Data Preparation

Environment Setup & Loading Data

First, we need to load our toolkit. We will use Pandas for data manipulation and Seaborn/Matplotlib for visualisation.

import pandas as pd  # The "Excel" of Python
import seaborn as sns  # For statistical plotting
import matplotlib.pyplot as plt  # The engine behind the plots

# Force all pandas tables to display 2 decimal places
pd.options.display.float_format = "{:,.2f}".format

# Set a nice theme for our charts
sns.set_theme(style="whitegrid")

# Load the dataset directly from the seaborn package
df = sns.load_dataset("penguins")

# Show the first 5 rows to verify it loaded correctly
display(df.head())

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex
0	Adelie	Torgersen	39.10	18.70	181.00	3,750.00	Male
1	Adelie	Torgersen	39.50	17.40	186.00	3,800.00	Female
2	Adelie	Torgersen	40.30	18.00	195.00	3,250.00	Female
3	Adelie	Torgersen	NaN	NaN	NaN	NaN	NaN
4	Adelie	Torgersen	36.70	19.30	193.00	3,450.00	Female

Data Cleaning

Real-world data is rarely perfect. Before we can analyse the penguins, we need to check for missing values (NaNs).

# 1. Create a clean summary of missing values
missing_summary = df.isnull().sum().to_frame(name="Missing Values")
display(missing_summary)

Table 1: Summary of Missing Values

	Missing Values
species	0
island	0
bill_length_mm	2
bill_depth_mm	2
flipper_length_mm	2
body_mass_g	2
sex	11

Since we have enough data, we will drop the rows with missing values to ensure our later analysis is accurate.

# Create a clean dataframe by dropping rows with any missing values
df_clean = df.dropna()

# Calculate how many rows were dropped
rows_removed = len(df) - len(df_clean)

print("-" * 30)
print(f"CLEANING REPORT")
print(f"• Original records: {len(df)}")
print(f"• Records kept:     {len(df_clean)}")
print(f"• Records removed:  {rows_removed}")
print("-" * 30)

------------------------------
CLEANING REPORT
• Original records: 344
• Records kept:     333
• Records removed:  11
------------------------------