AnnsKhan commited on
Commit
26aa82d
·
1 Parent(s): c763060

ignore parquet

Browse files
Files changed (2) hide show
  1. .gitignore +1 -1
  2. app.py +1 -1
.gitignore CHANGED
@@ -32,7 +32,7 @@ data/
32
  # before PyInstaller builds the exe, so as to inject date/other infos into it.
33
  *.manifest
34
  *.spec
35
-
36
  # Installer logs
37
  pip-log.txt
38
  pip-delete-this-directory.txt
 
32
  # before PyInstaller builds the exe, so as to inject date/other infos into it.
33
  *.manifest
34
  *.spec
35
+ *.parquet
36
  # Installer logs
37
  pip-log.txt
38
  pip-delete-this-directory.txt
app.py CHANGED
@@ -25,7 +25,7 @@ from datasets import load_dataset
25
  wandb.login(key=os.getenv("WANDB_API_KEY"))
26
  wandb.init(project="billion-row-analysis", name="benchmarking")
27
  dataset = load_dataset("AnnsKhan/jan_2024_nyc", split="train")
28
- parquet_path = "data/jan_2024.parquet"
29
  if not os.path.exists(parquet_path):
30
  dataset.to_pandas().to_parquet(parquet_path) # Save to disk
31
  os.environ["MODIN_ENGINE"] = "dask"
 
25
  wandb.login(key=os.getenv("WANDB_API_KEY"))
26
  wandb.init(project="billion-row-analysis", name="benchmarking")
27
  dataset = load_dataset("AnnsKhan/jan_2024_nyc", split="train")
28
+ parquet_path = "jan_2024.parquet"
29
  if not os.path.exists(parquet_path):
30
  dataset.to_pandas().to_parquet(parquet_path) # Save to disk
31
  os.environ["MODIN_ENGINE"] = "dask"