首先我們將樣本分為80%的訓練樣本與20%的測試樣本,如下程式碼:
$samples_20percent = Array(); //宣告20% samples 為Array
$labels_20percent = Array(); //宣告20% labels 為Array
$samples_80percent = Array(); //宣告80% samples 為Array
$labels_80percent = Array(); //宣告80% labels 為Array
/**
* 取得20%數量的亂數
*/
$randValue = Array(); //定義為陣列
$count = $count_20percent; //產生指定數量
for ($i=1; $i<=$count; $i++) {
$randValueTemp = mt_rand(0,count($getSample)-1); //產生0~(總數量-1)的亂數
if (in_array($randValueTemp, $randValue)) { //如果已產生過迴圈重跑
$i--;
}else{
$randValue[] = $randValueTemp; //若無重復則將亂數塞入陣列
}
}
asort($randValue); //排序
foreach($randValue as $value){
//把陣列內的亂數讀出,就將要的20% samples跟labels寫入到指定變數內
$samples_20percent[] = $total_sample[$value];
$labels_20percent[] = $getTargets[$value];
//刪除已取出資料的陣列元素
unset($total_sample[$value]);
unset($getTargets[$value]);
}
//20%擷取完畢資料,剩下的資料為80%的部分,array_values()方法函式會返回所指定陣列中所有的值並將其建立新索引(由0開始)
$samples_80percent = array_values($total_sample);
$labels_80percent = array_values($getTargets);
接下來建立一個新的分類器 KNearestNeighbors(),這個分類器可以調整兩個參數,一個是k的大小,另外個是距離的計算方式
因為我們有做標準化的動作,理論上不會被有特別某一個參數決定預測的結果
其中參數k我們設定為3,距離為預設
KNearestNeighbors($k=3)
接下來將訓練樣本與測試樣本放入分類器,完成訓練
使用predict,將測試的sample放入來預測測試樣本的成果
這樣我們就可以獲得預測的花之種類了
完整Code:
require_once __DIR__ . '/vendor/autoload.php';
use Phpml\Classification\KNearestNeighbors;
use Phpml\Dataset\CsvDataset;
//讀取Excel
$dataset = new CsvDataset('iris.csv',4);
//取得相關數值
$getSample = $dataset->getSamples();
$getTargets = $dataset->getTargets();
// max(最大化)
$sepalLength_max = 0;
$sepalWidth_max = 0;
$petalLength_max = 0;
$petalWidth_max = 0;
// min(最小化)
$sepalLength_min = 0;
$sepalWidth_min = 0;
$petalLength_min = 0;
$petalWidth_min = 0;
// array(標準化數值)
$sepalLength_array = [];
$sepalWidth_array = [];
$petalLength_array = [];
$petalWidth_array = [];
for($i=0; $i<count($getSample); $i++){
if($i==0){
// max(最大化參數賦予初始值)
$sepalLength_max = $getSample[$i][0];
$sepalWidth_max = $getSample[$i][1];
$petalLength_max = $getSample[$i][2];
$petalWidth_max = $getSample[$i][3];
// min(最小化參數賦予初始值)
$sepalLength_min = $getSample[$i][0];
$sepalWidth_min = $getSample[$i][1];
$petalLength_min = $getSample[$i][2];
$petalWidth_min = $getSample[$i][3];
}
// max(比較最大化)
if($getSample[$i][0] > $sepalLength_max){
$sepalLength_max = $getSample[$i][0];
}
if($getSample[$i][1] > $sepalWidth_max){
$sepalWidth_max = $getSample[$i][1];
}
if($getSample[$i][2] > $petalLength_max){
$petalLength_max = $getSample[$i][2];
}
if($getSample[$i][3] > $petalWidth_max){
$petalWidth_max = $getSample[$i][3];
}
// mix(比較最小化)
if($getSample[$i][0] < $sepalLength_min){
$sepalLength_min = $getSample[$i][0];
}
if($getSample[$i][1] < $sepalWidth_min){
$sepalWidth_min = $getSample[$i][1];
}
if($getSample[$i][2] < $petalLength_min){
$petalLength_min = $getSample[$i][2];
}
if($getSample[$i][3] < $petalWidth_min){
$petalWidth_min = $getSample[$i][3];
}
}
// x'= (x-min)/(max - min) 標準化數值(有效值取到小數第三位)
for($i=0; $i<count($getSample); $i++){
$sepalLength_array[] = round(($getSample[$i][0]-$sepalLength_min)/($sepalLength_max-$sepalLength_min), 3);
$sepalWidth_array[] = round(($getSample[$i][1]-$sepalWidth_min)/($sepalWidth_max-$sepalWidth_min), 3);
$petalLength_array[] = round(($getSample[$i][2]-$petalLength_min)/($petalLength_max-$petalLength_min), 3);
$petalWidth_array[] = round(($getSample[$i][3]-$petalWidth_min)/($petalWidth_max-$petalWidth_min), 3);
}
$count_total = count($getSample);
$count_20percent = round($count_total * 0.2);
$count_80percent = $count_total - $count_20percent;
$total_sample = Array();
for($i=0; $i<count($sepalLength_array); $i++){
$tempArrayValue = array(
$sepalLength_array[$i],
$sepalWidth_array[$i],
$petalLength_array[$i],
$petalWidth_array[$i],
);
$total_sample[] = $tempArrayValue;
}
$samples_20percent = Array(); //宣告20% samples 為Array
$labels_20percent = Array(); //宣告20% labels 為Array
$samples_80percent = Array(); //宣告80% samples 為Array
$labels_80percent = Array(); //宣告80% labels 為Array
/**
* 取得20%數量的亂數
*/
$randValue = Array(); //定義為陣列
$count = $count_20percent; //產生指定數量
for ($i=1; $i<=$count; $i++) {
$randValueTemp = mt_rand(0,count($getSample)-1); //產生0~(總數量-1)的亂數
if (in_array($randValueTemp, $randValue)) { //如果已產生過迴圈重跑
$i--;
}else{
$randValue[] = $randValueTemp; //若無重復則將亂數塞入陣列
}
}
asort($randValue); //排序
foreach($randValue as $value){
//把陣列內的亂數讀出,就將要的20% samples跟labels寫入到指定變數內
$samples_20percent[] = $total_sample[$value];
$labels_20percent[] = $getTargets[$value];
//刪除已取出資料的陣列元素
unset($total_sample[$value]);
unset($getTargets[$value]);
}
//20%擷取完畢資料,剩下的資料為80%的部分,array_values()方法函式會返回所指定陣列中所有的值並將其建立新索引(由0開始)
$samples_80percent = array_values($total_sample);
$labels_80percent = array_values($getTargets);
$classifier = new KNearestNeighbors($k=3);
$classifier->train($samples_80percent, $labels_80percent);
$resultDate = $classifier->predict($samples_20percent);
echo "<pre>";
var_dump($resultDate);
echo "</pre>";