Let's Build an Exploratory Data Analysis Project from Scratch | Python, Numpy, Pandas
Jovian Jovian
54.5K subscribers
216,425 views
5.4K

 Published On Streamed live on Mar 4, 2021

⚡For real-time updates on events, connections & resources, join our community on WhatsApp: https://jvn.io/wTBMmV0

In this live hands-on workshop, we’ll build an exploratory data analysis project from scratch in 2.5 hours. You can follow along and build your own project. Check out our FREE Certification course on Data Analysis with Python here: http://zerotopandas.com

Notebook used in the session: https://jovian.ai/aakashns-6l3/us-acc...
Dataset used (US Accidents): https://www.kaggle.com/sobhanmoosavi/...
Open Datasets tool: https://github.com/JovianML/opendatasets

Topics Covered
00:00:00 - Skip This Part
00:00:31 - Introduction
00:02:50 - Jovian Data Science Bootcamp
00:06:48 - 1. Select Real World Dataset
00:25:44 - 2. Data Preparation & Cleaning
00:46:38 - 3. Exploratory Analysis & Visualization
01:17:03 - 4. Ask & Answer Questions
01:46:02 - 5. Interactive Graphs
02:07:19 - 6. Summary & Conclusion


NOTE: The Dataset used in this workshop was updated recently from Kaggle, here are the things that changed since the live workshop.
- The filename of the dataset has been updated, the new filename is './us-accidents/US_Accidents_Dec20_updated.csv'. Please change the filename if you are getting errors while creating the dataframe.
- The "Source" column is removed from the updated dataset. Any mention of "Source" in this notebook can be ignored while using the updated dataset.

Here’s the step by step process that we follow in the workshop:
🔍 Select a large real-world dataset from Kaggle
⚒ Perform data preparation & cleaning using Pandas & Numpy
🔁 Perform exploratory analysis & visualization using Matplotlib & Seaborn
🙋‍♂️ Ask & answer questions about the data in a Jupyter notebook
📝 Summarize your inferences & write a conclusion
📑 Document, publish, and present and your Jupyter notebook online

------------------------------------------------
⚡ We’re launching a new exclusive program called the “Zero to Data Science Bootcamp” for a limited batch of participants with a new batch kicking off every month. More details here: https://zerotodatascience.com/

Learn industry-relevant skills from Silicon Valley engineers, build real-world projects, and start your data science career in 6 months. Over the 24 weeks, you will complete 7 data science courses, work on 14 weekly assignments, and build 4 real-world portfolio projects.

You will achieve the following over the duration of the boot camp:
- Master all the skills and tools required to become a Data Analyst
- Build unique real-world projects to create a strong professional portfolio
- Follow a structured and finetuned week-by-week learning roadmap
- Learn & interact with like-minded peers in a classroom-like setting
- Get personal attention and guidance whenever you need it
- Be fully prepared to apply for jobs, ace interviews, and get hired as a data analyst

------------------------------------------------
👨‍🏫 This workshop is taught by Aakash N S who is the co-founder and CEO of Jovian - a community learning platform for data science & ML. Previously, Aakash has worked as a software engineer (APIs & Data Platforms) at Twitter in Ireland & San Francisco and graduated from the Indian Institute of Technology, Bombay. He’s also an avid blogger, open-source contributor, and online educator.

------------------------------------------------
Learn Data Science the right way at https://www.jovian.ai
Get the latest news and updates on Machine Learning at   / jovianhq  
Connect with us professionally on   / jovianml  
Follow us on Instagram at   / jovian.ml  
Subscribe for new videos on Artificial Intelligence    / jovianml  

show more

Share/Embed