Add analyze_tables

[GaryShen2008]

Fix #256

Run COMPUTE STATISTICS before query running
It only runs on raw dataset, not including Iceberg and Delta Lake.

[greptile-apps]

Greptile Summary

This PR adds an --analyze_tables flag to both nds_power.py and nds_h_power.py. When set, instead of creating TempViews the scripts register permanent catalog tables via CREATE TABLE IF NOT EXISTS … USING … LOCATION and then run ANALYZE TABLE … COMPUTE STATISTICS on each one before executing benchmark queries; the feature is intentionally skipped for Iceberg and Delta Lake formats.

Confidence Score: 5/5

Safe to merge — all findings are P2 style issues with no functional impact.

Only P2 comments (inconsistent identifier quoting and a stale docstring). The core logic — catalog table creation, ANALYZE execution, and CLI wiring — is correct. No P0 or P1 issues found.

No files require special attention.

Important Files Changed

Filename	Overview
nds/nds_power.py	Adds analyze_tables flag that creates real catalog tables and runs ANALYZE TABLE COMPUTE STATISTICS before benchmark queries; minor inconsistency in backtick quoting for ANALYZE SQL and a stale docstring.
nds-h/nds_h_power.py	Mirrors nds_power.py changes: adds analyze_tables support with the same helper functions and the same minor issues (raw backtick formatting in ANALYZE SQL, stale docstring).

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[run_query_stream called] --> B{input_format\niceberg or delta?}
    B -- Yes, iceberg --> C[register_iceberg_tables]
    B -- Yes, delta --> D[register_delta_tables]
    B -- No --> E{analyze_tables flag?}
    E -- False --> F[reader.load.createOrReplaceTempView\nfor each table]
    E -- True --> G[_create_data_source_table\nCREATE TABLE IF NOT EXISTS USING LOCATION]
    G --> H[ANALYZE TABLE COMPUTE STATISTICS]
    F --> I[Run benchmark queries]
    H --> I
    C --> I
    D --> I

Loading

_{Reviews (2): Last reviewed commit: "Fix typo" | Re-trigger Greptile}

[greptile-apps]

Redundant default=False with store_true

argparse's store_true action already sets default=False implicitly; the explicit default=False is redundant. Same pattern appears in nds/nds_power.py. No functional impact, but it adds noise.

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

[Copilot]

Pull request overview

Adds an optional “analyze tables” step to the NDS and NDS-H power-run drivers so users can precompute Spark table statistics before executing benchmark queries (requested in issue #256).

Changes:

• Add --analyze_tables CLI flag to enable ANALYZE TABLE … COMPUTE STATISTICS after creating each TempView.
• Plumb the analyze_tables option through run_query_stream() → setup_tables() in both NDS and NDS-H power-run scripts.
• Record per-table ANALYZE timing in execution_time_list alongside TempView creation timings.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
nds/nds_power.py	Adds --analyze_tables flag and runs ANALYZE TABLE … COMPUTE STATISTICS after each TempView creation when enabled.
nds-h/nds_h_power.py	Mirrors the same --analyze_tables behavior for the NDS-H power run script.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[wjxiz1992]

LGTM