8 Stitching function

View or edit on GitHub

This page is synchronized from trase/models/lp/8_Stitching_function.ipynb. Last modified on 2026-05-06 16:54 CEST by Trase Admin. Please view or edit the original file there; changes should be reflected here after a midnight build (CET time), or manually triggering it with a GitHub action (link).

Stitching function

import pandas as pd

from trase.tools.sps import stitch_dataframes


df_1 = pd.DataFrame(
    data=[
        ("FARM-1", "SILO-1", 55),
        ("FARM-2", "SILO-1", 55),
        ("FARM-1", "SILO-2", 10),
        ("FARM-3", "SILO-3", 20),
    ],
    columns=["farm", "silo", "vol"],
)
df_1

	farm	silo	vol
0	FARM-1	SILO-1	55
1	FARM-2	SILO-1	55
2	FARM-1	SILO-2	10
3	FARM-3	SILO-3	20

df_2 = pd.DataFrame(
    data=[
        ("SILO-1", "PORT-1", 50),
        ("SILO-1", "PORT-2", 50),
        ("SILO-2", "PORT-1", 50),
    ],
    columns=["silo", "port", "vol"],
)
df_2

	silo	port	vol
0	SILO-1	PORT-1	50
1	SILO-1	PORT-2	50
2	SILO-2	PORT-1	50

df = stitch_dataframes(df_1, df_2, volume_column="vol")
df

	farm	matched	port	silo	vol
0	FARM-1	True	PORT-1	SILO-1	25.0
1	FARM-2	True	PORT-1	SILO-1	25.0
2	FARM-1	True	PORT-2	SILO-1	25.0
3	FARM-2	True	PORT-2	SILO-1	25.0
4	FARM-1	True	PORT-1	SILO-2	10.0
0	FARM-1	False	UNKNOWN	SILO-1	5.0
4	FARM-2	False	UNKNOWN	SILO-1	5.0
6	FARM-3	False	UNKNOWN	SILO-3	20.0
4	UNKNOWN	False	PORT-1	SILO-2	40.0

df = stitch_dataframes(df_1, df_2, volume_column="vol", indicator=True)
df

	_matched	farm	port	silo	vol
0	both	FARM-1	PORT-1	SILO-1	25.0
1	both	FARM-2	PORT-1	SILO-1	25.0
2	both	FARM-1	PORT-2	SILO-1	25.0
3	both	FARM-2	PORT-2	SILO-1	25.0
4	both	FARM-1	PORT-1	SILO-2	10.0
0	left_only	FARM-1	UNKNOWN	SILO-1	5.0
4	left_only	FARM-2	UNKNOWN	SILO-1	5.0
6	left_only	FARM-3	UNKNOWN	SILO-3	20.0
4	right_only	UNKNOWN	PORT-1	SILO-2	40.0