|
import os |
|
import pandas as pd |
|
import sklearn.datasets as skd |
|
from pathlib import Path |
|
|
|
def sklearnDatasets(url,query): |
|
try: |
|
current_directory = os.getcwd() |
|
downloads_folder = os.path.join(current_directory, query) |
|
print(f"{url} started downloading") |
|
os.makedirs(downloads_folder, exist_ok=True) |
|
|
|
dataset_func = getattr(skd, url, None) |
|
|
|
if dataset_func: |
|
dataset = dataset_func(data_home=downloads_folder) |
|
|
|
X, y = dataset.data, dataset.target |
|
|
|
df = pd.DataFrame(X, columns=dataset.feature_names) |
|
df['Target'] = y |
|
|
|
csv_file_path = os.path.join(downloads_folder, f"{url}.csv") |
|
df.to_csv(csv_file_path, index=False) |
|
|
|
|
|
else: |
|
print(f"Unknown dataset function: {url}. Please check the URL.") |
|
except Exception as e: |
|
print(f"Dataset Not found") |
|
|
|
|
|
|
|
|
