feat(visualization): export the hierarchy and graph charts as Python

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/visualization/IcicleChart/IcicleChartOpDesc.scala

@@ -22,10 +22,14 @@ package org.apache.texera.amber.operator.visualization.IcicleChart
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
 import com.kjetland.jackson.jsonSchema.annotations.{JsonSchemaInject, JsonSchemaTitle}
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.core.workflow.PortIdentity
 import org.apache.texera.amber.operator.PythonOperatorDescriptor
+import org.apache.texera.amber.operator.visualization.PlotlyStandaloneCode
 import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.operator.visualization.hierarchychart.HierarchySection
@@ -43,7 +47,7 @@ import javax.validation.constraints.{NotEmpty, NotNull}
   }
 }
 """)
-class IcicleChartOpDesc extends PythonOperatorDescriptor {
+class IcicleChartOpDesc extends PythonOperatorDescriptor with PlotlyStandaloneCode {
   @JsonProperty(required = true)
   @JsonSchemaTitle("Hierarchy Path")
   @JsonPropertyDescription(
@@ -132,4 +136,46 @@ class IcicleChartOpDesc extends PythonOperatorDescriptor {
     finalCode.encode
   }
 
+  // Output is an HTML chart, not a tabular DataFrame.
+  // The translator skips it in the leaf-DataFrame print block.
+  override def producesDataFrame(): Boolean = false
+
+  override def generateStandaloneCode(): String = {
+    val attributes = hierarchy.map(section => pyStringLiteral(section.attributeName)).mkString(", ")
+    val valueLit = pyStringLiteral(value)
+    // The error page is written to output.html, the same file a plotted chart lands
+    // in, so a reason for "no chart" is where the reader looks for the chart —
+    // printing it to the terminal alone left output.html absent. render_error's
+    // continuation line keeps the runtime path's indentation, since the HTML is
+    // triple-quoted and those spaces reach the browser.
+    s"""def render_error(error_msg):
+       |    return '''<h1>Icicle chart is not available.</h1>
+       |                  <p>Reason is: {} </p>
+       |               '''.format(error_msg)
+       |
+       |def fail(error_msg):
+       |    with open("output.html", "w", encoding="utf-8") as output:
+       |        output.write(render_error(error_msg))
+       |    print(f"Icicle chart error: {error_msg}")
+       |
+       |if in1df.empty:
+       |    fail("input table is empty.")
+       |else:
+       |    # On a copy: the same frame can feed another branch of the plan, and
+       |    # both the assignment and the drop below would otherwise reach it.
+       |    chart_df = in1df.copy()
+       |    chart_df[$valueLit] = chart_df[chart_df[$valueLit] > 0][$valueLit]
+       |    chart_df = chart_df.dropna(subset=[$attributes])
+       |    if chart_df.empty:
+       |        fail("value column contains only non-positive numbers or nulls.")
+       |    else:
+       |        fig = px.icicle(chart_df, path=[$attributes], values=$valueLit,
+       |                         color=$valueLit, hover_data=[$attributes],
+       |                         color_continuous_scale='RdBu')
+       |        fig.update_layout(margin=dict(l=0, r=0, b=0, t=0))
+       |        fig.write_json("output.json")
+       |        fig.write_html("output.html")
+       |        print("Icicle chart saved to output.html")""".stripMargin
+  }
+
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/visualization/PlotlyStandaloneCode.scala

@@ -0,0 +1,42 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.texera.amber.operator.visualization
+
+import org.apache.texera.amber.operator.StandaloneCodeGenerator
+
+/**
+  * A generator whose emitted code draws with plotly.
+  *
+  * Mixed in rather than stated per operator because the three modules are one
+  * dependency: a chart reaching for `px` today and `go` tomorrow would otherwise
+  * have to remember to edit a list that nothing checks. What the mixin does say,
+  * and the reason it is not simply always emitted, is that an operator NOT
+  * mixing it in draws nothing, so a script built only from those runs wherever
+  * pandas is installed.
+  */
+trait PlotlyStandaloneCode extends StandaloneCodeGenerator {
+
+  override def standaloneImports(): Seq[String] =
+    Seq(
+      "import plotly.express as px",
+      "import plotly.graph_objects as go",
+      "import plotly.io"
+    )
+}

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/visualization/dendrogram/DendrogramOpDesc.scala

@@ -23,10 +23,13 @@ import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
 import com.fasterxml.jackson.databind.annotation.JsonDeserialize
 import com.kjetland.jackson.jsonSchema.annotations.{JsonSchemaInject, JsonSchemaTitle}
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
 import org.apache.texera.amber.pybuilder.PyStringTypes.{EncodableString, PythonLiteral}
 import org.apache.texera.amber.core.workflow.PortIdentity
-import org.apache.texera.amber.operator.PythonOperatorDescriptor
+import org.apache.texera.amber.operator.{PythonOperatorDescriptor, StandaloneCodeGenerator}
 import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder
@@ -43,7 +46,7 @@ import javax.validation.constraints.NotNull
   }
 }
 """)
-class DendrogramOpDesc extends PythonOperatorDescriptor {
+class DendrogramOpDesc extends PythonOperatorDescriptor with StandaloneCodeGenerator {
   @JsonProperty(value = "xVal", required = true)
   @JsonSchemaTitle("Value X Column")
   @JsonPropertyDescription("The x values of points in dendrogram")
@@ -88,12 +91,15 @@ class DendrogramOpDesc extends PythonOperatorDescriptor {
       OperatorGroupConstants.VISUALIZATION_SCIENTIFIC_GROUP
     )
 
+  /** An unset threshold reaches the generated code as Python's `None`, which is
+    * scipy's own 0.7 * max distance — what a blank field already meant.
+    */
+  private def thresholdExpr: PythonLiteral = threshold.map(_.toString).getOrElse("None")
+
   private def createDendrogram(): PythonTemplateBuilder = {
     assert(xVal.nonEmpty, "Value X Column cannot be empty")
     assert(yVal.nonEmpty, "Value Y Column cannot be empty")
     assert(labels.nonEmpty, "Labels cannot be empty")
-    // Unset means None, which is scipy's own 0.7 * max distance.
-    val thresholdExpr: PythonLiteral = threshold.map(_.toString).getOrElse("None")
     pyb"""
        |        x = np.array(table[$xVal])
        |        y = np.array(table[$yVal])
@@ -146,4 +152,49 @@ class DendrogramOpDesc extends PythonOperatorDescriptor {
          |"""
     finalcode.encode
   }
+
+  override def producesDataFrame(): Boolean = false
+
+  override def generateStandaloneCode(): String = {
+
+    // render_error's continuation line keeps the runtime path's indentation — the
+    // HTML is triple-quoted, so those spaces reach the browser.
+    s"""import numpy as np
+       |import plotly.figure_factory as ff
+       |
+       |def render_error(error_msg):
+       |    return '''<h1>Dendrogram is not available.</h1>
+       |                  <p>Reason is: {} </p>
+       |               '''.format(error_msg)
+       |
+       |def _write_error(message):
+       |    with open("output.html", "w", encoding="utf-8") as output:
+       |        output.write(render_error(message))
+       |
+       |if in1df.empty:
+       |    _write_error("input table is empty.")
+       |else:
+       |    # A row missing either coordinate has no position to cluster from, and
+       |    # scipy refuses a NaN anywhere in the distance matrix. Bound to a name
+       |    # of its own: the same frame can feed another branch of the plan, which
+       |    # must still see every row.
+       |    chart_df = in1df.dropna(subset=[${pyStringLiteral(xVal)}, ${pyStringLiteral(yVal)}])
+       |    if chart_df.empty:
+       |        _write_error("input table has no rows with all of the configured columns filled in.")
+       |    # Clustering starts from the distances between rows, so a single row
+       |    # leaves scipy an empty distance matrix and it raises rather than draws.
+       |    elif len(chart_df) < 2:
+       |        _write_error("input table has fewer than two rows to cluster.")
+       |    else:
+       |        x = np.array(chart_df[${pyStringLiteral(xVal)}])
+       |        y = np.array(chart_df[${pyStringLiteral(yVal)}])
+       |        data = np.column_stack((x, y))
+       |        labels = chart_df[${pyStringLiteral(labels)}].tolist()
+       |        fig = ff.create_dendrogram(data, labels=labels, color_threshold=$thresholdExpr)
+       |        fig.update_layout(yaxis_title="Linkage Distance", margin=dict(l=0, r=0, b=0, t=0))
+       |        fig.write_json("output.json")
+       |        fig.write_html("output.html")
+       |        print("Dendrogram saved to output.html")""".stripMargin
+  }
+
 }

common/workflow-operator/src/main/scala/org/apache/texera/amber/operator/visualization/hierarchychart/HierarchyChartOpDesc.scala

@@ -22,10 +22,14 @@ package org.apache.texera.amber.operator.visualization.hierarchychart
 import com.fasterxml.jackson.annotation.{JsonProperty, JsonPropertyDescription}
 import com.kjetland.jackson.jsonSchema.annotations.{JsonSchemaInject, JsonSchemaTitle}
 import org.apache.texera.amber.core.tuple.{AttributeType, Schema}
-import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.PythonTemplateBuilderStringContext
+import org.apache.texera.amber.pybuilder.PythonTemplateBuilder.{
+  PythonTemplateBuilderStringContext,
+  pyStringLiteral
+}
 import org.apache.texera.amber.pybuilder.PyStringTypes.EncodableString
 import org.apache.texera.amber.core.workflow.PortIdentity
 import org.apache.texera.amber.operator.PythonOperatorDescriptor
+import org.apache.texera.amber.operator.visualization.PlotlyStandaloneCode
 import org.apache.texera.amber.operator.metadata.annotations.AutofillAttributeName
 import org.apache.texera.amber.operator.metadata.{OperatorGroupConstants, OperatorInfo}
 import org.apache.texera.amber.pybuilder.PythonTemplateBuilder
@@ -42,7 +46,7 @@ import javax.validation.constraints.{NotEmpty, NotNull}
   }
 }
 """)
-class HierarchyChartOpDesc extends PythonOperatorDescriptor {
+class HierarchyChartOpDesc extends PythonOperatorDescriptor with PlotlyStandaloneCode {
   @JsonProperty(required = true)
   @JsonSchemaTitle("Chart Type")
   @JsonPropertyDescription("Treemap or Sunburst")
@@ -137,4 +141,46 @@ class HierarchyChartOpDesc extends PythonOperatorDescriptor {
     finalCode.encode
   }
 
+  // Output is an HTML chart, not a tabular DataFrame.
+  // The translator skips it in the leaf-DataFrame print block.
+  override def producesDataFrame(): Boolean = false
+
+  override def generateStandaloneCode(): String = {
+    val attributes = hierarchy.map(section => pyStringLiteral(section.attributeName)).mkString(", ")
+    val valueLit = pyStringLiteral(value)
+    // The error page is written to output.html, the same file a plotted chart lands
+    // in, so a reason for "no chart" is where the reader looks for the chart —
+    // printing it to the terminal alone left output.html absent. render_error's
+    // continuation line keeps the runtime path's indentation, since the HTML is
+    // triple-quoted and those spaces reach the browser.
+    s"""def render_error(error_msg):
+       |    return '''<h1>Hierarchy chart is not available.</h1>
+       |                  <p>Reason is: {} </p>
+       |               '''.format(error_msg)
+       |
+       |def fail(error_msg):
+       |    with open("output.html", "w", encoding="utf-8") as output:
+       |        output.write(render_error(error_msg))
+       |    print(f"Hierarchy chart error: {error_msg}")
+       |
+       |if in1df.empty:
+       |    fail("input table is empty.")
+       |else:
+       |    # On a copy: the same frame can feed another branch of the plan, and
+       |    # both the assignment and the drop below would otherwise reach it.
+       |    chart_df = in1df.copy()
+       |    chart_df[$valueLit] = chart_df[chart_df[$valueLit] > 0][$valueLit]
+       |    chart_df = chart_df.dropna(subset=[$attributes])
+       |    if chart_df.empty:
+       |        fail("value column contains only non-positive numbers or nulls.")
+       |    else:
+       |        fig = px.${hierarchyChartType.getPlotlyExpressApiName}(chart_df, path=[$attributes], values=$valueLit,
+       |                         color=$valueLit, hover_data=[$attributes],
+       |                         color_continuous_scale='RdBu')
+       |        fig.update_layout(margin=dict(l=0, r=0, b=0, t=0))
+       |        fig.write_json("output.json")
+       |        fig.write_html("output.html")
+       |        print("Hierarchy chart saved to output.html")""".stripMargin
+  }
+
 }