Visão Geral

Curso Python for Finance. Maximize os retornos. Visualize seu portfólio. Execute seu mais recente Algoritmo de Negociação Assassino. Tudo isso e muito mais estão facilmente ao seu alcance aproveitando o poder do código aberto do Python.

Este Curso Python for Finance, ensina como aplicar Python a uma ampla gama de aplicativos de tecnologia financeira, incluindo a aquisição de dados de provedores de dados financeiros populares, bem como a limpeza, exploração e visualização dos conjuntos de dados resultantes. Os participantes aprendem como abordar a implementação de modelos algorítmicos e como construir modelos ricos e perspicazes, com ênfase em ética, conformidade e segurança. 

Objetivo

Após realizar este Curso Python for Finance você será capaz de:

• Extraia automaticamente dados financeiros de provedores de dados comuns
• Saiba como limpar, agregar e manipular dados financeiros de forma eficaz
• Conduzir análise elementar de série temporal
• Compreender processos estocásticos e modelos de ruído comuns
• Construir modelos para inferência e previsão, como ARIMA e regressão linear e logística
• Gere visualizações poderosas, como gráficos de velas
• Extraia dados financeiros raspando sites
• Compreender os fundamentos dos modelos de aprendizado de máquina supervisionados e não supervisionados aplicados às finanças
• Aplicar Redes Neurais Recorrentes (RNNs) e Unidades de Memória Longa e de Curto Prazo (LSTMs) a séries temporais financeiras e compreender suas limitações
• Entenda os princípios por trás da tecnologia Blockchain  

Pre-Requisitos

• Todos os alunos do treinamento Python For Finance já devem estar familiarizados com a sintaxe e os conceitos fundamentais do Python.

Materiais

Conteúdo Programatico

Introduction

Crunching the Numbers: Numerical Python With NumPy

• Introduction to the n-d-array
• NumPy operations
• Broadcasting
• Missing data in NumPy (masked array)
• NumPy structured arrays
• Improving performance through vectorization
• Random number generation
• Introduction to Monte-Carlo methods
• General approaches to implementing mathematical algorithms

Acquiring and Manipulating Financial Data With Pandas and Pandas-Datareader

• Series versus DataFrames
• Overview of data types in pandas
• Pandas I/O tools: CSV/Excel/SQL
• Pandas I/O tools: Pandas-datareader
• Subsetting DataFrames
• Creating and deleting variables
• Discretization of continuous data
• Scaling and standardizing data
• Identifying duplicates
• Dummy coding

Exploratory Data Analysis and Advanced Pandas Methods

• Uni- and multivariate statistical summaries and detecting outliers
• Group-wise calculations using pandas
• Pivot tables
• Long to wide and back: pivoting, stacking and melting
• Python visualization: Matplotlib and seaborn
• Pandas visualization: histograms, bar and box plots
• Pandas visualization: Scatter plots and pie charts
• Group-by plotting
• Pandas plot formatting
• mpl-finance and candlestick charts
• Merging DataFrames
• Pandas string methods
• Implementing regular expressions in pandas
• Handling missing data in pandas

Elementary Time Series Analysis

• Date/time formats in Python and pandas
• Running/rolling aggregates
• Resampling

Stochastic Processes

• Overview of noise models
• Stationarity
• Random walks and martingales
• Brownian motion
• Diffusion models
• The Black-Scholes model—and its limitations

Time Series Forecasting

• De-trending and seasonality
• Interpolation and extrapolation
• Auto-Regressive Integrated Moving Average (ARIMA) models

Measuring Impact: Testing For Group Differences

• Null hypothesis testing and p-values
• Group comparisons (p-values, t-tests, ANOVA, Chi-square tests)
• Correlation

Progressing, With Regression Models

• Linear regression
• Logistic regression
• Regression on count outcomes (Poisson processes)

Optional: Machine Learning Fundamentals for Finance with scikit-learn

• Requirements: NumPy, pandas. Time required: 4 hours
• Machine learning approaches to multivariate statistics
• Machine Learning theory
• Data pre-processing
• Supervised versus Unsupervised learning
• Unsupervised learning: clustering
  • Clustering algorithms
  • Evaluating cluster performance
• Dimensionality reduction
  • A priori
  • Principal component analysis (PCA)
  • Penalized regression
• Supervised learning: regression
  • Linear regression
  • Penalized linear regression
  • Stochastic gradient descent
  • Scoring new data sets
  • Cross-validation
  • Variance-bias trade-off
  • Feature importance
• Supervised learning: classification
  • Logistic regression
  • LASSO
  • Random forests
  • Ensemble methods
  • Feature importance
  • Scoring new data sets
  • Cross-validation

Recurrent Neural Nets and LSTMs with PyTorch

• Requirements: NumPy, pandas, Machine Learning fundamentals.
• Introduction to PyTorch
  • Introduction to tensor algebra and calculus
  • Tensor algebra in PyTorch
  • Training and validating models
• Regression in PyTorch
  • Optimizers in PyTorch
  • Linear regression
  • Logistic regression
• Artificial Neural Networks
  • Overview of Artificial Neural Networks (ANNs)
  • Recurrent Neural Networks (RNNs)
  • Sequence models and Long Short-Term Memory Networks (LSTMs)
• RNNs/LSTMs with PyTorch
  • Building, training and validating a basic ANN
  • Creating a RNN
  • Building a LSTM
  • Applications to financial time series, and cautionary tales

Scraping By: Obtaining Financial Data from Publicly Accessible Websites

• Requirements: Base Python. Time required: 2 hours
• Parsing HTML/CSS with BeautifulSoup
  • Navigating tree data structures
  • Selecting named node elements
  • Selecting by property
• Establishing a Connection
  • Urllib3 and connections
  • POST and GET directives
• Building a Web Scraper
  • Parsing a list of websites
  • Collecting and storing data
• Advanced Scraping: Building a Web Spider with Scrapy

Blockchain technologies

• Requirements: Basic Python, NumPy (useful, but not mandatory). Time required: 4 hours.
• The Ingredients For a Blockchain
  • Transaction records
  • The distributed ledger
  • Chain validation
  • Nonces
• The Hash Function
  • Overview of hash functions and tables
  • Cryptographic hash functions
  • Proof-of-work
• Advanced Functions
  • Return statements
  • The JSON format
  • Exception trapping
  • Assertions
• Constructing Your Own Blockchain
  • Generating a block
  • The genesis block
  • Generating a chain though block validation
• Shortcomings of current blockchain technologies