Merge pull request #48 from mkyl/kbd-flexible-deg-stats

Experiments/Experiments.jl

@@ -7,6 +7,7 @@ using CSV, DataFrames
 using Parquet2: Dataset
 using DelimitedFiles: writedlm
 using BenchmarkTools
+using Random
 
 include("../Source/CardinalityWithColors.jl")
 include("utils.jl")

Experiments/Scripts/coloring_methods.jl

@@ -2,7 +2,7 @@
 using Profile
 include("../Experiments.jl")
 
-datasets = [hprd]
+datasets = [aids]
 partitioning_schemes = [
                         [(Degree, 64)],
                         [(NeighborNodeLabels, 64)],
@@ -11,15 +11,15 @@ partitioning_schemes = [
                         [(Hash, 64)],
                         [(Degree, 8), (QuasiStable, 32), (NeighborNodeLabels, 24)],
                         [(Degree, 8), (NeighborNodeLabels, 24), (QuasiStable, 32)]]
-
+partitioning_schemes = [[(QuasiStable, 64)]]
 experiment_params = Vector{ExperimentParams}()
 for dataset in datasets
     for scheme in partitioning_schemes
             push!(experiment_params, ExperimentParams(dataset=dataset, partitioning_scheme=scheme))
     end
 end
 
-build_experiments(experiment_params)
+#build_experiments(experiment_params)
 
 run_estimation_experiments(experiment_params)
 

Experiments/Scripts/memory_exps.jl

@@ -9,12 +9,12 @@ experiment_params = Vector{ExperimentParams}()
 build_params = Vector{ExperimentParams}()
 for dataset in datasets
     for n in num_colors
-        push!(build_params, ExperimentParams(dataset=dataset, num_colors=n))
+        push!(build_params, ExperimentParams(dataset=dataset, partitioning_scheme=[(QuasiStable, n)]))
     end
 end
 build_experiments(build_params)
 
 graph_grouped_bar_plot(build_params; grouping=number_of_colors,
                                           y_type=memory_footprint,
                                           y_lims=[0, 16],
-                                          filename="memory_size_vs_colors_fp32_int16")
+                                          filename="memory_size_vs_colors_fp32_int16_2")

Experiments/Scripts/update_experiments.jl

@@ -1,15 +1,13 @@
-using Plots.PlotMeasures
-using Graphs
 include("../Experiments.jl")
 
-# datasets::Vector{DATASET} = [wordnet]
-datasets::Vector{DATASET} = [aids, human, yeast, wordnet, youtube, dblp, patents]
+ datasets::Vector{DATASET} = [wordnet]
+# datasets::Vector{DATASET} = [aids, human, yeast, wordnet, youtube, dblp, patents]
 # datasets::Vector{DATASET} = [aids, human, lubm80, yeast, hprd, wordnet, dblp, youtube, eu2005, patents]
 max_cycles = 6
-proportions_not_updated = [0, 0.2, 0.4, 0.6, 0.8, 1]
+proportions_not_updated = [0.05, 0.2, 0.4, 0.6, 0.8, 1]
 
-experiment_params_list::Vector{ExperimentParams} = [ExperimentParams(dataset=current_dataset, partitioner=QuasiStable, max_cycle_size=current_cycle, proportion_not_updated=current_proportion) 
-                                                    for current_dataset in datasets for current_cycle in 2:max_cycles for current_proportion in proportions_not_updated]
+experiment_params_list::Vector{ExperimentParams} = [ExperimentParams(dataset=current_dataset, max_cycle_size=current_cycle, proportion_not_updated=current_proportion)
+                                                    for current_dataset in datasets for current_cycle in 6:max_cycles for current_proportion in proportions_not_updated]
 println("started building")
 build_experiments(experiment_params_list)
 println("started estimating")
@@ -18,4 +16,4 @@ println("started graphing")
 # compare how overall accuracy is affected by summary updates
 graph_grouped_box_plot(experiment_params_list, x_type=dataset, y_type=estimate_error, grouping=proportion_not_updated, filename="overall-accuracy-and-updates")
 # compare how cycle stat accuracies are affected by summary updates
-graph_grouped_box_plot(experiment_params_list, x_type=proportion_not_updated, y_type=estimate_error, grouping=cycle_size, filename="cycle-stats-and-updates")
+graph_grouped_box_plot(experiment_params_list, x_type=proportion_not_updated, y_type=estimate_error, grouping=cycle_size, filename="cycle-stats-and-updates")

Experiments/graph_results.jl

@@ -1,4 +1,4 @@
-@enum GROUP dataset technique cycle_size summary_paths inference_paths query_type sampling_type cycle_stats number_of_colors build_phase proportion_not_updated proportion_deleted
+@enum GROUP dataset technique cycle_size summary_paths inference_paths query_type sampling_type cycle_stats number_of_colors build_phase proportion_not_updated proportion_deleted deg_stat_type
 
 @enum VALUE estimate_error runtime build_time memory_footprint
 
@@ -247,6 +247,8 @@ function get_value_from_param(experiment_param::ExperimentParams, value_type::GR
         return experiment_param.summary_params.proportion_not_updated
     elseif value_type == proportion_deleted
         return experiment_param.summary_params.proportion_deleted
+    elseif value_type == deg_stat_type
+        return experiment_param.summary_params.deg_stats_type
     else
         # default to grouping by technique
         return experiment_param.summary_params.partitioning_scheme

Experiments/run_estimators.jl

@@ -6,7 +6,7 @@ function run_estimation_experiments(experiment_params_list::Vector{ExperimentPar
         !isfile(summary_file_location) && error("The summary has not been built yet! \n Attempted File Location: $(summary_file_location)")
         summary::ColorSummary = deserialize(summary_file_location)
         experiment_results = []
-        push!(experiment_results, ("UpperBound", "Estimate", "LowerBound", "TrueCard", "EstimationTime", "QueryType", "QueryPath"))
+        push!(experiment_results, ("Estimate", "TrueCard", "EstimationTime", "QueryType", "QueryPath"))
         for i in 1:length(all_queries[dataset])
             query::QueryGraph = all_queries[dataset][i].query
             query_path = all_queries[dataset][i].query_path
@@ -17,12 +17,9 @@ function run_estimation_experiments(experiment_params_list::Vector{ExperimentPar
                                     sampling_strategy=experiment_params.sampling_strategy,
                                     only_shortest_path_cycle= experiment_params.only_shortest_path_cycle)) for _ in 1:3]
             estimate_time = median([x.time for x in  estimate_results]) # Convert back to seconds from nano seconds
-            bounds = estimate_results[1].value
-            upper_bound = bounds[3]
-            estimate = max(1, bounds[2])
-            lower_bound = bounds[1]
+            estimate = max(1, estimate_results[1].value)
             query_type = all_queries[dataset][i].query_type
-            push!(experiment_results, (upper_bound, estimate, lower_bound, exact_size, estimate_time, query_type, query_path))
+            push!(experiment_results, (estimate, exact_size, estimate_time, query_type, query_path))
         end
         results_file_location = "Experiments/Results/Estimation_"  * params_to_results_filename(experiment_params)
         writedlm(results_file_location, experiment_results, ",")

Project.toml

@@ -16,6 +16,7 @@ Parquet2 = "98572fba-bba0-415d-956f-fa77e587d26d"
 Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 Probably = "2172800d-0309-5a57-a84f-d50c94757422"
 QuasiStableColors = "9c3856af-3e7c-4d34-a6af-a406867b22e4"
+Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 StatsPlots = "f3b207a7-027a-5e70-b257-86293d7955fd"

Source/CardinalityWithColors.jl

@@ -8,55 +8,74 @@ QSC = QuasiStableColors
 using Graphs: SimpleDiGraphFromIterator, Edge, DiGraph, edges, nv, ne, add_edge!,
                 add_vertex!, vertices, all_neighbors, src, dst, outneighbors, inneighbors
 
-
 BoolPath = Vector{Bool}
 NodeId = Int
 Color = Int16
 StartEndColorPair = Tuple{Color, Color}
-abstract type Comparable end
-import Base .==
-function ==(a::T, b::T) where T <: Comparable
-    (a.path == b.path) && (a.colors == b.colors)
-end
 @auto_hash_equals mutable struct CyclePathAndColors
     path::BoolPath
     colors::StartEndColorPair
 end
 
-@enum PARTITIONER QuasiStable Hash Degree DirectedDegree SimpleLabel InOut LabelInOut NeighborEdges MostNeighbors NeighborNodeLabels
+@enum PARTITIONER QuasiStable Hash Degree NeighborNodeLabels
+
+function partitioner_to_string(x::PARTITIONER)
+    return if x == QuasiStable
+        "QS"
+    elseif x == Hash
+        "H"
+    elseif x == Degree
+        "D"
+    elseif x == NeighborNodeLabels
+        "NNL"
+    end
+end
+
+PartitioningScheme = Vector{Tuple{PARTITIONER, Int}}
 
+function Base.show(io::IO, x::Vector{Tuple{PARTITIONER, Int}})
+    output = "["
+    prefix = ""
+    for (p, n) in x
+        output*= prefix * partitioner_to_string(p) * ":" * string(n)
+        prefix = ";"
+    end
+    output *= "]"
+    show(io, output)
+end
 
 struct ColorSummaryParams
+    deg_stats_type::Type
     num_colors::Int
     max_cycle_size::Int
     max_partial_paths::Int
-    partitioning_scheme::Vector{Tuple{PARTITIONER, Int}}
+    partitioning_scheme::PartitioningScheme
     weighting::Bool
     proportion_not_updated::Float16
     proportion_deleted::Float16
 
-    function ColorSummaryParams(;max_cycle_size=4, max_partial_paths=1000,
-        partitioning_scheme::Vector{Tuple{PARTITIONER, Int}} = [(QuasiStable, 64)], weighting=true, proportion_not_updated = 1.0, proportion_deleted=0.0)
+    function ColorSummaryParams(;deg_stats_type = AvgDegStats, max_cycle_size=4, max_partial_paths=1000,
+        partitioning_scheme::PartitioningScheme = [(QuasiStable, 64)], weighting=true, proportion_not_updated = 1.0, proportion_deleted=0.0)
         num_colors = sum([x[2] for x in partitioning_scheme])
-        return new(num_colors, max_cycle_size, max_partial_paths, partitioning_scheme, weighting, proportion_not_updated, proportion_deleted)
+        return new(deg_stats_type, num_colors, max_cycle_size, max_partial_paths, partitioning_scheme, weighting, proportion_not_updated, proportion_deleted)
     end
 end
 
 function params_to_string(params::ColorSummaryParams)
-    summary_name = "ColorSummary_" * string(params.partitioning_scheme) * "_"
+    summary_name = "ColorSummary_" * string(params.deg_stats_type) * "_"
+    summary_name *= string(params.partitioning_scheme) * "_"
     summary_name *= string(params.max_cycle_size) * "_"
     summary_name *= string(params.max_partial_paths)* "_"
     summary_name *= string(params.proportion_not_updated) * "_"
     summary_name *= string(params.proportion_deleted)
     return summary_name
 end
 
-
-
 include("PropertyGraph.jl")
 include("datasets.jl")
 include("utils.jl")
 include("ExactSizeCalculator.jl")
 include("ColoringMethods.jl")
+include("DegreeStats.jl")
 include("ColorSummary.jl")
 include("QuasiStableCardinalityEstimator.jl")