Explore practical coding of basic machine learning models using Python. Gain insights into algorithms like linear regression, logistic regression, SVM, KNN, and decision trees.

Machine Learning with Python A Practical Beginners’ Guide by Oliver Theobald-01.png

MLtarball.tar.gz

jupyter1

jupyter2

jupyter3

jupyter4

jupyter5

jupyter6

jupyter7

jupyter8

jupyter9

jupyter10

jupyter11

jupyter12

jupyter13

jupyter14

jupyter15

jupyter16

jupyter17

jupyter18dtextra

jupyter19dt

jupyter20rf

jupyter21gbc

jupyter22gbr

jupyter-temp

pca6

split

lor1

lor2

lor3

lor4

lor5

lor6

lor7

lor8

lor9

svm9

knn9

gbc7

gbr1

gbr2

gbr3

gbr4

gbr5

gbr6

gbr7

gbr8

Mlxtend

This course teaches you how to code basic machine learning models. The content is designed for beginners with general knowledge of machine learning, including common algorithms such as linear regression, logistic regression, SVM, KNN, decision trees, and more. If you need a refresher, we have summarized key concepts from machine learning, and there are overviews of specific algorithms dispersed throughout the course.

A Practical Guide to Machine Learning with Python

## Quick overview
Our next supervised learning classification technique is **K-Nearest Neighbors** (k-NN), which classifies new unknown data points based on their proximity to known data points. This classification process is determined by setting the `k` number of data points closest to the target data point. For example, if you set `k` to 3, k-NN analyzes the nearest three data points (neighbors) to the target data point.

## Example
Given the following dataset and predict the class for p ($p_1=3$ and $p_2=7$) and value of $k=2$.

<table align="center">

  <tr>
    <td>Sr.</td>
    <td>P<sub>1</sub></td>
    <td>P<sub>2</sub></td>
    <td>Class</td>
  </tr>
  
  <tr>
    <td>i</td>
    <td>7</td>
    <td>7</td>
    <td>B</td>
  </tr>
  
  <tr>
    <td>ii</td>
    <td>7</td>
    <td>4</td>
    <td>B</td>
  </tr>
  
  <tr>
    <td>iii</td>
    <td>3</td>
    <td>4</td>
    <td>A</td>
  </tr>

  <tr>
    <td>iv</td>
    <td>1</td>
    <td>4</td>
    <td>A</td>
  </tr>

</table> 

- Euclidean distance
<div align="center">

$d\left( p,q\right)   = \sqrt {\sum _{i=1}^{n}  \left( q_{i}-p_{i}\right)^2 }$
</div>

$d(p,i)=\sqrt{(3-7)^2 + (7-7)^2} = 4$

$d(p,ii)=\sqrt{(3-7)^2 + (7-4)^2} = 5$

$d(p,iii)=\sqrt{(3-3)^2 + (7-4)^2} = 3$ $(n_1)$

$d(p,iv)=\sqrt{(3-1)^2 + (7-4)^2} = 3.6$ $(n_2)$

According to the distance, $n_1$ is in the $3^{rd}$ row and $n_2$ is in the $4^{th}$ row. Both are assigned the same label, **A**.


The k-nearest neighbor's technique is sometimes called a “memory-based procedure” because the full training data is used each time a prediction is made. For this reason, k-NN is generally not recommended for analyzing large datasets and measuring multiple distances in high-dimensional data. However, reducing the number of dimensions through a descending dimension algorithm such as principal component analysis (PCA) or merging variables is a common strategy to simplify and prepare a k-NN analysis.

The following steps are involved in the implementation of k-NN:
- 1 - Import libraries
- 2 - Import dataset
- 3 - Remove variables
- 4 - Scale data
- 5 - Set X and y values
- 6 - Set algorithm
- 7 - Evaluate
- 8 - Optimize 
- 9 - Predict

## Exercise
In the following code exercise, you will practice using k-nearest neighbors to predict the outcome of a user clicking on online advertising based on the class of nearby data points.

---

# Quick overview
Our next supervised learning classification technique is **K-Nearest Neighbors** (k-NN), which classifies new unknown data points based on their proximity to known data points. This classification process is determined by setting the `k` number of data points closest to the target data point. For example, if you set `k` to 3, k-NN analyzes the nearest three data points (neighbors) to the target data point.

# Example
Given the following dataset and predict the class for p ($p_1=3$ and $p_2=7$) and value of $k=2$.

<table align="center">

  <tr>
    <td>Sr.</td>
    <td>P<sub>1</sub></td>
    <td>P<sub>2</sub></td>
    <td>Class</td>
  </tr>
  
  <tr>
    <td>i</td>
    <td>7</td>
    <td>7</td>
    <td>B</td>
  </tr>
  
  <tr>
    <td>ii</td>
    <td>7</td>
    <td>4</td>
    <td>B</td>
  </tr>
  
  <tr>
    <td>iii</td>
    <td>3</td>
    <td>4</td>
    <td>A</td>
  </tr>

  <tr>
    <td>iv</td>
    <td>1</td>
    <td>4</td>
    <td>A</td>
  </tr>

</table> 

- Euclidean distance
<div align="center">

$d\left( p,q\right)   = \sqrt {\sum _{i=1}^{n}  \left( q_{i}-p_{i}\right)^2 }$
</div>

$d(p,i)=\sqrt{(3-7)^2 + (7-7)^2} = 4$

$d(p,ii)=\sqrt{(3-7)^2 + (7-4)^2} = 5$

$d(p,iii)=\sqrt{(3-3)^2 + (7-4)^2} = 3$ $(n_1)$

$d(p,iv)=\sqrt{(3-1)^2 + (7-4)^2} = 3.6$ $(n_2)$

According to the distance, $n_1$ is in the $3^{rd}$ row and $n_2$ is in the $4^{th}$ row. Both are assigned the same label, **A**.


The k-nearest neighbor's technique is sometimes called a “memory-based procedure” because the full training data is used each time a prediction is made. For this reason, k-NN is generally not recommended for analyzing large datasets and measuring multiple distances in high-dimensional data. However, reducing the number of dimensions through a descending dimension algorithm such as principal component analysis (PCA) or merging variables is a common strategy to simplify and prepare a k-NN analysis.

The following steps are involved in the implementation of k-NN:
- 1 - Import libraries
- 2 - Import dataset
- 3 - Remove variables
- 4 - Scale data
- 5 - Set X and y values
- 6 - Set algorithm
- 7 - Evaluate
- 8 - Optimize 
- 9 - Predict

# Exercise
In the following code exercise, you will practice using k-nearest neighbors to predict the outcome of a user clicking on online advertising based on the class of nearby data points.

---

This lesson will introduce the k-nearest neighbors technique and the steps involved in its implementation.

Introduction to K-Nearest Neighbors

Introduction to Course

Introduction to Machine Learning

Exploratory Data Analysis

Data Scrubbing

Pre-Model Algorithms

Customer Segmentation with K-Means Clustering

Split Validation

Model Design

Linear Regression

Logistic Regression

Support Vector Machines

K-Nearest Neighbors

Tree-Based Methods

Cardiovascular Disease Risk Prediction with Random Forest

Conclusion

Appendix

Introduction to K-Nearest Neighbors

Quick overview

Example

Sr.	P₁	P₂	Class
i	7	7	B
ii	7	4	B
iii	3	4	A
iv	1	4	A