Machine Learning

Iris Feature Analysis and Visualization in Python

Load the Iris dataset from scikit-learn, create a seaborn feature pairplot, and explore species separation patterns using an AI data analyst.

What

This AI Data Analyst workflow loads the Iris dataset from scikit-learn into a pandas DataFrame and reports basic statistics and dataset shape. It generates a seaborn pairplot of the four numeric features, colored by species, to visualize pairwise relationships. It then compares feature separation patterns across species and summarizes which measurements most clearly distinguish the classes.

Who

This is for learners and analysts who want a compact, conversational example of exploratory data analysis on a classic multiclass dataset. It helps you practice interpreting pairplots and translating visual separation into a feature-level summary.

Tools

  • scikit-learn
  • pandas
  • seaborn
  • matplotlib
  • numpy

Outcomes

  • Iris DataFrame with shape (150, 5) and df.describe() summary
  • Seaborn pairplot (4x4) colored by setosa, versicolor, and virginica
  • Identification of petal length and petal width as the strongest separators
  • Observation that setosa is fully isolated in petal feature space

Quality Score

9/10

gpt-5.2mljar-ai

Last scored: Apr 7, 2026

  • Task Completion: 2/2

    Excellent

    Loads the Iris dataset, computes summary statistics, creates a seaborn pairplot colored by species, and provides a textual interpretation of which features separate species.

  • Execution Correctness: 2/2

    Excellent

    Code is syntactically correct and uses valid sklearn/seaborn APIs; outputs shown (describe table and PairGrid/figure) are consistent with successful execution.

  • Output Quality: 2/3

    Good

    Pairplot and separation summary match expectations (petal features best; setosa isolated), but the expected explicit `df.describe()` output and explicit dataset shape (150, 5) are not shown; instead a transformed `describe().T` on dropped columns is provided.

  • Reasoning Quality: 2/2

    Excellent

    Reasoning aligns with standard Iris structure and is consistent with the pairplot interpretation (petal length/width strongest; sepal features overlap more).

  • Reliability: 1/1

    Excellent

    Workflow is reasonably robust (handles target mapping, avoids including numeric target in pairplot, checks missingness) and avoids unsupported claims beyond the displayed stats/plot.

#1
load iris dataset from scikit-learn and show basic statistics
#2
Thinking

Planning stats display

The user requested stats, so I think I'll outline that we'll start with inspection and then move to basic stats. I want to make sure I show the shape, columns, and head of the DataFrame sequentially in code. I also need to decide how to present the shape, columns, and head appropriately—maybe using a summary DataFrame for clarity. Since it suggests using multiple tables if needed, I’ll be careful to follow those guidelines. I'll craft the code importing the necessary libraries while considering how to include the target/species column.Constructing basic stats code

The user wants basic stats, so I’m considering whether to include the target column. If it's numeric, it'd probably be fine to include it. I think I’ll simplify my approach by using as_frame when loading iris data. My code will import necessary libraries and then create a DataFrame from the iris dataset. After displaying the shape and columns, I’ll show the head of the DataFrame. I just need to make sure I have that final expression right, using df.head() at the end.

#3

Let’s start by loading the Iris dataset and doing the initial inspection first. After that, we can do the descriptive statistics cleanly in the next step.

#4
Load and inspect iris data
from sklearn.datasets import load_iris
import pandas as pd
from IPython.display import display

iris = load_iris(as_frame=True)
df = iris.frame.copy()
df["species"] = df["target"].map(dict(enumerate(iris.target_names)))

display(pd.DataFrame({"rows": [df.shape[0]], "columns": [df.shape[1]]}))
display(pd.DataFrame({"column_name": df.columns}))
df.head()
#5
rows columns
0 150 6
#6
column_name
0 sepal length (cm)
1 sepal width (cm)
2 petal length (cm)
3 petal width (cm)
4 target
5 species
#7
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) target species
0 5.1 3.5 1.4 0.2 0 setosa
1 4.9 3.0 1.4 0.2 0 setosa
2 4.7 3.2 1.3 0.2 0 setosa
3 4.6 3.1 1.5 0.2 0 setosa
4 5.0 3.6 1.4 0.2 0 setosa
#8

The Iris data is already in a good tabular form: 150 rows and 6 columns, with 4 numeric flower measurements plus target and a readable species label. That confirms the dataset structure, but the actual basic statistics are still missing.

#9
Summarize dataframe statistics
df.describe(include="all")
#10
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) target species
count 150.000000 150.000000 150.000000 150.000000 150.000000 150
unique NaN NaN NaN NaN NaN 3
top NaN NaN NaN NaN NaN setosa
freq NaN NaN NaN NaN NaN 50
mean 5.843333 3.057333 3.758000 1.199333 1.000000 NaN
std 0.828066 0.435866 1.765298 0.762238 0.819232 NaN
min 4.300000 2.000000 1.000000 0.100000 0.000000 NaN
25% 5.100000 2.800000 1.600000 0.300000 0.000000 NaN
50% 5.800000 3.000000 4.350000 1.300000 1.000000 NaN
75% 6.400000 3.300000 5.100000 1.800000 2.000000 NaN
max 7.900000 4.400000 6.900000 2.500000 2.000000 NaN
#11

The Iris dataset is in a dataframe with 150 observations and 6 columns: four numeric flower measurements, a numeric target, and a readable species label.

From the basic statistics:

  • Sepal length (cm): mean 5.84, median 5.80, range 4.30 to 7.90
  • Sepal width (cm): mean 3.06, median 3.00, range 2.00 to 4.40
  • Petal length (cm): mean 3.76, median 4.35, range 1.00 to 6.90
  • Petal width (cm): mean 1.20, median 1.30, range 0.10 to 2.50
    (the output is truncated in the notebook view, but the summary indicates the standard descriptive stats were computed for this column as well)

A few useful takeaways from these statistics:

  • All numeric columns have 150 non-null values, so there are no missing values in the dataset.
  • Petal measurements vary much more than sepal measurements, especially petal length, which suggests petals may be more informative for distinguishing species.
  • The species column is categorical, while target is its numeric encoding.

This satisfies the request to load the Iris dataset from scikit-learn and show its basic statistics.

#12
create a feature pairplot colored by species
#13

Here’s a feature pairplot using the four measurement columns, colored by species. I’m leaving out target since it’s just the numeric encoding of the species label.

#14
Plot feature pairplot by species
import seaborn as sns
import matplotlib.pyplot as plt

feature_cols = [c for c in df.columns if c not in ["target", "species"]]

g = sns.pairplot(
    df[feature_cols + ["species"]],
    hue="species",
    diag_kind="hist",
    corner=False
)
g.fig.suptitle("Iris feature pairplot by species", y=1.02)

g
#15
<seaborn.axisgrid.PairGrid at 0x153157d40>
#16
Notebook output
#17

The pairplot is set up correctly for the four Iris measurement features and uses species as the color grouping, which matches the requested visualization.

From the observed notebook state:

  • The plot uses exactly these feature columns: sepal length, sepal width, petal length, and petal width.
  • species is present as a readable label column, so the hue mapping is meaningful rather than numeric.
  • The PairGrid and rendered figure indicate the pairplot was created successfully.

What this visualization shows:

  • You get pairwise scatterplots for all feature combinations, colored by species.
  • The diagonal panels show each feature’s distribution by species.
  • This is especially useful for seeing how well the species separate across measurements, with petal-related features typically giving the clearest separation in Iris data.

So the requested feature pairplot colored by species is in place and correctly configured.

#18
which features best separate the three species?
#19
Thinking

Analyzing flower measurements

I need to provide an answer based on the outputs without diving into code, focusing instead on concise insights. It seems that petal length and width are the best features for separating the species: Setosa is clearly distinct based on petal measures, while Versicolor and Virginica overlap, but can be better differentiated with a petal length/width combination. The sepal features don’t seem as strong, especially sepal width. Maybe I should suggest a next step since the user asked a direct question. I could answer using markdown.

#20

The petal features best separate the three species:

  • Petal length (cm)
  • Petal width (cm)

From the pairplot, the strongest separation is usually the petal length vs petal width view:

  • Setosa forms a clearly distinct cluster, far from the other two.
  • Versicolor and virginica also separate much better on petal measurements than on sepal measurements, though they still have some overlap.

The sepal features are less useful:

  • Sepal width (cm) is typically the weakest separator.
  • Sepal length (cm) helps a bit, but not nearly as much as the petal variables.

So if you want the single best feature pair for distinguishing species, use:

petal length (cm) + petal width (cm)

If you want, I can do one quick next plot showing just that 2D scatter for a clearer view.

Browse All Analysis Examples

Machine Learning

Time Series

Data Analysis

Exploratory Data Analysis

Finance

Nlp

Statistics