# These two numbers look the same, but R considers them "unequal"
1 == 1L
# [1] FALSE

# Verify their types
typeof(1)
# [1] "double"  (Double-precision floating-point numbers)

typeof(1L)
# [1] "integer" (Integer)

# numeric —— Double-precision floating-point numbers(Default number)
x <- 3.14
typeof(x)
# [1] "double"

# integer -- Strict Integers (Add L Suffix)
x <- 10L
typeof(x)
# [1] "integer"

# character —— String
x <- "Hello R"
typeof(x)
# [1] "character"

# logical —— Logical value(Must be all uppercase)
x <- TRUE
typeof(x)
# [1] "logical"

# complex —— Plural
x <- 1 + 2i
typeof(x)
# [1] "complex"

# Performance Comparison(1 A billion integers vs 1 A billion floating-point numbers)
# integer: ~400 MB
# numeric: ~800 MB

# Not required in normal situations integer,numeric That's enough

# 1. Ordinary Vectors:The two are consistent
x <- 1:10
typeof(x)
# [1] "integer"
class(x)
# [1] "integer"

# 2. Data Frame: The two are different!
y <- data.frame(a = 1:3, b = c("x", "y", "z"))
typeof(y)
# [1] "list"        ← The bottom layer is list

class(y)
# [1] "data.frame"  ← In business terms, it's a data frame.

# is.numeric() is the "superset" of is.integer()
is.numeric(1)     # [1] TRUE
is.numeric(1L)    # [1] TRUE
is.integer(1)     # [1] FALSE
is.integer(1L)    # [1] TRUE

# String → Numbers(Success)
as.numeric("3.14")
# [1] 3.14

# String → Numbers(Failure)
as.numeric("Hello")
# Warning: NAs introduced by coercion
# [1] NA

# One failure won't stop me,But there will be a warning
as.numeric(c("1", "2", "abc", "4"))
# Warning: NAs introduced by coercion
# [1]  1  2 NA  4

# Suppose we read one CSV,All columns are character
df <- data.frame(
  id = c("1", "2", "3"),
  value = c("10.5", "20.3", "30.1")
)

# Before Conversion
str(df)
# 'data.frame':	3 obs. of  2 variables:
#  $ id   : chr  "1" "2" "3"
#  $ value: chr  "10.5" "20.3" "30.1"

# After conversion
df$id <- as.numeric(df$id)
df$value <- as.numeric(df$value)
str(df)
#  $ id   : num  1 2 3
#  $ value: num  10.5 20.3 30.1

# NA Participating in calculations is contagious(NA It won't disappear)
x <- c(1, 2, NA, 4)
sum(x)
# [1] NA  <- The entire result turned out NA

# Must use na.rm = TRUE Skip NA
sum(x, na.rm = TRUE)
# [1] 7

# Inspection NA Location
is.na(x)
# [1] FALSE FALSE  TRUE FALSE

# 0 Divide by 0
0 / 0
# [1] NaN

# Taking the square root of a negative number
sqrt(-1)
# Warning: NaNs produced
# [1] NaN

# NaN It is special. NA(NA a subset of)
is.na(NaN)
# [1] TRUE  ← NaN Me too NA

# 1 Divide by 0
1 / 0
# [1] Inf

# A negative number divided by 0
-1 / 0
# [1] -Inf

# Inspection Inf
is.infinite(c(1, Inf, -Inf, 2))
# [1] FALSE  TRUE  TRUE FALSE

# NULL Doesn't take up memory
x <- NULL
length(x)
# [1] 0

# NA occupies 1 position, NULL disappears entirely
length(c(1, 2, NA, 4))    # [1] 4
length(c(1, 2, NULL, 4))  # [1] 3  ← NULL Swallowed whole

# Default return value for functions with no return value NULL
my_void_func <- function() { }
result <- my_void_func()
is.null(result)
# [1] TRUE

# ============================================
# Cleaning User-Input Data
# Features:Convert a character vector to a number,Processing NA
# ============================================

# 1. Simulate from CSV Read"Dirty Data"(All of them character)
raw_data <- c("1", "2.5", "3.14", "abc", "5", "", "7.8")
cat("Raw Data:\n")
print(raw_data)
cat("Primitive Types:", typeof(raw_data), "\n\n")

# 2. Convert to a number ("abc" and "" will become NA)
nums <- as.numeric(raw_data)
cat("After conversion:\n")
print(nums)

# 3. See which ones are NA
na_positions <- is.na(nums)
cat("\nNA Location:")
print(na_positions)

# 4. Statistics NA Quantity
na_count <- sum(na_positions)
cat("\nNA Quantity:", na_count, "\n")

# 5. Keep only non- NA the number
clean_nums <- nums[!na_positions]
cat("\nData After Cleaning:")
print(clean_nums)

# 6. Statistical Indicators
cat("\n=== Statistical Indicators ===\n")
cat("Total Number of Elements:", length(raw_data), "\n")
cat("Valid Data:", length(clean_nums), "\n")
cat("Invalid data:", na_count, "\n")
cat("Total:", sum(clean_nums), "\n")
cat("Average:", round(mean(clean_nums), 2), "\n")
cat("Maximum value:", max(clean_nums), "\n")
cat("Minimum value:", min(clean_nums), "\n")

Raw Data:
[1] "1" "2.5" "3.14" "abc" "5" "" "7.8"
Primitive Types: character

After conversion:
[1] 1.00 2.50 3.14   NA 5.00   NA 7.80

NA Location:
[1] FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE

NA Quantity: 2

Data After Cleaning:
[1] 1.00 2.50 3.14 5.00 7.80

=== Statistical Indicators ===
Total Number of Elements: 7
Valid Data: 5
Invalid data: 2
Total: 19.44
Average: 3.89
Maximum value: 7.8
Minimum value: 1