This Data Science laboratorial course was designed independently of the data science tool to use. However, it is my opinion that nowadays, the one that demonstrates the best balance between flexibility and results is Python, along with the set of packages specific created for this context.

The course is organized in several modules, covering the two main topics: mining multidimensional data (tabular format) and mining time series.

Data format	Lab	Topic	Procedures
Accessory Files			data folder
			config.py
			dslabs.mplstyle
			ds_charts.py
			ts_functions.py
Multidimensional data (tabular format)	Lab 0	Python for DS	Loading data with pandas
			Basic charts with matplotlib.pyplot
	Lab 1	Data profiling	Data dimensionality
			Data distribution
			Data granularity
			Data sparsity
	Lab 2	Data preparation	Missing values imputation
			Scaling
			Dummification
			Data balancing
	Lab 3	Classification
			Training Strategies
			Naive Bayes
			KNN
			Decision Trees
			Random Forests
			Gradient Boosting
			Neural networks (MLP)
	Lab 4	Clustering	Clustering
			Feature Extraction
	Lab 5	Pattern Mining
Time Series	Lab 6	Profiling
		Transformation
		Forecasting
		Motif Discovery