├──data
|    │
|    ├──`{javascript, java, python, ruby, php, go}_licenses.pkl`
|    ├──`{javascript, java, python, ruby, php, go}_dedupe_definitions_v2.pkl`
|    │
|    ├── javascript
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    ├── java
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    ├── python
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    ├── ruby
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    ├── ruby
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    ├── php
|    │   └── final
|    │       └── jsonl
|    │           ├── test
|    │           ├── train
|    │           └── valid
|    └── go
|        └── final
|            └── jsonl
|                ├── test
|                ├── train
|                └── valid
| 
└── saved_models

In [6]: data['pandas-dev/pandas']
Out[6]:
('pandas-dev/pandas/LICENSE',
 'BSD 3-Clause License\n\nCopyright (c) 2008-2012, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development
 Team\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are
 permitted provided that the following conditions are met:\n\n* Redistributions of source code must retain the above
 copyright notice, this\n  list of conditions and the following disclaimer.\n\n* Redistributions in binary form must
 reproduce the above copyright notice,\n  this list of conditions and the following disclaimer in the documentation\n
 and/or other materials provided with the distribution....')