Statistics For Data Science with Python — Statistic Distribution (6/10)

Normal Distribution

Scipy — Python for Data Science

Numpy— Python for Data Science

Type of Distributions

Statistics Skew

Distribuição Normal Padronizada

Z-Score

Teorema Central do Limite

SCIPY.Stats

Naïve Bayes e distribuições

Conversão Atributos Categóricos => Numéricos Discreto

Google Colaboratory

Aprendizagem Baseada em Distâncias — KNN

Linear Regression

Skewed Data with Machine Learning

Transforming Skewed Data

Neural Networks Initiators

Initializers

• https://keras.io/api/layers/initializers

Normality Tests

- Parametric statistics: the data is in some distribution, usually the normal distribution.
- Non-parametric statistics: data is in another (or unknown) distribution
- If the data is “normal”, we use parametric statistics. Otherwise, we use non-parametric statistics.

Shapiro-Wilk Test

Shapiro-Wilk Test
p-value is used to interpret the statistical test.
p <= alpha: rejects hypothesis, not normal
p > alpha: don’t reject the hypothesis, it’s normal

Python Notebook Colab