added dashboard process

climateintelligence · Sep 4, 2023 · 70d28c8 · 70d28c8
1 parent db90e85
commit 70d28c8
Show file tree

Hide file tree

Showing 4 changed files with 148 additions and 1 deletion.
diff --git a/duck/db.py b/duck/db.py
@@ -2,7 +2,7 @@
 from rdflib.plugins.sparql import prepareQuery
 
 # Provide the path to the SQLite database in the local folder
-DB_URL = "sqlite:///provenance.db"
+DB_URL = "sqlite:///provenance.sqlite"
 
 class GraphDB(object):
     def __init__(self):

diff --git a/duck/processes/__init__.py b/duck/processes/__init__.py
@@ -1,5 +1,7 @@
 from .wps_clintai import ClintAI
+from .wps_dashboard import Dashboard
 
 processes = [
     ClintAI(),
+    Dashboard(),
 ]
diff --git a/duck/processes/wps_dashboard.py b/duck/processes/wps_dashboard.py
@@ -0,0 +1,89 @@
+from pathlib import Path
+
+from pywps import Process, ComplexOutput, Format
+
+from duck import query
+
+class Dashboard(Process):
+    def __init__(self):
+        # inputs = [
+        #     ComplexInput('input_csv', 'CSV File', supported_formats=[Format('text/csv')]),
+        # ]
+        outputs = [
+            ComplexOutput(
+                'report', 
+                'Generated HTML Report', 
+                as_reference=True,
+                supported_formats=[Format('text/html')]
+            ),
+        ]
+
+        super(Dashboard, self).__init__(
+            self._handler,
+            identifier='dashboard',
+            title='Generate HTML Report',
+            version='1.0',
+            abstract='Generate an HTML report from a provenance database.',
+            # inputs=inputs,
+            outputs=outputs,
+        )
+
+    def _handler(self, request, response):
+        workdir = Path(self.workdir)
+        # input_csv = request.inputs['input_csv'][0].file
+
+        # Query the provenance database ... result is a Pandas DataFrame
+        df = query.query()
+
+        # Generate an HTML report from the DataFrame
+        html_report = self.write_html(df, workdir)
+
+        response.outputs['report'].file = html_report
+        response.outputs['report'].output_format = Format('text/html')
+
+        return response
+
+    def write_html(self, df, workdir):
+        # Convert the DataFrame to an HTML table
+        html_table = df.to_html(index=False)
+
+        # Define the HTML template
+        html_template = f"""
+        <!DOCTYPE html>
+        <html>
+        <head>
+            <title>Provenance Report</title>
+            <style>
+                table {{
+                    border-collapse: collapse;
+                    width: 100%;
+                    border: 1px solid #ddd;
+                }}
+
+                th, td {{
+                    text-align: left;
+                    padding: 8px;
+                }}
+
+                th {{
+                    background-color: #f2f2f2;
+                }}
+
+                tr:nth-child(even) {{
+                    background-color: #f2f2f2;
+                }}
+            </style>
+        </head>
+        <body>
+            <h1>Provenance Report</h1>
+            {html_table}
+        </body>
+        </html>
+        """
+
+        # Write the HTML template to a file
+        outfile = workdir / "provenance_report.html"
+        with outfile.open(mode='w') as file:
+            file.write(html_template)
+
+        return outfile
diff --git a/duck/query.py b/duck/query.py
@@ -0,0 +1,56 @@
+from duck.db import GraphDB
+import pandas as pd
+
+
+def query():
+    query_str = """
+        SELECT ?process ?dataset ?variable ?startTime ?endTime ?input ?output ?min ?max ?stddev
+        WHERE {
+            ?exec rdf:type provone:Execution ;
+                rdfs:label ?process ;
+                clint:dataset_name ?dataset ;
+                clint:variable_name ?variable ;
+                prov:startedAtTime ?startTime ;
+                prov:endedAtTime ?endTime ;
+                clint:min ?min ;
+                clint:max ?max ;
+                clint:stddev ?stddev .
+
+            ?input rdf:type prov:Entity .
+        
+            ?output rdf:type prov:Entity ;
+                prov:qualifiedDerivation [ prov:entity ?input; prov:hadActivity ?exec ] .
+    }
+    """
+    graph_db = GraphDB()
+    results = graph_db.query(query_str)
+
+    data = []
+    for row in results:
+        # print(row)
+        process = row.process.split("/")[-1]
+        dataset = row.dataset.value
+        variable = row.variable.value
+        start_time = row.startTime.value
+        end_time = row.endTime.value
+        input = row.input.split("/")[-1]
+        input = input.split("urn:clint:")[-1]
+        output = row.output.split("/")[-1]
+        output = output.split("urn:clint:")[-1]
+        min = row.min.value
+        max = row.max.value
+        stddev = row.stddev.value
+        data.append({
+            "Process": process, 
+            "Dataset": dataset,
+            "Variable": variable, 
+            "Start Time": start_time, 
+            "End Time": end_time,
+            "Input": input,
+            "Output": output,
+            "Min": min,
+            "Max": max,
+            "StdDev": stddev,
+        })
+    df = pd.DataFrame(data)
+    return df