Last active
November 16, 2017 20:12
-
-
Save sajjadmurtaza/c1a6c19f1c8d629c8bce71a07f88dc19 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
def find_final_one(list, g) | |
count = 0 | |
last_precision = 0 | |
last_recall = 0 | |
target = [] | |
list.each do |list| | |
count = (count + g.select { |g| list == g }.count).to_f | |
precision, recall = (count/list.count.to_f).to_f, (count/10).to_f | |
target << list if precision >= last_precision and recall >= last_recall | |
last_precision, last_recall = precision, recall | |
end | |
target | |
end |
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
require './find_final_one' | |
require 'csv' | |
imdb_csv = CSV.read("imdb.csv", :headers => true) | |
rotten_tomatoes_csv = CSV.read("rotten_tomatoes.csv", :headers => true) | |
g = [["imdb.Name", "rt.Name"],["imdb.YearRange", "rt.Year"],["imdb.ReleaseDate", "rt.ReleaseDate"],["imdb.Director", "rt.Director"],["imdb.Creator", "rt.Creator"], ["imdb.Cast", "rt.Cast"],["imdb.Duration", "rt.Duration"],["imdb.RatingValue", "rt.RatingValue"],["imdb.Genre", "rt.Genre"],["imdb.Description", "rt.Description"]] | |
imdb = imdb_csv.to_a | |
rt = rotten_tomatoes_csv.to_a | |
def get_list(imdb, rt, g) | |
i_row = imdb.count/imdb[0].count | |
i_col = imdb[0].count | |
r_row = rt.count/rt[0].count | |
r_col = rt[0].count | |
count = -1 | |
temp = [] | |
list = [] | |
for j in 0..(i_col-1) do | |
d = 0 | |
for l in 0..(r_col-1) do | |
sim_total = 0 | |
for i in 1..(i_row-1) do | |
str1 = imdb[i][j] | |
length1 = str1.nil? ? 0 : str1.length | |
sim_single = 0 | |
st1_type = str1.class | |
for k in 1..(r_row-1) do | |
str2 = rt[k][l] | |
length2 = str2.nil? ? 0 : str2.length | |
distance = 0 | |
st2_type = str2.class | |
m = 0 | |
while m < length1 and m < length2 do | |
if str1[m] != str2[m] | |
distance = distance + 1 | |
end | |
m = m + 1 | |
end | |
if length1 != length2 | |
distance = distance + (length1-length2).abs | |
end | |
type = 0 | |
if st1_type == st2_type | |
type = 1 | |
end | |
similarity = 0 | |
if distance <= length1/2 | |
similarity = 1 | |
end | |
sim_single = sim_single + similarity + type | |
end | |
sim_total = sim_total + sim_single | |
end | |
if sim_total > d and sim_total >= i_row/2 | |
list << ["imdb.#{imdb[0][j]}", "rt.#{rt[0][l]}"] | |
d = sim_total | |
end | |
end | |
end | |
find_final_one(list, g) | |
end | |
p get_list(imdb, rt, g) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment