Monsoon 2020: Completed #classroom

# DA Project ALOID

Predict the final class of the sample

194
6
1
1

## 🕵️ Introduction

Binary classifiers are amazing but you bring in a third class and they are as good as nothing. We bring to you not 3 but a 100 muticlass problem where you'll `predict the final class` of the sample.

Understand with code! Here is `getting started code` for you.`😄`

## 💾 Dataset

The dataset is based on Multiclass from binary: Expanding one-vs-all, one-vs-one and ECOC-based approaches link to research paper.In this dataset version, the target attribute is fixed and is given as a nominal feature. The dataset was generated for the improvement of multiclass calssifiers, so each data point has some relevant information about the class that you have to predict.

For simplification, attributes have been stored in the CSV file. The `train.csv` has `129` columns, the first column is the `class`label and the rest `128` contain the associated information about the class. There are 100 unique classes which are in the range [0-99].

## 📁 Files

Following files are available in the `resources` section:

• `train.csv` - (`8640` samples) File that should be used for training. It contains the feature representation and their respective outcomes.
• `test.csv` - ( `2160` samples) File that will be used for testing.

## 🚀 Submission

• Prepare a CSV containing header as `class` and values as predicted class(`100 unique values`) .
• Sample submission format is available in the resources section of the challenge page as sample_submission.csv.
Make your first submission here 🚀 !!

## 🖊 Evaluation Criteria

During evaluation F1 score will be used to test the efficiency of the model where,

$F1 = 2 * \frac{precision*recall}{precision+recall}$

• DA TAs

## 📚 References

• IEEE Transactions on Neural Networks and Learning Systems, 25(2):289-302, 2014
• Image Source