Created
May 5, 2017 11:33
-
-
Save sadeghian92/390e2b0afc24368a6b4f44abed3b6e7f to your computer and use it in GitHub Desktop.
PHP script to create User-Rating Matrix from MovieLens 100K Dataset. https://datahub.io/dataset/movielens/resource/e2117a93-4fd4-41c3-b0e8-6a8ff8b1ad09
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
<?php | |
$delimiter = "\t"; | |
$fp = fopen('YOUR_ABSOLUTE_PATH_TO_DIRECTORY' . 'u.data'), 'r'); | |
$ratings = []; | |
$items = []; | |
for ($i = 0; $i < 100000; $i++) { | |
$line = fgets($fp, 2048); | |
$data = str_getcsv($line, $delimiter); | |
$items[$data[1]] = $data[1]; | |
$ratings[$data[0]][$data[1]] = $data[2]; | |
} | |
$fw = fopen('YOUR_ABSOLUTE_PATH_TO_DIRECTORY' . 'user-rating-matrix.data', 'w'); | |
fwrite($fw, "Users"); | |
sort($items); | |
foreach ($items as $item) { | |
fwrite($fw, "\tItem-" . $item); | |
} | |
fwrite($fw, "\n"); | |
for ($i = 1; $i <= 943; $i++) { | |
fwrite($fw, "User-" . $i); | |
$userRatings = $ratings[$i]; | |
for ($j = 1; $j <= 1682; $j++) { | |
if (array_key_exists($j, $userRatings)) { | |
fwrite($fw, "\t" . $userRatings[$j]); | |
} else { | |
fwrite($fw,"\t?"); | |
} | |
} | |
fwrite($fw, "\n"); | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment