add data

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+df.json filter=lfs diff=lfs merge=lfs -text
+issues.json filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9
+
+WORKDIR /code
+ENV HOME=/code
+
+RUN pip install pip -U
+
+RUN pip install renumics-spotlight==1.3.0
+
+COPY . .
+COPY image/ .
+RUN chmod -R 777 /code
+CMD ["python", "run.py"]

df.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab769cff7e24089bfa5c126d88b3e582b490c9d30f2122f7a9bd699381d96ab1
+size 2124164

issues.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b6d1d9468b412057cb9a7fdab4f5df3eca880b98f25ab3467e703e2a548ebd
+size 39848

run.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import numpy as np
+from renumics import spotlight
+from renumics.spotlight.analysis.typing import DataIssue
+
+
+if __name__ == "__main__":
+    df = pd.read_json("df.json")
+    # df[
+    #     "GitHub"
+    # ] = '<a href="https://github.com/Renumics/spotlight" target="_blank">⭐ Check Out Spotlight on GitHub</a>'
+
+    issues = pd.read_json("issues.json")
+
+    spotlight_issues = []
+    for _, issue in issues.sort_values("metric").iterrows():
+        issue_metric = issue["metric"]
+        issue_title = f"{issue_metric:.2f} -> " + issue["explanation"]
+
+        predicate_strings = [
+            f"{x['minimum']:.1f}  < {x['column']} < {x['maximum']:.1f}"
+            for x in issue["predicates"]
+            if ("minimum" in x and "maximum" in x)
+        ]
+        issue_explanation = "; ".join(predicate_strings)
+
+        data_issue = DataIssue(
+            severity="medium",
+            title=issue_title,
+            description=issue_explanation,
+            rows=issue["rows"],
+            columns=[x["column"] for x in issue["predicates"]],
+        )
+        spotlight_issues.append(data_issue)
+
+    while True:
+        dtypes = {
+            "sg_projection": spotlight.Embedding,
+        }
+        view = spotlight.show(
+            df,
+            dtype=dtypes,
+            port=7860,
+            host="0.0.0.0",
+            allow_filebrowsing=False,
+            issues=spotlight_issues,
+            # layout="spotlight-layout.json",
+        )
+
+        view.close()