Train a Machine Learning model that classifies a given line with accuracy
Budget: €30 – €250 EUR
In this task, you are expected to train a Machine Learning model that classifies a given line as belonging to one of the following 12 novels:
0: alice_in_wonderland
1: dracula
2: dubliners
3: great_expectations
4: hard_times
5: huckleberry_finn
6: les_miserable
7: moby_dick
8: oliver_twist
9: peter_pan
10: tale_of_two_cities
11: tom_sawyer
Description:
You are provided with a zip file containing three text files - xtrain.txt, ytrain.txt, xtest.txt. Each line in xtrain.txt and xtest.txt comes from a different novel. The data has been obfuscated, however, the patterns in them are preserved. The novel ids corresponding to xtrain.txt are specified in ytrain.txt. You can use these labels to train a Machine Learning model (Deep Learning preferred).
With the learned model, predict the novel ids of the lines in xtest.txt (one prediction per line). As part of your submission, include
a) your predictions in a file named ytest.txt (in the same format as ytrain.txt)
b) Expected accuracy on the test set
c) the source code for training and prediction (< 10MB)
d) a brief description of your method (optional)
0: alice_in_wonderland
1: dracula
2: dubliners
3: great_expectations
4: hard_times
5: huckleberry_finn
6: les_miserable
7: moby_dick
8: oliver_twist
9: peter_pan
10: tale_of_two_cities
11: tom_sawyer
Description:
You are provided with a zip file containing three text files - xtrain.txt, ytrain.txt, xtest.txt. Each line in xtrain.txt and xtest.txt comes from a different novel. The data has been obfuscated, however, the patterns in them are preserved. The novel ids corresponding to xtrain.txt are specified in ytrain.txt. You can use these labels to train a Machine Learning model (Deep Learning preferred).
With the learned model, predict the novel ids of the lines in xtest.txt (one prediction per line). As part of your submission, include
a) your predictions in a file named ytest.txt (in the same format as ytrain.txt)
b) Expected accuracy on the test set
c) the source code for training and prediction (< 10MB)
d) a brief description of your method (optional)