#**Variables:**

##**1. Temperature (Temp):**

- **Description:** Temperature of the gearbox lubricant.
- **Type:** Numeric (float).
- **Units:** Degrees Celsius.

##**2. Viscosity (Visc):**

- **Description:** Viscosity of the lubricant, a measure of its resistance to flow.
- **Type:** Numeric (float).
- **Units:** Centistokes (cSt).

##**3. Pressure (Pres):**

- **Description:** Pressure within the gearbox.
- **Type:** Numeric (float).
- **Units:** Pascals (Pa).

##**4. Metal Particle Content (Metal):**

- **Description:** Concentration of metal particles in the lubricant.
- **Type:** Numeric (float).
- **Units:** Parts per million (ppm).

##**5. Water Content (Water):**

- **Description:** Percentage of water content in the lubricant.
- **Type:** Numeric (float).
- **Units:** Percentage (%).

##**6. Additive Levels (Additive):**

- **Description:** Levels of additives present in the lubricant (e.g., anti-wear additives).
- **Type:** Numeric (float).
- **Units:** Parts per million (ppm).

##**7. pH:**

- **Description:** pH value of the lubricant.
- **Type:** Numeric (float).
- **Units:** pH scale (0-14).

##**8. Density (Dens):**

- **Description:** Density of the lubricant.
- **Type:** Numeric (float).
- **Units:** Grams per cubic centimeter (g/cm³).

##**9. Conductivity (Cond):**

- **Description:** Electrical conductivity of the lubricant.
- **Type:** Numeric (float).
- **Units:** Siemens per meter (S/m).

##**10. Oxidation Index (Oxid):**

- **Description:** Oxidation stability index of the lubricant.
- **Type:**Numeric (float).
- **Units:** Arbitrary units (AU).

#**Target Variable:**

##**Gearbox State (Target):**
**Description:** Binary variable indicating the state of the gearbox.

**Values:**
- 0: Good condition.
- 1: Faulty condition.

#**Dataset Details:**

***Training Data:*** Contains labeled examples of gearbox states based on lubrication data for model training.

***Test Data:*** Unlabeled dataset used for final evaluation, where participants submit predictions for gearbox states.

***Note:*** Ensure that missing values (NaNs) and outliers are properly handled before training your models to ensure robust performance.

##**Files**

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format
*   **metaData.csv** - supplemental information about the data

## Columns

*   `example_id` - definition of example_id
*   `feature_1` - definition of feature_1
*   etc.