# Geology Forecast Challenge — Data

来源：https://www.kaggle.com/competitions/geology-forecast-challenge-open/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset consists of pre-processed and raw data.

## Pre-processed data
Pre-processed data is provided in the competition format described in the subsections. The pre-processed data uses non-overlapping sections of geology. However you can use the raw data and the provided interpolation script to extract more data for training.

### Columns
* Position number (in column names) is "**X**" (vertical section) position in feet relative to the current location of the drill bit.
* Values in cells are **Z**  (oriented up, in feet) coordinates of a layer boundary near a drilled well 

#### Column **geology_id**
Hash-based id of a specific row

#### Columns **-299**..**0**
Inferred (known) geology **Z** (oriented up) coordinate of a layer up to the current drilling location along **X** (vertical section).

The data is normalised so that **Z(0) = 0**. 

Note: not all columns **-299**..**0** are present in all rows. However, we guarantee that the 
values for columns **-49**..**0** are present in all the rows. 
The values will not have gaps starting from the first one in cell **-k** until **0**. 

#### Columns **1**..**300**
Geology to be predicted (realization 0 out of 10). 

In the `train.csv` these columns contains the true geology of layer segments.

#### Columns **r_1_pos_1**..**r_1_pos_300** ... **r_9_pos_1**..**r_9_pos_300**
Geology to be predicted (realizations 1 to 10). 

Note: The order of the realizations **0 to 10** does not change the score. 
This includes realization 0 described above.  

In the `train.csv` these columns contains the true geology of layer segments same as Columns **1**..**300**. 

## Raw data
The raw data is available in the `train_raw` folder.

Each CSV file has two columns: 

`VS_APPROX_adjusted` is the lateral coordinate along the well Vertical Section (VS),

`HORIZON_Z_adjusted` is the depth of the layer at this location.

Both of the variables are in feet and are normalized to start at 0,0



## Interpolation script
The interpolation script is the one used to produce the training data by splitting and interpolating the files in the `train_raw` folder.

It might be useful to modify it to get redundant overlapping data for training.