Build a classification model: Delicious +Asian and Indian Cuisines
+ +Cuisine classifiers 1
+In this lesson, we’ll explore a variety of classifiers to predict +a given national cuisine based on a group of ingredients. While +doing so, we’ll learn more about some of the ways that algorithms can be +leveraged for classification tasks.
+ +Preparation
+This lesson builds up on our previous +lesson where we:
+-
+
Made a gentle introduction to classifications using a dataset +about all the brilliant cuisines of Asia and India 😋.
+Explored some dplyr +verbs to prep and clean our data.
+Made beautiful visualizations using ggplot2.
+Demonstrated how to deal with imbalanced data by preprocessing it +using recipes.
+Demonstrated how to
prepandbakeour +recipe to confirm that it will work as supposed to.
+
Prerequisite
+For this lesson, we’ll require the following packages to clean, prep +and visualize our data:
+-
+
tidyverse: The tidyverse is a collection of R packages +designed to makes data science faster, easier and more fun!
+tidymodels: The tidymodels framework is a collection of packages +for modeling and machine learning.
+DataExplorer: The DataExplorer +package is meant to simplify and automate EDA process and report +generation.
+themis: The themis package provides Extra +Recipes Steps for Dealing with Unbalanced Data.
+nnet: The nnet +package provides functions for estimating feed-forward neural +networks with a single hidden layer, and for multinomial logistic +regression models.
+
You can have them installed as:
+install.packages(c("tidyverse", "tidymodels", "DataExplorer", "here"))
Alternatively, the script below checks whether you have the packages +required to complete this module and installs them for you in case they +are missing.
+suppressWarnings(if (!require("pacman"))install.packages("pacman"))
+
+pacman::p_load(tidyverse, tidymodels, DataExplorer, themis, here)Now, let’s hit the ground running!
+1. Split the data into training and test sets.
+We’ll start by picking a few steps from our previous lesson.
+Drop the most common ingredients that create confusion between
+distinct cuisines, using dplyr::select().
+Everyone loves rice, garlic and ginger!
+# Load the original cuisines data
+df <- read_csv(file = "https://raw.githubusercontent.com/microsoft/ML-For-Beginners/main/4-Classification/data/cuisines.csv")## New names:
+## Rows: 2448 Columns: 385
+## ── Column specification
+## ──────────────────────────────────────────────────────── Delimiter: "," chr
+## (1): cuisine dbl (384): ...1, almond, angelica, anise, anise_seed, apple,
+## apple_brandy, a...
+## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
+## Specify the column types or set `show_col_types = FALSE` to quiet this message.
+## • `` -> `...1`# Drop id column, rice, garlic and ginger from our original data set
+df_select <- df %>%
+ select(-c(1, rice, garlic, ginger)) %>%
+ # Encode cuisine column as categorical
+ mutate(cuisine = factor(cuisine))
+
+# Display new data set
+df_select %>%
+ slice_head(n = 5)Perfect! Now, time to split the data such that 70% of the data goes
+to training and 30% goes to testing. We’ll also apply a
+stratification technique when splitting the data to
+maintain the proportion of each cuisine in the training and
+validation datasets.
rsample, a package in +Tidymodels, provides infrastructure for efficient data splitting and +resampling:
+# Load the core Tidymodels packages into R session
+library(tidymodels)
+
+# Create split specification
+set.seed(2056)
+cuisines_split <- initial_split(data = df_select,
+ strata = cuisine,
+ prop = 0.7)
+
+# Extract the data in each split
+cuisines_train <- training(cuisines_split)
+cuisines_test <- testing(cuisines_split)
+
+# Print the number of cases in each split
+cat("Training cases: ", nrow(cuisines_train), "\n",
+ "Test cases: ", nrow(cuisines_test), sep = "")## Training cases: 1712
+## Test cases: 736# Display distribution of cuisines in the training set
+cuisines_train %>%
+ count(cuisine) %>%
+ arrange(desc(n))2. Deal with imbalanced data
+As you might have noticed in the original data set as well as in our +training set, there is quite an unequal distribution in the number of +cuisines. Korean cuisines are almost 3 times Thai cuisines. +Imbalanced data often has negative effects on the model performance. +Many models perform best when the number of observations is equal and, +thus, tend to struggle with unbalanced data.
+There are majorly two ways of dealing with imbalanced data sets:
+-
+
adding observations to the minority class: +
Over-samplinge.g using a SMOTE algorithm which +synthetically generates new examples of the minority class using nearest +neighbors of these cases.
+removing observations from majority class: +
Under-sampling
+
In our previous lesson, we demonstrated how to deal with imbalanced
+data sets using a recipe. A recipe can be thought of as a
+blueprint that describes what steps should be applied to a data set in
+order to get it ready for data analysis. In our case, we want to have an
+equal distribution in the number of our cuisines for our
+training set. Let’s get right into it.
# Load themis package for dealing with imbalanced data
+library(themis)
+
+# Create a recipe for preprocessing training data
+cuisines_recipe <- recipe(cuisine ~ ., data = cuisines_train) %>%
+ step_smote(cuisine)
+
+# Print recipe
+cuisines_recipe## ## ── Recipe ──────────────────────────────────────────────────────────────────────## ## ── Inputs## Number of variables by role## outcome: 1
+## predictor: 380## ## ── Operations## • SMOTE based on: cuisineYou can of course go ahead and confirm (using prep+bake) that the
+recipe will work as you expect it - all the cuisine labels having
+559 observations.
Since we’ll be using this recipe as a preprocessor for modeling, a
+workflow() will do all the prep and bake for us, so we
+won’t have to manually estimate the recipe.
Now we are ready to train a model 👩💻👨💻!
+3. Choosing your classifier
+
+Now we have to decide which algorithm to use for the job 🤔.
+In Tidymodels, the parsnip package
+provides consistent interface for working with models across different
+engines (packages). Please see the parsnip documentation to explore model types &
+engines and their corresponding model
+arguments. The variety is quite bewildering at first sight. For
+instance, the following methods all include classification
+techniques:
-
+
C5.0 Rule-Based Classification Models
+Flexible Discriminant Models
+Linear Discriminant Models
+Regularized Discriminant Models
+Logistic Regression Models
+Multinomial Regression Models
+Naive Bayes Models
+Support Vector Machines
+Nearest Neighbors
+Decision Trees
+Ensemble methods
+Neural Networks
+
The list goes on!
+What classifier to go with?
+So, which classifier should you choose? Often, running through +several and looking for a good result is a way to test.
+++AutoML solves this problem neatly by running these comparisons in the +cloud, allowing you to choose the best algorithm for your data. Try it +here
+
Also the choice of classifier depends on our problem. For instance,
+when the outcome can be categorized into
+more than two classes, like in our case, you must use a
+multiclass classification algorithm as opposed to
+binary classification.
A better approach
+A better way than wildly guessing, however, is to follow the ideas on +this downloadable ML +Cheat sheet. Here, we discover that, for our multiclass problem, we +have some choices:
+
+Reasoning
+Let’s see if we can reason our way through different approaches given +the constraints we have:
+-
+
Deep Neural networks are too heavy. Given our +clean, but minimal dataset, and the fact that we are running training +locally via notebooks, deep neural networks are too heavyweight for this +task.
+No two-class classifier. We do not use a +two-class classifier, so that rules out one-vs-all.
+Decision tree or logistic regression could work. +A decision tree might work, or multinomial regression/multiclass +logistic regression for multiclass data.
+Multiclass Boosted Decision Trees solve a different +problem. The multiclass boosted decision tree is most suitable +for nonparametric tasks, e.g. tasks designed to build rankings, so it is +not useful for us.
+
Also, normally before embarking on more complex machine learning
+models e.g ensemble methods, it’s a good idea to build the simplest
+possible model to get an idea of what is going on. So for this lesson,
+we’ll start with a multinomial logistic regression
+model.
++Logistic regression is a technique used when the outcome variable is +categorical (or nominal). For Binary logistic regression the number of +outcome variables is two, whereas the number of outcome variables for +multinomial logistic regression is more than two. See Advanced +Regression Methods for further reading.
+
4. Train and evaluate a Multinomial logistic regression model.
+In Tidymodels, parsnip::multinom_reg(), defines a model
+that uses linear predictors to predict multiclass data using the
+multinomial distribution. See ?multinom_reg() for the
+different ways/engines you can use to fit this model.
For this example, we’ll fit a Multinomial regression model via the +default nnet +engine.
+++I picked a value for
+penaltysort of randomly. There are +better ways to choose this value that is, by using +resamplingandtuningthe model which we’ll +discuss later.See Tidymodels: +Get Started in case you want to learn more on how to tune model +hyperparameters.
+
# Create a multinomial regression model specification
+mr_spec <- multinom_reg(penalty = 1) %>%
+ set_engine("nnet", MaxNWts = 2086) %>%
+ set_mode("classification")
+
+# Print model specification
+mr_spec## Multinomial Regression Model Specification (classification)
+##
+## Main Arguments:
+## penalty = 1
+##
+## Engine-Specific Arguments:
+## MaxNWts = 2086
+##
+## Computational engine: nnetGreat job 🥳! Now that we have a recipe and a model specification, we
+need to find a way of bundling them together into an object that will
+first preprocess the data then fit the model on the preprocessed data
+and also allow for potential post-processing activities. In Tidymodels,
+this convenient object is called a workflow and
+conveniently holds your modeling components! This is what we’d call
+pipelines in Python.
So let’s bundle everything up into a workflow!📦
+# Bundle recipe and model specification
+mr_wf <- workflow() %>%
+ add_recipe(cuisines_recipe) %>%
+ add_model(mr_spec)
+
+# Print out workflow
+mr_wf## ══ Workflow ════════════════════════════════════════════════════════════════════
+## Preprocessor: Recipe
+## Model: multinom_reg()
+##
+## ── Preprocessor ────────────────────────────────────────────────────────────────
+## 1 Recipe Step
+##
+## • step_smote()
+##
+## ── Model ───────────────────────────────────────────────────────────────────────
+## Multinomial Regression Model Specification (classification)
+##
+## Main Arguments:
+## penalty = 1
+##
+## Engine-Specific Arguments:
+## MaxNWts = 2086
+##
+## Computational engine: nnetWorkflows 👌👌! A workflow() can be fit
+in much the same way a model can. So, time to train a model!
# Train a multinomial regression model
+mr_fit <- fit(object = mr_wf, data = cuisines_train)
+
+mr_fit## ══ Workflow [trained] ══════════════════════════════════════════════════════════
+## Preprocessor: Recipe
+## Model: multinom_reg()
+##
+## ── Preprocessor ────────────────────────────────────────────────────────────────
+## 1 Recipe Step
+##
+## • step_smote()
+##
+## ── Model ───────────────────────────────────────────────────────────────────────
+## Call:
+## nnet::multinom(formula = ..y ~ ., data = data, decay = ~1, MaxNWts = ~2086,
+## trace = FALSE)
+##
+## Coefficients:
+## (Intercept) almond angelica anise anise_seed apple
+## indian 0.19723325 0.2409661 0 -5.004955e-05 -0.1657635 -0.05769734
+## japanese 0.13961959 -0.6262400 0 -1.169155e-04 -0.4893596 -0.08585717
+## korean 0.22377347 -0.1833485 0 -5.560395e-05 -0.2489401 -0.15657804
+## thai -0.04336577 -0.6106258 0 4.903828e-04 -0.5782866 0.63451105
+## apple_brandy apricot armagnac artemisia artichoke asparagus
+## indian 0 0.37042636 0 -0.09122797 0 -0.27181970
+## japanese 0 0.28895643 0 -0.12651100 0 0.14054037
+## korean 0 -0.07981259 0 0.55756709 0 -0.66979948
+## thai 0 -0.33160904 0 -0.10725182 0 -0.02602152
+## avocado bacon baked_potato balm banana barley
+## indian -0.46624197 0.16008055 0 0 -0.2838796 0.2230625
+## japanese 0.90341344 0.02932727 0 0 -0.4142787 2.0953906
+## korean -0.06925382 -0.35804134 0 0 -0.2686963 -0.7233404
+## thai -0.21473955 -0.75594439 0 0 0.6784880 -0.4363320
+## bartlett_pear basil bay bean beech
+## indian 0 -0.7128756 0.1011587 -0.8777275 -0.0004380795
+## japanese 0 0.1288697 0.9425626 -0.2380748 0.3373437611
+## korean 0 -0.2445193 -0.4744318 -0.8957870 -0.0048784496
+## thai 0 1.5365848 0.1333256 0.2196970 -0.0113078024
+## beef beef_broth beef_liver beer beet
+## indian -0.7985278 0.2430186 -0.035598065 -0.002173738 0.01005813
+## japanese 0.2241875 -0.3653020 -0.139551027 0.128905553 0.04923911
+## korean 0.5366515 -0.6153237 0.213455197 -0.010828645 0.27325423
+## thai 0.1570012 -0.9364154 -0.008032213 -0.035063746 -0.28279823
+## bell_pepper bergamot berry bitter_orange black_bean
+## indian 0.49074330 0 0.58947607 0.191256164 -0.1945233
+## japanese 0.09074167 0 -0.25917977 -0.118915977 -0.3442400
+## korean -0.57876763 0 -0.07874180 -0.007729435 -0.5220672
+## thai 0.92554006 0 -0.07210196 -0.002983296 -0.4614426
+## black_currant black_mustard_seed_oil black_pepper black_raspberry
+## indian 0 0.38935801 -0.4453495 0
+## japanese 0 -0.05452887 -0.5440869 0
+## korean 0 -0.03929970 0.8025454 0
+## thai 0 -0.21498372 -0.9854806 0
+## black_sesame_seed black_tea blackberry blackberry_brandy
+## indian -0.2759246 0.3079977 0.191256164 0
+## japanese -0.6101687 -0.1671913 -0.118915977 0
+## korean 1.5197674 -0.3036261 -0.007729435 0
+## thai -0.1755656 -0.1487033 -0.002983296 0
+## blue_cheese blueberry bone_oil bourbon_whiskey brandy
+## indian 0 0.216164294 -0.2276744 0 0.22427587
+## japanese 0 -0.119186087 0.3913019 0 -0.15595599
+## korean 0 -0.007821986 0.2854487 0 -0.02562342
+## thai 0 -0.004947048 -0.0253658 0 -0.05715244
+##
+## ...
+## and 308 more lines.The output shows the coefficients that the model learned during +training.
+Evaluate the Trained Model
+It’s time to see how the model performed 📏 by evaluating it on a +test set! Let’s begin by making predictions on the test set.
+# Make predictions on the test set
+results <- cuisines_test %>% select(cuisine) %>%
+ bind_cols(mr_fit %>% predict(new_data = cuisines_test))
+
+# Print out results
+results %>%
+ slice_head(n = 5)Great job! In Tidymodels, evaluating model performance can be done +using yardstick - a +package used to measure the effectiveness of models using performance +metrics. As we did in our logistic regression lesson, let’s begin by +computing a confusion matrix.
+# Confusion matrix for categorical data
+conf_mat(data = results, truth = cuisine, estimate = .pred_class)## Truth
+## Prediction chinese indian japanese korean thai
+## chinese 83 1 8 15 10
+## indian 4 163 1 2 6
+## japanese 21 5 73 25 1
+## korean 15 0 11 191 0
+## thai 10 11 3 7 70When dealing with multiple classes, it’s generally more intuitive to +visualize this as a heat map, like this:
+update_geom_defaults(geom = "tile", new = list(color = "black", alpha = 0.7))
+# Visualize confusion matrix
+results %>%
+ conf_mat(cuisine, .pred_class) %>%
+ autoplot(type = "heatmap")
The darker squares in the confusion matrix plot indicate high numbers +of cases, and you can hopefully see a diagonal line of darker squares +indicating cases where the predicted and actual label are the same.
+Let’s now calculate summary statistics for the confusion matrix.
+# Summary stats for confusion matrix
+conf_mat(data = results, truth = cuisine, estimate = .pred_class) %>% summary()If we narrow down to some metrics such as accuracy, sensitivity, ppv, +we are not badly off for a start 🥳!
+4. Digging Deeper
+Let’s ask one subtle question: What criteria is used to settle for a +given type of cuisine as the predicted outcome?
+Well, Statistical machine learning algorithms, like logistic
+regression, are based on probability; so what actually gets
+predicted by a classifier is a probability distribution over a set of
+possible outcomes. The class with the highest probability is then chosen
+as the most likely outcome for the given observations.
Let’s see this in action by making both hard class predictions and +probabilities.
+# Make hard class prediction and probabilities
+results_prob <- cuisines_test %>%
+ select(cuisine) %>%
+ bind_cols(mr_fit %>% predict(new_data = cuisines_test)) %>%
+ bind_cols(mr_fit %>% predict(new_data = cuisines_test, type = "prob"))
+
+# Print out results
+results_prob %>%
+ slice_head(n = 5)Much better!
+✅ Can you explain why the model is pretty sure that the first +observation is Thai?
+🚀Challenge
+In this lesson, you used your cleaned data to build a machine +learning model that can predict a national cuisine based on a series of +ingredients. Take some time to read through the many options +Tidymodels provides to classify data and other +ways to fit multinomial regression.
+THANK YOU TO:
+Allison Horst
+for creating the amazing illustrations that make R more welcoming and
+engaging. Find more illustrations at her gallery.
Cassie Breviu and Jen Looper for creating the +original Python version of this module ♥️
+Happy Learning,
+Eric, Gold Microsoft Learn +Student Ambassador.
+
+
+
+
+
+
+
+
+
Here γ is the so-called **discount factor** that determines to which extent you should prefer the current reward over the future reward and vice versa.
@@ -316,4 +316,5 @@ Overall, it is important to remember that the success and quality of the learnin
## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/46/)
-## Assignment [A More Realistic World](assignment.md)
+## Assignment
+[A More Realistic World](assignment.md)
diff --git a/8-Reinforcement/1-QLearning/images/bellman-equation.png b/8-Reinforcement/1-QLearning/images/bellman-equation.png
new file mode 100644
index 000000000..60ff3c97b
Binary files /dev/null and b/8-Reinforcement/1-QLearning/images/bellman-equation.png differ
diff --git a/8-Reinforcement/2-Gym/README.md b/8-Reinforcement/2-Gym/README.md
index de3eac373..b5e4237a6 100644
--- a/8-Reinforcement/2-Gym/README.md
+++ b/8-Reinforcement/2-Gym/README.md
@@ -1,7 +1,7 @@
# CartPole Skating
The problem we have been solving in the previous lesson might seem like a toy problem, not really applicable for real life scenarios. This is not the case, because many real world problems also share this scenario - including playing Chess or Go. They are similar, because we also have a board with given rules and a **discrete state**.
-https://white-water-09ec41f0f.azurestaticapps.net/
+
## [Pre-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/47/)
## Introduction
@@ -331,10 +331,11 @@ You should see something like this:
## [Post-lecture quiz](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/48/)
-## Assignment: [Train a Mountain Car](assignment.md)
+## Assignment
+[Train a Mountain Car](assignment.md)
## Conclusion
We have now learned how to train agents to achieve good results just by providing them a reward function that defines the desired state of the game, and by giving them an opportunity to intelligently explore the search space. We have successfully applied the Q-Learning algorithm in the cases of discrete and continuous environments, but with discrete actions.
-It's important to also study situations where action state is also continuous, and when observation space is much more complex, such as the image from the Atari game screen. In those problems we often need to use more powerful machine learning techniques, such as neural networks, in order to achieve good results. Those more advanced topics are the subject of our forthcoming more advanced AI course.
\ No newline at end of file
+It's important to also study situations where action state is also continuous, and when observation space is much more complex, such as the image from the Atari game screen. In those problems we often need to use more powerful machine learning techniques, such as neural networks, in order to achieve good results. Those more advanced topics are the subject of our forthcoming more advanced AI course.
diff --git a/9-Real-World/1-Applications/README.md b/9-Real-World/1-Applications/README.md
index 3cf3e16d2..36643172c 100644
--- a/9-Real-World/1-Applications/README.md
+++ b/9-Real-World/1-Applications/README.md
@@ -19,16 +19,14 @@ The finance sector offers many opportunities for machine learning. Many problems
We learned about [k-means clustering](../../5-Clustering/2-K-Means/README.md) earlier in the course, but how can it be used to solve problems related to credit card fraud?
K-means clustering comes in handy during a credit card fraud detection technique called **outlier detection**. Outliers, or deviations in observations about a set of data, can tell us if a credit card is being used in a normal capacity or if something unusual is going on. As shown in the paper linked below, you can sort credit card data using a k-means clustering algorithm and assign each transaction to a cluster based on how much of an outlier it appears to be. Then, you can evaluate the riskiest clusters for fraudulent versus legitimate transactions.
-
-https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.680.1195&rep=rep1&type=pdf
+[Reference](https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.680.1195&rep=rep1&type=pdf)
### Wealth management
In wealth management, an individual or firm handles investments on behalf of their clients. Their job is to sustain and grow wealth in the long-term, so it is essential to choose investments that perform well.
One way to evaluate how a particular investment performs is through statistical regression. [Linear regression](../../2-Regression/1-Tools/README.md) is a valuable tool for understanding how a fund performs relative to some benchmark. We can also deduce whether or not the results of the regression are statistically significant, or how much they would affect a client's investments. You could even further expand your analysis using multiple regression, where additional risk factors can be taken into account. For an example of how this would work for a specific fund, check out the paper below on evaluating fund performance using regression.
-
-http://www.brightwoodventures.com/evaluating-fund-performance-using-regression/
+[Reference](http://www.brightwoodventures.com/evaluating-fund-performance-using-regression/)
## 🎓 Education
@@ -37,14 +35,12 @@ The educational sector is also a very interesting area where ML can be applied.
### Predicting student behavior
[Coursera](https://coursera.com), an online open course provider, has a great tech blog where they discuss many engineering decisions. In this case study, they plotted a regression line to try to explore any correlation between a low NPS (Net Promoter Score) rating and course retention or drop-off.
-
-https://medium.com/coursera-engineering/controlled-regression-quantifying-the-impact-of-course-quality-on-learner-retention-31f956bd592a
+[Reference](https://medium.com/coursera-engineering/controlled-regression-quantifying-the-impact-of-course-quality-on-learner-retention-31f956bd592a)
### Mitigating bias
[Grammarly](https://grammarly.com), a writing assistant that checks for spelling and grammar errors, uses sophisticated [natural language processing systems](../../6-NLP/README.md) throughout its products. They published an interesting case study in their tech blog about how they dealt with gender bias in machine learning, which you learned about in our [introductory fairness lesson](../../1-Introduction/3-fairness/README.md).
-
-https://www.grammarly.com/blog/engineering/mitigating-gender-bias-in-autocorrect/
+[Reference](https://www.grammarly.com/blog/engineering/mitigating-gender-bias-in-autocorrect/)
## 👜 Retail
@@ -53,14 +49,12 @@ The retail sector can definitely benefit from the use of ML, with everything fro
### Personalizing the customer journey
At Wayfair, a company that sells home goods like furniture, helping customers find the right products for their taste and needs is paramount. In this article, engineers from the company describe how they use ML and NLP to "surface the right results for customers". Notably, their Query Intent Engine has been built to use entity extraction, classifier training, asset and opinion extraction, and sentiment tagging on customer reviews. This is a classic use case of how NLP works in online retail.
-
-https://www.aboutwayfair.com/tech-innovation/how-we-use-machine-learning-and-natural-language-processing-to-empower-search
+[Reference](https://www.aboutwayfair.com/tech-innovation/how-we-use-machine-learning-and-natural-language-processing-to-empower-search)
### Inventory management
Innovative, nimble companies like [StitchFix](https://stitchfix.com), a box service that ships clothing to consumers, rely heavily on ML for recommendations and inventory management. Their styling teams work together with their merchandising teams, in fact: "one of our data scientists tinkered with a genetic algorithm and applied it to apparel to predict what would be a successful piece of clothing that doesn't exist today. We brought that to the merchandise team and now they can use that as a tool."
-
-https://www.zdnet.com/article/how-stitch-fix-uses-machine-learning-to-master-the-science-of-styling/
+[Reference](https://www.zdnet.com/article/how-stitch-fix-uses-machine-learning-to-master-the-science-of-styling/)
## 🏥 Health Care
@@ -69,20 +63,17 @@ The health care sector can leverage ML to optimize research tasks and also logis
### Managing clinical trials
Toxicity in clinical trials is a major concern to drug makers. How much toxicity is tolerable? In this study, analyzing various clinical trial methods led to the development of a new approach for predicting the odds of clinical trial outcomes. Specifically, they were able to use random forest to produce a [classifier](../../4-Classification/README.md) that is able to distinguish between groups of drugs.
-
-https://www.sciencedirect.com/science/article/pii/S2451945616302914
+[Reference](https://www.sciencedirect.com/science/article/pii/S2451945616302914)
### Hospital readmission management
Hospital care is costly, especially when patients have to be readmitted. This paper discusses a company that uses ML to predict readmission potential using [clustering](../../5-Clustering/README.md) algorithms. These clusters help analysts to "discover groups of readmissions that may share a common cause".
-
-https://healthmanagement.org/c/healthmanagement/issuearticle/hospital-readmissions-and-machine-learning
+[Reference](https://healthmanagement.org/c/healthmanagement/issuearticle/hospital-readmissions-and-machine-learning)
### Disease management
The recent pandemic has shone a bright light on the ways that machine learning can aid in stopping the spread of disease. In this article, you'll recognize the use of ARIMA, logistic curves, linear regression, and SARIMA. "This work is an attempt to calculate the rate of spread of this virus and thus to predict the deaths, recoveries, and confirmed cases, so that it may help us to prepare better and survive."
-
-https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7979218/
+[Reference](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7979218/)
## 🌲 Ecology and Green Tech
@@ -93,22 +84,19 @@ Nature and ecology consists of many sensitive systems where the interplay betwee
You learned about [Reinforcement Learning](../../8-Reinforcement/README.md) in previous lessons. It can be very useful when trying to predict patterns in nature. In particular, it can be used to track ecological problems like forest fires and the spread of invasive species. In Canada, a group of researchers used Reinforcement Learning to build forest wildfire dynamics models from satellite images. Using an innovative "spatially spreading process (SSP)", they envisioned a forest fire as "the agent at any cell in the landscape." "The set of actions the fire can take from a location at any point in time includes spreading north, south, east, or west or not spreading.
This approach inverts the usual RL setup since the dynamics of the corresponding Markov Decision Process (MDP) is a known function for immediate wildfire spread." Read more about the classic algorithms used by this group at the link below.
-
-https://www.frontiersin.org/articles/10.3389/fict.2018.00006/full
+[Reference](https://www.frontiersin.org/articles/10.3389/fict.2018.00006/full)
### Motion sensing of animals
While deep learning has created a revolution in visually tracking animal movements (you can build your own [polar bear tracker](https://docs.microsoft.com/learn/modules/build-ml-model-with-azure-stream-analytics/?WT.mc_id=academic-77952-leestott) here), classic ML still has a place in this task.
Sensors to track movements of farm animals and IoT make use of this type of visual processing, but more basic ML techniques are useful to preprocess data. For example, in this paper, sheep postures were monitored and analyzed using various classifier algorithms. You might recognize the ROC curve on page 335.
-
-https://druckhaus-hofmann.de/gallery/31-wj-feb-2020.pdf
+[Reference](https://druckhaus-hofmann.de/gallery/31-wj-feb-2020.pdf)
### ⚡️ Energy Management
In our lessons on [time series forecasting](../../7-TimeSeries/README.md), we invoked the concept of smart parking meters to generate revenue for a town based on understanding supply and demand. This article discusses in detail how clustering, regression and time series forecasting combined to help predict future energy use in Ireland, based off of smart metering.
-
-https://www-cdn.knime.com/sites/default/files/inline-images/knime_bigdata_energy_timeseries_whitepaper.pdf
+[Reference](https://www-cdn.knime.com/sites/default/files/inline-images/knime_bigdata_energy_timeseries_whitepaper.pdf)
## 💼 Insurance
@@ -117,8 +105,7 @@ The insurance sector is another sector that uses ML to construct and optimize vi
### Volatility Management
MetLife, a life insurance provider, is forthcoming with the way they analyze and mitigate volatility in their financial models. In this article you'll notice binary and ordinal classification visualizations. You'll also discover forecasting visualizations.
-
-https://investments.metlife.com/content/dam/metlifecom/us/investments/insights/research-topics/macro-strategy/pdf/MetLifeInvestmentManagement_MachineLearnedRanking_070920.pdf
+[Reference](https://investments.metlife.com/content/dam/metlifecom/us/investments/insights/research-topics/macro-strategy/pdf/MetLifeInvestmentManagement_MachineLearnedRanking_070920.pdf)
## 🎨 Arts, Culture, and Literature
@@ -127,8 +114,7 @@ In the arts, for example in journalism, there are many interesting problems. Det
### Fake news detection
Detecting fake news has become a game of cat and mouse in today's media. In this article, researchers suggest that a system combining several of the ML techniques we have studied can be tested and the best model deployed: "This system is based on natural language processing to extract features from the data and then these features are used for the training of machine learning classifiers such as Naive Bayes, Support Vector Machine (SVM), Random Forest (RF), Stochastic Gradient Descent (SGD), and Logistic Regression(LR)."
-
-https://www.irjet.net/archives/V7/i6/IRJET-V7I6688.pdf
+[Reference](https://www.irjet.net/archives/V7/i6/IRJET-V7I6688.pdf)
This article shows how combining different ML domains can produce interesting results that can help stop fake news from spreading and creating real damage; in this case, the impetus was the spread of rumors about COVID treatments that incited mob violence.
@@ -137,16 +123,14 @@ This article shows how combining different ML domains can produce interesting re
Museums are at the cusp of an AI revolution in which cataloging and digitizing collections and finding links between artifacts is becoming easier as technology advances. Projects such as [In Codice Ratio](https://www.sciencedirect.com/science/article/abs/pii/S0306457321001035#:~:text=1.,studies%20over%20large%20historical%20sources.) are helping unlock the mysteries of inaccessible collections such as the Vatican Archives. But, the business aspect of museums benefits from ML models as well.
For example, the Art Institute of Chicago built models to predict what audiences are interested in and when they will attend expositions. The goal is to create individualized and optimized visitor experiences each time the user visits the museum. "During fiscal 2017, the model predicted attendance and admissions within 1 percent of accuracy, says Andrew Simnick, senior vice president at the Art Institute."
-
-https://www.chicagobusiness.com/article/20180518/ISSUE01/180519840/art-institute-of-chicago-uses-data-to-make-exhibit-choices
+[Reference](https://www.chicagobusiness.com/article/20180518/ISSUE01/180519840/art-institute-of-chicago-uses-data-to-make-exhibit-choices)
## 🏷 Marketing
### Customer segmentation
The most effective marketing strategies target customers in different ways based on various groupings. In this article, the uses of Clustering algorithms are discussed to support differentiated marketing. Differentiated marketing helps companies improve brand recognition, reach more customers, and make more money.
-
-https://ai.inqline.com/machine-learning-for-marketing-customer-segmentation/
+[Reference](https://ai.inqline.com/machine-learning-for-marketing-customer-segmentation/)
## 🚀 Challenge
diff --git a/README.md b/README.md
index 1a40ccbd4..4cc946f7b 100644
--- a/README.md
+++ b/README.md
@@ -100,11 +100,11 @@ By ensuring that the content aligns with projects, the process is made more enga
| 08 | North American pumpkin prices 🎃 | [Regression](2-Regression/README.md) | Build a logistic regression model |