This course comprises of 40 case studies that will enrich your learning experience. In addition, we also have 4 Projects that will enhance your implementation skills. Below are few case studies, which are part of this course:
Case Study 1: Maple Leaves Ltd is a start-up company which makes herbs from different types of plants and its leaves. Currently, the system they use to classify the trees which they import in a batch is quite manual. A laborer from his experience decides the leaf type and subtype of plant family. They have asked us to automate this process and remove any manual intervention from this process.
You have to classify the plant leaves by various classifiers from different metrics of the leaves and to choose the best classifier for future reference.
Case Study 2: BookRent is the largest online and offline book rental chain in India. The company charges a fixed fee per month plus rental per book. So, the company makes more money when user rents more books.
You as an ML expert and must model recommendation engine so that user gets a recommendation of books based on the behavior of similar users. This will ensure that users are renting books based on their individual taste.
The company is still unprofitable and is looking to improve both revenue and profit. Compare the Error using two approaches – User Based Vs Item Based
Case Study 3: Handle missing values and fit a decision tree and compare its accuracy with random forest classifier.
Predict the survival of a horse based on various observed medical conditions. Load the data from ‘horses.csv’ and observe whether it contains missing values. Replace the missing values by the most frequent value in each column. Fit a decision tree classifier and observe the accuracy. Fit a random forest classifier and observe the accuracy.
Case Study 4: Principal component analysis using scikit learn.
Load the digits dataset from sklearn and write a helper function to plot the image. Fit a logistic regression model and observe the accuracy.
Using scikit learn perform a PCA transformation such that the transformed dataset can explain 95% of the variance in the original dataset. Compare it with a model and also comment on the accuracy. Compute the confusion matrix and count the number of instances that have gone wrong. For each of the wrong sample, plot the digit along with the predicted and original label.
Case Study 5: Read the datafile “letterCG.data” and set all the numerical attributes as features. Split the data in to train and test sets.
Fit a sequence of AdaBoostClassifier with varying number of weak learners ranging from 1 to 16, keeping the max_depth as 1. Plot the accuracy on the test set against the number of weak learners, using decision tree classifier as the base classifier.