PYTHON +ML+DL
1. PYTHON INTRODUCTION: 15 HOURS
• History • Features • Why Python for ML?: 0.5h
• Basic Python Programming (Syntax, Variables, Operators, Conditionals, Loops): 2h
• String Manipulation (Accessing, Operations, Slices): 1h
• Lists (Intro, Access, Operations, Functions): 1h
• Tuples (Intro, Access, Operations, Functions): 1h
• Dictionaries (Intro, Access, Working, Properties): 1h
• Functions (Defining, Arguments, Anonymous, Global/Local): 1.5h
• Modules (Import, Math, Random, Packages): 1h
• Exception Handling (Except, Try-Finally, User Defined): 1h
• OOPs (Class/Object/Attributes, Inheritance, Overloading): 5h
2. PYTHON LIBRARIES: 12 HOURS
• NumPy: Installing, Arrays (1D/2D/Multi), Random, Indexing/Slicing, Shape/Reshape,
Join/Split/Search/Sort/Filter: 5h
• Pandas: Intro/Setup, Data structures, Loading, Indexing/Selection, Text/Aggregation,
Missing Data, Grouping/Merging, Date/Multi-Index: 5h
• Matplotlib: Plotting, Subplots, Markers, Line style, Charts/Graphs: 1.5h
• Seaborn: Multiple charts: 0.5h
3. BASIC STATISTICS: 4 HOURS
• Mean • Mode • Median • Variables • Standard Deviation • Outliers • Hypothesis: 4h
4. SQL: 8 HOURS
• Database basics, Types, DBMS vs RDBMS, Normalization/Denormalization: 1h
• MySQL Install, Data Models, DBMS Language, ACID: 1h
• SQL: Data Types, Commands, Operators, Keys, Joins: 2h
• GROUP BY/HAVING/ORDER BY, Subqueries (SELECT/INSERT/UPDATE/DELETE): 1.5h
• Set Operations, Functions, SQL vs NoSQL, Python Connection: 2.5h
5. DATA PREPROCESSING: 5 HOURS
• Overview, Get Database, Import Libraries/Datasets: 1h
• Missing data, Categorical Data: 1h
• Splitting (Train/Test), Feature Scaling: 1.5h
• Working directories: 0.5h
6. INTRODUCTION OF ALL: 2 HOURS
• Machine Learning • Deep Learning • AI • Data Science: 2h
7. MACHINE LEARNING: 25 HOURS
• 7.1 Regression: Linear Theory + Hands-on (House prices), Polynomial/Overfitting, RMSE/R²,
Regularization + Project: 6h
• 7.1 Classification: Logistic + Diabetes, Metrics (Precision/Recall/F1/ROC), Trees/RF/SVM +
Spam Project: 6h
• 7.2 Ensemble: Intro, Max Voting/Averaging/Weighted,
Stacking/Blending/Bagging/Boosting, AdaBoost/XGB: 4h
• 7.3 Performance: Confusion Matrix, Accuracy, Report (Precision/Recall/F1), R2Score: 2h
• 7.4 Unsupervised: K-Means + Customers, Hierarchical + Movies, PCA + Project (Customer
segments): 7h
8. ML CAPSTONE: 8 HOURS
• 5 Projects assignment: 8h
9. NEURAL NETWORKS + DL BASICS: 10 HOURS
• Intro Neural Networks + TensorFlow/Keras hands-on: 2h
• CNNs + MNIST digits: 2.5h
• RNNs + Text generator: 2h
• Transfer Learning + Image classification project: 3.5h
10. ADVANCED + CAPSTONE: 11 HOURS
• NLP Intro + Sentiment analysis: 2h
• Time Series + ARIMA/LSTM sales forecast: 2.5h
• Reinforcement Learning + Game simulation: 1.5h
• DL Capstone: Recommendation/Medical/Chatbot project: 5h