Data analysis isn’t just about numbers—it’s about stories.
In this report, we use the famous iris dataset and the powerful {report} package in R to narrate a tale hidden within petal lengths, sepal widths, and three unique flower species. The {report} package allows us to go beyond charts and tables, turning statistical summaries into clear, human-readable insights.
We’ll walk through:
Key flower characteristics
How species differ through statistical summaries and visuals
Whether a model can “tell” us about flower type from its features
Let’s begin—petal by petal.
df <- iris
head(df) Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6 3.1 1.5 0.2 setosa
5 5.0 3.6 1.4 0.2 setosa
6 5.4 3.9 1.7 0.4 setosaThis dataset contains 150 flower samples from 3 iris species: setosa, versicolor, and virginica.
str(df)'data.frame': 150 obs. of 5 variables:
$ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
$ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
$ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
$ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
$ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...for (col in names(df)[sapply(df, is.numeric)]) {
mean_val <- round(mean(df[[col]]), 2)
min_val <- min(df[[col]])
max_val <- max(df[[col]])
cat(glue("**{col}** ranges from {min_val} to {max_val}, with an average of {mean_val}.\n\n"))
}**Sepal.Length** ranges from 4.3 to 7.9, with an average of 5.84.
**Sepal.Width** ranges from 2 to 4.4, with an average of 3.06.
**Petal.Length** ranges from 1 to 6.9, with an average of 3.76.
**Petal.Width** ranges from 0.1 to 2.5, with an average of 1.2.for (col in names(df)[sapply(df, is.numeric)]) {
cat("### Variable:", col, "\n\n")
try(print(report(df[[col]])), silent = TRUE)
cat("\n\n")
}### Variable: Sepal.Length
x: n = 150, Mean = 5.84, SD = 0.83, Median = 5.80, MAD = 1.04, range: [4.30,
7.90], Skewness = 0.31, Kurtosis = -0.55, 0% missing
### Variable: Sepal.Width
x: n = 150, Mean = 3.06, SD = 0.44, Median = 3.00, MAD = 0.44, range: [2,
4.40], Skewness = 0.32, Kurtosis = 0.23, 0% missing
### Variable: Petal.Length
x: n = 150, Mean = 3.76, SD = 1.77, Median = 4.35, MAD = 1.85, range: [1,
6.90], Skewness = -0.27, Kurtosis = -1.40, 0% missing
### Variable: Petal.Width
x: n = 150, Mean = 1.20, SD = 0.76, Median = 1.30, MAD = 1.04, range: [0.10,
2.50], Skewness = -0.10, Kurtosis = -1.34, 0% missingThis model gives us a narrative of how petal length differs by species, written in plain English by {report}.
model <- lm(Petal.Length ~ Species, data = df)
report(model)We fitted a linear model (estimated using OLS) to predict Petal.Length with
Species (formula: Petal.Length ~ Species). The model explains a statistically
significant and substantial proportion of variance (R2 = 0.94, F(2, 147) =
1180.16, p < .001, adj. R2 = 0.94). The model's intercept, corresponding to
Species = setosa, is at 1.46 (95% CI [1.34, 1.58], t(147) = 24.02, p < .001).
Within this model:
- The effect of Species [versicolor] is statistically significant and positive
(beta = 2.80, 95% CI [2.63, 2.97], t(147) = 32.51, p < .001; Std. beta = 1.59,
95% CI [1.49, 1.68])
- The effect of Species [virginica] is statistically significant and positive
(beta = 4.09, 95% CI [3.92, 4.26], t(147) = 47.52, p < .001; Std. beta = 2.32,
95% CI [2.22, 2.41])
Standardized parameters were obtained by fitting the model on a standardized
version of the dataset. 95% Confidence Intervals (CIs) and p-values were
computed using a Wald t-distribution approximation.numeric_vars <- df %>% select(where(is.numeric))
for (col in names(numeric_vars)) {
print(
ggplot(df, aes(x = Species, y = .data[[col]], fill = Species)) +
geom_boxplot() +
labs(title = paste(col, "by Species"), x = "Species", y = col) +
theme_minimal()
)
}
“Do different species have different petal or sepal sizes?”
Boxplots compare species visually:
Setosa has much smaller petals than others
Versicolor and Virginica differ more subtly
This reinforces the idea that species identity influences measurements, which is a key part of the story.
ggplot(df, aes(x = Sepal.Length, y = Petal.Length, color = Species)) +
geom_point(size = 3, alpha = 0.7) +
labs(title = "Sepal vs Petal Length by Species") +
theme_minimal()
“Can we visually separate the species?”
Scatter plots show relationships between variables, often revealing clusters:
Setosa forms a distinct group
Versicolor and Virginica overlap
These visuals help the reader see why machine learning might work — or struggle.
In this report, we turned a well-known dataset into a compelling narrative—powered by R and the {report} package.
Rather than just plotting and calculating, we let the data speak in plain language. We learned that:
Flower measurements differ significantly across species
Setosa is clearly distinct; Virginica and Versicolor subtly overlap
A statistical model could explain much of this separation
{report} allowed us to describe data not just with numbers, but with sentences
The {report} package reminds us that data storytelling is not just for analysts—it’s for readers. When we write our results like we speak, we make insights accessible, reproducible, and beautifully human.
This is how we let data tell its story.