我开始处理大数据。 我的输入是包含许多列的每日csv文件,我将导入这三列:
我的目标是什么?
我设计了这个数据模型有三个表(感谢Rock建议我在之前的帖子中使用计数器)
CREATE TABLE container_u_id (
parent_id int,
user_id text,
grandparent_a boolean,
grandparent_b boolean,
PRIMARY KEY (parent_id, user_id)
)
CREATE TABLE unique_u_id (
parent_id int,
counter_uu counter,
PRIMARY KEY (parent_id)
)
CREATE TABLE no_exclusive_unique_u_id (
parent_id int,
counter_uu counter,
PRIMARY KEY (parent_id)
)
使用php和Cassandra的pdo驱动程序导入数据 这是我的剧本
$relpath = realpath(dirname(__FILE__)) . '/';
include_once($relpath."config/init.php");
$dsn = "cassandra:host=127.0.0.1;port=9160";
$db = new PDO($dsn);
$db->exec("USE phpcassa");
$array_grandparent_id = array(12345, 67890);
$file_csv = new CSVFile("file.csv");
foreach ($file_csv as $row) {
$user_id = $row['USER_ID'];
$parent_id = $row['PARENT_ID'];
if(in_array($row['GRANDPARENT_ID'], $array_grandparent_id)){
$is_grandparent_a = ($row['GRANDPARENT_ID']==12345) ? 'TRUE' : 'FALSE';
$is_grandparent_b = ($row['GRANDPARENT_ID']==67890) ? 'TRUE' : 'FALSE';
$query= "INSERT INTO container_u_id (user_id, parent_id, grandparent_a, grandparent_b) VALUES('".$user_id."', ".$parent_id.", ".$is_grandparent_a.", ".$is_grandparent_b." ) IF NOT EXISTS;";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
$result_insert = $stmt->fetchAll();
$is_uu = ($result_insert[0]['[applied]']) ? True : False;
if($is_uu===False){
$status_grandparent_a = $result_insert[0]['grandparent_a'];
$status_grandparent_b = $result_insert[0]['grandparent_b'];
//if user belong to both grandparents then it is already present onto both counter tables
if($status_grandparent_a===False || $status_grandparent_b===False){
if($status_grandparent_a===False && $is_grandparent_a=='TRUE'){
$query = "UPDATE container_u_id SET grandparent_a = true WHERE user_id='".$user_id."' AND parent_id = ".$parent_id.";";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
$query= "UPDATE no_exclusive_so SET counter_uu = counter_uu + 1 WHERE parent_id = ".$parent_id.";";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
}elseif($status_grandparent_b===False && $is_grandparent_b=='TRUE'){
$query = "UPDATE container_u_id SET grandparent_b = true WHERE user_id='".$user_id."' AND parent_id = ".$parent_id.";";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
$query= "UPDATE no_exclusive_so SET counter_uu = counter_uu + 1 WHERE parent_id = ".$parent_id.";";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
}
}
}
if($is_uu){
$query= "UPDATE unique_u_id SET counter_uu = counter_uu + 1 WHERE parent_id = ".$parent_id.";";
$stmt = $db->prepare($query);
$status_exec = $stmt->execute();
}
}
}
然后从这个csv示例开始
Yzc4Jknl0-3c, 34, 12345
Yzc4Jknl0-3c, 34, 67890
Yzc4Jknl0-3c, 34, 12345
01w44Xz0w3c1, 13, 12345
01w44Xz0w3c1, 21, 12345
01w44Xz0w3c1, 21, 12345
qFxg0023Exy4, 21, 67890
在代码的最后,表格显示了这些结果
SELECT * FROM container_u_id;
parent_id | user_id | grandparent_a | grandparent_b
-----------+--------------+---------------+--------------
34 | Yzc4Jknl0-3c | True | True
13 | 01w44Xz0w3c1 | True | False
21 | 01w44Xz0w3c1 | True | False
21 | qFxg0023Exy4 | False | True
SELECT * FROM unique_u_id;
parent_id | counter_uu
-----------+------------
34 | 1
13 | 1
21 | 2
SELECT * FROM no_exclusive_unique_u_id;
parent_id | counter_uu
-----------+------------
34 | 1
现在,让我们开始说出我的怀疑。 该脚本有效,但速度很慢。对于获取5000万行,脚本花费的时间为8到10个小时。 开发环境是:
因此,我想改善表现......我的问题是: