# AFML Assignment 1 EC Campus — Data

来源：https://www.kaggle.com/competitions/afml-assignment-1-ec-campus/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## File Structure

```
── <TeamID>_<TeamName>/           # Your team-specific folder
    ├── train_part1_clean.csv      # Clean training weights
    ├── train_part1_noise.csv      # Your team's noisy training data
    ├── test_part1.csv             # Your team's noisy test data (TO DENOISE)
    ├── train_part2.csv            # Your team's translation training data
    ├── test_part2.txt             # Your team's translation test phrases
    └── boilerplate.ipynb          # Part 2 starter code
```

**Everything you need is in your team folder!**

### Data Format - Part 1

1. **`train_part1_clean.csv`** - Clean neural network weights for training reference
2. **`train_part1_noise.csv`** - Noisy version of training weights (YOUR specific noise pattern)
3. **`test_part1.csv`** - Noisy test weights that YOU need to denoise

Each CSV file contains:
- A very large number of numerical values
- These represent flattened and reshaped weights from a pretrained neural network
- All values are floating-point numbers representing model parameters

**Important:** Each team has a DIFFERENT noise pattern applied to their data. Do not share or use data from other teams' folders!

### Data format - Part 2
**Common Files (available to all teams):**
1. **`boilerplate.ipynb`** - Jupyter Notebook with starter code (see below)

**Team-Specific Files (in your `<TeamID>_<TeamName>/` folder):**
1. **`train_part2.csv`** - YOUR team's parallel corpus containing:
   - `encoded_text`: Text in the mystery encoded language
   - `text`: Corresponding English translations
   
2. **`test_part2.csv`** - YOUR team's specific encoded phrases to translate
   - These phrases are unique to your team
   - Will include team member names and email addresses

3. **`<TeamID>_denoised_test_part1.csv`** (YOUR output from Part 1) - Contains the denoised weights of the pretrained LSTM model