##The Task

Train a ML model to classify the faults, if any, in the drivetrain of a WT given the data in the companion file.

##The train dataset

The train dataset has recorded 20 seconds of an experiment where 7 different faults were induced in a wind turbine model, at a sampling frequency of 100KHz, thus the dataset has stored a total of 2 000 000 points for each fault.  

The train dataset is organized by fault types, 2000 samples for each of 7 common faults, a total of 14000 samples. Each sample has 3 x 1000 points, the information of each of the 3 channels of a 3-D accelerometer. 
This dataset is divided in 2 arrays: X and y, where X is the sample data and y the label.
The fault samples are ordered in the dataset as follows:   

0000..1999: no fault   
2000..3999: fault type 1   
...   
12000..13999: fault type 6   

The train dataset is in HDF5 format stored in a ‘.mat’ Matlab file:

train.mat

##The test dataset

After training, the model should be evaluated on the test dataset has 420 samples, with 3 x 100000 points each, the information of each of the 3 channels of a 3-D accelerometer, thus for each of the 7 different faults there are 60 samples.

The evaluation dataset is shuffled and stores only the array X with the sample data.
There is no information on the labels.

The goal is to predict to correct label for each sample.