This is the AI LaunchPad track syllabus — 6 months · 24 weeks.View the full program
What you'll be able to do
- Clean and analyze real datasets with Pandas and NumPy
- Visualize data and run EDA with Matplotlib and Seaborn
- Build and evaluate machine-learning models with scikit-learn
- Apply NLP basics and understand the deep-learning workflow
- Deploy a trained model and tune it for better performance
Tools & technologies
PythonJupyterNumPyPandasMatplotlibSeabornEDAscikit-learnRegressionClassificationClusteringPCA
The syllabus
Python Programming and Logic Building
Programming Fundamentals and Decision Logic
- Day 1Data science roles and workflow · Python, VS Code and Jupyter installation · First Python program and notebookBuild: Data Science Starter Notebook
- Day 2Variables and identifiers · Numbers, strings and Boolean types · Input, output and type conversionBuild: Student Data Recorder
- Logic Building 1Problem decomposition · Algorithms, pseudocode and flowcharts · Sequence-based arithmetic problemsBuild: Business KPI Calculator
- Day 4Arithmetic and assignment operators · String indexing and slicing · String methods and formatted outputBuild: Text Cleaning Utility
- Day 5Comparison and logical operators · if, elif and else · Nested decisions and validation rulesBuild: Data Quality Rule Engine
- Logic Building 2Decision tables · Multi-condition problems · Boundary cases and branch debuggingBuild: Loan Eligibility Simulator
Loops, Collections and Advanced Logic
- Day 7while loops · Counters, accumulators and sentinel values · Input validation using loopsBuild: Survey Response Collector
- Day 8for loops and range · Nested loops · break, continue and iteration controlBuild: Automated Summary Generator
- Logic Building 3Searching and counting algorithms · Digit and sequence manipulation · Pattern-based problem solvingBuild: Number and Pattern Toolkit
- Day 10Lists and tuples · Indexing, slicing and collection methods · List comprehensionsBuild: Student Score Analyser
- Day 11Dictionaries and sets · Frequency counting · Membership and duplicate detectionBuild: Categorical Frequency Profiler
- Logic Building 4Collection-based problems · Sorting and searching logic · Menu-driven application designBuild: Console Inventory Analytics
Functions, Files and Professional Python
- Day 13Functions and parameters · Return values and scope · Lambda functions and reusable logicBuild: Reusable Business Metrics Library
- Day 14Text, CSV and JSON file handling · Exceptions and validation · Logging and debugging fundamentalsBuild: Robust File Data Loader
- Day 15Classes and objects · Dataclasses and composition · Modules, packages and virtual environmentsBuild: Dataset Catalogue Manager
- Day 16Jupyter and Google Colab workflow · Git and GitHub fundamentals · Repository, README and environment structureBuild: Reproducible Data Science Repository
- Day 17NumPy arrays and dimensions · Shapes, data types and indexing · Slicing and reshapingBuild: Array Statistics Toolkit
- Day 18Multi-file Python architecture · Modular data processing · Testing, documentation and reportingBuild: Command-Line Dataset Profiler
NumPy, pandas and Data Preparation
Numerical Computing and pandas Foundations
- Day 19NumPy vectorisation · Broadcasting · Aggregate and universal functionsBuild: Vectorised Sales Calculator
- Day 20Matrix operations · Random-number generation · Simulations and numerical missing valuesBuild: Demand Simulation Engine
- Day 21pandas Series and DataFrames · Dataset loading and inspection · Columns, indexes and data typesBuild: Dataset Inspection Dashboard
- Day 22Row and column selection · Boolean filtering · Sorting and index operationsBuild: Employee Records Explorer
- Day 23Grouping and aggregation · Pivot tables and crosstabs · Transformations and calculated columnsBuild: Retail KPI Analyser
- Day 24apply, map and vectorised operations · MultiIndex fundamentals · Exporting processed datasetsBuild: pandas Analytics Workbook
Data Collection, Cleaning and Integration
- Day 25CSV, Excel, JSON and Parquet imports · Delimiters, encodings and schemas · Multi-file ingestionBuild: Multi-Source Data Importer
- Day 26REST APIs and the Requests library · JSON normalisation · Basic web scraping, responsible extraction and robots rulesBuild: Public Data Collector
- Day 27Missing-value diagnosis · Duplicate and invalid-record handling · Data-type correctionBuild: Automated Data Cleaner
- Day 28String cleaning and regular expressions · Categorical variables · Dates, times and time zonesBuild: Customer Record Standardiser
- Day 29Merge, join and concatenate · Wide and long data formats · Pivot, melt and reshape operationsBuild: Unified Sales Dataset Builder
- Day 30Reusable cleaning functions · Data dictionaries and validation rules · Data-quality reportingBuild: CleanData Processing Pipeline
SQL and Relational Data Analysis
SQL Foundations
- Day 31Relational database fundamentals · Tables, keys and relationships · PostgreSQL, pgAdmin and ER diagramsBuild: Retail Database Schema
- Day 32SELECT, DISTINCT and aliases · WHERE, ORDER BY and LIMIT · Comparison and logical filteringBuild: Customer Query Console
- Day 33String and numerical functions · Date functions · CASE, COALESCE and null handlingBuild: Transaction Classification Queries
- Day 34Aggregate functions · GROUP BY and HAVING · Business KPI calculationsBuild: SQL Sales KPI Report
- Day 35Inner and outer joins · Self and cross joins · Set operationsBuild: Customer 360 SQL View
- Day 36Subqueries · Common Table Expressions · Views and reusable analysis queriesBuild: Business Analysis SQL Pack
Advanced SQL and Data Integration
- Day 37ROW_NUMBER, RANK and DENSE_RANK · LAG and LEAD · Partitioned calculationsBuild: Customer Ranking Engine
- Day 38Running totals and moving averages · Funnel analysis · Cohort and retention queriesBuild: Subscription Retention Analysis
- Day 39Constraints and transactions · Indexes and query plans · Normalisation and performance conceptsBuild: Optimised Analytics Database
- Day 40Python–PostgreSQL connectivity · SQLAlchemy fundamentals · Parameterised queries and pandas.read_sqlBuild: Python–SQL Analytics Connector
- Day 41Extract, transform and load workflow · Incremental data loading · Pipeline validation and error handlingBuild: API-to-PostgreSQL Pipeline
- Day 42Database problem framing · Multi-table business analysis · SQL report and recommendationsBuild: E Commerce SQL Intelligence Project
Probability, Statistics and Experimentation
Statistics and Probability Foundations
- Day 43Population and sample · Mean, median and mode · Variance, standard deviation and percentilesBuild: Statistical Profile Card
- Day 44Events and probability rules · Conditional probability and independence · Bayesʼ theoremBuild: Customer Conversion Probability Tool
- Day 45Discrete and continuous variables · Normal, binomial, Poisson and exponential distributions · Distribution simulationBuild: Probability Distribution Simulator
- Day 46Random, stratified and cluster sampling · Sampling bias · Central Limit Theorem and bootstrap samplingBuild: Sampling Strategy Laboratory
- Day 47Covariance and correlation · Pearson and Spearman correlation · Causation, confounding and spurious relationshipsBuild: Relationship Diagnostic Tool
- Day 48Standard error · Confidence intervals · Margin of error and sample-size conceptsBuild: Confidence Interval Calculator
Inferential Statistics and A/B Testing
- Day 49Null and alternative hypotheses · Significance levels and p-values · Type I, Type II and test-selection logicBuild: Hypothesis Test Selection Assistant
- Day 50One-sample and two-sample t-tests · Paired tests and proportion tests · Effect size and practical significanceBuild: Campaign Lift Analyser
- Day 51Chi-square tests · ANOVA and post-hoc comparisons · Non-parametric testsBuild: Category Impact Study
- Day 52Regression inference with statsmodels · Coefficients, intervals and significance · Residual and assumption diagnosticsBuild: Price Driver Analysis
- Day 53Control and treatment groups · Randomisation, power and sample size · A/B testing and experiment validityBuild: Product Experiment Planner
- Day 54Experiment-data preparation · Statistical-test execution · Effect interpretation and business recommendationBuild: End-to-End A/B Test Report
Visualization, BI, EDA and Data Storytelling
Visualization and Business Intelligence
- Day 55Visualization principles · Chart-selection framework · Matplotlib figure and axes fundamentalsBuild: Business KPI Chart Pack
- Day 56Subplots and layouts · Labels, annotations and reference lines · Publication-quality exportBuild: Executive Report Figures
- Day 57Seaborn distribution plots · Relationship and categorical plots · Heatmaps and pair plotsBuild: Customer Behaviour Visual Atlas
- Day 58Plotly interactive charts · Hover, filters and animation · Interactive chart exportBuild: Interactive Sales Explorer
- Day 59Excel tables and formulas · Pivot tables and calculated fields · Power Query and data validationBuild: Business Data Analysis Workbook
- Day 60Power BI data model · DAX measure fundamentals · Filters, drill-through and dashboard storytellingBuild: Executive Power BI Dashboard
Exploratory Data Analysis and Communication
- Day 61CRISP DM and data-science methodology · Business-question formulation · Success metrics, constraints and data ethicsBuild: Data Science Problem Canvas
- Day 62Dataset profiling · Univariate analysis · Missingness, distributions and data-quality patternsBuild: Dataset Health Report
- Day 63Bivariate analysis · Multivariate analysis · Correlation and segment comparisonBuild: Feature Relationship Explorer
- Day 64Outlier identification · Transformations and scaling · Encoding and feature constructionBuild: Feature Engineering Workshop
- Day 65Funnel analysis · Cohort and retention analysis · Customer and product performance metricsBuild: Growth Analytics Notebook
- Day 66EDA question formulation · Insight selection and evidence · Executive narrative and recommendationsBuild: Consumer Behaviour EDA Case Study
Applied Predictive Modelling
Machine-Learning Foundations for Data Scientists
- Day 67Predictive-modelling workflow · Features, targets and baselines · Train, validation and test sets; leakage preventionBuild: Baseline Prediction Pipeline
- Day 68Simple and multiple linear regression · Ridge, Lasso and Elastic Net · Regression metrics and residualsBuild: Housing Price Predictor
- Day 69Logistic regression · Probabilities and thresholds · Binary and multiclass classificationBuild: Customer Churn Classifier
- Day 70K-nearest neighbours · Naive Bayes · Support Vector MachinesBuild: Risk Classification Benchmark
- Day 71Regression and classification metrics · Cross-validation · Class imbalance, calibration and threshold tuningBuild: Model Evaluation Dashboard
- Day 72Preprocessing and feature selection · Model training and comparison · Interpretation and business recommendationBuild: Loan Outcome Prediction System
Tree Models, Ensembles and Model Interpretation
- Day 73Decision-tree splitting · Impurity and information gain · Depth control and pruningBuild: Approval Decision Tree
- Day 74Bagging and bootstrap sampling · Random forests · Out-of-bag evaluation and feature importanceBuild: Employee Attrition Forest
- Day 75Gradient boosting · XGBoost fundamentals · Learning rate, tree depth and early stoppingBuild: Conversion Propensity Booster
- Day 76Pipeline and ColumnTransformer · Grid and randomised search · Feature selection and reproducible tuningBuild: Automated Model Tuner
- Day 77Permutation importance and SHAP · Fairness and subgroup evaluation · Model cards, limitations and ethicsBuild: Explainable Risk Model
- Day 78Multi-model benchmarking · Error and segment analysis · Technical and business model selectionBuild: Predictive Analytics Benchmark Project
Unsupervised Learning and Time-Series Analytics
Specialised Data-Science Methods
- Day 79K-means clustering · Hierarchical clustering and DBSCAN · Elbow, silhouette and cluster interpretationBuild: Customer Segmentation Engine
- Day 80Principal Component Analysis · Explained variance and reconstruction · Dimensionality-reduction visualizationBuild: High-Dimensional Product Map
- Day 81Statistical anomaly rules · Isolation Forest · One-Class SVM and anomaly evaluationBuild: Fraud and Quality Anomaly Detector
- Day 82Time-series indexes and resampling · Trends, seasonality and stationarity concepts · Lag and rolling-window featuresBuild: Sales Time-Series Feature Builder
- Day 83Forecasting baselines · Time-based validation and walk-forward testing · Forecast metrics and model comparisonBuild: Product Demand Forecaster
- Day 84Customer clustering · Segment profiling · Segment-level forecasting and recommendationsBuild: Customer Segment and Demand Report
Reproducible Data Products and Deployment
Production-Oriented Data Science
- Day 85Notebook-to-script workflow · Configuration, requirements and project structure · Markdown, data lineage and R/RStudio awarenessBuild: Reproducible Analysis Package
- Day 86Unit testing for data functions · Schema and data-quality tests · Linting and basic GitHub ActionsBuild: Tested Data Processing Pipeline
- Day 87Streamlit widgets and layouts · Interactive filters, charts and tables · Caching and session stateBuild: Interactive Business Insight Application
- Day 88FastAPI routes · Pydantic request and response schemas · Prediction and data-service endpointsBuild: Data Science REST API
- Day 89Docker images and containers · Dependency and environment management · Containerised Streamlit and API servicesBuild: Containerised Data Product
- Day 90Cloud application deployment · Logging, health checks and versioning · Basic monitoring and rollbackBuild: Public Data Science Application
Sprint 1 Technical Capstone
End-to-End Data Science Product
- Day 91Business problem and stakeholder definition · Data-source selection and success metrics · Architecture, repository and milestone planBuild: Capstone Design Blueprint
- Day 92Data acquisition and SQL schema · Cleaning and transformation pipeline · Data dictionary and validation reportBuild: Capstone Data Foundation
- Day 93Exploratory analysis · Statistical inference and experiment analysis · Business insights and recommendationsBuild: Capstone Insight Report
- Day 94Feature engineering · Predictive or segmentation model · Evaluation, explanation and limitation analysisBuild: Capstone Predictive Engine
- Day 95Power BI or Streamlit dashboard · FastAPI and Docker integration · Cloud deployment and technical documentationBuild: Capstone Data Product
- Day 96Reproducibility and quality review · Executive presentation and application demonstration · Technical viva and architecture defenceBuild: Customer360 Intelligence Platform