# application-failure-prediction-part1 — Data

来源：https://www.kaggle.com/competitions/application-failure-prediction-part1/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Training Data

The training data for this assignment can be found in the file `train_data.csv`. This file contains resource consumption metrics of 20,000 jobs run on one of the HPC clusters at Purdue University. A **job** is typically an execution of a scientific application on the HPC cluster, e.g., training your model with one set of parameters can be considered as a **job**.

The training data consists of about 8% failure data (this is referred to as the “positive class”). You will build Machine Learning models in Python to predict whether a job will fail or not, given the resource usage data.

The columns in the data file are:

- **`job_id`**: Unique identifier for a job.
- **`memory_GB`**: Aggregate memory utilization for a job.
- **`network_log10_MBps`**: Aggregate network utilization for a job (in logarithmic scale).
- **`local_IO_log10_MBps`**: Aggregate local disk IO for a job (in logarithmic scale).
- **`NFS_IO_log10_MBps`**: Aggregate remote filesystem (NFS) IO for a job (in logarithmic scale).
- **`failed`**: Failure status of a job. A failed job is marked as `1`.

# Test Data

Test data for this competition may be found in the file `test_data_unlabeled.csv`. This file contains resource usage metrics from 10,000 jobs. The columns in the the test data are identical to the training data except for the column `failed`. Your Machine Learning model should predict the value of this column.

The test data contains about 20% validation data which will be used to determine your ranking in the Public leaderboard. The rest 80% of test data will be used to determine your final score.