- This can be useful when working with big csv files for example. - You can work with chunks of the data and prevent a potential MemoryError due to the data not fitting into memory. - The impact on our script is processing one line of the entire file

data_pipeline.py

file_name = "techcrunch.csv"
lines = (line for line in open(file_name))
list_line = (s.rstrip().split(",") for s in lines)
cols = next(list_line)
company_dicts = (dict(zip(cols, data)) for data in list_line)
funding = (
    int(company_dict["raisedAmt"])
    for company_dict in company_dicts
    if company_dict["round"] == "a"
)
total_series_a = sum(funding)
print(f"Total series A fundraising: ${total_series_a}")