esp-studio-examples/Analytics/analytics_streaminghistogram/model.xml at main · sassoftware/esp-studio-examples · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
<project name='project' pubsub='auto' threads='1' use-tagged-token='true'>
    <description>
	This example is a basic demonstration of using the streaming histogram algorithm.
	The algorithm processes a stream of numerical data and puts it in bins to generate
	boundaries for creating a histogram that fits it.

	This project contains a single continuous query consisting of the following:
	1.	A source window that receives the data to fit into a histogram
	2.	A calculate window that performs bucketing
    </description>
      <contqueries>
        <contquery name='contquery' trace='w_data w_calculate'>
          <windows>
            <window-source name='w_data' insert-only='true' index='pi_EMPTY'>
            <description>
		This source window receives the included example input data via a file socket
		connector. The input data stream is placed into three fields for each observation:
		an ID that acts as the data stream's key, named id; an x coordinate of data, named
		x_c; and a y coordinate of data, named y_c.
            </description>
              <schema>
                <fields>
                  <field name='id'  type='int64' key='true'/>
                  <field name='x_c' type='double'/>
                  <field name='y_c' type='double'/>
                </fields>
              </schema>
              <connectors>
                <connector class='fs' name='publisher'>
                  <properties>
                    <property name='type'>pub</property>
                    <property name='fstype'>csv</property>
                    <property name='fsname'>input.csv</property>
                    <property name='transactional'>true</property>
                    <property name='blocksize'>1</property>
                  </properties>
                </connector>
              </connectors>
            </window-source>
            <window-calculate name='w_calculate' algorithm='Histogram' index='pi_EMPTY'>
            <description>
		This calculate window receives data events from the source window and publishes output
		variable values for bin centers and heights for quantiles. In this example, the following
		algorithm parameters govern the Histogram algorithm:

		nBins:		Specifies the maximum number of bin in the histogram.
		alpha:		Specifies the fading out factor (must be between 0 and 1). The recommended
				value for alpha is greater than 0.997.
		halfLifeSteps:	Specifies the number of steps at which the weight of the input reaches half
				of its original weight.
		quantileList:	Specifies a comma-separated list that contains quantiles to compute. Probabilities
				must be in the range [0,1] and sorted in ascending order.
		reportInterval:	Specifies the interval of reporting histogram and quantile results (if any).

		Additionally, the following input-map and output-map properties define this calculate window:

		input:		Specifies the input variable with which to build the histogram.

		binCentersOut:	Specifies a list of output variable names for bin centers.
		binHeightsOut:	Specifies a list of output variable names for bin heights.
		quantilesOut:	Specifies a list of output variable names for quantiles.

		The resulting output is written to the file result.out via a file socket connector.
            </description>
              <schema>
                <fields>
                  <field name='id'         type='int64' key='true'/>
                  <field name='binCenters' type='array(dbl)'/>
                  <field name='binHeights' type='array(dbl)'/>
                  <field name='quantiles'  type='array(dbl)'/>
                </fields>
              </schema>
              <parameters>
                <properties>
                  <property name="nBins">5</property>
                  <property name="alpha">0.999</property>
                  <property name="halfLifeSteps">2</property>
                  <property name="quantileList">0.25,0.50,0.75</property>
                  <property name="reportInterval">10</property>
                </properties>
              </parameters>
              <input-map>
                <properties>
                  <property name="input">x_c</property>
                </properties>
              </input-map>
              <output-map>
                <properties>
                  <property name="binCentersOut">binCenters[1-20]</property>
                  <property name="binHeightsOut">binHeights[1-20]</property>
                  <property name="quantilesOut">quantiles[1-3]</property>
                </properties>
              </output-map>
              <connectors>
                <connector class='fs' name='sub'>
                  <properties>
                    <property name='type'>sub</property>
                    <property name='fstype'>csv</property>
                    <property name='fsname'>result.out</property>
                    <property name='snapshot'>true</property>
                    <property name='header'>true</property>
                  </properties>
                </connector>
              </connectors>
            </window-calculate>
          </windows>
          <edges>
            <edge source='w_data' target='w_calculate' role='data'/>
          </edges>
        </contquery>
      </contqueries>
    </project>