如何在csv中聚合置信水平

Question

我的程序当前循环通过pdf/image文件目录，并使用Azure计算机视觉REST API生成json文件。使用下面的JsonToCsv()，我将这些文件中的特定json元素导出到csv文件中，因此输出如下所示：

file.csv输出：

page,text,words,confidence
1,The quick brown fox jumps,The,0.958
1,The quick brown fox jumps,quick,0.57
1,The quick brown fox jumps,brown,0.799
1,The quick brown fox jumps,fox,0.442
1,The quick brown fox jumps,jumps,0.878
1,over,over,0.37
1,the lazy dog!,the,0.909
1,the lazy dog!,lazy,0.853
1,the lazy dog!,dog!,0.41

我想做的是合并单词，使它们由逗号而不是单独的行分隔，因此，平均出包含这些单词的整个文本的置信度。例如，新文件希望：

page,text,words,confidence
1,The quick brown fox jumps,The,quick,brown,fox,jumps,0.729
1,over,over,0.37
1,the lazy dog!,the,lazy,dog!,0.724

其中第一文本中的CCD_ 2是组合和划分的相关置信水平的结果/平均值：例如CCD_。对最后一个文本也执行了相同的操作。

我该如何更新下面的函数来实现这一点？

JsonToCsv()代码：

private static void JsonToCsv(string jsonFile, string csvfFile) {   
using (var p = new ChoJSONReader(jsonFile)
.WithJSONPath("$..readResults")
)
{
using (var w = new ChoCSVWriter(csvfFile).WithFirstLineHeader())
{
w.Write(p
.SelectMany(r1 => ((dynamic[])r1.lines).SelectMany(r2 => ((dynamic[])r2.words).Select(r3 => new
{
r1.page,
r2.text,
words = r3.text,
r3.confidence
}))));
}
}
}

示例JSON文件：

{
"status": "succeeded",
"createdDateTime": "2020-05-28T05:13:21Z",
"lastUpdatedDateTime": "2020-05-28T05:13:22Z",
"analyzeResult": {
"version": "3.1.0",
"readResults": [
{
"page": 1,
"language": "en",
"angle": 0.8551,
"width": 2661,
"height": 1901,
"unit": "pixel",
"lines": [
{
"boundingBox": [
67,
646,
2582,
713,
2580,
876,
67,
821
],
"text": "The quick brown fox jumps",
"words": [
{
"boundingBox": [
143,
650,
435,
661,
436,
823,
144,
824
],
"text": "The",
"confidence": 0.958
},
{
"boundingBox": [
540,
665,
926,
679,
926,
825,
541,
823
],
"text": "quick",
"confidence": 0.57
},
{
"boundingBox": [
1125,
686,
1569,
700,
1569,
838,
1125,
828
],
"text": "brown",
"confidence": 0.799
},
{
"boundingBox": [
1674,
703,
1966,
711,
1966,
851,
1674,
841
],
"text": "fox",
"confidence": 0.442
},
{
"boundingBox": [
2083,
714,
2580,
725,
2579,
876,
2083,
855
],
"text": "jumps",
"confidence": 0.878
}
]
},
{
"boundingBox": [
187,
1062,
485,
1056,
486,
1120,
189,
1126
],
"text": "over",
"words": [
{
"boundingBox": [
190,
1064,
439,
1059,
441,
1122,
192,
1126
],
"text": "over",
"confidence": 0.37
}
]
},
{
"boundingBox": [
664,
1008,
1973,
1023,
1969,
1178,
664,
1154
],
"text": "the lazy dog!",
"words": [
{
"boundingBox": [
668,
1008,
923,
1015,
923,
1146,
669,
1117
],
"text": "the",
"confidence": 0.909
},
{
"boundingBox": [
1107,
1018,
1447,
1023,
1445,
1178,
1107,
1162
],
"text": "lazy",
"confidence": 0.853
},
{
"boundingBox": [
1639,
1024,
1974,
1023,
1971,
1170,
1636,
1178
],
"text": "dog!",
"confidence": 0.41
}
]
}
]
}
]
}
}

Answer 1

使用Linq可以生成预期格式的CSV。下面的示例展示了

StringBuilder csv = new StringBuilder();
using (var p = new ChoJSONReader("*** YOUR JSON PATH ***")
.WithJSONPath("$..readResults")
)
{
using (var w = new ChoCSVWriter(csv)
.WithFirstLineHeader()
)
{
w.Write(p
.SelectMany(r1 => ((dynamic[])r1.lines)
.Select(r2 => new
{
r1.page,
r2.text,
words = String.Join(",", ((dynamic[])r2.words).Select(s1 => s1.text)),
confidence = ((dynamic[])r2.words).Select(s1 => (double)s1.confidence).Average()
})));
}
}
Console.WriteLine(csv.ToString());