Data Science 101: Methodology, Python, and Essential Math

Name: Data Science 101: Methodology, Python, and Essential Math
Rating: 4.0 (12 reviews)

From data science methodology, to an introduction to data science in Python, to essential math for data science.

Created byErmin Dedic

Last updated 4/2022

English

English [Auto],

What you'll learn

Explain data science methodology, starting with business understanding and ending at deployment
Identify the various elements of machine learning and natural language processing involved in building a simple Chatbot
Indicate how to create and work with variables, data structures, looping structures, decision structures, and functions.
Recall the various functionality of the two main data science libraries: Numpy and Pandas
Solve a system of linear equations
Define the idea of a vector space
Recognize the proper probability model for your use case
Compute a least squares solution via pseudoinverse

Course content

20 sections • 185 lectures • 14h 54m total length

Matching Activity - Match the Project to the Data Role5:54
Data Scientist, Data Analyst, Business Analyst, and Data Engineer. These are the typical roles in the data science world. Do you know which position you want? Will this activity change your intentions for the future? Did you guess right?
Intro to Data Science2:41
A data science career may be right for you if you are a methodological person and like to solve problems.
What a Data Scientist Does?2:13
You are considering a data science career so you want to know..what the heck do data scientists do anyway? As with most questions, it depends on the context but I lay out some possibilities.
Big Data2:21
Explore how volume, velocity, and variety define big data, stressing traditional storage and processing while variability and veracity shape data quality and integration across structured and unstructured data.
Big Data
Data Mining4:16
Data Mining
Machine Learning vs. Deep Learning3:57
Learn how machine learning, a subset of AI, differs from deep learning, a deeper neural network approach; recognize narrow AI and how layered networks classify images.
Advice to Data Scientists4:39
A data science career may be right for you if you have the data science skills mentioned in the lecture, or if you are willing to work on developing these skills. For example, do statistics seem interesting to you even though you are currently not skilled at it? Great. Passion and willingness to learn are all that matters.

What IS the best language for Data Science?2:22
A data science career may be in your future but you're not sure where to start. One common problem for newbies is to wonder...what the best language for data science actually is. I have particular answers based on your specific context.
Python2:20
If I didn't know anything about you or your plans, the best language for data science would be Python. It is the ONLY programming language for data science that I can suggest to students no matter their particular plans or location around the world. Find out why in this lecture.
SAS3:26
I have taught SAS programming for many years. One thing that still surprises me is rarely hearing SAS in the category of best language for data science. Discover my argument for SAS in this lecture.
R2:30
R is a very popular language for data science and data analysis in academic settings.
SQL3:45
SQL is a must-learn.
Programming Languages

Data Science Methodology/Process Intro6:44
An introduction to data science methodology.
Business Understanding6:06
The first and arguably the most important aspect of data science methodology is business understanding.
Data Understanding5:54
The second aspect of data science methodology is data understanding.
Data Prep9:00
The third part of data science methodology is data preparation. This is seen as nonsexy work but nevertheless important.
Modeling7:28
Modeling is one of the more fun aspects of data science methodology.
Evaluation9:47
Evaluation of model performance is an essential part of data science methodology.
Deployment7:41
An often overlooked aspect of the data science process is deployment.
What Would You Pick?

Purpose of Chatbot Section7:52
What is a Chatbot?2:56
Signing up for Watson Assistant2:07
Learn how to sign up for a free IBM Watson Assistant account, navigate the IBM Cloud sign-up process, and log in if you already have an account.
Creating a name - Healthcare Service Chatbot4:01
Learn to build a Watson assistant for health care by creating an assistant named health care and adding a two-node dialogue with a welcome and anything else.
Intents8:14
Create intents such as book appointment for a health care bot, train with user examples, connect to a dialogue node, and test the flow using try it.
Entities8:06
Learn to create an appointment type entity, add values and synonyms, enable fuzzy matching, and connect it to the dialogue flow; train the model by correcting intents to improve understanding.
Suggestions for More Learning2:36
Section Recap: Natural Language Processing , Machine Learning, and Use Cases6:04
Explore natural language processing as a service that turns unstructured text into structured data for machine learning, including text classification and intent detection, with rule-based and hybrid approaches.

Libraries5:42
Explore essential Python libraries for data science, including NumPy, pandas, Matplotlib, seaborn, and scikit-learn, plus TensorFlow, to clean, visualize, and model data.
API's3:37
Access data from remote services via RESTful APIs over HTTP, using get requests and XML or JSON formats, to power on-demand model scoring and embedded analytics.
Datasets7:02
Define data sets as structured collections of data in tabular formats such as Excel or CSV, with rows as observations and columns as variables.

Intro to Github2:41
Create a Repository4:20
Log in to GitHub and create a private repository called Hello world to organize a project with a readme, store files, and optionally clone or download content.
Creating Branch and Commit Changes7:04
Learn to create a branch from the main branch, use feature branches for edits, and commit changes with descriptive messages before merging.
Pull Request and Merging Pull Request6:09
Learn how to create and review a pull request from a feature branch, compare diffs with the main branch, and merge changes while managing commits and branch deletion.

Windows - Download Anaconda Distribution (includes Python!)2:42
Download the Anaconda distribution on Windows to get Python and essential data science packages, and learn how this bundle simplifies package management, including 64-bit or 32-bit selection via control panel.
Windows - Install Anaconda Distribution4:46
Install the Anaconda distribution on Windows, select 64-bit, install for you only, avoid adding to the path environment variable, optionally register Anaconda as the default python, and review installation details.
Windows - Setting Up Environment4:53
Windows - Opening Jupyter Notebook2:18
Open Anaconda prompt, activate the correct environment, and launch Jupyter notebook to access your data in a desktop folder. Keep datasets and notebooks together for easier imports.
MacOS - Anaconda Download and Install3:31
Learn to download the macOS Anaconda graphic installer, complete the setup with license and destination choices, and verify the installation by running conda list in the terminal.
MacOS - Conda Environment4:31
Set up a dedicated conda environment on macOS for each project by creating, activating, and installing key data science libraries (pandas, numpy, matplotlib) and Jupyter Notebook.
MacOS - Jupyter Notebook2:09
Jupyter Notebook Interface and Shortcuts8:02

How to Use Markdown Cells (Adding Headers, Links, and Images)2:04
Comments - Inline and Block Comments4:40
Python Indentation3:37
Learn how Python indentation defines code blocks, using colons and body alignment in for loops, if statements, and else blocks to write clean, executable code.
Writing Single and Multiple Lines of Code3:08
Understanding Variables2:28
Learn how variables save values for later use in Python, with examples like storing the sum of four and five and using meaningful names such as height_m and height_f.
Main Data Types and Creating Them (Integer, Float, String, List, Dictionary)5:36
Explore the main Python data types—integers, floats, strings, lists, and dictionaries—by examining type() checks, creating examples, and understanding keys and values.
Lists - How To Use11:09
Dictionaries - How To Use4:25
Creating A Tuple1:10
Tuple - How To Use5:21
Learn how to work with tuples using integer indexing (positive and negative), slicing, and the count and index methods, while recognizing that tuples are immutable and items cannot be reassigned.
Creating a Set2:13
Learn how to create a set in Python using curly braces for integers or mixed data types, and via the set() function from a list.
Set - How To Use3:08
Operators12:04
Fill in Activity 1 - Fundamentals0:03

Introducing Decision and Looping Structures2:57
If statement4:00
Set a cash flow variable to 500000 and use an if statement to print a message when the cash flow is greater than 450000, illustrating booleans, indentation, and execution.
Else Statement3:16
Elif2:52
Explore how the Python elif statement extends an if-else chain to evaluate multiple expressions. Using a cash flow example, the lecture demonstrates thresholds at 500000 and 400000 with corresponding prints.
For Loop2:44
Explore how to use for loops to iterate over lists in Python, print items, and manage indentation, building intuition for data science examples.
While Loop4:17
This lecture explains how the while loop repeats a block until a condition is met, using a count example that increments and prints Hello, student three times.
Break and Continue Statements3:23

Requirements

None. This course is ideal for a beginner to Data Science.

Description

Welcome! Nice to have you. I'm certain that by the end you will have learned a lot and earned a valuable skill. You can think of the course as compromising 3 parts, and I present the material in each part differently. For example, in the last section, the essential math for data science is presented almost entirely via whiteboard presentation.

The opening section of Data Science 101 examines common questions asked by passionate learners like you (i.e., what do data scientists actually do, what's the best language for data science, and addressing different terms (big data, data mining, and comparing terms like machine learning vs. deep learning).

Following that, you will explore data science methodology via a Healthcare Insurance case study. You will see the typical data science steps and techniques utilized by data professionals. You might be surprised to hear that other roles than data scientists do actually exist. Next, if machine learning and natural language processing are of interest, we will build a simple chatbot so you can get a clear sense of what is involved. One day you might be building such systems.

The following section is an introduction to Data Science in Python. You will have an opportunity to master python for data science as each section is followed by an assignment that allows you to practice your skills. By the end of the section, you will understand Python fundamentals, decision and looping structures, Python functions, how to work with nested data, and list comprehension. The final part will show you how to use the two most popular libraries for data science, Numpy, and Pandas.

The final section delves into essential math for data science. You will get the hang of linear algebra for data science, along with probability, and statistics. My goal for the linear algebra part was to introduce all necessary concepts and intuition so that you can gain an understanding of an often utilized technique for data fitting called least squares. I also wanted to spend a lot of time on probability, both classical and bayesian, as reasoning about problems is a much more difficult aspect of data science than simply running statistics.

So, don't wait, start Data Science 101 and develop modern-day skills. If you should not enjoy the course for any reason, Udemy offers a 30-day money-back guarantee.

Who this course is for:

Beginners to Data Science or those interested in a data science career.
Individuals considering switching fields.
Individuals who want to get a big picture overview before focusing on specific Data Science topics.
You are interested in an Introduction to data science in Python.
You are interested in learning the essential math for data science.

Data Science 101: Methodology, Python, and Essential Math

What you'll learn

Explore related topics

Course content

Intro to Data Science 1017 lectures • 26min

Best Language for Data Science?5 lectures • 14min

Data Science Methodology7 lectures • 53min

Data Science Via Chatbot8 lectures • 42min

Libraries, API's, Datasets3 lectures • 16min

Github4 lectures • 20min

Introduction to Data Science in Python3 lectures • 6min

Installation/Jupyter/Comments (Windows and MacOS/Jupyter Notebook)8 lectures • 33min

Introduction to Data Science in Python - Python Fundamentals14 lectures • 1hr 1min

Introduction to Data Science in Python - Decision and Looping Structures7 lectures • 23min

Requirements

Description

Who this course is for: