Created
June 19, 2018 06:26
-
-
Save jinliangwei/a10a2bffc1c4fdfa38acb495ff5c43d4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const K = 100 | |
const num_iterations = 1 | |
const step_size = 0.01 | |
const dim_x = 5000 | |
const dim_y = 5000 | |
const num_elements = 100 | |
struct DenseArrayAccessor{T, N} <: AbstractArray{T, N} | |
key_begin::Int64 | |
values::Vector{T} | |
dims::NTuple{N, Int64} | |
DenseArrayAccessor{T, N}(key_begin::Int64, | |
values::Vector{T}, | |
dims::Vector{Int64}) where {T, N} = new(key_begin, | |
values, | |
tuple(dims...)) | |
end | |
Base.IndexStyle{T<:DenseArrayAccessor}(::Type{T}) = IndexLinear() | |
function Base.size(accessor::DenseArrayAccessor) | |
return accessor.dims | |
end | |
function Base.getindex{T, N}(accessor::DenseArrayAccessor{T, N}, | |
i::Int)::T | |
return accessor.values[i - accessor.key_begin] | |
end | |
function Base.setindex!{T, N}(accessor::DenseArrayAccessor{T, N}, | |
v, i::Int) | |
accessor.values[i - accessor.key_begin] = v | |
end | |
function Base.similar{T}(accessor::DenseArrayAccessor, | |
::Type{T}, dims::Dims) | |
return Array{T, length(dims)}(dims) | |
end | |
struct DenseArray{T, N} <: AbstractArray{T, N} | |
accessor::Nullable{AbstractArray} | |
DenseArray{T, N}(accessor::AbstractArray) where {T, N} = new(accessor) | |
DenseArray{T, N}() where {T, N} = new(Nullable{AbstractArray}()) | |
end | |
Base.IndexStyle{T<:DenseArray}(::Type{T}) = IndexLinear() | |
function Base.size(dist_array::DenseArray) | |
return get(dist_array.accessor).dims | |
end | |
function Base.getindex{T, N}(dist_array::DenseArray{T, N}, | |
I...)::T | |
accessor = get(dist_array.accessor) | |
return getindex(accessor, I...) | |
end | |
function Base.setindex!{T, N}(dist_array::DenseArray{T, N}, | |
v, I...) | |
accessor = get(dist_array.accessor) | |
setindex!(accessor, v, I...) | |
end | |
function Base.similar{T, N}(dist_array::DenseArray{T, N}, | |
::Type{T}, dims::Dims) | |
accessor = get(dist_array.accessor) | |
return similar(accessor, T, dims) | |
end | |
function parse_line() | |
token_tuple = (rand(1:dim_x), | |
rand(1:dim_y), | |
1.0) | |
return token_tuple | |
end | |
function load_data() | |
num_lines::Int64 = 0 | |
ratings = Array{Tuple{Int64, Int64, Float64}}(0) | |
for i = 1:num_elements | |
token_tuple = parse_line() | |
push!(ratings, token_tuple) | |
end | |
return ratings | |
end | |
function get_dimension(ratings::Array{Tuple{Int64, Int64, Float64}}) | |
max_x = 0 | |
max_y = 0 | |
for idx in eachindex(ratings) | |
if ratings[idx][1] > max_x | |
max_x = ratings[idx][1] | |
end | |
if ratings[idx][2] > max_y | |
max_y = ratings[idx][2] | |
end | |
end | |
return max_x + 1, max_y + 1 | |
end | |
println("serial sgd mf starts here!") | |
ratings = load_data() | |
println("load data done!") | |
function train(ratings, step_size, num_iterations) | |
dim_x, dim_y = get_dimension(ratings) | |
println((dim_x, dim_y)) | |
W = DenseArray{Float64, 2}(DenseArrayAccessor{Float64, 2}(0, randn(K * dim_x) ./ 10, [K, dim_x])) | |
H = DenseArray{Float64, 2}(DenseArrayAccessor{Float64, 2}(0, randn(K * dim_y) ./ 10, [K, dim_y])) | |
# W = DenseArrayAccessor{Float64, 2}(0, randn(K * dim_x) ./ 10, [K, dim_x]) | |
# H = DenseArrayAccessor{Float64, 2}(0, randn(K * dim_y) ./ 10, [K, dim_y]) | |
W_grad = zeros(K) | |
H_grad = zeros(K) | |
@time for iteration = 1:num_iterations | |
@time for rating in ratings | |
x_idx = rating[1] + 1 | |
y_idx = rating[2] + 1 | |
rv = rating[3] | |
W_row = @view W[:, x_idx] | |
H_row = @view H[:, y_idx] | |
pred = dot(W_row, H_row) | |
diff = rv - pred | |
@. W_grad = -2 * diff * H_row | |
@. H_grad = -2 * diff * W_row | |
@. W[:, x_idx] = W_row - step_size * W_grad | |
@. H[:, y_idx] = H_row - step_size * H_grad | |
end | |
if iteration % 1 == 0 || | |
iteration == num_iterations | |
println("evaluate model") | |
err = 0.0 | |
for rating in ratings | |
x_idx = rating[1] + 1 | |
y_idx = rating[2] + 1 | |
rv = rating[3] | |
W_row = @view W[:, x_idx] | |
H_row = @view H[:, y_idx] | |
pred = dot(W_row, H_row) | |
err += (rv - pred) ^ 2 | |
end | |
println("iteration = ", iteration, | |
" err = ", err) | |
end | |
end | |
end | |
train(ratings, step_size, num_iterations) | |
@code_warntype train(ratings, step_size, num_iterations) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment