filter out one dataframe across multiple columns if any strings in a specific row of another dataframe match in r in r

main.r
# Sample dataframes
df1 <- data.frame(
  id = c(1, 2, 3, 4),
  col1 = c("apple", "banana", "cherry", "date"),
  col2 = c("kiwi", "mango", "pine", "peach"),
  stringsAsFactors = FALSE
)

df2 <- data.frame(
  id = c(1, 2),
  match_col1 = c("apple", "mango"),
  match_col2 = c("kiwi", "peach"),
  stringsAsFactors = FALSE
)

# To filter df1 based on matches in df2 across multiple columns
# First, specify the columns in df1 to check
cols_to_check <- c("col1", "col2")

# Filter function
filter_df <- function(df1, df2, cols_to_check) {
  # Initialize an empty vector to store the indices of rows to keep
  keep_indices <- numeric(0)
  
  # Iterate over each row in df1
  for (i in 1:nrow(df1)) {
    # Assume the row is to be kept initially
    keep_row <- TRUE
    
    # Iterate over each row in df2
    for (j in 1:nrow(df2)) {
      # For each column to check
      for (col in cols_to_check) {
        # If the value in df1 matches the value in df2 for any of the specified columns
        if (df1[i, col] == df2[j, col]) {
          # Do not keep this row
          keep_row <- FALSE
          break
        }
      }
      # If we've already determined not to keep the row, break the loop
      if (!keep_row) break
    }
    
    # If we keep the row, add its index
    if (keep_row) {
      keep_indices <- c(keep_indices, i)
    }
  }
  
  # Return the filtered dataframe
  return(df1[keep_indices, ])
}

# Usage
filtered_df <- filter_df(df1, df2, cols_to_check = c("col1", "col2"))
print(filtered_df)
1510 chars
58 lines