Naive Bayes Classifiers for Text Documents: Python in Excel Tutorial (Free File)

Data science is THE BEST use case for Python in Excel! Want to have more impact at work? Do you have text data? Use Python in Excel to analyze it!
Text data is in Word docs, customer service chats, notes fields in IT systems. Text data is everywhere in every organization.
With Python in Excel, you can now harvest the value hidden in your text data.
I will use the Naïve Bayes machine learning technique with text documents in this video.
Naïve Bayes is commonly used in text analytics to classify documents.
A real-world scenario where Naïve Bayes has been successfully used for years is classifying emails and text messages as illegitimate (i.e., spam) or legitimate (i.e., ham).
☕ If you found this content useful and would like to support the channel, you can buy me a coffee: www.buymeacoffee.com/DaveOnData
--------------------------------------------------------------------------------------------
VIDEO CHAPTERS
--------------------------------------------------------------------------------------------
00:00 Intro
01:42 Tokenization
05:31 Document Vectors
06:40 The Naïve Bayes Algorithm
10:50 The Math of Naïve Bayes
18:10 Training the Naïve Bayes Model in Excel
24:46 Testing the Naïve Bayes Model in Excel
28:06 What’s Next?
--------------------------------------------------------------------------------------------
FREE MACHINE LEARNING CRASH COURSES
--------------------------------------------------------------------------------------------
If you're ready to see what Python in Excel skills make possible, be sure to check out my FREE on-demand machine learning crash courses!
Here's what you get with any of these courses:
1️⃣ On-Demand: Watch the course when it fits your schedule
2️⃣ PDF of all slides
3️⃣ All Python code as a Jupyter Notebook
4️⃣ All data so you can experiment
5️⃣ Resources to continue your learning.
Machine learning with Python in Excel. You've got this if you want it:
💻 Decision Trees with Python:
bit.ly/DecisionTreesWithPython
💻 Tuning Decision Trees with Python:
bit.ly/TuningDecisionTreesWit...
💻 Logistic Regression with Python:
bit.ly/LogisticRegressionWith...
💻 Cluster Analysis with Python:
bit.ly/ClusterAnalysisWithPython
--------------------------------------------------------------------------------------------
GET THE MICROSOFT EXCEL WORKBOOK
--------------------------------------------------------------------------------------------
Here's the link to the GitHub for my Python in Excel video workbooks:
github.com/DaveOnData/PythonI...
NOTE - You have to have access to Python in Excel to run the code!
#pythoninexcel #pythonexcel #pythonforexcel

[@DaveOnData]

✅ You don't need Microsoft to give you access to Python in Excel to start building your skills. Find out how to get started NOW: czcams.com/video/0iV4FtpSriY/video.html

[@kristoferbrown8007]

Dave, you delivered as promised! I cannot wait for the upcoming clustering video, as the main challenge we have is applying labels to projects by evaluating a product description or similar field. The same could be done with value props, etc. Understanding which buckets these projects fall into would be extremely helpful when trying to understand relationships. Thanks again!

[@DaveOnData]

@kristoferbrown8007 - Excellent! You will likely enjoy my next video, then. The video will cover TF-IDF for text clustering, but not how k-means works. If it would be helpful for your, I have a free crash course on k-means clustering: bit.ly/ClusterAnalysisWithPython

[@michaelt312]

Ok, I see a video from you. Giddy.
I see Bayes in the title. Giddy and elated.

[@DaveOnData]

Thank you! I hope many professionals are excited about what Python in Excel brings to the table.

[@MaozRosenthal]

Dear David thank you for highly educating videos that allow all of us to take a new look at Microsoft Excel and find some of its less known features. I have a question about this video: Should the code work on non-English non-Latin texts? I get errors that relate to English specific issues (lower case staff) and was wondering if this analysis with Python in Excel can go beyond English. Thanks again for great videos.

[@DaveOnData]

@MaozRosenthal - The default support for non-English text is rudimentary using scikit-learn classes. I've asked Microsoft to prioritize adding the NLTK to Python in Excel to get more options. You may find the following Stack Overflow article of interest:
stackoverflow.com/questions/61394233/is-countvectorizer-in-sklearn-only-meant-for-english

[@andrewvanderpallen155]

Thanks for the video David. My question is how do I deploy the model to be used in excel ?So for example I have built a stock predictor model, I want to be able to share this model with a colleague so they can use the model. Can I send them the excel file with a "Dashboard" sheet where they would just enter a single set of the variables(features like High, Low, Open, Close, Volume etc) and have an output cell display the predicted value ?

[@DaveOnData]

@andrewvanderpallen155 - If I understand your question correctly, this scenario would be supported if the colleague can access Python in Excel (e.g., they have the subscription add-on).
The current word from Microsoft is Python in Excel outputs (e.g., visualizations), which colleagues can view without Python in Excel but cannot run Python formulas.

[@andrewvanderpallen155]

@@DaveOnData Thanks for your answer. The colleague cannot access Python in Excel yet. I was thinking since the model would be kind of a finished product they wouldn’t need python to use it but I was wrong.