Created
March 4, 2020 11:12
-
-
Save raryo/22c4120bab9f4468d919e8aa0b7c2ad0 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
function main() | |
# input data | |
ui_array, r_array = read_data("./ml-100k/u.data") | |
n_user = length(unique([ui[1] for ui in ui_array])) | |
n_item = length(unique([ui[2] for ui in ui_array])) | |
γ::Float64 = 0.07 | |
λ::Float64 = 0.01 | |
# parameters | |
P, Q = fit(n_user, n_item, ui_array, r_array, 50, 5, γ, λ) | |
end | |
function read_data(file_path) | |
f = open(file_path) | |
data = readlines(f) | |
ui_array::Array{Tuple{Int64,Int64}, 1} = [] | |
r_array::Array{Float64, 1} = [] | |
for l in data | |
u, i, r, ts = [parse(Int, x) for x in split(l, "\t")] | |
append!(ui_array, [(u, i)]) | |
append!(r_array, r) | |
end | |
return ui_array, r_array | |
end | |
function fit(n_user::Int64, | |
n_item::Int64, | |
ui_array::Array{Tuple{Int64,Int64}, 1}, | |
r_array::Array{Float64, 1}, | |
n_itr::Int64, n_fac::Int64, γ::Float64, | |
λ::Float64) ::Tuple{Array{Float64,2},Array{Float64,2}} | |
# init parameters | |
P::Array{Float64,2} = randn(Float64, n_user, n_fac) | |
Q::Array{Float64,2} = randn(Float64, n_item, n_fac) | |
# config traindata | |
train_data = [(u, i, r) for ((u, i), r) in zip(ui_array, r_array)] | |
# optimaize: SGD | |
for itr in 1:n_itr | |
loss = 0 | |
for (u, i, r) in train_data | |
# calc error | |
pu, qi = P[u, :], Q[i, :] | |
e = r - pu ⋅ qi | |
Q[i, :] += γ * (e * pu - λ * qi) | |
P[u, :] += γ * (e * qi - λ * pu) | |
# calc loss | |
loss += e*e + λ * (P[u, :] ⋅ P[u, :] + Q[i, :] ⋅ Q[i, :]) | |
end | |
println("$itr: $loss") | |
end | |
return P, Q | |
end | |
main() |
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
import numpy as np | |
import numba | |
from numba import njit, jit | |
from numba.typed import List | |
import sys | |
class MFEstimator(): | |
def __init__(self, n_user, n_item, n_itr=50, n_fac=5, γ=0.07, λ=0.01, met='RMSE'): | |
self.n_user = n_user | |
self.n_item = n_item | |
self.n_itr = n_itr | |
self.n_fac = n_fac | |
self.γ = γ | |
self.λ = λ | |
self.met = met | |
# initialize output matrix | |
self.P = np.random.normal(scale=0.0001, size=(self.n_user, self.n_fac)) | |
self.Q = np.random.normal(scale=0.0001, size=(self.n_item, self.n_fac)) | |
def fit(self, X, r): | |
#tdata = [(u, i, r) for (u,i), r in zip(X, r)] | |
tdata = np.array([[X[i][0], X[i][1], r[i]] for i in range(len(r))]) | |
self.P, self.Q = MFEstimator.sgd(tdata, self.P, self.Q, self.γ, self.λ, self.n_itr) | |
@staticmethod | |
@njit | |
def sgd(tdata, P, Q, γ, λ, n_itr): | |
x = 1 | |
loss = 0.0 | |
for itr in range(n_itr): | |
for j in range(len(tdata)): | |
u, i, r = tdata[j] | |
# calc diff | |
pu, qi = P[u, :].copy(), Q[i, :].copy() | |
e = r - pu @ qi | |
# update | |
Q[i] += γ * (e * pu - λ * qi) | |
P[u] += γ * (e * qi - λ * pu) | |
# calcluate loss | |
loss += e * e + λ * (np.sum(P[u] ** 2)+ np.sum(Q[i] ** 2)) | |
print(itr, loss) | |
return P, Q | |
DATA_PATH = './ml-100k/u.data' | |
def read_data(data_path=DATA_PATH): | |
ui_list = List() | |
r_list = List() | |
appe_ui = ui_list.append | |
appe_r = r_list.append | |
with open(data_path, 'r') as f: | |
u_data = f.readlines() | |
for l in u_data: | |
u, i, r, ts = [int(x) for x in l.split('\t')] | |
ui = List() | |
ui.append(u - 1) | |
ui.append(i - 1) | |
appe_ui(ui) | |
appe_r(r) | |
return ui_list, r_list | |
import pickle | |
def main(): | |
ui, r = read_data() | |
n_user, n_item = 943, 1682 | |
model = MFEstimator(n_user, n_item) | |
model.fit(ui, r) | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment