R: معالجة سلاسل R: دليل شامل لمكتبة `stringr`

Name      Cell phone number            Email
Alice      138-0000-1234     zhangsan@163.COM
Bob      +86 139 0000 5678  lisi@example.com  
Charlie      (13900001111)    wangwu@gmail.com
Diana      138.0000.2222     zhaoliu@ qq.com
Eve      13900003333       

Name      Cell phone number       Email
Alice      13800001234  zhangsan@163.com
Bob      13900005678  lisi@example.com
Charlie      13900001111  wangwu@gmail.com
Diana      13800002222  zhaoliu@qq.com
Eve      13900003333  NA

library(stringr)

# 1. Delete a Phone Number(Remove spaces,-,.,+86,())
clean_phone <- str_replace_all(phones, "[\\s\\-\\.\\(\\)\\+86]", "")

# 2. Clean Up Your Inbox(Remove spaces,Convert to lowercase)
clean_email <- str_trim(emails) |> str_to_lower()

# 3. Verify the mobile phone number format
is_valid_phone <- str_detect(clean_phone, "^1[3-9]\\d{9}$")

# 1. Single quotation mark
s1 <- 'Hello'

# 2. Double quotation marks
s2 <- "World"

# 3. Character vector
fruits <- c("Apple", "Banana", "Cherries")
class(fruits)
# [1] "character"

# 4. nchar Number of characters
nchar("Hello")
# [1] 5

nchar("Hello")  # UTF-8 One Chinese character 1 characters
# [1] 2

# paste Default sep = " "
paste("Hello", "World")
# [1] "Hello World"

# paste0 No separators
paste0("Hello", "World")
# [1] "HelloWorld"

# Vectorized Concatenation
paste("No.", 1:3, "Place")
# [1] "No. 1 Place" "No. 2 Place" "No. 3 Place"

# collapse Combine vectors into a single string
paste(c("A", "B", "C"), collapse = "-")
# [1] "A-B-C"

library(stringr)

# 1. Basic Splicing
str_c("Hello", "World", sep = " ")
# [1] "Hello World"

# 2. Multi-Parameter Concatenation
str_c("a", "b", "c", sep = "-")
# [1] "a-b-c"

# 3. Vectorized Concatenation
str_c("No.", 1:3, "Place", sep = "")
# [1] "No.1Place" "No.2Place" "No.3Place"

# 4. collapse Merge Vectors
str_c(c("A", "B", "C"), collapse = " | ")
# [1] "A | B | C"

# 5. Processing NA
str_c("Hello", NA, "World")
# [1] NA
str_c("Hello", NA, "World", na.rm = TRUE)
# [1] "HelloWorld"

# Number of characters(Not the number of bytes)
str_length("Hello")
# [1] 5

str_length("Hello")
# [1] 2

# String Vectors
str_length(c("abc", "Hello", "Hello World"))
# [1]  3  2 12

# NA Processing
str_length(NA)
# [1] NA  ← stringr Explicit Return NA

# 1. Extract a Substring(1-based,Including both ends)
str_sub("Hello World", 1, 5)
# [1] "Hello"

# 2. Negative Index(From the last digit)
str_sub("Hello World", -5)  # Finally 5 ea
# [1] "World"

# 3. Modify a Substring
s <- "Hello World"
str_sub(s, 1, 5) <- "Hi"
s
# [1] "Hi World"

# 4. Vectorization
str_sub(c("apple", "banana", "cherry"), 1, 3)
# [1] "app" "ban" "che"

# 1. Does it contain a substring?
str_detect("Hello World", "World")
# [1] TRUE

# 2. Using regular expressions
str_detect(c("apple", "banana", "cherry"), "^a")  # Starting with a
# [1]  TRUE FALSE FALSE

# 3. Count(Includes several times)
str_count("ababab", "ab")
# [1] 3

# 1. Replace the first match
str_replace("Hello World World", "World", "R")
# [1] "Hello R World"

# 2. Replace all matches
str_replace_all("Hello World World", "World", "R")
# [1] "Hello R R"

# 3. Using regular expressions
str_replace_all("abc 123 def 456", "\\d+", "X")
# [1] "abc X def X"

# 1. Remove leading and trailing spaces
str_trim("  Hello World  ")
# [1] "Hello World"

# 2. Left edge
str_trim("  Hello", side = "left")
# [1] "Hello"

# 3. Go to the right end
str_trim("Hello  ", side = "right")
# [1] "Hello"

# 1. Left-aligned
str_pad("42", width = 5, side = "left", pad = "0")
# [1] "00042"

# 2. Right-aligned
str_pad("Hi", width = 5, side = "right", pad = "-")
# [1] "Hi---"

# 3. Filled on both sides
str_pad("Hi", width = 6, side = "both", pad = "-")
# [1] "--Hi--"

# 1. All Caps
str_to_upper("Hello World")
# [1] "HELLO WORLD"

# 2. All lowercase
str_to_lower("Hello World")
# [1] "hello world"

# 3. Capitalize the first letter
str_to_title("hello world")
# [1] "Hello World"

# 4. Capitalize the first word of a sentence
str_to_sentence("hello world")
# [1] "Hello world"

# Truncate excessively long strings(add ...)
str_trunc("This is a very long sentence.", width = 10)
# [1] "This is..."

# 1. Basic Division
str_split("a,b,c", ",")
# [[1]]
# [1] "a" "b" "c"

# 2. Limit on the Number of Partitions
str_split("a,b,c", ",", n = 2)
# [[1]]
# [1] "a"     "b,c"

# 3. Simplify the result(Vectors, Not Lists)
str_split("a,b,c", ",", simplify = TRUE)
#      [,1] [,2] [,3]
# [1,] "a"  "b"  "c"

# ============================================
# In-Depth Cleaning of Customer Data
# Features:Delete a Phone Number,Email,Name,Address
# ============================================

library(stringr)
library(dplyr)

# 1. Preparing Raw Data
customers <- tibble(
  name = c("  Alice  ", "Bob", "wangwu", "ZHAO liu", "Eve"),
  phone = c("138-0000-1234", "+86 139 0000 5678", "(13900001111)",
            "138.0000.2222", "13900003333"),
  email = c("zhangsan@163.COM", " lisi@example.com  ",
            "wangwu@gmail.com", "zhaoliu@ qq.com", NA)
)

cat("=== Raw Data ===\n")
print(customers)

# 2. Clean Name
customers <- customers |>
  mutate(
    # Remove spaces + Capitalize the first letter(English Name)
    name_clean = str_trim(name) |>
      str_to_title() |>
      str_replace_all("\\s+", " ")  # Replace multiple spaces with a single space
  )

# 3. Delete a Phone Number(Remove spaces,-,.,+86,())
customers <- customers |>
  mutate(
    phone_clean = str_replace_all(phone, "[\\s\\-\\.\\(\\)\\+86]", ""),
    # Verification 11 Mobile phone number
    phone_valid = str_detect(phone_clean, "^1[3-9]\\d{9}$")
  )

# 4. Clean Up Your Inbox
customers <- customers |>
  mutate(
    email_clean = str_trim(email) |> str_to_lower(),
    # Verify the email address format
    email_valid = str_detect(email_clean, "^[\\w.+-]+@[\\w.-]+\\.[a-z]{2,}$")
  )

# 5. Output the cleaning results
cat("\n=== Data After Cleaning ===\n")
print(customers |> select(name_clean, phone_clean, phone_valid,
                          email_clean, email_valid))

# 6. Extracting Data Features
customers <- customers |>
  mutate(
    # Identify the mobile carrier based on a phone number
    operator = case_when(
      str_detect(phone_clean, "^1(3[0-9]|4[5-9]|5[0-35-9]|66|7[2-35-8]|8[0-9]|9[0-35-9])\\d{8}$") ~ "China Mobile",
      str_detect(phone_clean, "^1(3[0-2]|4[5-7]|5[3-5-7]|6[2567]|7[0-3]|8[0-3])\\d{8}$") ~ "China Unicom",
      str_detect(phone_clean, "^1(33|34|49|53|7[37]|8[0-2])\\d{8}$") ~ "China Telecom",
      TRUE ~ "Unknown"
    ),
    # Email Domain
    email_domain = str_extract(email_clean, "@[a-z0-9.]+"),
    # Before the phone number 3 bit
    phone_prefix = str_sub(phone_clean, 1, 3)
  )

cat("\n=== Data Characteristics ===\n")
print(customers |> select(name_clean, operator, phone_prefix, email_domain))

# 7. Text Statistics
cat("\n=== Distribution of Email Domain Names ===\n")
print(table(customers$email_domain))

cat("\n=== Distribution of Carriers ===\n")
print(table(customers$operator))

# 8. Identify invalid data
cat("\n=== Invalid data ===\n")
invalid <- customers |> filter(!phone_valid | !email_valid)
print(invalid |> select(name_clean, phone_clean, phone_valid,
                        email_clean, email_valid))

=== Data After Cleaning ===
# A tibble: 5 × 6
  name_clean phone_clean   phone_valid email_clean         email_valid
  <chr>      <chr>         <lgl>       <chr>               <lgl>      
1 Alice       13800001234   TRUE        zhangsan@163.com    TRUE       
2 Bob       13900005678   TRUE        lisi@example.com    TRUE       
3 Wangwu     13900001111   TRUE        wangwu@gmail.com    TRUE       
4 Zhao Liu   13800002222   TRUE        zhaoliu@qq.com      TRUE       
5 Eve       13900003333   TRUE        <NA>                FALSE      

=== Distribution of Carriers ===
  China Telecom China Unicom China Mobile 
        1        2        2