mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-27 00:05:13 +02:00
Feature/pkgsplit (#83)
* Starting to spawn base package * More package hacking * Bedrock and VertexAI * Parquet split * Updated templates * Utils
This commit is contained in:
parent
3fb75c617b
commit
9b91d5eee3
262 changed files with 630 additions and 420 deletions
|
|
@ -1,45 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
"""
|
||||
Concatenates multiple parquet files into a single parquet output
|
||||
"""
|
||||
|
||||
import pyarrow as pa
|
||||
import pyarrow.parquet as pq
|
||||
import pandas as pd
|
||||
import sys
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
prog="combine-parquet",
|
||||
description=__doc__
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'-i', '--input',
|
||||
nargs='*',
|
||||
help=f'Input files'
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'-o', '--output',
|
||||
help=f'Output files'
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
df = None
|
||||
|
||||
for file in args.input:
|
||||
|
||||
part = pq.read_table(file).to_pandas()
|
||||
|
||||
if df is None:
|
||||
df = part
|
||||
else:
|
||||
df = pd.concat([df, part], ignore_index=True)
|
||||
|
||||
if df is not None:
|
||||
|
||||
table = pa.Table.from_pandas(df)
|
||||
pq.write_table(table, args.output)
|
||||
Loading…
Add table
Add a link
Reference in a new issue