#%%
from sklearn import cluster, covariance, manifold
import yfinance as yf
import pandas as pd
import numpy as np
from sklearn import metrics

# List of tickers
cfdtickers = [
    'AUDNZD=X', 'AUDCAD=X', 'AUDCHF=X', 'AUDJPY=X', 'CHFJPY=X',
    'EURGBP=X', 'EURAUD=X', 'EURJPY=X', 'EURCHF=X', 'EURNZD=X',
    'EURCAD=X', 'GBPCHF=X', 'GBPJPY=X', 'CADCHF=X', 'CADJPY=X',
    'GBPAUD=X', 'GBPCAD=X', 'GBPNZD=X', 'NZDCAD=X', 'NZDCHF=X',
    'NZDJPY=X', 'NZDUSD=X', 'USDSGD=X', 'EURUSD=X',
]

# Downloading data for each ticker and extracting the 'Close' column
data = {ticker: yf.download(ticker, start="2023-01-01", end="2024-01-01")['Close'] for ticker in cfdtickers}

# Creating a DataFrame from the downloaded data
df = pd.DataFrame(data)
df= df.pct_change()
df=df.ffill()
df=df.bfill()


pct_change_combined_stock_df = df
pct_change_combined_stock_df = pct_change_combined_stock_df.dropna()

variation = pct_change_combined_stock_df

edge_model = covariance.GraphicalLassoCV(verbose=True)
X = variation.copy()
X /= X.std(axis=0)
edge_model.fit(X)

_, labels = cluster.affinity_propagation(edge_model.covariance_)



n_labels = labels.max()
names=[]

for stock in pct_change_combined_stock_df.columns.tolist():
    names.append(stock)

names = np.array(names)

sectorTickers = {f'Cluster {i+1}': ', '.join(names[labels == i]) for i in range(n_labels + 1)}
print("sectorTickers",sectorTickers)

# Calculate silhouette score
silhouette_score = metrics.silhouette_score(X, labels)
print("Silhouette Score:", silhouette_score)


# %%