|
| 1 | +/* |
| 2 | + * Licensed to the Apache Software Foundation (ASF) under one |
| 3 | + * or more contributor license agreements. See the NOTICE file |
| 4 | + * distributed with this work for additional information |
| 5 | + * regarding copyright ownership. The ASF licenses this file |
| 6 | + * to you under the Apache License, Version 2.0 (the |
| 7 | + * "License"); you may not use this file except in compliance |
| 8 | + * with the License. You may obtain a copy of the License at |
| 9 | + * |
| 10 | + * http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | + * |
| 12 | + * Unless required by applicable law or agreed to in writing, |
| 13 | + * software distributed under the License is distributed on an |
| 14 | + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 15 | + * KIND, either express or implied. See the License for the |
| 16 | + * specific language governing permissions and limitations |
| 17 | + * under the License. |
| 18 | + */ |
| 19 | + |
| 20 | +package org.apache.texera.amber.operator.visualization.ternaryContour |
| 21 | + |
| 22 | +import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription} |
| 23 | +import com.kjetland.jackson.jsonSchema.annotations.JsonSchemaTitle |
| 24 | +import org.apache.texera.amber.core.tuple.{AttributeType, Schema} |
| 25 | +import org.apache.texera.amber.core.workflow.OutputPort.OutputMode |
| 26 | +import org.apache.texera.amber.core.workflow.{InputPort, OutputPort, PortIdentity} |
| 27 | +import org.apache.texera.amber.operator.PythonOperatorDescriptor |
| 28 | +import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName |
| 29 | +import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo} |
| 30 | + |
| 31 | +/** |
| 32 | + * Visualization Operator for Ternary Plots. |
| 33 | + * |
| 34 | + * This operator uses three data fields to construct a ternary plot. |
| 35 | + * The points can optionally be color coded using a data field. |
| 36 | + */ |
| 37 | + |
| 38 | +class TernaryContourOpDesc extends PythonOperatorDescriptor { |
| 39 | + |
| 40 | + // Add annotations for the first variable |
| 41 | + @JsonProperty(value = "firstVariable", required = true) |
| 42 | + @JsonSchemaTitle("Variable 1") |
| 43 | + @JsonPropertyDescription("First variable data field") |
| 44 | + @AutofillAttributeName var firstVariable: String = "" |
| 45 | + |
| 46 | + // Add annotations for the second variable |
| 47 | + @JsonProperty(value = "secondVariable", required = true) |
| 48 | + @JsonSchemaTitle("Variable 2") |
| 49 | + @JsonPropertyDescription("Second variable data field") |
| 50 | + @AutofillAttributeName var secondVariable: String = "" |
| 51 | + |
| 52 | + // Add annotations for the third variable |
| 53 | + @JsonProperty(value = "thirdVariable", required = true) |
| 54 | + @JsonSchemaTitle("Variable 3") |
| 55 | + @JsonPropertyDescription("Third variable data field") |
| 56 | + @AutofillAttributeName var thirdVariable: String = "" |
| 57 | + |
| 58 | + // Add annotations for the fourth variable |
| 59 | + @JsonProperty(value = "fourthVariable", required = true) |
| 60 | + @JsonSchemaTitle("Variable 4") |
| 61 | + @JsonPropertyDescription("Fourth variable data field") |
| 62 | + @AutofillAttributeName var fourthVariable: String = "" |
| 63 | + |
| 64 | + // OperatorInfo instance describing ternary plot |
| 65 | + override def operatorInfo: OperatorInfo = |
| 66 | + OperatorInfo( |
| 67 | + userFriendlyName = "Ternary Contour", |
| 68 | + operatorDescription = "A ternary contour plot shows how a measured value changes across all mixtures of three components that always sum to a constant (usually 100%).", |
| 69 | + operatorGroupName = OperatorGroupConstants.VISUALIZATION_SCIENTIFIC_GROUP, |
| 70 | + inputPorts = List(InputPort()), |
| 71 | + outputPorts = List(OutputPort(mode = OutputMode.SINGLE_SNAPSHOT)) |
| 72 | + ) |
| 73 | + |
| 74 | + override def getOutputSchemas( |
| 75 | + inputSchemas: Map[PortIdentity, Schema] |
| 76 | + ): Map[PortIdentity, Schema] = { |
| 77 | + val outputSchema = Schema() |
| 78 | + .add("html-content", AttributeType.STRING) |
| 79 | + Map(operatorInfo.outputPorts.head.id -> outputSchema) |
| 80 | + Map(operatorInfo.outputPorts.head.id -> outputSchema) |
| 81 | + } |
| 82 | + |
| 83 | + /** Returns a Python string that drops any tuples with missing values */ |
| 84 | + def manipulateTable(): String = { |
| 85 | + // Check for any empty data field names |
| 86 | + assert(firstVariable.nonEmpty && secondVariable.nonEmpty && thirdVariable.nonEmpty) |
| 87 | + s""" |
| 88 | + | # Remove any tuples that contain missing values |
| 89 | + | table.dropna(subset=['$firstVariable', '$secondVariable', '$thirdVariable', '$fourthVariable'], inplace = True) |
| 90 | + | |
| 91 | + | #Remove rows where any of the first three variables are negative |
| 92 | + | table = table[(table[['$firstVariable', '$secondVariable', '$thirdVariable']] >= 0).all(axis=1)] |
| 93 | + | |
| 94 | + | #Remove zero-sum rows |
| 95 | + | s = table['$firstVariable'] + table['$secondVariable'] + table['$thirdVariable'] |
| 96 | + | table = table[s > 0] |
| 97 | + |""".stripMargin |
| 98 | + } |
| 99 | + |
| 100 | + /** Returns a Python string that creates the ternary contour plot figure */ |
| 101 | + def createPlotlyFigure(): String = { |
| 102 | + s""" |
| 103 | + | A = table['$firstVariable'].to_numpy() |
| 104 | + | B = table['$secondVariable'].to_numpy() |
| 105 | + | C = table['$thirdVariable'].to_numpy() |
| 106 | + | Z = table['$fourthVariable'].to_numpy() |
| 107 | + | fig = ff.create_ternary_contour(np.array([A,B,C]), Z, pole_labels=['$firstVariable', '$secondVariable', '$thirdVariable'], interp_mode='cartesian') |
| 108 | + |""".stripMargin |
| 109 | + } |
| 110 | + |
| 111 | + /** Returns a Python string that yields the html content of the ternary contour plot */ |
| 112 | + override def generatePythonCode(): String = { |
| 113 | + val finalCode = |
| 114 | + s""" |
| 115 | + |from pytexera import * |
| 116 | + | |
| 117 | + |import plotly.express as px |
| 118 | + |import plotly.io |
| 119 | + |import plotly.figure_factory as ff |
| 120 | + |import numpy as np |
| 121 | + | |
| 122 | + |class ProcessTableOperator(UDFTableOperator): |
| 123 | + | |
| 124 | + | # Generate custom error message as html string |
| 125 | + | def render_error(self, error_msg): |
| 126 | + | return '''<h1>TernaryContour is not available.</h1> |
| 127 | + | <p>Reasons are: {} </p> |
| 128 | + | '''.format(error_msg) |
| 129 | + | |
| 130 | + | @overrides |
| 131 | + | def process_table(self, table: Table, port: int) -> Iterator[Optional[TableLike]]: |
| 132 | + | if table.empty: |
| 133 | + | yield {'html-content': self.render_error("Input table is empty.")} |
| 134 | + | return |
| 135 | + | ${manipulateTable()} |
| 136 | + | if table.empty: |
| 137 | + | yield {'html-content': self.render_error("No valid rows left (every row has at least 1 missing value).")} |
| 138 | + | return |
| 139 | + | ${createPlotlyFigure()} |
| 140 | + | # Convert fig to html content |
| 141 | + | html = plotly.io.to_html(fig, include_plotlyjs = 'cdn', auto_play = False) |
| 142 | + | yield {'html-content':html} |
| 143 | + |""".stripMargin |
| 144 | + finalCode |
| 145 | + } |
| 146 | + |
| 147 | +} |
0 commit comments