yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-14 17:13:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #156 from rasbt/improve-bonus-code-ch06

Browse Source 
Improve bonus code in chapter 06
This commit is contained in:
Sebastian Raschka 2024-05-14 19:44:20 -05:00 committed by GitHub
commit e4227c899b
2 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ch06/03_bonus_imdb-classification/README.md
View File

@ -14,7 +14,7 @@ pip install -r requirements-extra.txt
The codes are using the 50k movie reviews from IMDb ([dataset source](https://ai.stanford.edu/~amaas/data/sentiment/)) to predict whether a movie review is positive or negative. The codes are using the 50k movie reviews from IMDb ([dataset source](https://ai.stanford.edu/~amaas/data/sentiment/)) to predict whether a movie review is positive or negative.
Run the following code to create the `train.csv`, `val.csv`, and `test.csv` datasets: Run the following code to create the `train.csv`, `validation.csv`, and `test.csv` datasets:
```bash ```bash
python download-prepare-dataset.py python download-prepare-dataset.py

7
ch06/03_bonus_imdb-classification/download-prepare-dataset.py
View File

@ -19,7 +19,8 @@ def reporthook(count, block_size, total_size):
duration = time.time() - start_time duration = time.time() - start_time
progress_size = int(count * block_size) progress_size = int(count * block_size)
percent = count * block_size * 100 / total_size percent = count * block_size * 100 / total_size
speed = progress_size / (1024**2 * duration)
speed = int(progress_size / (1024 * duration)) if duration else 0
sys.stdout.write( sys.stdout.write(
f"\r{int(percent)}% | {progress_size / (1024**2):.2f} MB " f"\r{int(percent)}% | {progress_size / (1024**2):.2f} MB "
f"| {speed:.2f} MB/s | {duration:.2f} sec elapsed" f"| {speed:.2f} MB/s | {duration:.2f} sec elapsed"
@ -32,6 +33,7 @@ def download_and_extract_dataset(dataset_url, target_file, directory):
if os.path.exists(target_file): if os.path.exists(target_file):
os.remove(target_file) os.remove(target_file)
urllib.request.urlretrieve(dataset_url, target_file, reporthook) urllib.request.urlretrieve(dataset_url, target_file, reporthook)
print("\nExtracting dataset ...")
with tarfile.open(target_file, "r:gz") as tar: with tarfile.open(target_file, "r:gz") as tar:
tar.extractall() tar.extractall()
else: else:
@ -74,6 +76,9 @@ def partition_and_save(df, sizes=(35000, 5000, 10000)):
if __name__ == "__main__": if __name__ == "__main__":
dataset_url = "http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz" dataset_url = "http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz"
print("Downloading dataset ...")
download_and_extract_dataset(dataset_url, "aclImdb_v1.tar.gz", "aclImdb") download_and_extract_dataset(dataset_url, "aclImdb_v1.tar.gz", "aclImdb")
print("Creating data frames ...")
df = load_dataset_to_dataframe() df = load_dataset_to_dataframe()
print("Partitioning and saving data frames ...")
partition_and_save(df) partition_and_save(df)