R: R EDA: التحليل الاستكشافي للبيانات — منهجية شاملة

library(DataExplorer)

# One line EDA Report
create_report(df, output_file = "eda_report.html")

# Prepare the data
df <- iris  # Use iris as demo

# Basic Information
dim(df)         # [1] 150 5  ← 150 row 5 col
nrow(df)        # [1] 150
ncol(df)        # [1] 5
names(df)       # Listed
str(df)         # Structure
# 'data.frame':	150 obs. of  5 variables:
#  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 ...
#  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 ...
#  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 ...
#  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 ...
#  $ Species     : Factor w/ 3 levels "setosa",...

# Data Preview
head(df, 3)    # First 3 rows
tail(df, 3)    # Last 3 rows

# Column Types
sapply(df, class)
# Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species
#   "numeric"    "numeric"   "numeric"   "numeric"    "factor"

# Automatic Recognition
library(dplyr)
df |> summarise(across(everything(), class))

summary(iris)
#   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width
#  Min.   :4.30   Min.   :2.00   Min.   :1.00   Min.   :0.1
#  1st Qu.:5.10   1st Qu.:2.80   1st Qu.:1.60   1st Qu.:0.3
#  Median :5.80   Median :3.00   Median :4.35   Median :1.3
#  Mean   :5.84   Mean   :3.05   Mean   :3.76   Mean   :1.2
#  3rd Qu.:6.40   3rd Qu.:3.30   3rd Qu.:5.10   3rd Qu.:1.8
#  Max.   :7.90   Max.   :4.40   Max.   :6.90   Max.   :2.5
#       Species
#  setosa    :50
#  versicolor:50
#  virginica :50

install.packages("skimr")
library(skimr)

skim(iris)
# ── Data Summary ────────────────────────
# Values                           
# Number of rows                   150
# Number of columns                  5
# ── Variable type: factor ──
# Species: 1 unique, 50 each
# ── Variable type: numeric ──
# Sepal.Length: mean=5.84, sd=0.83, p0=4.3, p25=5.1, p50=5.8, p75=6.4, p100=7.9
# ... (Each variable 20+ metrics)

# Simulating Data with Missing Values
df <- data.frame(
  a = c(1, 2, NA, 4),
  b = c("x", NA, "z", "w"),
  c = c(NA, 2, 3, NA)
)

# Number of missing values
colSums(is.na(df))
# a b c
# 1 1 2

# Proportion of Missing Values
colMeans(is.na(df)) * 100
# a b c
# 25 25 50

# Entire rows with NA
sum(!complete.cases(df))  # [1] 3

install.packages("naniar")
library(naniar)

# Missing Value Patterns
vis_miss(iris)  # iris has no missing values, can draw empty chart
# Simulation with Missing Values
df_with_na <- iris
df_with_na[sample(150, 20), 1] <- NA
df_with_na[sample(150, 10), 3] <- NA
vis_miss(df_with_na)

# Missing Correlation
gg_miss_upset(df_with_na)

# Missing vs Variable Relationships
ggplot(df_with_na, aes(x = Sepal.Length, y = Petal.Length)) +
  geom_miss_point()  # The red dot indicates a missing item.

library(ggplot2)

# Histogram
ggplot(iris, aes(x = Sepal.Length)) +
  geom_histogram(bins = 30, fill = "skyblue", color = "white") +
  labs(title = "Sepal.Length Distribution")

# Density Plot
ggplot(iris, aes(x = Sepal.Length, fill = Species)) +
  geom_density(alpha = 0.5) +
  labs(title = "Sepal.Length Distribution by Species")

# Box-and-Whisker Plot (Identifying Outliers)
ggplot(iris, aes(y = Sepal.Length)) +
  geom_boxplot(fill = "lightblue", outlier.color = "red") +
  labs(title = "Sepal.Length Box-and-Whisker Plot")

# Box-and-Whisker Plot by Species
ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
  geom_boxplot() +
  labs(title = "Sepal.Length Distribution by Species")

# Scatter Plot + Return
ggplot(iris, aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
  geom_point(size = 3) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Sepal vs Petal Length")

# Pair Graphs (Scatter Plot Matrix)
library(GGally)
ggpairs(iris, aes(color = Species))

# CalculateCorrelation Coefficient
cor_matrix <- cor(iris |> select(-Species))
print(round(cor_matrix, 2))

# Visualization of Related Matrices
library(corrplot)
corrplot(cor_matrix, method = "circle", type = "upper")

# ggplot2 Version
library(reshape2)
melted <- melt(cor_matrix)
ggplot(melted, aes(Var1, Var2, fill = value)) +
  geom_tile() +
  scale_fill_gradient2(low = "blue", high = "red", mid = "white",
                       midpoint = 0) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

detect_outliers <- function(x) {
  q1 <- quantile(x, 0.25, na.rm = TRUE)
  q3 <- quantile(x, 0.75, na.rm = TRUE)
  iqr <- q3 - q1
  lower <- q1 - 1.5 * iqr
  upper <- q3 + 1.5 * iqr
  x < lower | x > upper
}

# Applications
iris |>
  mutate(across(where(is.numeric), detect_outliers, .names = "{.col}_out")) |>
  select(ends_with("_out")) |>
  summarise(across(everything(), sum))

# Sepal.Length_out Sepal.Width_out Petal.Length_out  Petal.Width_out
#        0                4               0                0

detect_outliers_z <- function(x, threshold = 3) {
  z <- (x - mean(x, na.rm = TRUE)) / sd(x, na.rm = TRUE)
  abs(z) > threshold
}

install.packages("DataExplorer")
library(DataExplorer)

# 1. One-Line Report
create_report(iris, output_file = "eda_report.html")

# 2. Report Contents
plot_intro(iris)        # Data Overview
plot_missing(iris)      # Missing values
plot_histogram(iris)    # Histogram of All Numeric Columns
plot_density(iris)      # Density Plot
plot_bar(iris)          # Bar Chart by Category
plot_boxplot(iris)      # Box-and-Whisker Plot
plot_scatterplot(iris)  # Scatter Plot Matrix
plot_correlation(iris)  # Related Matrices

install.packages("SmartEDA")
library(SmartEDA)

ExpReport(iris, op_file = "smarteda_report.html")
ExpNumStat(iris)         # Statistical Data
ExpCatStat(iris)         # Categorical Statistics

# ============================================
# iris + mpg Both Datasets Complete EDA
# Features: 5-step EDA Complete Process
# ============================================

library(ggplot2)
library(dplyr)
library(skimr)
library(naniar)
library(GGally)

# 1. Step 1: Data Shape
cat("=== Step 1: Data Shape ===\n")
cat("iris:", nrow(iris), "rows x", ncol(iris), "cols\n")
cat("mpg:", nrow(mpg), "rows x", ncol(mpg), "cols\n\n")

# 2. Step 2: Type + Abstract
cat("=== Step 2: Type and Abstract ===\n")
cat("iris Column Types:\n")
print(sapply(iris, class))
cat("\nmpg Column Types:\n")
print(sapply(mpg, class))

cat("\niris Summary:\n")
print(summary(iris))

cat("\nmpg Summary:\n")
print(summary(mpg |> select(displ, year, cyl, cty, hwy)))

# 3. Step 3: Missing Value Analysis
cat("\n=== Step 3: Missing values ===\n")
cat("iris Missing values:", sum(is.na(iris)), "\n")
cat("mpg Missing values:", sum(is.na(mpg)), "\n\n")

# Simulation with Missing Data
set.seed(42)
iris_na <- iris
iris_na[sample(150, 20), 1] <- NA
iris_na[sample(150, 10), 3] <- NA

vis_miss(iris_na, cluster = TRUE)
gg_miss_upset(iris_na)

# 4. Step 4: Distribution Visualization
cat("\n=== Step 4: Distribution Visualization ===\n")

# 4.1 Distribution of Numeric Variables
iris |>
  select(-Species) |>
  pivot_longer(everything(), names_to = "variable", values_to = "value") |>
  ggplot(aes(x = value)) +
  geom_histogram(bins = 20, fill = "skyblue", color = "white") +
  facet_wrap(~ variable, scales = "free") +
  labs(title = "iris 4 Distribution of a Numeric Variable")

# 4.2 By Component
ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
  geom_boxplot() +
  labs(title = "Sepal.Length Box-and-Whisker Plot by Species")

# 4.3 Scatter Plot Matrix
ggpairs(iris, aes(color = Species))

# 5. Step 5: Correlation Matrix
cat("\n=== Step 5: Correlation Matrix ===\n")
cor_matrix <- cor(iris |> select(-Species))
print(round(cor_matrix, 2))

library(corrplot)
corrplot(cor_matrix, method = "circle", type = "upper",
         addCoef.col = "black", number.cex = 0.8)

# 6. Outlier Detection
cat("\n=== Step 6: Outlier Detection ===\n")
detect_outliers <- function(x) {
  q1 <- quantile(x, 0.25, na.rm = TRUE)
  q3 <- quantile(x, 0.75, na.rm = TRUE)
  iqr <- q3 - q1
  lower <- q1 - 1.5 * iqr
  upper <- q3 + 1.5 * iqr
  sum(x < lower | x > upper, na.rm = TRUE)
}

iris |>
  summarise(across(where(is.numeric), detect_outliers)) |>
  print()

# 7. Automated Reports
cat("\n=== Step 7: Automated Reports ===\n")
library(DataExplorer)
create_report(iris, output_file = "iris_eda_report.html")
cat("iris_eda_report.html Generated\n")
create_report(mpg, output_file = "mpg_eda_report.html")
cat("mpg_eda_report.html Generated\n")

# 8. Summary of Business Insights
cat("\n=== Business Insights ===\n")
cat("1. iris 4 None of the numerical variables have missing values.\n")
cat("2. Setosa Species' Petal.Length Significantly smaller than the other two\n")
cat("3. Petal.Length and Petal.Width Highly correlated (0.96)\n")
cat("4. Sepal.Width The distribution is approximately normal\n")
cat("5. mpg 11 Numeric variables, 38 Vehicle models\n")