Supervised Machine Learning using ScikitLearn Classifiers

Data:

The zip file "MMIS671.hw3.data.zip" contains 3 CSV files: "hw3.train.csv", "hw3.test.csv", and "hw3.new.csv".

The CSV file "hw3.train.csv" contains 50,000 rows and 51 columns. The first column 'y' is the output variable with 3 classes: 0, 1, 2. The remaining 50 columns contain input features: x1, x2, ... , x50.

The CSV file "hw3.test.csv" contains 10,000 rows and 51 columns. The first column 'y' is the output variable with 3 classes: 0, 1, 2. The remaining 50 columns contain input features: x1, x2, ... , x50.

The CSV file "hw3.new.csv" contains 100 rows and 51 columns. The first column 'ID' is an identifier for the 100 unlabeled samples. The remaining 50 columns contain input features: x1, x2, ... , x50.

**Important Note: I have the 3 CSV files and can email them because I don't see an area where I can attach files to the question.**

Task 0.

Read data from the CSV files "hw3.train.csv", "hw3.test.csv", and "hw3.new.csv" into pandas dataframes train, test, and new, respectively. Confirm that the dataframes contain the correct number of rows and columns.

Report the class distribution of 'y' in train and test by specifying the proportion of examples in each class. Round the proportions to 4 decimal places.

Class distribution of y:

\f