50 lines
1.3 KiB
Python
Executable File
50 lines
1.3 KiB
Python
Executable File
#!/usr/bin/env -S uv run --script
|
|
# /// script
|
|
# requires-python = ">=3.10"
|
|
# dependencies = [
|
|
# "pandas",
|
|
# "rich",
|
|
# ]
|
|
# ///
|
|
"""
|
|
Sample standalone tool: print a summary of a CSV file.
|
|
|
|
The block above is inline script metadata (PEP 723). uv reads it and runs the
|
|
script in its own throwaway environment, so the tool's dependencies stay out
|
|
of the project's environment.
|
|
|
|
Usage:
|
|
uv run tools/csv_summary.py data.csv
|
|
./tools/csv_summary.py data.csv (after chmod +x)
|
|
"""
|
|
|
|
import argparse
|
|
|
|
import pandas as pd
|
|
from rich.console import Console
|
|
from rich.table import Table
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description=__doc__.strip().splitlines()[0])
|
|
parser.add_argument("csv_file", help="path to the CSV file to summarise")
|
|
args = parser.parse_args()
|
|
|
|
df = pd.read_csv(args.csv_file)
|
|
|
|
table = Table(title=f"{args.csv_file} ({len(df)} rows)")
|
|
table.add_column("column")
|
|
table.add_column("dtype")
|
|
table.add_column("non-null", justify="right")
|
|
table.add_column("mean", justify="right")
|
|
for name in df.columns:
|
|
col = df[name]
|
|
mean = f"{col.mean():.4g}" if pd.api.types.is_numeric_dtype(col) else "-"
|
|
table.add_row(str(name), str(col.dtype), str(col.count()), mean)
|
|
|
|
Console().print(table)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|