HOW TO USE THE EXCEL FILE FOR BENCHAMRKS

import pandas as pd
from datetime import datetime
import pytz
import logbook
import pandas as pd

# FIRST I CONVERTED THE EXCEL FILE TO CSV BEFOREHAND - READ THE CSV FILE AND SEPARATE IT THROUGH THE ';'
filepath = '/Users/cemalarican/Desktop/SPYCSV.csv'
data = pd.read_csv(filepath, sep=';', header=1)

# ONLY CONSIDER THE TIME AND CLOSE COLUMNS
data = data[['time', 'close']]

# SET THE TIME COLUMN AS THE NEW INDEX - AND WRITE IT TO A NEW CSV FILE FOR THE BENCHMARK RETURNS
data.set_index('time', inplace=True)
data.to_csv('/Users/cemalarican/Desktop/NEWDATA.csv')


log = logbook.Logger(__name__)
def get_benchmark_returns(symbol='SPY'):

    filelike = '/Users/cemalarican/Desktop/NEWDATA.csv'
    log.info("Reading benchmark returns from {}", filelike)

    df = pd.read_csv(
        filelike,
        index_col=['time'],
        parse_dates=['time'],
    ).tz_localize('utc')

    if 'close' not in df.columns:
        raise ValueError("The column 'return' not found in the "
                         "benchmark file \n"
                         "Expected benchmark file format :\n"
                         "date, return\n"
                         "2020-01-02 00:00:00+00:00,0.01\n"
                         "2020-01-03 00:00:00+00:00,-0.02\n")

    return df['close'].sort_index().pct_change().iloc[1:]

bench = get_benchmark_returns()
bench