Scikit-learn Machine Learning Certification

Module 1: Introduction to Scikit-learn

• Scikit-learn ecosystem
• Machine learning fundamentals
• Scikit-learn API
• Estimators
• Transformers
• Predictors

Module 2: Machine Learning Workflow

• Problem definition
• Data collection
• Data preparation
• Model development
• Model evaluation
• Prediction workflow

Module 3: Preparing Data with Scikit-learn

• Feature matrices
• Target variables
• Training data
• Testing data
• train_test_split
• Dataset preparation

Module 4: Data Preprocessing

• Missing-value handling
• SimpleImputer
• Standardization
• Normalization
• Data transformation
• Preprocessing strategies

Module 5: Categorical Data Encoding

• Categorical features
• OrdinalEncoder
• OneHotEncoder
• Label encoding
• Unknown categories
• Encoding workflows

Module 6: Feature Scaling & Transformation

• StandardScaler
• MinMaxScaler
• RobustScaler
• Power transformations
• Feature distributions
• Scaling selection

Module 7: Feature Engineering

• Feature creation
• Polynomial features
• Feature interactions
• Transformation techniques
• Feature selection
• Data preparation

Module 8: Linear Regression

• Regression fundamentals
• LinearRegression
• Model fitting
• Coefficients
• Predictions
• Regression interpretation

Module 9: Regularized Regression

• Ridge regression
• Lasso regression
• Elastic Net
• Regularization
• Feature coefficients
• Model comparison

Module 10: Logistic Regression

• Classification fundamentals
• LogisticRegression
• Probability prediction
• Binary classification
• Multiclass classification
• Decision thresholds

Module 11: Decision Trees

• DecisionTreeClassifier
• DecisionTreeRegressor
• Splitting criteria
• Tree depth
• Feature importance
• Overfitting control

Module 12: Ensemble Learning

• Ensemble concepts
• Random Forest
• Bagging
• AdaBoost
• Gradient Boosting
• Voting models

Module 13: Support Vector Machines

• Support vectors
• Hyperplanes
• Margins
• Kernels
• SVC
• SVR

Module 14: K-Nearest Neighbours & Naive Bayes

• KNN concepts
• Distance metrics
• Neighbour selection
• Naive Bayes
• Probabilistic classification
• Algorithm comparison

Module 15: Clustering

• Unsupervised learning
• K-Means
• Hierarchical clustering
• DBSCAN
• Cluster evaluation
• Segmentation

Module 16: Dimensionality Reduction

• High-dimensional data
• PCA
• Principal components
• Explained variance
• Feature compression
• Visualization

Module 17: Model Evaluation

• Accuracy
• Precision
• Recall
• F1 score
• Confusion matrix
• Regression metrics

Module 18: Cross-Validation

• Validation strategies
• K-fold cross-validation
• Stratified K-fold
• Cross-validation scores
• Data leakage
• Reliable evaluation

Module 19: Hyperparameter Tuning

• Hyperparameters
• GridSearchCV
• RandomizedSearchCV
• Parameter grids
• Scoring metrics
• Model optimization

Module 20: Scikit-learn Pipelines

• Pipeline concepts
• Pipeline class
• ColumnTransformer
• Preprocessing integration
• Model integration
• Preventing data leakage

Module 21: Model Interpretation & Persistence

• Feature importance
• Permutation importance
• Model inspection
• Saving models
• Loading models
• Reusable prediction workflows

Module 22: Practical Machine Learning Project

• Problem definition
• Dataset preparation
• Feature engineering
• Pipeline development
• Model evaluation
• Prediction and interpretation