AI - Python for Data Science

• Write clean, efficient Python code for data tasks 
• Analyze and manipulate datasets using pandas and numpy 
• Visualize data using matplotlib, seaborn, and plotly 
• Apply foundational statistics and probability concepts 
• Build reproducible data workflows using Python tools 

Module 1: Python Programming Concepts 

• Type Hints and return values 
• Python functions 
• Built-in functions 
• Meta classes and closures 
• Built-in Modules and Decorators 
• JavaScript Object Notation 
• HTP Requests and API 

Exercise: Build a simple text-based data calculator (e.g., weather tracker) 

Module 2: Working with Data using pandas and numpy 

• Series and DataFrames 
• Importing/exporting data (CSV, Excel, JSON) 

• Indexing, slicing, and filtering 
• Aggregation and group operations 
• Intro to numpy arrays and broadcasting 

Project: Analyze a CSV dataset (e.g., global population or Netflix titles) 

Module 3: Data Cleaning and Transformation 

• Handling missing data 
• String operations and data type conversion 
• Duplicates and outlier detection 
• Merging and joining datasets 
• Date/time parsing and manipulation 

Assignment: Clean and transform a messy dataset (e.g., survey or ecommerce data) 

Module 4: Intro to SQL with Python 

• SQL basics (SELECT, WHERE, JOIN) 
• Running SQL queries using SQLAlchemy 
• Integrating SQL data into pandas workflows 

Module 5: Data Visualization with Python 

• Plotting with matplotlib: line, bar, scatter, pie 
• Styling and annotations 
• seaborn: histograms, boxplots, violin plots, heatmaps 
• Intro to plotly for interactive charts 

Project: Create a data dashboard (static or interactive) 

Module 6: Exploratory Data Analysis (EDA) 

• Summary statistics 
• Distributions and frequency analysis 
• Correlation analysis 
• Crosstabs and pivot tables 
• Visual EDA storytelling 

Exercise: Perform an EDA on a public dataset (e.g., Titanic, World Bank) 

Module 7: Basic Probability & Statistical Analysis 

• Descriptive statistics (mean, median, std, IQR) 
• Probability basics: events, conditional, independence 
• Common distributions: normal, binomial, uniform 
• Central Limit Theorem (CLT) introduction 

Assignment: Analyze patterns using a real dataset 

Module 8: Hypothesis Testing & Inferential Statistics 

• Sampling and confidence intervals 
• t-tests, chi-square tests 
• p-values and statistical significance 
• Assumptions and limitations 

Exercise: Conduct hypothesis testing on real-world data 

Module 9: Automating & Documenting Data Workflows 

• Using Python scripts to automate data cleaning 
• Creating reusable functions and modules 
• Introduction to argparse and basic CLI tools 
• Exporting reports and dataframes to Excel/PDF/CSV 
• Documenting analysis with Markdown and Notebooks 

Project: Build a reproducible end-to-end data pipeline 

Module 10: Working with APIs and Web Data 

• HTTP requests with requests 
• Parsing JSON data 
• Accessing open APIs (e.g., weather, finance) 
• Intro to web scraping (using BeautifulSoup) 

Core Tools & Libraries 

• Python, Jupyter, Google Colab 
• pandas, numpy 
• matplotlib, seaborn, plotly 
• scipy.stats for statistical functions 
• requests, json, datetime 

Suggested Resources 

• Book: Python for Data Analysis by Wes McKinney 
• Sites: Kaggle Datasets, Our World in Data, Data.gov 

Capstone Project (Final Week) 

Students complete an independent or group project using real-world data. Deliverables include: 

• Cleaned dataset 
• Visualizations 
• EDA report 
• Statistical findings 
• Optional: automated script/report 

Examples: 

• Analysis of open government spending 
• Weather trend explorer 

Quiz: 15 % of final grade

Project: 20 % of final grade

Examination: 15% of the final grade

Master of Liberal Arts: Software Engineering - Harvard University

Graduate Certificate: Data Science - Harvard University

BSc(Hons) : Mathematical Sciences (Computer Science Major) - Kogi State University