Cannabis Data Science

🚯 Today we underscore the usefulness of archiving cannabis lab results. Following the principle of "never throw away data", we archive 5,500 lab results performed by SC Labs that have since vanished from the internet.🛣️ As straightforward as the task may seem, nuances of human language are critical in parsing lab results. We realize that we need to use natural language processing (NLP) in our COA...

🦠Want to know more about Hops Latent Viroid? Today, the CEO, Angel Fernandez, PhD., and VP of R&D, Ajith Anand at 🧬MyFloraDNA, a biotech lab in California, join us to share what they have learned from their 275,000+ tests for Hops Latent Viroid.👨‍🔬You can see their latest research here: https://www.mdpi.com/1999-4915/15/7/1487 🤝 Join the fun, data wrangling, and analytics in the Cannabis...

☀️ This week we talk about the need for open data in the cannabis space because summary statistics can't be trusted and consumers benefit from actually being able to see the data for themselves. Why? Because homegrow is often prohibited and bad actors plus shady businesses cut corners and use bad business practices because cannabis is in a legal gray area. There are a few good actors who deliver t...

🧑‍🌾 Join the meetup where backyard botanists share tales of tall plants. See how homegrowers, in the face of adversity and defying all odds, can grow a plant pesticide-free when multi-million dollar companies can't. 🐌 This isn't your grandma's garden club; it's a peek into a subculture where the legacy of the 60s and 70s meets the high-tech of the 21st century. Contemplate the corporate tentacl...

🌎 In a world where information is just a click away, imagine having a treasure trove of cannabis data so tantalizingly close, yet frustratingly out of reach! This episode sets out to address just that - the tragic case of abundant cannabis certificates of analysis (COAs) that are often locked away from consumers.🤝 Join the fun, data wrangling, and analytics in the Cannabis Data Science meetup, e...

🕵️‍♀️ In the spirit of discovery, we're donning our statistical hats, plunging into the Massachusetts cannabis industry. Using statistics as our torch, we meticulously inspect cannabis licensee data, with a focus tighter than a well-rolled joint. We traverse through cultivation sizes, scrutinize performance data, and contrast the performance of disadvantaged business enterprises (DBEs) and non-DBE...

🧑‍🌾 Join the meetup as we uncover traces of a banned pesticide, PBZ, proliferating in the markets in Washington State. We advocate for open data, reasoning that access to knowledge may be the best way to ensure public safety and encourage responsible cultivation practices. We aim to put the incentive in the right place, deter malpractice, enhance market competition, and promote honesty between l...

🥸 Unleash the power of your COAs. Behold the Cannabis Data Science Team demonstrate the art and science of parsing COAs. Meet CoADoc, an open-source AI-powered COA parsing wizard. Given COAs in any format, you can get YOUR data.🦾 Curious about integrating rich lab data into your app? We zoom in on the CoADoc API, a tool that you can use today to finally access cannabis lab results as easy as the...

🧄 Fearing public scrutiny, labs often cringe at the thought of their data under the lens of scientists from around the world. But what if the microscope is only as powerful as its user? Dive into the potent world of lab results as we search for "garlic" aromas in 1,200 Florida lab results, sifting through the intensity of each complex scent to identify distinctive garlic strains. It's a fascinati...

🐍 In our latest escapade, we gather the sources, methods, and data needed to parse 15,000+ COAs from Florida's top cannabis companies. 👨‍💻 You know, when your friendly neighborhood dispensary acts like their printer is "offline" or they've suddenly developed amnesia when you ask for COAs for your strains? Yeah, we've all been there. 🍃 Worry no more, we're here to empower you with AI-powered Co...

🐢 Ever see a Python-powered data-snapping turtle? We're diving into the lake of PSI Labs' test results, snapping up cannabis lab data with turtle-like tenacity. By the end, we have a treasure trove of test results tucked safely away in our shell. Slow and steady might win the race, but in Cannabis Data Science, a quick snap seals the deal!🤝 Join the fun, data wrangling, and analytics in the Cann...

💰 Today we bag 125,000+ lab results from across the US, analyzing CA, CT, MA, MI, and WA state's most precious botanical data. And oh did we find treasures! Our quest? Seeking international cannabis varieties, in particular, landraces - the purest, oldest, and most genetically unaltered strains of our favorite plant.🌎 In this exciting expedition, we look into a variety of strains from Thai to Co...

🌿🌍We explore cannabis cultivation around the world. We discover cultivators in South Africa and count the number of licenses by province. As we paint a picture of the burgeoning cannabis industry in the Rainbow Nation, we discover pure gold!📊 Get ready for some difficult data collection, eye-catching visualizations, and a lively conversation about the global cannabis landscape.🤝 Join the fun,...

🌴 Welcome to the dark understory of the cannabis industry. Join as we explore intensity and polarity by user, strain, and brand, searching for valuable insights that may help us understand cannabis user preferences and behavior.📊 Leveraging strain reviews, this intriguing analysis employs SIA (the Sentiment Intensity Analyzer) to rank review intensity and classify polarity. By providing a compre...

🌟 Join the intriguing discussion of personality and cannabis preferences! Discover if your personality may affect the chemotype of cannabis you may like to consume. We delve into Revealed Preferences theory and The Big 5 Personality Traits (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) to uncover potential connections. 🧠🌿 Join us as we build a model between personal...

🎢Welcome to the thrilling world of cannabis statistics! In this action-packed exclusive episode, our intrepid team dives headfirst into an analysis of variance (ANOVA) adventure, exploring various intriguing data points from the Massachusetts Cannabis Control Commission. With the right tools in hand and the API primed, our data science heroes embark on a journey to gather vital intel on cannabis...

😊 In this long-awaited episode, we use natural language processing (NLP) to rank strain reviews by consumer and examine whether certain compounds are related to the review rankings. We build a model that you can use to determine if any specific compounds have a positive or negative relationship with the sentiment of consumer reviews. Follow along as we:1. Prepare and visualize strain and lab resu...

💸 In an exclusive session, we explore data from the Massachusetts Cannabis Control Commission and the Federal Reserve Economic Data (FRED) to test if there have been structural breaks in consumer preferences and the aggregate cannabis production function (in MA). We use the Chow Test to deal with heterogeneity. We aggregate daily production data into monthly and quarterly averages, calculate sale...

💡In curiosity, we start applying phylogenetics to study the genesis of some of the most popular cannabis strains, including Runtz, Jack Herer, and Haze varieties. We are able to identify all Runtz varieties grown in Washington State in 2022, when each variety was first tested, and who grew the variety. The groundwork is then laid to untangle the web of strains with data of propagation techniques...

🐛 Join us as we uncover facts about pesticide use in the cannabis industry. Using public lab results, we identify various pesticides used and count the number of contaminated samples in Washington State. We also build a statistical model to predict the likelihood of detecting pesticides, such as Piperonyl butoxide (PBO), in cannabis flower and hydrocarbon concentrates. 🤝 Join the fun, data wrang...

🧬 Join us as we dive into the question of how much THC and CBD in cannabis is influenced by genetics versus the environment. We uncover research published 35 years ago that gives us a starting point to untangle the variation observed in THC and CBD levels. Don't miss this opportunity to learn more about cannabis and its genetics! 🤝 Join the fun, data wrangling, and analytics in the Cannabis Data...

Get ready to dive into the world of cannabis sales in Washington for 2022! We crunch gigabytes to uncover the top performers in the industry. We calculate sales by licensee on a daily and monthly basis, compile statistics, and use iteration to make sure that we've got all the data we need. And the best part? We tell you exactly who sold the most on the most important day of the year, 4/20, as well...

🕵️ Molds and diseases and pests, oh my! We confront some of the many cannabis contaminants and discuss how they affect producers and consumers alike. We also discuss the laboratories screening for contaminants and how any anomalies could be detected with an application of Benford's Law. 🤝 Join the fun, data wrangling, and analytics in the Cannabis Data Science meetup: https://www.meetup.com/canna...

🔬 We tackle the sticky issue of lab shopping for cannabis quality control tests: the phenomena of cannabis cultivators patronizing labs that flout quality control testing regulations. 🤝 Join the fun, data wrangling, and analytics in the Cannabis Data Science meetup, every Wednesday at 8:30am PST | 10:30am CDT | 11:30am EST. https://www.meetup.com/cannabis-data-science/ 🧑‍💻 Find the data and so...

🚀 We forecast cannabis sales (and plants) in Massachusetts for the remainder of 2021 and for 2022 using Box-Jenkins methodology (ARIMA modelling). We visualize and save the forecasts so that we can compare the forecasts with actual data in the future. 🤝 Join the fun, data wrangling, and analytics in the Cannabis Data Science meetup: https://www.meetup.com/cannabis-data-science/ 🧑‍💻 Find the da...