Created
September 9, 2012 15:15
-
-
Save kuniyoshi/3684962 to your computer and use it in GitHub Desktop.
Calculate Euclid, and Pearson Distance
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
-module(reco_cons). | |
-compile(export_all). | |
read() -> | |
{ok, D} = file:consult("reco.cons"), | |
D. | |
get_persons(Data) -> | |
{critics, D1} = lists:keyfind(critics, 1, Data), | |
[K || {K, _} <- D1]. | |
calc_sim_distance([Data, PersonA, PersonB, euclid]) -> | |
calc_euclid_distance(prepare_calc(Data, PersonA, PersonB)); | |
calc_sim_distance([Data, PersonA, PersonB, pearson]) -> | |
calc_pearson_distance(prepare_calc(Data, PersonA, PersonB)). | |
prepare_calc(Data, PersonA, PersonB) -> | |
{critics, D1} = lists:keyfind(critics, 1, Data), | |
{PersonA, PdA} = lists:keyfind(PersonA, 1, D1), | |
{PersonB, PdB} = lists:keyfind(PersonB, 1, D1), | |
Keys = lists:filter(fun (Key) -> | |
lists:keymember(Key, 1, PdB) | |
end, [Key || {Key, _} <- PdA]), | |
[PdA, PdB, Keys]. | |
calc_euclid_distance([_, _, []]) -> | |
0.0; | |
calc_euclid_distance([PersonDataA, PersonDataB, Keys]) -> | |
lists:sum(lists:map(fun (Key) -> | |
{Key, VA} = lists:keyfind(Key, 1, PersonDataA), | |
{Key, VB} = lists:keyfind(Key, 1, PersonDataB), | |
1 / (1 + math:sqrt(math:pow(VA, 2) + math:pow(VB, 2))) | |
end, Keys)). | |
calc_pearson_distance([_, _, []]) -> | |
0.0; | |
calc_pearson_distance([PersonDataA, PersonDataB, Keys]) -> | |
VLA = [V || {_, V} <- [lists:keyfind(Key, 1, PersonDataA) || Key <- Keys]], | |
VLB = [V || {_, V} <- [lists:keyfind(Key, 1, PersonDataB) || Key <- Keys]], | |
SA = lists:sum(VLA), | |
SB = lists:sum(VLB), | |
SAP = lists:sum([math:pow(V, 2) || V <- VLA]), | |
SBP = lists:sum([math:pow(V, 2) || V <- VLB]), | |
SM = lists:sum(lists:map(fun (Key) -> | |
{Key, VA} = lists:keyfind(Key, 1, PersonDataA), | |
{Key, VB} = lists:keyfind(Key, 1, PersonDataB), | |
VA * VB | |
end, Keys)), | |
Length = length(Keys), | |
N = SM - (SA * SB / Length), | |
D = math:sqrt((SAP - math:pow(SA, 2) / Length) * (SBP - math:pow(SB, 2) / Length)), | |
case D of | |
0.0 -> | |
0.0; | |
_ -> | |
N / D | |
end. | |
%% reco.cons | |
%% {critics, [{"Lisa Rose", | |
%% [{"Lady in the Water", 2.5}, | |
%% {"Snakes on a Plane", 3.5}, | |
%% {"Just My Luck", 3.0}, | |
%% {"Superman Returns", 3.5}, | |
%% {"You, Me and Dupree", 2.5}, | |
%% {"The Night Listener", 3.0}]}, | |
%% {"Gene Seymour", | |
%% [{"Lady in the Water", 3.0}, | |
%% {"Snakes on a Plane", 3.5}, | |
%% {"Just My Luck", 1.5}, | |
%% {"Superman Returns", 5.0}, | |
%% {"The Night Listener", 3.0}, | |
%% {"You, me and Dupree", 3.5}]}, | |
%% {"Michael Phillips", | |
%% [{"Lady in the Water", 2.5}, | |
%% {"Snakes on a Plane", 3.0}, | |
%% {"Superman Returns", 3.5}, | |
%% {"The Night Listener", 4.0}]}, | |
%% {"Claudia Puig", | |
%% [{"Snakes on a Plane", 3.5}, | |
%% {"Just My Luck", 3.0}, | |
%% {"The Night Listener", 4.5}, | |
%% {"Superman Returns", 4.0}, | |
%% {"You, Me and Dupree", 2.5}]}, | |
%% {"Mick LaSalle", | |
%% [{"Lady in the Water", 3.0}, | |
%% {"Snakes on a Plane", 4.0}, | |
%% {"Jus My Luck", 2.0}, | |
%% {"Superman Returns", 3.0}, | |
%% {"The Night Listener", 3.0}, | |
%% {"You, Me and Dupree", 2.0}]}, | |
%% {"Jack Matthews", | |
%% [{"Lady in the Water", 3.0}, | |
%% {"Snakes on a Plane", 4.0}, | |
%% {"The Night Listener", 3.0}, | |
%% {"Superman Returns", 5.0}, | |
%% {"You, Me and Dupree", 3.5}]}, | |
%% {"Toby", | |
%% [{"Snakes on a Plane", 4.5}, | |
%% {"You, Me and Dupree", 1.0}, | |
%% {"Superman Returns", 4.0}]}]}. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
--- output sample
62> f().
ok
63> c(reco_cons).
{ok,reco_cons}
64> PA = lists:nth(1, reco_cons:get_persons(reco_cons:read())).
"Lisa Rose"
65> PB = lists:nth(2, reco_cons:get_persons(reco_cons:read())).
"Gene Seymour"
66> reco_cons:calc_sim_distance([reco_cons:read(), PA, PB, euclid]).
0.9331349018354814
67> reco_cons:calc_sim_distance([reco_cons:read(), PA, PB, pearson]).
0.547619047619046
68>