// modeling · application
Python is a powerful tool for creating models. Python allows creating models using almost all of the algorithms explored in the Theory section. In this section, models are created in a Supervised and Unsupervised Learning setup along with Time Series Forecasting models.
Various kinds of models can be created using Python for solving Regression and Classification problems. The Linear Regression model can be created using the library statsmodels, while Sklearn is the backbone for creating various other kinds of models: StandardScaler for regularised Linear Regression, DecisionTreeRegressor for Decision Trees, and KNeighborsRegressor for KNN. Similar libraries handle Classification problems, where ANN, SVM and Naive Bayes are also explored. Various Ensemble methods such as Bagging, Boosting and Stacking are also implemented using Python. For Regression problems, the Boston Dataset has been used, while for Classification problems, the Titanic dataset has been put to use.
Sklearn again helps in creating the majority of models that work in the Unsupervised Learning setup: Kmeans, DBSCAN and AgglomerativeClustering for Clustering (using the Iris dataset without the dependent variable), Principal Component Analysis and Factor Analysis for Dimensionality Reduction (using the Boston dataset), and One Class SVM and Isolation Forest for Anomaly Detection (using the Iris dataset).
The Air Passengers dataset has been used for creating various Time Series models, using Averaging techniques, Smoothening techniques, and ARIMA methods for forecasting.
Supervised Learning Models
Unsupervised Learning Models
Time Series Forecasting
TM