[Drop NA] Drop rows containing missing values NA in a data frame #python #R

drop_na.py

# Refs: https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.dropna.html
import pandas as pd
import numpy as np

df = pd.DataFrame({"x": [1, 2, np.nan],
                "y": ["a", np.nan, "b"]
                })

# Drop each row containing at least a NA
df.dropna()
#      x  y
# 0  1.0  a

# Drop each row where the x column contains a NA
df.dropna(subset=["x"])
#      x    y
# 0  1.0    a
# 1  2.0  NaN

drop_na.R

# Refs: https://tidyr.tidyverse.org/reference/drop_na.html
library(dplyr)
library(tidyr)

df <- tibble(x = c(1, 2, NA), y = c("a", NA, "b"))

# Drop each row containing at least a NA
df %>% drop_na()
# # A tibble: 1 x 2
#       x y    
#   <dbl> <chr>
# 1     1 a

# Drop each row where the x column contains a NA
df %>% drop_na(x)
# # A tibble: 2 x 2
#       x y    
#   <dbl> <chr>
# 1     1 a    
# 2     2 NA