Python script to extract the part of csv columns

extract_cost_explore.py

"""
Python script to extract the part of csv columns

Params:
    input_file: str : file path for original cost-explore report csv
    output_file: str : file path for extracted csv
    columns_to_keep: list[str] : list of columns to extract
"""

import sys

import pandas as pd

# Define the input and output file paths
input_file = "/path/to/my-daily-report-00001.csv"
output_file = "/path/to/Downloads/my-daily-report-00001-extracted.csv"

# Specify the columns you want to keep
columns_to_keep = [
    "lineItem/UsageStartDate",
    "lineItem/UsageEndDate",
    "lineItem/ProductCode",
    "lineItem/UsageType",
    "lineItem/Operation",
    "lineItem/AvailabilityZone",
    "lineItem/ResourceId",
    "lineItem/UsageAmount",
    "lineItem/NormalizationFactor",
    "lineItem/NormalizedUsageAmount",
    "lineItem/CurrencyCode",
    "lineItem/BlendedCost",
    "lineItem/LineItemDescription",
]

# ignore mixed dtype error with low_memory disabled
df = pd.read_csv(input_file, low_memory=False)

# Check if all target columns are present in the DataFrame
missing_columns = [col for col in columns_to_keep if col not in df.columns]
if missing_columns:
    print(f"Error: The following columns are missing in the input file: {missing_columns}")
    sys.exit()

df_extracted = df[columns_to_keep]

# Save the extracted DataFrame to a new CSV file without the index
df_extracted.to_csv(output_file, index=False)

print(f"Extraction complete. Saved to: {output_file}")