A complete first data exploration
Create a Python project that loads, inspects, cleans and summarizes customer data. You will understand what the dataset contains before using it for Ai.
Beginner Project • Basic PythonPython Data
Python Data
Explorer
Load, inspect, clean and summarize a small customer dataset before building your first Ai model.
0% complete
Your work is saved automatically.Complete the fields below. Your answers stay in this browser.
Creating a Python projectLoading CSV dataUnderstanding rows and columnsChecking data typesFinding missing valuesRemoving duplicatesCalculating summariesFiltering and groupingCreating a chart
LevelBeginner
CodingBasic Python
Time60–90 minutes
SoftwarePython, VS Code and Jupyter or .py
Librariespandas + matplotlib
customer-data.csvSample dataset ↓data-explorer.pyComplete starter script ↓requirements.txtRequired packages ↓README-template.mdProject documentation ↓
project-02-python-data-explorer/
├── data/customer-data.csv
├── notebooks/data-explorer.ipynb
├── outputs/data-summary.txt
├── README.md
└── requirements.txtSeven guided steps
Explore the customer dataset
Run each code block, confirm its output, then mark the step complete.
Install the packages
Prepare pandas for data work and matplotlib for the chart.
VS Code terminal
pip install pandas matplotlibrequirements.txt
pandas
matplotlibLoad the dataset
Read the CSV file and handle a missing-file error clearly.
Python
import pandas as pd
file_path = "data/customer-data.csv"
try:
df = pd.read_csv(file_path)
print("Dataset loaded successfully.")
except FileNotFoundError:
print(f"Dataset not found: {file_path}")Expected result
Dataset loaded successfully.
Inspect the data
Understand its size, columns, values and data types.
Python
print(df.head())
print(df.shape)
print(df.columns)
df.info()Check data quality
Find missing values and duplicates before changing the data.
Check quality
print("Missing values:")
print(df.isnull().sum())
print("\nDuplicate rows:")
print(df.duplicated().sum())Clean the data
df = df.drop_duplicates()
df["Monthly Spending"] = df["Monthly Spending"].fillna(
df["Monthly Spending"].median()
)Important
Replace each column name with the exact name used in your dataset. Check why a row is duplicated before removing it.
Summarize the dataset
Calculate useful numerical and category summaries.
Python
print(df.describe())
average_spending = df["Monthly Spending"].mean()
average_purchases = df["Number of Purchases"].mean()
print("Average monthly spending:", round(average_spending, 2))
print("Average number of purchases:", round(average_purchases, 2))
print(df["Membership Type"].value_counts())Filter and group the data
Find high-spending customers and compare membership groups.
Python
high_spending_customers = df[df["Monthly Spending"] > 100]
print(high_spending_customers.head())
membership_summary = (
df.groupby("Membership Type")["Monthly Spending"]
.mean()
.sort_values(ascending=False)
)
print(membership_summary)Create a simple chart
Visualise average spending across membership groups.
Python
import matplotlib.pyplot as plt
membership_summary.plot(kind="bar")
plt.title("Average Spending by Membership Type")
plt.xlabel("Membership Type")
plt.ylabel("Average Monthly Spending")
plt.tight_layout()
plt.show()Expected result
A bar chart comparing average spending across membership groups.
Final output
Complete your project evidence
Cleaned datasetPython notebook or scriptData summaryOne chartThree findingsREADME file
Write three important findings
Responsible data check
Completion checklist
Confirm your Data Explorer
Portfolio explanation
I created a Python Data Explorer using pandas. I loaded and inspected a customer dataset, checked data types, handled missing values, removed duplicates, calculated summary statistics and created a chart comparing customer groups. This project developed my basic Python, data-cleaning and exploratory-analysis skills.