- 205
- 155 892
AnalytiCode
United States
เข้าร่วมเมื่อ 20 ก.พ. 2014
Welcome to the Ultimate Hub for Analytical Data Science & Measurement Science!
Howdy! I’m Chris Pulliam, a PhD Measurement Scientist with a passion for innovating at the intersection of measurement and data science. On this channel, I combine my 10+ years in the lab with expertise in data science and teaching to bring you:
- Signal processing tutorials
- Machine learning techniques
- Scientific data visualization
- Near IR and Mass Spectrometry data interpretation
- Analytical chemistry, and more!
Whether you're diving into data or just data curious, there’s a video or playlist here for you!
Disclaimer: Opinions are my own, not my employers.
Visit my Medium Blog to see many of these ideas written out: medium.com/@chrisjpulliam
If you want to chat find me on LinkedIn: www.linkedin.com/in/chrispulliam3/
Howdy! I’m Chris Pulliam, a PhD Measurement Scientist with a passion for innovating at the intersection of measurement and data science. On this channel, I combine my 10+ years in the lab with expertise in data science and teaching to bring you:
- Signal processing tutorials
- Machine learning techniques
- Scientific data visualization
- Near IR and Mass Spectrometry data interpretation
- Analytical chemistry, and more!
Whether you're diving into data or just data curious, there’s a video or playlist here for you!
Disclaimer: Opinions are my own, not my employers.
Visit my Medium Blog to see many of these ideas written out: medium.com/@chrisjpulliam
If you want to chat find me on LinkedIn: www.linkedin.com/in/chrispulliam3/
Can Data Science and NIRS Quantitate Coffee Adulteration?
Dive into the world of advanced data science and chemistry! In this video, I show you how to harness the power of Near-Infrared Spectroscopy (NIRS) and Ridge Regression to detect and quantify material adulteration in coffee. Learn step-by-step how to:
✅ Import and preprocess NIRS data
✅ Build and optimize a Ridge Regression model
✅ Visualize the results for clear insights
Whether you’re passionate about coffee, data science, or analytical chemistry, this video has something for you. Perfect for beginners and pros alike-start your journey to uncovering what’s really in your coffee!
Don’t forget to like, subscribe, and hit the bell to never miss an update on science-powered problem-solving.
pd.read_csv('raw.githubusercontent.com/chrisp33/Analytical_YT_Tutorials/refs/heads/main/Data/adulterated_data_regression.csv')
✅ Import and preprocess NIRS data
✅ Build and optimize a Ridge Regression model
✅ Visualize the results for clear insights
Whether you’re passionate about coffee, data science, or analytical chemistry, this video has something for you. Perfect for beginners and pros alike-start your journey to uncovering what’s really in your coffee!
Don’t forget to like, subscribe, and hit the bell to never miss an update on science-powered problem-solving.
pd.read_csv('raw.githubusercontent.com/chrisp33/Analytical_YT_Tutorials/refs/heads/main/Data/adulterated_data_regression.csv')
มุมมอง: 48
วีดีโอ
Want to DETECT Coffee Fraud? Watch This Now!
มุมมอง 11619 ชั่วโมงที่ผ่านมา
Curious about whether your coffee is authentic or adulterated? In this video, I’ll guide you through using Near Infrared (NIR) spectroscopy data with Python to uncover the truth! You’ll learn step-by-step how to: 1. Import and process your data using Pandas and Scikit-learn (sklearn). 2. Build a Support Vector Classifier (SVC) model to predict coffee adulteration. Whether you’re a data enthusia...
How to use Pandas Groupby Like a Pro!
มุมมอง 27014 วันที่ผ่านมา
Pandas Groupby is a powerful tool for Python based data analysis. In this video I will demonstrate several techniques for using Pandas Groupby with various chemistry examples! 0:00 Introducing Groupby 0:42 Basic Groupby operations 1:49 Multilevel Groupby 2:50 Custom Groupby aggregations 3:40 Fill missing values with Groupby 4:57 Using Custom Functions with Groupby
Why You Should NEVER Use Pandas’ inplace Argument!
มุมมอง 9114 วันที่ผ่านมา
Is the Pandas inplace Argument Slowing You Down? In this video, I reveal the hidden dangers of using the Pandas inplace argument-and why it might be holding back your data analysis game. If you love method chaining for clean, efficient code, you’ll want to rethink inplace! I'll show you exactly how this argument can break your flow and lead to unpredictable behavior in your scripts. Curious to ...
How PCA and Signal Processing Can Save Your Near IR Data!
มุมมอง 14521 วันที่ผ่านมา
Are you making this common mistake when analyzing Near IR data? In this video, we uncover a systematic error I discovered while running PCA on my Near IR coffee data. Before we can dive into building an accurate classification model, this error needs to be addressed. But how do you catch it, and more importantly, how do you fix it? I'll show you step-by-step how to use PCA to detect and correct...
Unlocking Insights: How to Perform EDA on 110 Coffee Samples
มุมมอง 294หลายเดือนก่อน
Exploratory Data Analysis on Coffee Adulteration: Unveiling Hidden Patterns! In this follow-up to my coffee adulteration video, I dive into Exploratory Data Analysis (EDA) on over 100 coffee samples, all analyzed with a Trinamix Near Infrared Spectrometer (NIRS). In this video, I demonstrate how heatmaps and advanced signal processing techniques can reveal novel features hidden within the data....
Can You Detect Fake Coffee? Building an Adulteration Dataset!
มุมมอง 118หลายเดือนก่อน
In this video, I demonstrate how to generate a dataset of authentic and intentionally adulterated coffee samples using a blend of fresh ground coffee and cornmeal. By carefully mixing these ingredients, I create synthetic samples that simulate real-world coffee adulteration-perfect for testing with our portable Near Infrared Spectrometer (NIRS) from Trinamix. Watch as I walk through the process...
How to Use Python & F-Test for NIR Data Feature Selection like a pro!
มุมมอง 142หลายเดือนก่อน
In this video, we dive into the exciting world of feature selection for Near-Infrared (NIR) spectroscopy data using Python's powerful F-test. Learn how to uncover the most significant features in your spectral data and boost the accuracy of your machine learning models. We'll guide you step-by-step on implementing the F-test in Python, helping you understand key concepts and apply them to real-...
How to Use Python Pandas to Merge, Join, and Concatenate Like A Pro!
มุมมอง 175หลายเดือนก่อน
Storing chemistry data often involves multiple data tables, whether it’s from different experiments, measurements, or metadata. Managing and combining this data can be a challenge, but with Pandas, it becomes simple using Merge, Join, and Concatenate functions. In this video, I’ll walk you through how to: ✅ Merge data on single and multiple keys ✅ Explore practical use cases for Merge, Join, an...
How A Chemist Tests For ADULTERATED Coffee at Home! (Proof of Concept)
มุมมอง 607หลายเดือนก่อน
In this video, we explore how a portable Near-Infrared (NIR) spectrometer can be used to detect coffee adulteration. Watch as we break down the process of analyzing the Near IR spectra using Python, uncovering differences in coffee composition that could indicate impurities or additives. Whether you're a coffee lover, a scientist, or just curious about practical spectroscopy, this tutorial show...
How to Use Pandas to Clean String Data!
มุมมอง 236หลายเดือนก่อน
text data can be quite messy but Pandas and python is a great quickly cleaning it. Recommended Video: th-cam.com/video/a39iVtDYjlE/w-d-xo.html 0:00 Intro 0:16 Getting into the notebook 0:24 Basic String Methods 1:00 Access dataframe columns for cleaining 2:34 Converting Datatypes String to Numerical 3:40 Extracting and Splitting Strings and Regex 6:25 Advance String Methods 7:24 Closing
How to use Kmeans and Ipywidgets to unlock new data insights!
มุมมอง 1212 หลายเดือนก่อน
In this video, we dive into how k-means clustering can be used to create labels for completely unlabeled data. The dataset includes authentic coffee samples and known adulterants, but none of it was labeled! Watch as we use Python to apply unsupervised machine learning on Near-Infrared (NIR) spectra, uncovering hidden patterns and distinguishing genuine coffee from its impure counterparts. This...
How to Handle Missing Values in Pandas Like a Pro!
มุมมอง 1692 หลายเดือนก่อน
In this video I will demonstrate how to handle missing values like a professional using Python Pandas!. By the end of this video you know how to find missing data, drop missing data, and fill missing data using Python pandas methods. If you have a completely empty dataframe check this video out: th-cam.com/video/WdxgSF-gvn0/w-d-xo.html 0:00 Intro 0:16 Setting up the notebook 0:49 Spotting missi...
Detecting Coffee Outliers with Near IR and Python
มุมมอง 1692 หลายเดือนก่อน
Detecting Coffee Outliers with Near IR and Python
Data Validation in Python: Using df.empty to Ensure Clean Data
มุมมอง 1072 หลายเดือนก่อน
Data Validation in Python: Using df.empty to Ensure Clean Data
Near IR + Python data analysis of 20 Coffees!
มุมมอง 1852 หลายเดือนก่อน
Near IR Python data analysis of 20 Coffees!
The Truth About Standard Scaler: Can It Correct Skewed Data?
มุมมอง 922 หลายเดือนก่อน
The Truth About Standard Scaler: Can It Correct Skewed Data?
Boost Performance with Python Feature Selection with NIRS data
มุมมอง 2592 หลายเดือนก่อน
Boost Performance with Python Feature Selection with NIRS data
How to Boost Plastic Detection Accuracy with NIR Spectroscopy!
มุมมอง 1243 หลายเดือนก่อน
How to Boost Plastic Detection Accuracy with NIR Spectroscopy!
Build Better Models with PCA | NIRS Plastic Prediction!
มุมมอง 1413 หลายเดือนก่อน
Build Better Models with PCA | NIRS Plastic Prediction!
Let's explore total dissolved solids in the LA River!
มุมมอง 513 หลายเดือนก่อน
Let's explore total dissolved solids in the LA River!
Evaluate Spectroscopy Signal with Percent RSD!
มุมมอง 1544 หลายเดือนก่อน
Evaluate Spectroscopy Signal with Percent RSD!
Evaluate Sample Replicates with Pearson Correlation and Python!
มุมมอง 1825 หลายเดือนก่อน
Evaluate Sample Replicates with Pearson Correlation and Python!
Boosting Analytical Data with Derivative Signal Processing!
มุมมอง 1935 หลายเดือนก่อน
Boosting Analytical Data with Derivative Signal Processing!
Analyzing Vacuum Soil and Dryer Lint with Near IR Spectroscopy!
มุมมอง 1935 หลายเดือนก่อน
Analyzing Vacuum Soil and Dryer Lint with Near IR Spectroscopy!
Boosting Job Performance with Peloton: My Success Story
มุมมอง 696 หลายเดือนก่อน
Boosting Job Performance with Peloton: My Success Story
Catch Lemons BEFORE THEY ROT with Near IR!
มุมมอง 1476 หลายเดือนก่อน
Catch Lemons BEFORE THEY ROT with Near IR!
Chemical Analysis at Home: Analyzing Plastic Containers!
มุมมอง 2076 หลายเดือนก่อน
Chemical Analysis at Home: Analyzing Plastic Containers!
What an awesome breakdown. Loved the video!
Thanks boss!
Go outside today :)
I feel we need a basics of NIR spectroscopy, probably :)
I got you! I’ll get on that
Have a great week!
I need an app to upload cas numbers and it will generate a list with all info
A streamlit app would probably be the best approach especially for rapid trial and error
@@CJP3 I am absolutely stunned that nothing exists for this. We have thousands of cas numbers to upload which we will need to generate a table, link to SDS library and provide structure, hazard classes and so on. There are terrible chemical inventory so called companies like bioraft out here , making money and providing none of that service.
Terrible sound, cant hear what you say…
Sorry about that, the sound in later videos is MUCH better. I was still very much a newbie in this video lol
If you are coming from the Medium article that references this video (Thanks by the way!). The code: sns.scatterplot(x = peak_data.index, y = peak_data.values, color = 'red', alpha = 0.5) Should be: sns.scatterplot(x = peak_data["mz"], y = peak_data["int"], color = 'red', alpha = 0.5) I wishes I would have found this video sooner.
Nice work bro!! But as a German, I cannot not mention this aint real bread 😅😅😂
Hahahahaha fair enough! One day I hope to taste real bread!
@CJP3 Its remarkable simple to make at home!! I bet youll find plenty tasty looking but simple recipes when searching for 'How to make German bread' and believe me its so worth it!! We even have fairly cheap mini bread-baking machines that make the process even more convinient ;)
@@Wassermelonenbaum ok I’m sold - let me do some quick research 🧐
Closer 😬
😂
Have a great weekend!🎉
now you need Mitsubishi TO-ST1-T!
😂 that’s a fancy toaster - I had to look it up
what about caramelization? can that be observed
interesting
Thanks boss!!
Have a great weekend!!🎉
I use it for parametric building energy modelling and its grest for creating graphs and understanding how buildings work plus clients love all the visuals
That’s incredible! Thanks for sharing :)
Have a great weekend!!
My man -- phenomenal video! I came across this at the right time. I'm finding peaks in methane mixing ratio data during a controlled release test. Very helpful -- thank you very much!
My pleasure! Good luck with your experiment!!
Very helpful explanation -- now tossing out my Phenylephrine stash!
Haha I certainly did!
Awesome! Just solved my problem here! Very simple and very clear! Thank you!
My pleasure!
Have a peaceful holiday season!
Here is the data :) github.com/chrisp33/Analytical_YT_Tutorials/blob/main/Data/adulterated_coffee_class_full_data.csv You can use: pd.read_csv('github.com/chrisp33/Analytical_YT_Tutorials/blob/main/Data/adulterated_coffee_class_full_data.csv?raw=true') to read it into your environment directly if you have an internet connection :)
@@CJP3 thank you! Would share any findings!
Would you be open to sharing the dataset you collected? I would love to work on it and make my own model.
Howdy boss! here is the data :) github.com/chrisp33/Analytical_YT_Tutorials/blob/main/Data/adulterated_coffee_class_full_data.csv You can use pd.read_csv('github.com/chrisp33/Analytical_YT_Tutorials/blob/main/Data/adulterated_coffee_class_full_data.csv?raw=true') to read it into your environment directly if you have an internect connection :)
Thanks for watching!! Have a great day!
how much is the device please?
@ howdy boss it varies depending on the service side it’s approx 10-20K but best to talk a salesperson
Probably a different experiement.. do differently roasted beans have different profiles?
That is an awesome idea!! 🤯
Thank u, as a math student, I am used to take time to process things, U slowing down was really helpful
Thank you very much! 🙏🏽 good luck on your learning journey!
Very, very usefull video!
Thanks boss! 🙏🏽
Great video, sir, Where can I find the video at 0:40 that explains how to create interactive boxplot? and any chance, could you share your codes ?
🤦🏽♂️ this video should have gone public next week! The video that’s referenced is public tomorrow 😂 god catch!
@@CJP3 :)
Cool, please share the data so we can learn by replicating!
Will do :)
Enjoy the video! Have a great day
Well done and very easy to follow
Thank you 🙏🏽
This is so cool. Def following to see more. I feel like a lot of python videos are focused on data or swe, so it's cool to see this application. Have you tried using polars?
Howdy! I haven’t used polars yet because my data doesn’t seem very large. Do you think I should explore it?
Algo bump for a good video, love the casual way you made the more scientific terms easier to understand while not doing it to the point of misinformation
Appreciate it, its a lot of hard work 🙏🏽
What does that device cost. I can not find it for sale anywhere.
Howdy, it cost about 10K-20K
Buy the bean ground the bean yourself. Fresh coffee every time. But ground coffee and it's spoils. Odd isn't it that tea literally spoils never is packaged as single use thingies and ground coffee in big bags. Well except they put whatever in it. Just buy coffee beans and a espresso maker a proper coffee maker that makes actual coffee. The silver ones takes 4 minutes. And isn't harder then to press a button on a machine you have to clean every use. O o Dude humans are fucking hopeless
Hahaha
Impressive!
Thank you!!🙏🏽
Thank you for the video
You're welcome, my pleasure!
Sir, Could you share the codes which you displayed on the video ?
Yep, I’ll share the code in GitHub, would that work?
Have a great day! I hope you enjoy the video!🎉
I do want to warn about the regex, it applies the python regex and it can be really slow for complex/large data but other than that it's quite useful
Thanks for the warning ⚠️
Have a great day!
Are there other topics you’d like me to tackle?
Thank you for this great video!
Thank you so much!! 🙏🏽
I enjoy the video. It gives me a good line of thought for my project.
Thanks boss! So glad it was helpful!
@Analyticode, Well done. But this would have be lovely if you had use jubyter note.
Glad you liked it! Yeah been experimenting more and more with VSCode using an Ipynb kernel. It’s really grown on me. Do you prefer Jupyter? I’ve used it previously but it always felt incomplete and the extension management was difficult. Maybe I’ll reloop.
Such a cool and informative video! Thanks
Thanks boss!!
What other foods should we build a dataset on? Someone recommended 🍫 !!
Thank you! This is really helpful.
My pleasure boss!
What other pandas concepts to you want to learn about? 👨🏽🏫📝
nice, appreciate the video
Thanks boss!!
What other foods would you like me to look at!? 🥘 🥕
chocolate?
@@LesStudy-vm9cnthat’s a good and tasty idea!! I will 💯 do that!!
Have a great day! I’m taking suggestions, what video do want to see?! 📝