def add_country_holidays(country_name)
       raise Error, "Country holidays must be added prior to model fitting." if @history
+
+      # Fix for previously documented keyword argument
+      if country_name.is_a?(Hash) && country_name[:country_name]
+        country_name = country_name[:country_name]
+      end
+
       # Validate names.
       get_holiday_names(country_name).each do |name|
         # Allow merging with existing holidays
@@ -616,6 +622,10 @@ module Prophet
       end
       raise ArgumentError, "Must be a data frame" unless df.is_a?(Rover::DataFrame)
 
+      unless df.include?("ds") && df.include?("y")
+        raise ArgumentError, "Data frame must have ds and y columns"
+      end
+
       history = df[!df["y"].missing]
       raise Error, "Data has less than 2 non-nil rows" if history.size < 2
 
@@ -961,6 +971,12 @@ module Prophet
       Rover::DataFrame.new({"ds" => dates})
     end
 
+    def to_json
+      require "json"
+
+      JSON.generate(as_json)
+    end
+
     private
 
     # Time is preferred over DateTime in Ruby docs
@@ -1007,5 +1023,189 @@ module Prophet
       u = Numo::DFloat.new(size).rand(-0.5, 0.5)
       loc - scale * u.sign * Numo::NMath.log(1 - 2 * u.abs)
     end
+
+    SIMPLE_ATTRIBUTES = [
+      "growth", "n_changepoints", "specified_changepoints", "changepoint_range",
+      "yearly_seasonality", "weekly_seasonality", "daily_seasonality",
+      "seasonality_mode", "seasonality_prior_scale", "changepoint_prior_scale",
+      "holidays_prior_scale", "mcmc_samples", "interval_width", "uncertainty_samples",
+      "y_scale", "logistic_floor", "country_holidays", "component_modes"
+    ]
+
+    PD_SERIES = ["changepoints", "history_dates", "train_holiday_names"]
+
+    PD_TIMESTAMP = ["start"]
+
+    PD_TIMEDELTA = ["t_scale"]
+
+    PD_DATAFRAME = ["holidays", "history", "train_component_cols"]
+
+    NP_ARRAY = ["changepoints_t"]
+
+    ORDEREDDICT = ["seasonalities", "extra_regressors"]
+
+    def as_json
+      if @history.nil?
+        raise Error, "This can only be used to serialize models that have already been fit."
+      end
+
+      model_dict =
+        SIMPLE_ATTRIBUTES.to_h do |attribute|
+          [attribute, instance_variable_get("@#{attribute}")]
+        end
+
+      # Handle attributes of non-core types
+      PD_SERIES.each do |attribute|
+        if instance_variable_get("@#{attribute}").nil?
+          model_dict[attribute] = nil
+        else
+          v = instance_variable_get("@#{attribute}")
+          d = {
+            "name" => "ds",
+            "index" => v.size.times.to_a,
+            "data" => v.to_a.map { |v| v.iso8601(3) }
+          }
+          model_dict[attribute] = JSON.generate(d)
+        end
+      end
+      PD_TIMESTAMP.each do |attribute|
+        model_dict[attribute] = instance_variable_get("@#{attribute}").to_f
+      end
+      PD_TIMEDELTA.each do |attribute|
+        model_dict[attribute] = instance_variable_get("@#{attribute}").to_f
+      end
+      PD_DATAFRAME.each do |attribute|
+        if instance_variable_get("@#{attribute}").nil?
+          model_dict[attribute] = nil
+        else
+          # use same format as Pandas
+          v = instance_variable_get("@#{attribute}")
+
+          v = v.dup
+          v["ds"] = v["ds"].map { |v| v.iso8601(3) } if v["ds"]
+          v.delete("col")
+
+          fields =
+            v.types.map do |k, t|
+              type =
+                case t
+                when :object
+                  "datetime"
+                when :int64
+                  "integer"
+                else
+                  "number"
+                end
+              {"name" => k, "type" => type}
+            end
+
+          d = {
+            "schema" => {
+              "fields" => fields,
+              "pandas_version" => "0.20.0"
+            },
+            "data" => v.to_a
+          }
+          model_dict[attribute] = JSON.generate(d)
+        end
+      end
+      NP_ARRAY.each do |attribute|
+        model_dict[attribute] = instance_variable_get("@#{attribute}").to_a
+      end
+      ORDEREDDICT.each do |attribute|
+        model_dict[attribute] = [
+          instance_variable_get("@#{attribute}").keys,
+          instance_variable_get("@#{attribute}").transform_keys(&:to_s)
+        ]
+      end
+      # Other attributes with special handling
+      # fit_kwargs -> Transform any numpy types before serializing.
+      # They do not need to be transformed back on deserializing.
+      # TODO deep copy
+      fit_kwargs = @fit_kwargs.to_h { |k, v| [k.to_s, v.dup] }
+      if fit_kwargs.key?("init")
+        fit_kwargs["init"].each do |k, v|
+          if v.is_a?(Numo::NArray)
+            fit_kwargs["init"][k] = v.to_a
+          # elsif v.is_a?(Float)
+          #   fit_kwargs["init"][k] = v.to_f
+          end
+        end
+      end
+      model_dict["fit_kwargs"] = fit_kwargs
+
+      # Params (Dict[str, np.ndarray])
+      model_dict["params"] = params.transform_values(&:to_a)
+      # Attributes that are skipped: stan_fit, stan_backend
+      # Returns 1.0 for Prophet 1.1
+      model_dict["__prophet_version"] = "1.0"
+      model_dict
+    end
+
+    def self.from_json(model_json)
+      require "json"
+
+      model_dict = JSON.parse(model_json)
+
+      # We will overwrite all attributes set in init anyway
+      model = Prophet.new
+      # Simple types
+      SIMPLE_ATTRIBUTES.each do |attribute|
+        model.instance_variable_set("@#{attribute}", model_dict.fetch(attribute))
+      end
+      PD_SERIES.each do |attribute|
+        if model_dict[attribute].nil?
+          model.instance_variable_set("@#{attribute}", nil)
+        else
+          d = JSON.parse(model_dict.fetch(attribute))
+          s = Rover::Vector.new(d["data"])
+          if d["name"] == "ds"
+            s = s.map { |v| Time.parse(v).utc }
+          end
+          model.instance_variable_set("@#{attribute}", s)
+        end
+      end
+      PD_TIMESTAMP.each do |attribute|
+        model.instance_variable_set("@#{attribute}", Time.at(model_dict.fetch(attribute)))
+      end
+      PD_TIMEDELTA.each do |attribute|
+        model.instance_variable_set("@#{attribute}", model_dict.fetch(attribute).to_f)
+      end
+      PD_DATAFRAME.each do |attribute|
+        if model_dict[attribute].nil?
+          model.instance_variable_set("@#{attribute}", nil)
+        else
+          d = JSON.parse(model_dict.fetch(attribute))
+          df = Rover::DataFrame.new(d["data"])
+          df["ds"] = df["ds"].map { |v| Time.parse(v).utc } if df["ds"]
+          if attribute == "train_component_cols"
+            # Special handling because of named index column
+            # df.columns.name = 'component'
+            # df.index.name = 'col'
+          end
+          model.instance_variable_set("@#{attribute}", df)
+        end
+      end
+      NP_ARRAY.each do |attribute|
+        model.instance_variable_set("@#{attribute}", Numo::NArray.cast(model_dict.fetch(attribute)))
+      end
+      ORDEREDDICT.each do |attribute|
+        key_list, unordered_dict = model_dict.fetch(attribute)
+        od = {}
+        key_list.each do |key|
+          od[key] = unordered_dict[key].transform_keys(&:to_sym)
+        end
+        model.instance_variable_set("@#{attribute}", od)
+      end
+      # Other attributes with special handling
+      # fit_kwargs
+      model.instance_variable_set(:@fit_kwargs, model_dict["fit_kwargs"].transform_keys(&:to_sym))
+      # Params (Dict[str, np.ndarray])
+      model.instance_variable_set(:@params, model_dict["params"].transform_values { |v| Numo::NArray.cast(v) })
+      # Skipped attributes
+      # model.stan_backend = nil
+      model.instance_variable_set(:@stan_fit, nil)
+      model
+    end
   end
 end

data/lib/prophet/holidays.rb

@@ -2,25 +2,21 @@ module Prophet
   module Holidays
     def get_holiday_names(country)
       years = (1995..2045).to_a
-      make_holidays_df(years, country)["holiday"].uniq
+      holiday_names = make_holidays_df(years, country)["holiday"].uniq
+      # TODO raise error in 0.4.0
+      logger.warn "Holidays in #{country} are not currently supported"
+      holiday_names
     end
 
     def make_holidays_df(year_list, country)
       holidays_df[(holidays_df["country"] == country) & (holidays_df["year"].in?(year_list))][["ds", "holiday"]]
     end
 
-    # TODO marshal on installation
+    # TODO improve performance
     def holidays_df
       @holidays_df ||= begin
-        holidays = {"ds" => [], "holiday" => [], "country" => [], "year" => []}
         holidays_file = File.expand_path("../../data-raw/generated_holidays.csv", __dir__)
-        CSV.foreach(holidays_file, headers: true, converters: [:date, :numeric]) do |row|
-          holidays["ds"] << row["ds"]
-          holidays["holiday"] << row["holiday"]
-          holidays["country"] << row["country"]
-          holidays["year"] << row["year"]
-        end
-        Rover::DataFrame.new(holidays)
+        Rover.read_csv(holidays_file, converters: [:date, :numeric])
       end
     end
   end

data/lib/prophet/stan_backend.rb

@@ -6,7 +6,7 @@ module Prophet
     end
 
     def load_model
-      model_file = File.expand_path("../../vendor/prophet-#{platform}/bin/prophet", __dir__)
+      model_file = File.expand_path("../../vendor/#{platform}/bin/prophet", __dir__)
       raise Error, "Platform not supported yet" unless File.exist?(model_file)
       CmdStan::Model.new(exe_file: model_file)
     end
@@ -139,15 +139,15 @@ module Prophet
         "windows"
       elsif RbConfig::CONFIG["host_os"] =~ /darwin/i
         if RbConfig::CONFIG["host_cpu"] =~ /arm|aarch64/i
-          "mac-arm"
+          "arm64-darwin"
         else
-          "mac"
+          "x86_64-darwin"
         end
       else
         if RbConfig::CONFIG["host_cpu"] =~ /arm|aarch64/i
-          "linux-arm"
+          "aarch64-linux"
         else
-          "linux"
+          "x86_64-linux"
         end
       end
     end

data/lib/prophet/version.rb

@@ -1,3 +1,3 @@
 module Prophet
-  VERSION = "0.3.0"
+  VERSION = "0.4.0"
 end

data/lib/prophet.rb

@@ -21,9 +21,12 @@ module Prophet
     Forecaster.new(**kwargs)
   end
 
-  def self.forecast(series, count: 10)
+  def self.forecast(series, count: 10, country_holidays: nil, cap: nil, verbose: false, **options)
     raise ArgumentError, "Series must have at least 10 data points" if series.size < 10
 
+    # error early on unknown keywords
+    m = Prophet.new(**options)
+
     # check type to determine output format
     # check for before converting to time
     keys = series.keys
@@ -62,12 +65,14 @@ module Prophet
 
     # use series, not times, so dates are handled correctly
     df = Rover::DataFrame.new({"ds" => series.keys, "y" => series.values})
+    df["cap"] = cap if cap
 
-    m = Prophet.new
-    m.logger.level = ::Logger::FATAL # no logging
+    m.logger.level = ::Logger::FATAL unless verbose
+    m.add_country_holidays(country_holidays) if country_holidays
     m.fit(df)
 
     future = m.make_future_dataframe(periods: count, include_history: false, freq: freq)
+    future["cap"] = cap if cap
     forecast = m.predict(future)
     result = forecast[["ds", "yhat"]].to_a
 
@@ -84,13 +89,23 @@ module Prophet
     result.map { |v| [v["ds"], v["yhat"]] }.to_h
   end
 
-  def self.anomalies(series)
-    df = Rover::DataFrame.new(series.map { |k, v| {"ds" => k, "y" => v} })
-    m = Prophet.new(interval_width: 0.99)
-    m.logger.level = ::Logger::FATAL # no logging
+  # TODO better name for interval_width
+  # TODO DRY with forecast method
+  def self.anomalies(series, interval_width: 0.99, country_holidays: nil, cap: nil, verbose: false, **options)
+    df = Rover::DataFrame.new({"ds" => series.keys, "y" => series.values})
+    df["cap"] = cap if cap
+
+    m = Prophet.new(interval_width: interval_width, **options)
+    m.logger.level = ::Logger::FATAL unless verbose
+    m.add_country_holidays(country_holidays) if country_holidays
     m.fit(df)
+
     forecast = m.predict(df)
     # filter df["ds"] to ensure dates/times in same format as input
     df["ds"][(df["y"] < forecast["yhat_lower"]) | (df["y"] > forecast["yhat_upper"])].to_a
   end
+
+  def self.from_json(model_json)
+    Forecaster.from_json(model_json)
+  end
 end

data/stan/{unix/prophet.stan → prophet.stan}

@@ -101,8 +101,9 @@ data {
 }
 
 transformed data {
-  matrix[T, S] A;
-  A = get_changepoint_matrix(t, t_change, T, S);
+  matrix[T, S] A = get_changepoint_matrix(t, t_change, T, S);
+  matrix[T, K] X_sa = X .* rep_matrix(s_a', T);
+  matrix[T, K] X_sm = X .* rep_matrix(s_m', T);
 }
 
 parameters {
@@ -133,10 +134,10 @@ model {
   beta ~ normal(0, sigmas);
 
   // Likelihood
-  y ~ normal(
-  trend
-  .* (1 + X * (beta .* s_m))
-  + X * (beta .* s_a),
-  sigma_obs
+  y ~ normal_id_glm(
+    X_sa,
+    trend .* (1 + X_sm * beta),
+    beta,
+    sigma_obs
   );
 }

data/vendor/aarch64-linux/licenses/sundials-license.txt

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2002-2022, Lawrence Livermore National Security and Southern Methodist University.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/vendor/aarch64-linux/licenses/sundials-notice.txt

@@ -0,0 +1,21 @@
+This work was produced under the auspices of the U.S. Department of
+Energy by Lawrence Livermore National Laboratory under Contract
+DE-AC52-07NA27344.
+
+This work was prepared as an account of work sponsored by an agency of
+the United States Government. Neither the United States Government nor
+Lawrence Livermore National Security, LLC, nor any of their employees
+makes any warranty, expressed or implied, or assumes any legal liability
+or responsibility for the accuracy, completeness, or usefulness of any
+information, apparatus, product, or process disclosed, or represents that
+its use would not infringe privately owned rights.
+
+Reference herein to any specific commercial product, process, or service
+by trade name, trademark, manufacturer, or otherwise does not necessarily
+constitute or imply its endorsement, recommendation, or favoring by the
+United States Government or Lawrence Livermore National Security, LLC.
+
+The views and opinions of authors expressed herein do not necessarily
+state or reflect those of the United States Government or Lawrence
+Livermore National Security, LLC, and shall not be used for advertising
+or product endorsement purposes.

data/vendor/arm64-darwin/licenses/sundials-license.txt

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2002-2022, Lawrence Livermore National Security and Southern Methodist University.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/vendor/arm64-darwin/licenses/sundials-notice.txt

@@ -0,0 +1,21 @@
+This work was produced under the auspices of the U.S. Department of
+Energy by Lawrence Livermore National Laboratory under Contract
+DE-AC52-07NA27344.
+
+This work was prepared as an account of work sponsored by an agency of
+the United States Government. Neither the United States Government nor
+Lawrence Livermore National Security, LLC, nor any of their employees
+makes any warranty, expressed or implied, or assumes any legal liability
+or responsibility for the accuracy, completeness, or usefulness of any
+information, apparatus, product, or process disclosed, or represents that
+its use would not infringe privately owned rights.
+
+Reference herein to any specific commercial product, process, or service
+by trade name, trademark, manufacturer, or otherwise does not necessarily
+constitute or imply its endorsement, recommendation, or favoring by the
+United States Government or Lawrence Livermore National Security, LLC.
+
+The views and opinions of authors expressed herein do not necessarily
+state or reflect those of the United States Government or Lawrence
+Livermore National Security, LLC, and shall not be used for advertising
+or product endorsement purposes.

data/vendor/x86_64-darwin/licenses/sundials-license.txt

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2002-2022, Lawrence Livermore National Security and Southern Methodist University.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.