ee.ConfusionMatrix

建立混淆矩陣。矩陣的軸 0 (資料列) 對應實際值，軸 1 (資料欄) 則對應預測值。

用量	傳回
ee.ConfusionMatrix(array, order)	ConfusionMatrix

引數	類型	詳細資料
array	物件	代表混淆矩陣的整數 2D 方陣。請注意，與 ee.Array 建構函式不同，這個引數無法接受清單。
order	清單，預設值為空值	非連續或非以零為基礎的矩陣，其資料列和資料欄的大小和順序。

範例

程式碼編輯器 (JavaScript)

// A confusion matrix. Rows correspond to actual values, columns to
// predicted values.
var array = ee.Array([[32, 0, 0,  0,  1, 0],
                      [ 0, 5, 0,  0,  1, 0],
                      [ 0, 0, 1,  3,  0, 0],
                      [ 0, 1, 4, 26,  8, 0],
                      [ 0, 0, 0,  7, 15, 0],
                      [ 0, 0, 0,  1,  0, 5]]);
print('Constructed confusion matrix',
      ee.ConfusionMatrix(array));

// The "order" parameter refers to row and column class labels. When
// unspecified, the class labels are assumed to be a 0-based sequence
// incrementing by 1 with a length equal to row/column size.
print('Default row/column labels (unspecified "order" parameter)',
      ee.ConfusionMatrix({array: array, order: null}).order());

// Set the "order" parameter when custom class label integers are required. The
// list of integer value labels should correspond to the matrix axes left to
// right / top to bottom.
var order = [11, 22, 42, 52, 71, 81];
print('Specified row/column labels (specified "order" parameter)',
      ee.ConfusionMatrix({array: array, order: order}).order());

Python 設定

請參閱 Python 環境頁面，瞭解 Python API 和如何使用 geemap 進行互動式開發。

import ee
import geemap.core as geemap

Colab (Python)

from pprint import pprint

# A confusion matrix. Rows correspond to actual values, columns to
# predicted values.
array = ee.Array([[32, 0, 0,  0,  1, 0],
                  [ 0, 5, 0,  0,  1, 0],
                  [ 0, 0, 1,  3,  0, 0],
                  [ 0, 1, 4, 26,  8, 0],
                  [ 0, 0, 0,  7, 15, 0],
                  [ 0, 0, 0,  1,  0, 5]])
print('Constructed confusion matrix:')
pprint(ee.ConfusionMatrix(array).getInfo())

# The "order" parameter refers to row and column class labels. When
# unspecified, the class labels are assumed to be a 0-based sequence
# incrementing by 1 with a length equal to row/column size.
print('Default row/column labels (unspecified "order" parameter):',
      ee.ConfusionMatrix(array, None).order().getInfo())

# Set the "order" parameter when custom class label integers are required. The
# list of integer value labels should correspond to the matrix axes left to
# right / top to bottom.
order = [11, 22, 42, 52, 71, 81]
print('Specified row/column labels (specified "order" parameter):',
      ee.ConfusionMatrix(array, order).order().getInfo())