8d89fe80ff
- Archive: 85 agent .txt files → docs/archive/agents/legacy_txt/ - Scripts: Move 110 shell scripts → scripts/ (keep deploy.sh in root) - Models: Move 18 .safetensors → ml/models/checkpoints/training_artifacts/ - Delete: 34 directories (~33GB freed) - target/, coverage_*, test artifacts - Build: Clean 14 build artifacts (.rlib, .o, .pid, binaries) - Tests: Move 14 .rs files → tests/standalone/ - SQL: Move 5 files → sql/ (keep init-db*.sql for Docker) - Wave 153: Archive to docs/archive/historical/wave153/ - Docs: Archive 9 markdown files to wave_d/reports/ and historical/ Total impact: ~34GB freed (both waves), root directory cleaned from 583 to ~40 essential files Directory count reduced from 65 to 31 (52% reduction) All historical data preserved in organized archive structure
26 lines
853 B
Rust
26 lines
853 B
Rust
//! Quick utility to check Parquet file row count
|
|
use std::fs::File;
|
|
|
|
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
|
let args: Vec<String> = std::env::args().collect();
|
|
let path = args.get(1).expect("Usage: check_parquet_rows <file.parquet>");
|
|
|
|
let file = File::open(path)?;
|
|
let builder = parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder::try_new(file)?;
|
|
let metadata = builder.metadata();
|
|
|
|
let mut total_rows = 0;
|
|
for i in 0..metadata.num_row_groups() {
|
|
total_rows += metadata.row_group(i).num_rows();
|
|
}
|
|
|
|
println!("{} rows in {}", total_rows, path);
|
|
println!("Minimum required: 120 rows (50 warmup + 60 lookback + 10 forecast)");
|
|
if total_rows < 120 {
|
|
println!("❌ INSUFFICIENT DATA");
|
|
} else {
|
|
println!("✅ Sufficient data");
|
|
}
|
|
Ok(())
|
|
}
|