Code Editor Alternative to JupyterLab Part 2

# clean_data.py
import argparse
import boto3
import pandas as pd
from sklearn.preprocessing import StandardScaler

s3 = boto3.client("s3")

def upload_to_s3(local_path, bucket, key):
    """Upload a local file to S3."""
    s3.upload_file(local_path, bucket, key)

def process_data(input_path, output_path):
    """Perform data preprocessing: handle missing values and scale numeric columns."""
    df = pd.read_csv(input_path)

    # Fill missing values with median for numeric columns only
    df.fillna(df.median(numeric_only=True), inplace=True)

    # Standardize numeric columns
    numeric_cols = df.select_dtypes(include=["float64", "int64"]).columns
    scaler = StandardScaler()
    if len(numeric_cols) > 0:
        df[numeric_cols] = scaler.fit_transform(df[numeric_cols])

    # Save processed data
    df.to_csv(output_path, index=False)

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Process CSV data and upload results to S3.")
    parser.add_argument("--input-bucket", type=str, required=True, help="S3 bucket containing input data")
    parser.add_argument("--input-key", type=str, required=True, help="S3 key for input data")
    parser.add_argument("--output-bucket", type=str, required=True, help="S3 bucket for processed data")
    parser.add_argument("--output-key", type=str, required=True, help="S3 key for processed data")
    args = parser.parse_args()

    # Example local paths derived from S3 keys (adjust as needed)
    input_path = "/tmp/input.csv"
    output_path = "/tmp/output.csv"

    # Download input from S3
    s3.download_file(args.input_bucket, args.input_key, input_path)

    # Process and upload
    process_data(input_path, output_path)
    upload_to_s3(output_path, args.output_bucket, args.output_key)

usage: clean_data.py [-h] --input-bucket INPUT_BUCKET --input-key INPUT_KEY --output-bucket OUTPUT_BUCKET --output-key OUTPUT_KEY
clean_data.py: error: the following arguments are required: --input-bucket, --input-key, --output-bucket, --output-key

import pandas as pd

data = {
    "Bedrooms": [2, 3, 4, None],
    "Price": [200000, 250000, None, 150000],
    "Neighborhood": ["Downtown", None, "Suburb", "Rural"]
}

df = pd.DataFrame(data)
print(df)