Feature Scaling: Normalization & Standardization | Machine Learning | Data Science #shorts

Analytics Vidhya · Beginner ·📊 Data Analytics & Business Intelligence ·3y ago

Key Takeaways

The video covers the difference between normalization and standardization in machine learning, explaining how standardization converts features to Z scores and normalization brings data values to a unit, with examples of using Normalizer from sklearn and StandardScaler from scikit-learn.

Full Transcript

normalization and standardization Prasad I have been using them interchangeably just wanted to check are these two the same no they are not so in standardization we convert the features to the corresponding Z scores by removing the mean and dividing by the standard deviation whereas in normalization the aim is to bring the data values to a unit now basically normalization means to recompute the values such that the sum of the squares of the recomputed values is equal to 1. finally standardization is done on features or Columns of your data whereas normalization is done on the rows or your data points by using the psychic learn function called as normalizer whereas standardization is done by using your scikitlan function called as standard scale

Original Description

#sql #normalization #database #datascience
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Analytics Vidhya · Analytics Vidhya · 0 of 60

← Previous Next →
1 The DataHour: Data Science in Retail
The DataHour: Data Science in Retail
Analytics Vidhya
2 The DataHour: Anomaly detection using NLP and Predictive Modeling
The DataHour: Anomaly detection using NLP and Predictive Modeling
Analytics Vidhya
3 The DataHour: Energy Data Science Project from Scratch
The DataHour: Energy Data Science Project from Scratch
Analytics Vidhya
4 The DataHour: Explainable AI Need and Implementation
The DataHour: Explainable AI Need and Implementation
Analytics Vidhya
5 The DataHour: Google Cloud AI/ML
The DataHour: Google Cloud AI/ML
Analytics Vidhya
6 Prediction to Production in Machine Learning #machinelearning #prediction
Prediction to Production in Machine Learning #machinelearning #prediction
Analytics Vidhya
7 Practical Applications of Data science in Ecommerce
Practical Applications of Data science in Ecommerce
Analytics Vidhya
8 How to tackle Overfitting?#machinelearning #overfitting
How to tackle Overfitting?#machinelearning #overfitting
Analytics Vidhya
9 Building Data Pipelines on GCP #googlecloud #datapipelines #data
Building Data Pipelines on GCP #googlecloud #datapipelines #data
Analytics Vidhya
10 Hands-on with A/B Testing #abtesting #datascience
Hands-on with A/B Testing #abtesting #datascience
Analytics Vidhya
11 Efficient Implementations of Transformers #transformers #cnn  #machinelearning
Efficient Implementations of Transformers #transformers #cnn #machinelearning
Analytics Vidhya
12 Modern Deep Learning Architecture #deeplearning  #architecture #deeplearningtutorial
Modern Deep Learning Architecture #deeplearning #architecture #deeplearningtutorial
Analytics Vidhya
13 Key steps for Designing Artificial Neural Network (ANN) for Image classification #machinelearning
Key steps for Designing Artificial Neural Network (ANN) for Image classification #machinelearning
Analytics Vidhya
14 5 things you should know about Azure SQL #azure #sql #datahour #datascience
5 things you should know about Azure SQL #azure #sql #datahour #datascience
Analytics Vidhya
15 AI & ML in the Automotive Industry #machinelearning #ai
AI & ML in the Automotive Industry #machinelearning #ai
Analytics Vidhya
16 Building Machine Learning Models in BigQuery
Building Machine Learning Models in BigQuery
Analytics Vidhya
17 NLP aspects in Telecommunication Industry
NLP aspects in Telecommunication Industry
Analytics Vidhya
18 Practical Time Series Analysis
Practical Time Series Analysis
Analytics Vidhya
19 Fundamentals of Quantum Computing
Fundamentals of Quantum Computing
Analytics Vidhya
20 A DAY IN THE LIFE of a Data Scientist (From waking up to working on algorithms)
A DAY IN THE LIFE of a Data Scientist (From waking up to working on algorithms)
Analytics Vidhya
21 Classification Machine Learning Model from Scratch
Classification Machine Learning Model from Scratch
Analytics Vidhya
22 Knowledge Graph Solutions using Neo4j
Knowledge Graph Solutions using Neo4j
Analytics Vidhya
23 Model Guesstimation (MLOps)
Model Guesstimation (MLOps)
Analytics Vidhya
24 ETL Pipelines in Google Cloud Platform
ETL Pipelines in Google Cloud Platform
Analytics Vidhya
25 Key steps for Designing Convolutional Neural Network(CNN) for Image Classification
Key steps for Designing Convolutional Neural Network(CNN) for Image Classification
Analytics Vidhya
26 Getting Started with AWS EC2 #amazon #aws
Getting Started with AWS EC2 #amazon #aws
Analytics Vidhya
27 How to Use Azure NLP and Graph Databases for Intelligent Knowledge Mining
How to Use Azure NLP and Graph Databases for Intelligent Knowledge Mining
Analytics Vidhya
28 Certified AI & ML BlackBelt Plus Program #shorts
Certified AI & ML BlackBelt Plus Program #shorts
Analytics Vidhya
29 Visualizing Data using Python #machinelearning #visualization #python
Visualizing Data using Python #machinelearning #visualization #python
Analytics Vidhya
30 DCNN for Machine RUL Prediction using Time-series Data #timeseries #machinelearning #datascience
DCNN for Machine RUL Prediction using Time-series Data #timeseries #machinelearning #datascience
Analytics Vidhya
31 M in ML stands for Math & Magic
M in ML stands for Math & Magic
Analytics Vidhya
32 An Unsupervised ML approach using Clustering
An Unsupervised ML approach using Clustering
Analytics Vidhya
33 Customizing Large Language Models GPT3 for Real-life Use Cases #gpt3 #datascience
Customizing Large Language Models GPT3 for Real-life Use Cases #gpt3 #datascience
Analytics Vidhya
34 Model Parameters vs Hyperparameters - Techniques in ML Engineering #machinelearning
Model Parameters vs Hyperparameters - Techniques in ML Engineering #machinelearning
Analytics Vidhya
35 Practical MLOps #mlops #datascience
Practical MLOps #mlops #datascience
Analytics Vidhya
36 Data Engineering with Databricks #dataengineering #databricks
Data Engineering with Databricks #dataengineering #databricks
Analytics Vidhya
37 Multi-Objective Optimisation
Multi-Objective Optimisation
Analytics Vidhya
38 When Airflow Meets Kubernetes
When Airflow Meets Kubernetes
Analytics Vidhya
39 AI in Banking
AI in Banking
Analytics Vidhya
40 Learn Convolutional Neural Network for Image Recognition
Learn Convolutional Neural Network for Image Recognition
Analytics Vidhya
41 Extracting Value from Data
Extracting Value from Data
Analytics Vidhya
42 How to measure Marketing Channel Effectiveness
How to measure Marketing Channel Effectiveness
Analytics Vidhya
43 Transforming Lives | Data Science Immersive Bootcamp
Transforming Lives | Data Science Immersive Bootcamp
Analytics Vidhya
44 Stock Market Analysis - AI driven approach
Stock Market Analysis - AI driven approach
Analytics Vidhya
45 Become a Data Engineering Professional in 2022 | Future Trends + Skills Required
Become a Data Engineering Professional in 2022 | Future Trends + Skills Required
Analytics Vidhya
46 Ensemble Techniques in Machine Learning #machinelearning #ensemble #datascience
Ensemble Techniques in Machine Learning #machinelearning #ensemble #datascience
Analytics Vidhya
47 The Power of Visualization | Tableau Full Course | Analytics Vidhya
The Power of Visualization | Tableau Full Course | Analytics Vidhya
Analytics Vidhya
48 Demand for Data Engineers is on the Rise | Data Engineer | Analytics Vidhya
Demand for Data Engineers is on the Rise | Data Engineer | Analytics Vidhya
Analytics Vidhya
49 Data Visualization in Data Science | DataHour | Analytics Vidhya
Data Visualization in Data Science | DataHour | Analytics Vidhya
Analytics Vidhya
50 Role of Optimization in Machine Learning & Deep Learning | DataHour | Analytics Vidhya
Role of Optimization in Machine Learning & Deep Learning | DataHour | Analytics Vidhya
Analytics Vidhya
51 Solving any Machine Learning Problem | Approach and Steps Involved
Solving any Machine Learning Problem | Approach and Steps Involved
Analytics Vidhya
52 Topic Modeling Explained with Implementation | Using LDA in Python | DataHour by Arpendu Ganguly
Topic Modeling Explained with Implementation | Using LDA in Python | DataHour by Arpendu Ganguly
Analytics Vidhya
53 Data Engineering in E-Commerce | The Best Case Study
Data Engineering in E-Commerce | The Best Case Study
Analytics Vidhya
54 Introduction to Classification using Azure Machine Learning | DataHour | Analytics Vidhya
Introduction to Classification using Azure Machine Learning | DataHour | Analytics Vidhya
Analytics Vidhya
55 Introduction to Federated Learning | DataHour | Analytics Vidhya
Introduction to Federated Learning | DataHour | Analytics Vidhya
Analytics Vidhya
56 Diffusion Models for Generative Arts | DataHour | Analytics Vidhya
Diffusion Models for Generative Arts | DataHour | Analytics Vidhya
Analytics Vidhya
57 Master Google Analytics in 1 Hour | DataHour | Analytics Vidhya
Master Google Analytics in 1 Hour | DataHour | Analytics Vidhya
Analytics Vidhya
58 Learn Hypothesis Testing | DataHour | Analytics Vidhya
Learn Hypothesis Testing | DataHour | Analytics Vidhya
Analytics Vidhya
59 A Practical Approach to Kaggle Competition | DataHour | Analytics Vidhya
A Practical Approach to Kaggle Competition | DataHour | Analytics Vidhya
Analytics Vidhya
60 Making AI work for Business | DataHour | Analytics Vidhya
Making AI work for Business | DataHour | Analytics Vidhya
Analytics Vidhya

The video teaches the difference between normalization and standardization in machine learning, and how to apply them using sklearn and scikit-learn. It explains the importance of feature scaling in machine learning pipelines. By watching this video, viewers will understand when to use normalization and standardization, and how to implement them in their own projects.

Key Takeaways
  1. Import necessary libraries, including sklearn and scikit-learn
  2. Load dataset and identify features to scale
  3. Apply standardization using StandardScaler
  4. Apply normalization using Normalizer
  5. Compare results and choose appropriate scaling method
💡 Normalization and standardization are not interchangeable terms, and the choice of scaling method depends on the specific problem and dataset.

Related Reads

📰
Exploring Data the Right Way: A Practical Walkthrough of the CRISP-DM Data Understanding Phase
Learn to explore data effectively using the CRISP-DM framework's Data Understanding phase
Medium · Data Science
📰
Exploring Data the Right Way: A Practical Walkthrough of the CRISP-DM Data Understanding Phase
Learn to explore data effectively using the CRISP-DM framework's Data Understanding phase, a crucial step in any data science project
Medium · Programming
📰
Exploring Data the Right Way: A Practical Walkthrough of the CRISP-DM Data Understanding Phase
Learn to explore data effectively using the CRISP-DM framework's Data Understanding phase, a crucial step in any data science project
Medium · Python
📰
What Hiring Managers Actually Think When They See Your Data Science GitHub in 2026
Learn what hiring managers think when they see your Data Science GitHub in 2026 and how to improve your profile
Medium · Machine Learning
Up next
Salesforce Tableau CRM & Einstein Discovery Consultant Exam: Full Syllabus Breakdown (New 2025 Bluep
Emily Unfiltered
Watch →