grouping, ordering, and filling in Python and R

group-and-fill.py

import numpy as np, pandas as pd

# code to be compared to group-and-fill.R
# task: fill specific columns down, within each group, ordering by the order.
df = pd.DataFrame(
    columns=["group", "order", "attribute_1", "attribute_2", "irrelevant"],
    data = [
        ["a",    0,      1,      1, "hello"],
        ["a",    2, np.nan,      3,  np.nan],  # this one out of order
        ["a",    1,      6, np.nan, "world"],
        ["b",    0,      2,      7, "foo"  ],
        ["b",    1, np.nan,     10, "bar"  ],
    ]
)
df.sort_values(by=["group", "order"], inplace=True)
df[["attribute_1", "attribute_2"]] = (
    df
    .groupby("group")["attribute_1", "attribute_2"]
    .apply(lambda group: group.ffill())
)
df

group-and-fill.R

# code to be compared to group-and-fill.py
# task: fill specific columns down, within each group, ordering by the order.
library(tidyverse)

df <- tribble(
  ~group, ~order, ~attribute_1, ~attribute_2, ~irrelevant,
  "a",   0,    1,    1,   "hello",
  "a",   2,   NA,    3,    NA    , # this one out of ordr
  "a",   1,    6,   NA,   "world",
  "b",   0,    2,    7,   "foo"  ,
  "b",   1,   NA,   10,   "bar"
)

df %>% 
  group_by(group) %>% 
  arrange(group, order) %>% 
  fill(attribute_1, attribute_2)