# Proclus Academy

## Machine Learning / Deep Learning

**Matplotlib**doesn't support dot plots natively. So how can you draw them?

Let's write our own function and use it to sketch highly customizable dot plots.

**Scikit-Learn**to measure

**Precision**,

**Recall**, and

**F1 Score**for classification models?

Also, does **Scikit-Learn** provide a way to handle **imbalanced classes**?

**Accuracy**can be a misleading metric for certain types of classification problems.

Let's explore how **Precision**, **Recall**, and **F1 Score** can give a realistic view of a model’s predictive power.

You'll also gain practical skills to generate these metrics using **Scikit-Learn**.

**Normal Distribution**and some of its distinctive features.

You'll also learn about **Empirical Rule**, which dictates how values are spread in specific intervals around the mean.

**Area Under Density Curve**. What does it represent? What are some of its practical applications?

You'll also learn to plot and analyze partial areas under the curve using **Matplotlib**, **Seaborn**, and **Numpy**.

**Data Distribution**enables you to extract general patterns from the data.

You'll also learn to visualize distribution as **Histogram** and **Density Curve** using **Matplotlib** and **Seaborn.**

**Matplotlib**to draw

**pie charts**with customized colors and labels. You can even apply styles tailored to each slice.

Along the way, you'll see what's an **exploding** pie chart and how to draw it. Finally, you'll learn to plot **Donut Charts**!

**Stratified Sampling**can help.

You'll also develop practical skills and learn how to do sampling using **Python** and **Pandas**.

**balanced**or

**imbalanced classes**and

**binary**or

**multiclass**labels.

You can even produce datasets that are **harder to classify**!