功能介绍

多分类评估是对多分类算法的预测结果进行效果评估。

流式的实验支持累计统计和窗口统计。

给出Precision、Recall、F-Measure、Sensitivity、Accuracy、Specificity和Kappa。

Precision

Recall

F-Measure

Sensitivity

Accuracy

Specificity

Kappa

Logloss

参数说明

脚本示例

脚本代码

import numpy as np
import pandas as pd
data = np.array([
    ["prefix1", "{\"prefix1\": 0.9, \"prefix0\": 0.1}"],
    ["prefix1", "{\"prefix1\": 0.8, \"prefix0\": 0.2}"],
    ["prefix1", "{\"prefix1\": 0.7, \"prefix0\": 0.3}"],
    ["prefix0", "{\"prefix1\": 0.75, \"prefix0\": 0.25}"],
    ["prefix0", "{\"prefix1\": 0.6, \"prefix0\": 0.4}"]])
df = pd.DataFrame({"label": data[:, 0], "detailInput": data[:, 1]})
inOp = BatchOperator.fromDataframe(df, schemaStr='label string, detailInput string')
metrics = EvalMultiClassBatchOp().setLabelCol("label").setPredictionDetailCol("detailInput").linkFrom(inOp).collectMetrics()
print("Prefix0 accuracy:", metrics.getAccuracy("prefix0"))
print("Prefix1 recall:", metrics.getRecall("prefix1"))
print("Macro Precision:", metrics.getMacroPrecision())
print("Micro Recall:", metrics.getMicroRecall())
print("Weighted Sensitivity:", metrics.getWeightedSensitivity())
inOp = StreamOperator.fromDataframe(df, schemaStr='label string, detailInput string')
EvalMultiClassStreamOp().setLabelCol("label").setPredictionDetailCol("detailInput").setTimeInterval(1).linkFrom(inOp).print()
StreamOperator.execute()

脚本运行结果

Prefix0 accuracy: 0.6
Prefix1 recall: 1.0
Macro Precision: 0.3
Micro Recall: 0.6
Weighted Sensitivity: 0.6