# -*- coding: utf-8 -*-
"""
Spyder Editor

A FAIRE:
    
    1/ telecharger les cours des composantes du CAC40 (ou DJIA, ou ...)
    en prix journaliers (au moins le "close") si possible depuis 5 ans
    
    Idee: utiliser yahoo comme source et par exemple yfinance 
    "pip install yfinance"
    
    2/ dessiner l'histograme du prix et du rendement (avec "log" et "linéaire")
    
    3/ tester la normalité des prix, celle des rendements log 
    et celle des rendements "linéaires"
    (par exemple utiliser scipy.stats.normaltest)

"""


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from  scipy.stats import normaltest
import yfinance as yf

ticker_list_cac40= ['ORA.PA','ATO.PA']

full_ticker_list_CAC40_nov21_wiki=["AI.PA","AIR.PA","ALO.PA","MT.AS","CS.PA","BNP.PA","EN.PA","CAP.PA","CA.PA",
"ACA.PA","BN.PA","DSY.PA","ENGI.PA","EL.PA","ERF.PA","RMS.PA","KER.PA","OR.PA",
"LR.PA","MC.PA","ML.PA","ORA.PA","RI.PA","PUB.PA","RNO.PA","SAF.PA","SGO.PA","SAN.PA",
"SU.PA","GLE.PA","STLA.PA","STM.PA","TEP.PA","HO.PA","TTE.PA","URW.AS","VIE.PA","DG.PA",
"VIV.PA","WLN.PA"]

historical_prices={}

for tt in ticker_list_cac40:
    tk = yf.Ticker(tt)
    hist_tk = tk.history(period="max")
    historical_prices[tt]= hist_tk

# version avec csv sur le site du cours
data = pd.read_csv('cac40_30.csv',sep=';', index_col = 0)
data.head()
data.keys()

# plot histogram of prices
_=data.hist(bins=30, figsize = (15,15))
niveau=0.01

pvalues=[]
for cols in data.keys():
    # tester la normalité de chaque colonne
    pv=normaltest(data[cols],nan_policy='omit').pvalue
    pvalues.append(pv)
    if(pv<niveau):
        res="not normal"
    else:
        res='normal'
    print("Test pval=",pv, 'res=',res)
print("no. of normal = ",sum([1 for pv in pvalues if pv >=niveau]))    
print("no. of normal = ",
      sum([1 for res in pvalues if res <=niveau]))

# calculer les rendements, plot hist, test
#returns= (data.diff()/data.shift(1)).shift(-1)#rdt linéaire
returns= np.log(data/data.shift(1))#rdt log
_=returns.hist(bins=30, figsize = (15,15))
pvalues=[]
for cols in returns.keys():
    # tester la normalité de chaque colonne
    pv=normaltest(returns[cols],nan_policy='omit').pvalue
    pvalues.append(pv)
    if(pv<niveau):
        res="not normal"
    else:
        res='normal'
    print("Test pval=",pv, 'res=',res)
print("no. of normal = ",sum([1 for pv in pvalues if pv >=niveau]))    
print("no. of normal = ",
      sum([1 for res in pvalues if res <=niveau]))

#calcul de la moyenne des returns, et la covariance
mean_returns=returns.mean()
cov_matrix= returns.cov()
nb = mean_returns.shape[0]
allocation=np.random.randn(nb)#a rendre la somme=1 ex: softmax
rdt = allocation@mean_returns
vol = allocation@cov_matrix@allocation