ETF Allocations Dataset

etf.py

def _etf_diversity_dataset(etf_tickers_and_allocations):
  
  ETFs = []

  for etf_ticker, allocation in etf_tickers_and_allocations.items():
    etf_holdings_dataset = _etf_holdings_dataset(etf_ticker, allocation)
    ETFs.append(etf_holdings_dataset)
  
  etf_diversity_dataset = pd.concat(ETFs).groupby(by=["ticker", "sedol"]).sum()
  etf_diversity_dataset = etf_diversity_dataset.sort_values(by="funds_allocation", ascending=False)
  etf_diversity_dataset["funds_allocation"] = etf_diversity_dataset["funds_allocation"].round(3)
  
  return etf_diversity_dataset

etf_tickers_and_allocations = {
    "VDC": 20000, 
    "VCR": 20000, 
    "VGT": 20000, 
    "VOO": 20000,
    "VUG": 20000, 
    }

etf_diversity_dataset = _etf_diversity_dataset(etf_tickers_and_allocations)
print(etf_diversity_dataset)

# ticker sedol    funds_allocation                    
# AAPL   2046251          8506.425
# MSFT   2588173          6918.250
# AMZN   2000019          6523.805
# TSLA   B616C79          4637.269
# PG     2704407          2835.639
# ...                          ...
# VRM    BMFZYY5             0.157
# AUR    BMF0P92             0.128
# LEN/B  2578293             0.125
# NWS    BBGVT51             0.009
# HAYW   BMFQC33             0.001

# [1153 rows x 1 columns]