from pandas import read_table
def download_data(fileLocation, fields):
”’
Downloads the data for this script into a pandas DataFrame. Uses columns indices provided
”’
frame = read_table(
fileLocation,
# Specify the file encoding
# Latin-1 is common for data from US sources
encoding=’latin-1′,
#encoding=’utf-8′, # UTF-8 is also common
# Specify the separator in the data
sep=’,’, # comma separated values
# Ignore spaces after the separator
skipinitialspace=True,
# Generate row labels from each row number
index_col=None,
# Generate column headers row from each column number
header=0, # use the first line as headers
usecols=fields
)
# Return the entire frame
return frame