[DOCS] Add blog post: spatial statistics with sedona.stats

[jiayuasu]

Did you read the Contributor Guide?

• Yes, I have read the Contributor Rules and Contributor Development Guide

Is this PR related to a ticket?

• No: this is a documentation update. The PR name follows the format [DOCS] my subject

What changes were proposed in this PR?

A new blog post on the spatial statistics module (sedona.stats), which currently has no blog coverage. It works through the classic exploratory-spatial-analysis workflow as one investigation on the OSM POI shapefile bundled at docs/usecases/data (12,873 points):

• Moran's I — global spatial autocorrelation (is anything clustered at all?)
• Getis-Ord Gi* — hotspot significance on a geohash grid (where, exactly?)
• DBSCAN — density clustering with spheroidal distances (what are the groupings?)
• Local Outlier Factor — spatial anomalies (who doesn't belong?)
• A closing section on how each primitive distributes (distance-join weighting, connected-components clustering, ST_KNN-based neighbor search)

Includes a cover image and three figures rendered from the actual analysis results (hotspot z-score map, cluster map, outlier map). The post also notes the Spark checkpoint-directory requirement for DBSCAN and uses a CAST(... AS DOUBLE) on the count column for Moran's I — the integer-column failure behind that workaround is filed as #3218.

How was this patch tested?

• Every snippet was executed against Apache Sedona (PySpark, current snapshot jars) on the bundled shapefile; all numbers shown (Moran I = 0.2519 / z = 12.69, 26 significant Gi* hotspots with top z = 14.94, 72 DBSCAN clusters, LOF top outliers) are the real outputs of those runs.
• The three figures are plotted directly from the exported results of the same runs; the implementation claims in the scale section were checked against the Scala sources (Weighting, DBSCAN, LocalOutlierFactor).
• The site was built with mkdocs serve and the rendered post verified (all four images load, code highlighting, blog index entry).
• SVG validated as well-formed XML; pre-commit hooks pass on the changed files.

Did this PR include necessary documentation updates?

• Yes, I have updated the documentation.