Visão Geral

O Curso Data Science in Python Fundamentals, foi desenvolvido para iniciantes em Ciência da Computação. Inclui conhecimento sobre como configurar seu ambiente, escrever suas primeiras linhas de código em Python, utilizar bibliotecas numéricas e técnicas de visualização de dados. Ele pode ser usado como uma fonte independente de insights ou um trampolim para um caminho de aprendizado de máquina mais interessante.

Materiais

Conteúdo Programatico

Setting up

1. Jupyter Notebook
2. Jupyter Notebook magic
3. Google Colab

Basic Python Syntax

1. Variables
2. Strings
3. Arithmetic Operators
4. If statement

Hands-on Lab: Writing a “Hello World” program, working with all the Python basic data types, using basic module operations, getting familiar with input and output

1. Functions
2. Lists
3. Dictionaries
4. Tuples
5. For and While statements

Hands-on Lab: Writing our first Python function, understanding the similarities and differences between the different kinds of collections, using the specific Python syntax for doing collection search and iteration

1. Modules
2. Error handling
3. Exceptions

Hands-on Lab: Learning how to import modules in different ways, how to create our own module, how to do exception handling an elegant way and how to declare and raise our own custom exceptions

Basic Python OOP

1. Classes and Objects
2. Attributes and Methods
3. Abstraction and Encapsulation
4. Inheritance
5. Polymorphism

Hands-on Lab: Writing our first Python class, getting familiar with dunders, creating a basic class hierarchy; learning the difference between class aggregation and inheritance and some use cases for each; learning the Python philosophy around private class attributes and methods

Data Visualization

1. Matplotlib
2. Grids
3. Formatting Axes
4. Bar Plot
5. Histograms
6. Pie Chart
7. Scatter Plot
8. Contour Plot
9. Quiver Plot
10. Box Plot
11. Violin Plot
12. Seaborn

Hands-on Lab: Ploting basic polynomes and mathematical functions, playing with the number of discrete points in the plot, modifying different style and color parameters, finishing up the plot with labels and a legend and exporting it to different formats

Pandas

1. Series
2. DataFrame
3. Indexing
4. Sorting
5. Aggregations

Hands-on Lab: Getting some experience in declaring and working with Series and DataFrames, reading DataFrames from real files, converting numpy arrays to Series and back, Indexing by boolean indexes

1. GroupBy
2. Missing Data
3. Merging and Joining
4. Concatenation
5. Visualization

Hands-on Lab: Learning different basic methods of data cleaning and preprocessing. Getting some statistical measurements of the data. Trying to correlate data from multiple DataFrames

NumPy

1. Data Types
2. Ndarray
3. Indexing
4. Slicing
5. Broadcasting

Hands-on Lab: Working out the syntax and conceptual differences between python lists and numpy arrays, converting from one to the other, analyzing the different kind of data types and array shapes, learning to think through problems in a vectorized way

1. Binary Operators
2. Mathematical Functions
3. Statistical Functions
4. Basic Linear Algebra

Hands-on Lab: Learning how to apply functions and operators directly on vectors, computing some classical statistical aggregates efficiently, trying to index and apply operations on multiple vectors in the easiest way

Project: Preprocessing Pipeline for Machine Learning Algorithms