Quickstart

import pandas as pd

from parquetranger import TableRepo

df = pd.DataFrame(
    {
        "A": [1, 2, 3, 4, 5, 6],
        "B": ["x", "y", "z", "x1", "x2", "x3"],
        "C": [1, 2, 1, 1, 1, 2],
        "C2": ["a", "a", "b", "a", "c", "c"],
    },
    index=["a1", "a2", "a3", "a4", "a5", "a6"],
)

df

	A	B	C	C2
a1	1	x	1	a
a2	2	y	2	a
a3	3	z	1	b
a4	4	x1	1	a
a5	5	x2	1	c
a6	6	x3	2	c

trepo = TableRepo("some_tmp_path", group_cols="C2")  # this creates the directory

trepo.extend(df)

trepo.get_full_df()

	A	B	C	C2
a1	1	x	1	a
a2	2	y	2	a
a4	4	x1	1	a
a3	3	z	1	b
a5	5	x2	1	c
a6	6	x3	2	c

df2 = pd.DataFrame(
    {
        "A": [21, 22, 23],
        "B": ["X", "Y", "Z"],
        "C": [10,20,1],
        "C2": ["a", "b", "a"],
    },
    index=["a1", "a4", "a7"]
    )

trepo.replace_records(df2)  # replaces based on index

trepo.get_full_df()

	A	B	C	C2
a2	2	y	2	a
a1	21	X	10	a
a7	23	Z	1	a
a3	3	z	1	b
a4	22	Y	20	b
a5	5	x2	1	c
a6	6	x3	2	c

trepo.replace_groups(df2)

trepo.get_full_df()  # replaced the whole groups where C2==a and C2==b with the records that were present in df2

	A	B	C	C2
a1	21	X	10	a
a7	23	Z	1	a
a4	22	Y	20	b
a5	5	x2	1	c
a6	6	x3	2	c

trepo.replace_all(df2)  # erases everything and puts df2 in. all traces of df are lost

trepo.get_full_df()

	A	B	C	C2
a1	21	X	10	a
a7	23	Z	1	a
a4	22	Y	20	b

trepo.replace_records(df, by_groups=True)  # replaces records based on index, but only looks for indices within groups, so this way duplicate a4 index is possible
# as they are in different groups, with different values in C2

trepo.get_full_df()

	A	B	C	C2
a7	23	Z	1	a
a1	1	x	1	a
a2	2	y	2	a
a4	4	x1	1	a
a4	22	Y	20	b
a3	3	z	1	b
a5	5	x2	1	c
a6	6	x3	2	c

trepo.purge()  # deletes everything