ium_z487177/skryptdocker

76 lines
3.2 KiB
Plaintext
Raw Normal View History

import subprocess
import zipfile
import os
import pandas as pd
import re
from sklearn.model_selection import train_test_split
# Skrypt 1 funkcje
def download_kaggle_dataset(dataset_id, destination_folder):
try:
result = subprocess.run(["kaggle", "datasets", "download", "-d", dataset_id, "-p", destination_folder], check=True, capture_output=True, text=True)
zip_filename = re.search(r"(\S+\.zip)", result.stdout).group(1)
print(f"Dataset {dataset_id} successfully downloaded.")
return os.path.join(destination_folder, zip_filename)
except subprocess.CalledProcessError as e:
print(f"Error downloading dataset {dataset_id}: {e}")
return None
def unzip_file(zip_filepath, destination_folder):
try:
with zipfile.ZipFile(zip_filepath, 'r') as zip_ref:
zip_ref.extractall(destination_folder)
print(f"Files extracted to {destination_folder}.")
except Exception as e:
print(f"Error unzipping file {zip_filepath}: {e}")
def combine_csv_files(train_file, test_file, output_file):
try:
train_df = pd.read_csv(train_file)
test_df = pd.read_csv(test_file)
combined_df = pd.concat([train_df, test_df], ignore_index=True)
combined_df.to_csv(output_file, index=False)
print(f"Combined CSV files saved to {output_file}.")
except Exception as e:
print(f"Error combining CSV files: {e}")
# Skrypt 2 funkcje
def split_data(data, train_ratio, dev_ratio, random_seed=42):
train_data, temp_data = train_test_split(data, train_size=train_ratio, random_state=random_seed)
dev_data, test_data = train_test_split(temp_data, train_size=dev_ratio / (1 - train_ratio), random_state=random_seed)
return train_data, dev_data, test_data
def main():
2023-04-20 12:02:46 +02:00
# Pobierz i wypakuj dane z Kaggle
dataset_id = "iabhishekofficial/mobile-price-classification"
2023-04-20 12:02:46 +02:00
destination_folder = "/app/data"
zip_filepath = download_kaggle_dataset(dataset_id, destination_folder)
if zip_filepath is not None:
unzip_file(zip_filepath, destination_folder)
train_file = os.path.join(destination_folder, "train.csv")
test_file = os.path.join(destination_folder, "test.csv")
output_file = os.path.join(destination_folder, "combined.csv")
combine_csv_files(train_file, test_file, output_file)
2023-04-20 12:02:46 +02:00
# Wczytanie danych z pliku CSV
data = pd.read_csv(output_file)
2023-04-20 12:02:46 +02:00
# Podział danych na zbiory train, dev, test z proporcjami 6:2:2
train_data, dev_data, test_data = split_data(data, train_ratio=0.6, dev_ratio=0.2)
2023-04-20 12:02:46 +02:00
# Zapisanie podzielonych danych do plików CSV
output_dir = "/app/output"
os.makedirs(output_dir, exist_ok=True)
train_data.to_csv(os.path.join(output_dir, 'Train1.csv'), index=False)
dev_data.to_csv(os.path.join(output_dir, 'Dev1.csv'), index=False)
test_data.to_csv(os.path.join(output_dir, 'Test1.csv'), index=False)
# Wypisanie liczby wierszy w każdym pliku
print(f"Liczba wierszy w pliku Train1.csv: {len(train_data)}")
print(f"Liczba wierszy w pliku Dev1.csv: {len(dev_data)}")
print(f"Liczba wierszy w pliku Test1.csv: {len(test_data)}")
if __name__ == "__main__":
main()