Jacobisah

Name a Nigerian city and I will tell you a dataset you could analyse from it. 🧵

Example:
Lagos → traffic congestion patterns, property prices by LGA, ride-hailing trip data
Drop your city below.

Let us show Nigerian learners that local data is everywhere.

The honest timeline for learning data analysis in Nigeria
Month 1 — Python basics (variables, loops, functions)
Month 2 — Pandas and NumPy (data manipulation)
Month 3 — Matplotlib and visualisation
Month 4 — Real project with a Nigerian dataset
Month 5 — SQL basics
Month 6 — Apply for jobs or start freelancing

Six months. Consistent daily effort.
It is doable. Many have done it.
Start your month 1. 👇
enemzy.blogspot.com

JacobIsah Programming Hub Blog Welcome to Jacob Isah's developer blog. Explore practical guides, project walkthroughs, and career advice focused on Python, AI, Data Science, and ML

Weekend project for Nigerian Python beginners:
Build a simple currency converter.
Features:
✅ Input amount in Naira
✅ Convert to USD, GBP, EUR
✅ Display all three results
✅ Use a dictionary for exchange rates

Uses: variables, input(), dictionaries, f-strings.
Full Python tutorial on the blog 👇
enemzy.blogspot.com

JacobIsah Programming Hub Blog Welcome to Jacob Isah's developer blog. Explore practical guides, project walkthroughs, and career advice focused on Python, AI, Data Science, and ML

Python challenge
What does this print?
data = [10, 20, 30, 40, 50]
result = [x * 2 for x in data if x > 20]
print(result)

A) [60, 80, 100]
B) [20, 40, 60, 80, 100]
C) [30, 40, 50]
D) Error

Drop your answer below. 👇

Pandas cheat sheet — save this:
pythondf.head() # first 5 rows
df.info() # column types and nulls
df.describe() # stats summary
df.isnull().sum() # count missing values
df.dropna() # remove missing rows
df.fillna(0) # fill missing with 0
df['col'].unique() # unique values in column
df.groupby('col').mean() # group and average
Full data analysis guide 👇
https://buff.ly/swl228Q

A Python skill that pays directly in Nigeria
Web scraping.
Businesses pay freelancers to scrape
— Competitor pricing data
— Job listings
— Property listings
— News and social data
All you need is Python + BeautifulSoup or Scrapy.
Your Python foundation starts here 👇
https://jacobisah.selar.com/282021d88q

Buy Python for Data Analysts "From Zero to Your First Real Data Project" by Jacob Isah on Selar Python for Data AnalystsFrom Zero to Your First Real Data ProjectThe beginner-friendly Python guide built for Nigerians who want practical tech skills, real projects, and career opportunities in data analysis.✅ No programming experience required✅ Learn step-by-step in plain English✅ Build a re...

The biggest mistake Nigerian data learners make on LinkedIn:
Listing courses without projects.
"Completed Google Data Analytics Certificate" alone will not get you hired.
"Completed Google Certificate + analysed Lagos housing data + published findings on GitHub" will.
Your portfolio is your proof.
Build your foundation here.
https://jacobisah.selar.com/profitabledataanalystsecrets

Buy Profitable Data Analyst Secret by Jacob Isah on Selar From Confused Beginner to Job-Ready Data Analyst in Weeks — Even If You've Never Written a Line of CodeMaster Python, SQL, and Power BI through 5 real-world projects. Build a portfolio that attracts recruiters. Learn the exact script to land high-paying gigs in Nigeria.

It is Friday.
This weekend you could:
A) Watch Netflix for 10 hours
B) Spend 3 hours and learn enough Python to build your first data project
Option B changes your career trajectory.
Option A does not.
Step-by-step Python guide waiting for you 👇
https://buff.ly/z3bJmxt

Buy 50 Python Exercises for Data Analysts by Jacob Isah on Selar From Python Beginner to Data Pro in Weeks, Not Years.50-Exercise Python Workbook for Aspiring Data Analysts & Scientists

Beginner's Guide to Data Science with Python

When I wrote my first Python script, I had no idea it would eventually help me analyze thousands of rows of data, build predictive models, and teach hundreds of learners how to do the same. If you are reading this, you are probably where I was curious, a little confused, and wondering: where do I even start with data science?

This guide is the answer I wish I had. It is built from five-plus years of hands-on experience in software engineering, Python development, and educating beginners. You will get a clear roadmap, the right tools, real-world examples, and honest opinions not just a list of buzzwords.

Whether you are a complete beginner or someone who knows a little Python and wants to break into data science, this post is for you.

What Is Data Science and Why Python?

Data science is the process of collecting, cleaning, analyzing, and interpreting data to help people and organizations make better decisions. It blends statistics, programming, and domain knowledge into one powerful skill set.

Now, why Python? Here is my honest take after working with multiple programming languages:

Python is beginner-friendly. Its syntax reads almost like plain English, which makes learning faster.

It has the largest data science ecosystem. Libraries like pandas, NumPy, and scikit-learn are battle-tested tools used by professionals worldwide.

It is in high demand. Python consistently ranks as the top language for data science and machine learning jobs.

The community is massive. When you get stuck, there are thousands of tutorials, forums, and open-source projects to help you.

My opinion: If you are going to invest time in one language for data science, Python is the smartest choice in 2026 and beyond. I have used Java and JavaScript extensively in my engineering career, and Python still wins when it comes to data work.

Step 1: Learn Python Basics First

Before jumping into data science libraries, you need a solid Python foundation. Many beginners skip this step and end up confused later. Do not make that mistake.

Here are the core Python concepts you need to understand:

Variables and data types: integers, strings, floats, booleans

Lists, dictionaries, and tuples: how to store and organize data

Loops and conditionals: for loops, while loops, if-else statements

Functions: how to write reusable blocks of code

File handling: reading and writing CSV files

Basic error handling: try and except blocks

Here is a simple example of how Python code looks:

# A simple Python function to calculate average
def calculate_average(numbers):
total = sum(numbers)
count = len(numbers)
return total / count

scores = [85, 90, 78, 92, 88]
print("Average score:", calculate_average(scores))
# Output: Average score: 86.6

Clean. Simple. Readable. That is Python.

Recommended resource: Learn free and well-structured for beginners.

Step 2: The 5 Python Libraries Every Data Scientist Needs

Once your Python basics are solid, these five libraries will become your daily toolkit. I use all of them regularly in projects.

NumPy: The Foundation of Numerical Computing

NumPy (Numerical Python) is the backbone of almost every data science library. It lets you work with large arrays and matrices of numbers efficiently.

import numpy as np

# Create an array and calculate the mean
data = np.array([10, 20, 30, 40, 50])
print("Mean:", np.mean(data)) # 30.0
print("Std Dev:", np.std(data)) # 14.14

Pandas: Your Data Manipulation Powerhouse

Pandas is where most data scientists spend 60 to 70 percent of their time. It gives you the DataFrame a table-like structure that makes loading, filtering, and transforming data straightforward.

import pandas as pd

# Load a CSV and inspect it
df = pd.read_csv("sales_data.csv")
print(df.head()) # View first 5 rows
print(df.describe()) # Summary statistics
print(df.isnull().sum()) # Check for missing values

Matplotlib and Seaborn: Making Data Visual

Matplotlib is the go-to library for creating charts and graphs. Seaborn builds on top of it to create more beautiful statistical visualizations with less code.

import matplotlib.pyplot as plt
import seaborn as sns

# Simple bar chart
months = ["Jan", "Feb", "Mar", "Apr"]
sales = [4000, 4500, 3900, 5200]

plt.bar(months, sales, color="steelblue")
plt.title("Monthly Sales")
plt.xlabel("Month")
plt.ylabel("Revenue")
plt.show()

Scikit-learn: Machine Learning Made Accessible

Scikit-learn is the most popular machine learning library for Python. From regression to classification to clustering, it handles it all with a consistent and beginner-friendly interface.

from sklearn.linear_model import LinearRegression
import numpy as np

# Simple linear regression example
X = np.array([[1], [2], [3], [4], [5]])
y = np.array([2, 4, 5, 4, 5])

model = LinearRegression()
model.fit(X, y)
print("Prediction for X=6:", model.predict([[6]]))

Jupyter Notebook: Your Data Science Workspace

Jupyter Notebook is not just a library but an interactive environment where you write code, see results, and add notes all in one place. It is the industry standard for data exploration and sharing analysis.

Step 3: Understand the Data Science Workflow

Professional data scientists follow a repeatable process. Understanding this workflow early will save you a lot of confusion.

Define the problem: What question are you trying to answer?

Collect the data: CSV files, databases, APIs, web scraping

Clean the data: Handle missing values, fix data types, remove duplicates

Explore the data (EDA): Use statistics and charts to understand patterns

Build a model: Apply machine learning or statistical analysis

Evaluate and interpret: How accurate is your model? What does it tell you?

Communicate results: Visualize and explain your findings clearly

In my experience, steps 2 and 3, collecting and cleaning data, take up to 80 per cent of a real project's time. The glamorous modelling step is actually the quickest part. Keep that in mind so you are not surprised.

Step 4: Tools and Environments to Set Up

Here is the setup I recommend for every beginner. Keep it simple.

Anaconda: Install this first. It comes with Python, Jupyter Notebook, and most data science libraries pre-installed. It is the easiest way to get started.

VS Code: A lightweight, powerful code editor. Great for writing Python scripts and working with notebooks.

Google Colab: A free, browser-based Jupyter environment. No installation needed. Perfect when you are just starting out or want to run code on the go.

GitHub: Start saving your projects here early. It builds your portfolio and teaches you version control, a skill every professional data scientist needs.

Step 5: How to Analyse Sales Data

Let me walk you through a simplified version of a real project I worked on: analyzing sales data for a retail business to find which products performed best.

The Problem

A small business owner wanted to know: which product categories were driving the most revenue, and which months had the weakest sales?

The Data

We had a CSV file with 5,000 rows containing columns for date, product category, units sold, and revenue.

Step 1: Load and Inspect

import pandas as pd

df = pd.read_csv("retail_sales.csv")
print(df.shape) # (5000, 4)
print(df.dtypes) # Check data types
print(df.isnull().sum()) # Check missing values

Step 2 Clean the Data

# Drop rows with missing revenue values
df = df.dropna(subset=["revenue"])

# Convert date column to datetime
df["date"] = pd.to_datetime(df["date"])

# Extract month
df["month"] = df["date"].dt.month

Step 3 Analyze and Visualize

import matplotlib.pyplot as plt

# Revenue by category
category_revenue = df.groupby("category")["revenue"].sum().sort_values(ascending=False)
category_revenue.plot(kind="bar", color="coral", figsize=(10, 5))
plt.title("Revenue by Product Category")
plt.ylabel("Total Revenue")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

The Finding

Electronics accounted for 42 percent of total revenue, while the weakest months were January and August. This insight helped the business plan targeted promotions for those slow months.

This is data science in action. No fancy machine learning needed. Just clean data, clear analysis, and actionable insights.

Recommended resource: How to Clean Messy Data in Python with Pandas (Beginner Tutorial)

Step 6: Common Beginner Mistakes to Avoid

I have taught hundreds of learners, and these are the mistakes I see over and over:

Skipping Python basics and jumping straight to machine learning. You will get lost fast. Build the foundation first.

Ignoring data cleaning. Dirty data produces wrong results. Always inspect your data before analyzing it.

Memorizing code instead of understanding it. Learn why each line works, not just what it does.

Not working on real projects. Tutorials are great for learning, but real projects build real skills. Start with datasets from Kaggle or Google Dataset Search.

Trying to learn everything at once. Data science is broad. Focus on the fundamentals for 90 days before branching out into deep learning or big data tools.

Not documenting your work. Write comments in your code. Explain your analysis in notebooks. Future you will thank current you.

Step 7 Your 90-Day Learning Roadmap

Here is the exact roadmap I would give a student starting from zero today:

Month 1: Python and Data Fundamentals (Days 1 to 30)

Complete a Python basics course (variables, loops, functions, file I/O)

Learn NumPy arrays and operations

Learn pandas (reading CSVs, filtering, grouping, merging)

Practice with 2 datasets from Kaggle

Month 2: Data Analysis and Visualization (Days 31 to 60)

Master exploratory data analysis (EDA)

Learn Matplotlib and Seaborn

Work on a complete data analysis project end to end

Learn basic statistics: mean, median, variance, correlation

Month 3: Introduction to Machine Learning (Days 61 to 90)

Learn supervised learning: linear regression, logistic regression, decision trees

Learn how to evaluate models: accuracy, precision, recall

Build your first machine learning project

Push everything to a GitHub portfolio

Is 90 days enough to become a professional? No. But it is enough to build real skills, complete projects, and confidently apply for junior data analyst roles or data science internships.

Free Resources and Cheatsheet

Here are the resources I genuinely recommend all free:

Python Official Docs: The most reliable Python reference

Kaggle Learn: Free, short courses on Python, pandas, and machine learning with real datasets

Google Colab: Free notebook environment, no setup required

Pandas Documentation: Official docs with examples

Scikit-learn User Guide: Clear explanations of every algorithm

Sentdex on YouTube: One of the best Python and data science YouTube channels

Free Python for Data Science Cheatsheet

Want a one-page PDF covering pandas, NumPy, Matplotlib, and scikit-learn commands? Fill out this form https://forms.gle/ioDj65ApyKL7rCEA7, and I will send it to you for free.
It covers the 20 percent of commands you will use 80 percent of the time.

Conclusion

Data science with Python is one of the most valuable skills you can learn in 2024. The good news is you do not need a degree or years of experience to get started. You need the right foundation, the right tools, and consistent practice.

Here is a quick recap of everything we covered:

Why Python is the best language for data science

The core Python basics you need before anything else

The 5 must-know libraries: NumPy, pandas, Matplotlib, Seaborn, and Scikit-learn

The 7-step data science workflow professionals use

A real-world sales data case study

The most common beginner mistakes and how to avoid them

A clear 90-day roadmap to go from zero to your first project

I started my own journey writing simple Python scripts. Today, Python is a core part of my engineering and teaching work. The path is not always straight, but it is absolutely worth walking.

Start today. Pick one concept. Write one line of code. Build from there.

If you found this guide helpful, share it with someone who is trying to break into data science. And do not forget to drop a comment below I read every single one.

About the Author: Jacob Isah is a software engineer, educator, and content creator with over five years of experience in full-stack development. He specializes in Python, Django, JavaScript, and ReactJS, with deep expertise in building APIs and teaching programming to beginners. He runs JacobIsah Programming Hub / NEXODE LTD, focused on practical tech education for African learners and beyond.

References

Python Software Foundation — The Python Tutorial

pandas Development Team — pandas Documentation

NumPy Developers — NumPy Documentation

Scikit-learn Developers — Scikit-learn User Guide

Matplotlib Development Team — Matplotlib Documentation

Michael Waskom — Seaborn: Statistical Data Visualization

Project Jupyter — Jupyter Documentation

Kaggle — Learn Data Science

Beginner's Guide to Data Science with Python A beginner's guide to data science with Python — covering tools, libraries, roadmap, real examples, and expert tips from software engineer Jacob Isah.

Unpopular opinion
The free Python and data resources available to Nigerian learners in 2026 are better than what was available in paid bootcamps in 2018.

The bottleneck is not access to resources.
It is structured practice and accountability.

That is what we fix 👇
enemzy.blogspot.com

JacobIsah Programming Hub Blog Welcome to Jacob Isah's developer blog. Explore practical guides, project walkthroughs, and career advice focused on Python, AI, Data Science, and ML