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.

This page shows an AI data analysis example. A workflow is a list of prompts (instructions) used to complete one analysis task step by step. We send the same prompt list to multiple AI models, then compare their notebook outputs and scores.

What this AI workflow does

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 example is for

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.

Expected analysis outcomes

These are the results the AI workflow is expected to generate.

  • 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

Tools and libraries used

Main Python packages and tooling used to run this AI data analysis task.

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

Prompt sequence

This is the exact list of prompts used in this workflow. The same prompt sequence is sent to each model so outputs and scores can be compared fairly.

  1. 1load iris dataset from scikit-learn and show basic statistics
  2. 2create a feature pairplot colored by species
  3. 3which features best separate the three species?

Model Comparison

We compared several LLM models on the same analysis task. The table below shows their scores side by side. You can also open each model run to check the full conversation and notebook results.

Model SourceScoreTaskExecutionOutputReasoningReliabilityRun
gemma4:31b10/102/22/23/32/21/1Open gemma4:31b conversation
glm-5.110/102/22/23/32/21/1Open glm-5.1 conversation
gpt-5.410/102/22/23/32/21/1Open gpt-5.4 conversation
gpt-oss:120b10/102/22/23/32/21/1Open gpt-oss:120b conversation
qwen3-coder-next10/102/22/23/32/21/1Open qwen3-coder-next conversation
qwen3.5:397b10/102/22/23/32/21/1Open qwen3.5:397b conversation
How scoring works

Each run is graded on five dimensions:

  • Task Completion (0-2): how fully the workflow answered the requested analysis task and completed required steps.
  • Execution Correctness (0-2): whether generated code is correct, consistent, and likely runnable without major fixes.
  • Output Quality (0-3): how well tables, charts, and results match the expected analytical outcomes.
  • Reasoning Quality (0-2): clarity and correctness of interpretation, explanation, and conclusions.
  • Reliability (0-1): robustness of the run, including low hallucination risk and stable behavior.

The final score is the sum of these dimensions, so total score = 0-10. Higher values indicate more complete, correct, and reliable notebook results for this workflow.

AI Analysis with gpt-5.4

This run uses AI with a step-by-step list of prompts to perform the analysis task Iris Feature Analysis and Visualization in Python. Below, you can review the full conversation generated with gpt-5.4. After the conversation, we show detailed score cards for this run.

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

Planning iris data loading

I need to think about how to handle the user's request to load the iris dataset and show basic statistics. I should first check if the dataset is loaded and then inspect it, showing details like shape, columns, and head. I realize I shouldn't combine loading with plotting or modeling, so I’ll keep it iterative. I'll provide clear code to load the iris data into a DataFrame and present these statistics concisely, adhering to best practices.

#3

Let’s start by loading the Iris dataset into a pandas DataFrame and doing the required first inspection: shape, columns, and the first few rows.

#4
Load and preview iris data
from sklearn.datasets import load_iris
import pandas as pd

iris = load_iris(as_frame=True)
df = iris.frame.copy()

display(df.shape)
display(df.columns.to_list())
df.head()
#5
(150, 5)
#6
['sepal length (cm)',
 'sepal width (cm)',
 'petal length (cm)',
 'petal width (cm)',
 'target']
#7
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) target
0 5.1 3.5 1.4 0.2 0
1 4.9 3.0 1.4 0.2 0
2 4.7 3.2 1.3 0.2 0
3 4.6 3.1 1.5 0.2 0
4 5.0 3.6 1.4 0.2 0
#8

The current output confirms the Iris data is in a tidy table with 150 rows and 5 columns: four numeric flower measurements plus a numeric target label for species. The first rows show realistic measurement values and indicate the target is encoded as integers.

To actually show the basic statistics, the missing piece is a summary table of the numeric columns.

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

The Iris dataset shown in the notebook has 150 observations and 5 columns: four flower measurements and one target label.

From the summary statistics:

  • Sepal length averages 5.84 cm, with values ranging from 4.3 cm to 7.9 cm.
  • Sepal width averages 3.06 cm, ranging from 2.0 cm to 4.4 cm.
  • Petal length averages 3.76 cm, with a wider spread from 1.0 cm to 6.9 cm.
  • Petal width averages 1.20 cm, ranging from 0.1 cm to 2.5 cm.
  • Each measurement column has 150 non-null values, so there are no missing values in this dataset.

A useful interpretation is that the petal measurements vary much more than the sepal measurements, especially petal length, which often makes them more informative for distinguishing Iris species.

The target column is numeric and encoded as 0, 1, 2, with a mean of 1.0, consistent with the standard scikit-learn Iris labeling.

#12
create a feature pairplot colored by species
#13
Thinking

Creating pairplot for species

I need to provide an answer with one step, focusing on mapping targets to species names and creating a pairplot. I should utilize the existing notebook state and analyze the latest outputs with a specific goal. I'll keep it to one code block for clarity while ensuring to create a "species" column derived from iris.target_names.

The final expression will likely involve sns.pairplot with hue set to “species,” and I want to make sure it’s clear and colored correctly.

#14

We already have the Iris data and summary stats, so the next step is to map the numeric target values to species names and draw a pairplot colored by species.

#15
Plot iris feature pairplot
import seaborn as sns
import matplotlib.pyplot as plt

df_plot = df.copy()
df_plot["species"] = df_plot["target"].map(dict(enumerate(iris.target_names)))

g = sns.pairplot(
    df_plot.drop(columns="target"),
    hue="species",
    corner=True,
    diag_kind="hist"
)
g.fig.suptitle("Iris feature pairplot by species", y=1.02)
g
#16
<seaborn.axisgrid.PairGrid at 0x12b0534d0>
#17
Notebook output
#18

The pairplot is set up correctly for the Iris features and is colored by the three species labels derived from iris.target_names.

From the notebook state:

  • df_plot contains the four numeric feature columns plus a species column, so the hue grouping is based on readable species names rather than numeric target codes.
  • The pairplot excludes the numeric target column, which keeps the visualization focused on the actual flower measurements.
  • The rendered PairGrid with 14 axes matches a lower-triangle pairplot with diagonal distributions for the four features.

What this plot shows:

  • Petal length and petal width should provide the clearest separation among species.
  • Setosa is typically distinctly separated from the other two species on petal measurements.
  • Versicolor and virginica usually show some overlap in sepal measurements, with better separation in petal-based feature pairs.

So the requested feature pairplot colored by species has been produced appropriately, and it is well-structured for comparing species-level separation across the Iris measurements.

#19
which features best separate the three species?
#20
Thinking

Analyzing pairplot data

I need to provide an answer based on the observed pairplot. It seems like I don't need any code, just a concise analysis of the outputs. I should mention that petal length and width are the strongest features, while sepal measurements are less significant. I can highlight that Setosa is distinct due to its petal characteristics, and that there’s some overlap between Versicolor and Virginica in terms of sepal features. Let's craft this analysis!

#21

The petal features best separate the three species:

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

From the pairplot, these two show the clearest clustering by species:

  • Setosa is very clearly separated from the other two on both petal measurements.
  • Versicolor and virginica are also better distinguished by petal length/width than by sepal features, though they still overlap a bit.

The sepal features are less useful for separation:

  • Sepal width (cm) shows substantial overlap across species.
  • Sepal length (cm) helps somewhat, but not nearly as much as the petal variables.

If I had to rank them for species separation based on the plot:

  1. Petal width (cm)
  2. Petal length (cm)
  3. Sepal length (cm)
  4. Sepal width (cm)

If you want, the next step can be a quick boxplot or violin plot for the two petal features to make that separation even easier to see.

Score cards for gpt-5.4 for Iris Feature Analysis and Visualization in Python

Total score: 10/10

  • Task Completion: 2/2

    Excellent

    The notebook loads the Iris dataset, shows basic statistics with df.describe(), creates a species-colored pairplot, and answers which features separate the species best.

  • Execution Correctness: 2/2

    Excellent

    The code shown is syntactically valid and consistent with the displayed outputs, including the DataFrame shape, summary table, and rendered pairplot.

  • Output Quality: 3/3

    Excellent

    Outputs match the expected outcomes semantically: a 150x5 Iris table, a species-colored pairplot, and a correct summary that petal length/width best separate species with setosa isolated.

  • Reasoning Quality: 2/2

    Excellent

    The explanations correctly interpret the statistics and pairplot, identifying petal features as most discriminative and noting setosa’s clear separation.

  • Reliability: 1/1

    Excellent

    The workflow is consistent and grounded in the displayed notebook outputs without obvious hallucinations or contradictions.

Try MLJAR Studio

Run the same type of AI-powered data analysis on your own datasets with conversational notebooks in MLJAR Studio.

Download Free TrialLearn about AI Data Analyst

Explore More AI Analysis Examples

Discover additional workflows across categories. Each example includes prompts, conversation outputs, and model-level scoring so you can compare approaches and results.

Exploratory Data Analysis

Time Series

Data Analysis

Machine Learning

NLP

Finance

Statistics