Curriculum

• What is Data Science? Key concepts, processes, and applications
• The role of a Data Scientist: Problem solver, data analyst, and decision-maker
• Tools of the Trade: Python, Jupyter Notebook, SQL, visualization libraries

• Introduction to the business context of data science projects (e.g., sales forecasting, customer segmentation, anomaly detection, etc.)
• Translating business goals into data science tasks: Framing the problem (e.g., predicting sales, understanding trends, improving operational efficiencies)
• Case Study Exploration: Chuimatt Supermarkets (or other business cases)

• Defining project objectives and key deliverables
• Setting up the project environment (tools, platforms, and software)
• Overview of the project management process: Milestones, timelines, and collaboration

Overview: This module is designed to introduce students to Python programming from scratch, with a focus on how Python is used in Data Science. By the end of this module, students will have a solid foundation in Python and be ready to dive into more advanced data science topics in subsequent modules.

• What is Python?
  • A versatile, beginner-friendly programming language used in a wide variety of fields, especially in data science and machine learning.
  • Python’s popularity in data science: Libraries like Pandas, NumPy, Matplotlib, Seaborn, and Scikit-learn.
• Why Python for Data Science?
  • Easy to learn and use: Clear, readable syntax.
  • Extensive libraries and frameworks for data manipulation, analysis, and machine learning.
  • Strong community support.
• Setting up Python Environment
  • Installing Python: Anaconda distribution (recommended for data science).
  • Installing Python on different platforms: Windows, macOS, Linux.
  • Setting up Jupyter Notebooks for interactive coding.
  • PyCharm or VS Code for writing Python scripts.

• Python Syntax and Structure
  • Writing Python code in a script or interactive environment.
  • Understanding indentation and code blocks.
  • Basic commands: Print statements, comments, basic input/output.
• Data Types in Python
  • Numbers: Integers (int), Floating-point numbers (float).
  • Strings: Text data (str).
  • Boolean: True or False (bool).
  • Lists: Ordered collection of elements (list).
  • Tuples: Immutable sequence (tuple).
  • Dictionaries: Key-value pairs (dict).
  • Sets: Unordered collection of unique elements (set).
• Basic Operations
  • Arithmetic operations (+, -, *, /).
  • String manipulation: Concatenation, slicing, formatting.
  • List operations: Indexing, slicing, appending.
  • Dictionary operations: Adding/removing keys, accessing values.

• If-Else Statements
  • Writing conditional logic with if, elif, and else.
  • Understanding comparison operators (==, !=, <, >, etc.).
  • Using logical operators (and, or, not).
• Loops in Python
  • For Loop: Iterating over a sequence (e.g., list, string, range).
  • While Loop: Repeating a block of code as long as a condition is true.
  • Using break and continue to control loop flow.

• Defining Functions
  • The purpose of functions: Reusability, abstraction.
  • Function syntax: def function_name(): Arguments and return values.
  • Calling functions with arguments.
• Built-in Functions
  • Common Python built-in functions: print(), len(), type(), input().
  • Working with list comprehension for efficient loops and conditionals.

• Installing and Importing Libraries
  • Using pip and conda to install libraries.
  • Importing libraries in Python: import pandas as pd, import numpy as np, etc.
• Exploring Essential Data Science Libraries
  • Pandas: For data manipulation and analysis.
  • NumPy: For numerical operations and handling arrays.
  • Matplotlib: For basic data visualization (charts, graphs).
  • Seaborn: For statistical data visualization.

• Lists, Tuples, and Dictionaries
  • Creating, accessing, and manipulating lists, tuples, and dictionaries.
  • Common methods: .append(), .pop(), .remove(), .keys(), .values().
• Using Collections
  • Introduction to collections module: Counter, defaultdict.
  • Working with sets and handling duplicates.
  • Sorting and filtering collections using list comprehensions.

• Reading and Writing Files
  • Opening, reading, and writing files in Python.
  • Handling CSV files with Python’s built-in csv module.
  • Introduction to Pandas: Reading and writing data using pd.read_csv() and df.to_csv().
• Introduction to Pandas DataFrames
  • What is a DataFrame? An overview of how it is used to store tabular data.
  • Loading and inspecting data with Pandas (head(), tail(), info()).
  • Accessing specific rows, columns, and elements in a DataFrame.

• Data Cleaning Basics
  • Handling missing data using Pandas (isnull(), dropna(), fillna()).
  • Dropping duplicates and cleaning strings.
  • Renaming columns and other data transformations.
• Basic Data Visualization
  • Plotting simple graphs with Matplotlib: Line plots, bar charts, histograms.
  • Plotting data with Seaborn: Scatter plots, heatmaps, and pair plots.
  • Visualizing data trends: Time-series, relationships between variables.

• Mini Project: Analyzing a Simple Dataset
  • Students will use what they've learned to analyze a small dataset (e.g., sales data or customer data).
  • Tasks: Load the data, clean it, perform basic analysis, and create visualizations.
  • Presenting the findings: Using Python and Jupyter Notebooks to document the analysis.

• Understanding different data formats: SQL databases, CSV files, APIs, web scraping
• Connecting to databases (e.g., SQL, NoSQL) and data pipelines
• Importing data into Python using Pandas, SQLAlchemy, and other tools

• Overview of data exploration: Descriptive statistics, visualizations (e.g., histograms, bar plots, correlation heatmaps)
• Data cleaning: Handling missing values, duplicate entries, and outliers
• Data preprocessing: Encoding categorical variables, scaling numerical features, and normalizing data

• Identifying key features and understanding relationships in data
• Creating basic visualizations using Matplotlib and Seaborn
• Identifying patterns and trends in data (e.g., seasonality, time-based trends)

• Creating new features based on existing data: Aggregation, time-based features, external factors
• Extracting insights: Interaction terms, feature crossing, and transformations
• Handling domain-specific features: Dealing with promotions, holidays, regional differences

• Encoding categorical features (One-Hot Encoding, Label Encoding, etc.)
• Feature scaling: Standardization and normalization
• Time-series data preparation: Creating lag features, rolling averages, and other transformations

• Techniques for selecting important features: Correlation analysis, Feature Importance from models (e.g., Random Forest, XGBoost)
• Dimensionality reduction: PCA (Principal Component Analysis), t-SNE for visualization

• Regression Models: Linear Regression, Ridge and Lasso Regression
• Classification Models: Logistic Regression, Decision Trees, Random Forests, and Support Vector Machines
• Model evaluation metrics: MAE, MSE, RMSE, R², AUC, Accuracy, Precision, Recall, F1-score

• Clustering Techniques: K-Means, DBSCAN, Hierarchical Clustering
• Dimensionality Reduction: PCA, t-SNE, UMAP
• Anomaly Detection: Isolation Forest, One-Class SVM

• Ensemble Learning: Random Forests, AdaBoost, Gradient Boosting, and XGBoost
• Model stacking and blending for improved predictions
• Hyperparameter tuning: GridSearchCV and RandomizedSearchCV

• Time Series Forecasting: ARIMA, Exponential Smoothing, and Facebook Prophet
• Handling seasonality, trends, and cyclical data

• Introduction to visualizing data using Matplotlib, Seaborn, and Plotly
• Time series visualizations, trend analysis, and seasonal effects
• Geospatial visualizations for location-based analysis (e.g., store sales by region)

• Using Streamlit or Dash to create interactive web applications
• Creating dashboards for sales trends, predictions, and insights
• Integrating with external data sources for real-time updates

• Generating business insights from model predictions
• Communicating findings in business-friendly language
• Creating reports and presentations with Power BI or Tableau (optional)

• Advanced dashboards with Kibana, Elasticsearch, or other reporting tools for large datasets
• Building dashboards that allow users to query data in real-time

• Introduction to deploying models: Why deploy models? When to deploy models?
• Exporting models using Pickle or Joblib
• Building APIs using Flask or FastAPI for serving models

• Deploying models on cloud platforms like Heroku, AWS, or Google Cloud
• Setting up CI/CD pipelines for continuous integration and delivery of updates

• Monitoring model performance in production (drift detection, retraining models)
• Setting up alerts and logs for production models
• Retraining models as new data becomes available

• Overview of the final project: What is the business problem? What datasets are provided?
• Setting up project scope, timeline, and deliverables

• Working with real-world datasets (similar to the Chuimatt Supermarket case)
• Collecting, cleaning, and preparing data for modeling

• Building predictive models based on the business problem
• Experimenting with different algorithms and techniques

• Creating dashboards and presenting insights from the model
• Reporting business recommendations based on data science results

• Submitting code, model, and reports
• Presentation of the solution to the client (instructor/peers)