def capm(start_date, end_date, ticker1, ticker2):
#get the data from Yahoo Finance
stock1 = pdr.get_data_yahoo(ticker1, start_date, end_date)
stock2 = pdr.get_data_yahoo(ticker2, start_date, end_date)
#we prefer monthly returns instead of daily returns
return_stock1 = stock1.resample('M').last()
return_stock2 = stock2.resample('M').last()
#creating a dataFrame from the data - Adjusted Closing Price is used as usual
data = pd.DataFrame(
{
's_adjclose': return_stock1['Adj Close'],
'm_adjclose': return_stock2['Adj Close']
},
index=return_stock1.index)
#natural logarithm of the returns
data[['s_returns',
'm_returns']] = np.log(data[['s_adjclose', 'm_adjclose']] /
data[['s_adjclose', 'm_adjclose']].shift(1))
#no need for NaN/missing values values so let's get rid of them
data = data.dropna()
#covariance matrix: the diagonal items are the vairances - off diagonals are the covariances
#the matrix is symmetric: cov[0,1] = cov[1,0] !!!
covmat = np.cov(data["s_returns"], data["m_returns"])
print(covmat)
#calculating beta according to the formula
beta = covmat[0, 1] / covmat[1, 1]
print("Beta from formula:", beta)
#using linear regression to fit a line to the data [stock_returns, market_returns] - slope is the beta
beta, alpha = np.polyfit(data["m_returns"], data['s_returns'], deg=1)
print("Beta from regression:", beta)
#plot
fig, axis = plt.subplots(1, figsize=(20, 10))
axis.scatter(data["m_returns"], data['s_returns'], label="Data points")
axis.plot(data["m_returns"],
beta * data["m_returns"] + alpha,
color='red',
label="CAPM Line")
plt.title('Capital Asset Pricing Model, finding alphas and betas')
plt.xlabel('Market return $R_m$', fontsize=18)
plt.ylabel('Stock return $R_a$')
plt.text(0.08, 0.05, r'$R_a = \beta * R_m + \alpha$', fontsize=18)
plt.legend()
plt.grid(True)
plt.show()
#calculate the expected return according to the CAPM formula
expected_return = risk_free_rate + beta * (data["m_returns"].mean() * 12 -
risk_free_rate)
print("Expected return:", expected_return)
def get_data(t1, t2):
df1 = load_ticker(t1)
df2 = load_ticker(t2)
data = pd.concat([df1, df2], axis=1)
data = data.dropna()
data['t1'] = data[t1]
data['t2'] = data[t2]
data['t1_returns'] = data[t1 + '_returns']
data['t2_returns'] = data[t2 + '_returns']
return data
def capm(start, end, ticker1, ticker2):
#Get stock data
stock1 = pdr.get_data_yahoo(ticker1, start, end)
#Get market data
stock2 = pdr.get_data_yahoo(ticker2, start, end)
#Resample for monthly data
return_s1 = stock1.resample('M').last()
return_s2 = stock2.resample('M').last()
#Create a dataframe with the adjusted close
data = pd.DataFrame(
{
's_adjclose': return_s1['Adj Close'],
'm_adjclose': return_s2['Adj Close']
},
index=return_s1.index)
#Calc the stock and market retuens by computing log(n)/log(n-1)
data[['s_returns',
'm_returns']] = np.log(data[['s_adjclose', 'm_adjclose']] /
data[['s_adjclose', 'm_adjclose']].shift(1))
#Drop null values
data = data.dropna()
#Generate covarience matrix
covmat = np.cov(data["s_returns"], data["m_returns"])
#Calc beta from matrix
beta = covmat[0, 1] / covmat[1, 1]
print("Beta from formula: ", beta)
#Calc beta from regression
beta, alpha = np.polyfit(data["m_returns"], data["s_returns"], deg=1)
print("Beta from regression: ", beta)
#Calc expected return
expected_return = risk_free_return + beta * (
data["m_returns"].mean() * 12 - risk_free_return)
print("Expected Return: ", expected_return)
ax.lines[0].set_alpha(0.3)
#%%
# example: Visualizing Seattle Bycicle Counts
data = pd.read_csv('data/Fremont_Bridge.csv', index_col = 'Date',
parse_dates =True)
#%%
print(data.head())
print(data.columns)
#%%
data.columns = ['Total', 'East', 'West']
#%%
data.dropna().describe()
#%%
# Visualizing the data
data.plot()
plt.ylabel('Hourly Bicycle Count')
#%% resample data to a coarser grid
weekly = data.resample('W').sum()
weekly.plot(style = [':', '--', '-'])
plt.ylabel('Weekly bicycle count')
#%%
# aggregating data with rolling mean
daily = data.resample('D').sum()
daily.rolling(30, center = True).sum().plot(style = [':', '--', '-'])
pd.value_counts(obj.values,sort=False)
mask = obj.isin(['b','c'])
mask
obj[mask]
data = DataFrame(({'Qu1':[1,3,4,3,4],'Qu2':[2,3,1,2,3],'Qu3':[1,5,2,4,4]}))
data
result = data.apply(pd.value.counts).fillna(0)
result
string_data = Series(['aardvark','artichoke',np.nan,'avocado'])
string_data
string_data.isnull()
string_data[0]=None
string_data.isnull()
from numpy import nan as NA
data = Series([1, NA, 3.5, NA, 7])
data.dropna()
data[data.notnull()]
data= DataFrame([[1.,6.5,3.],[1.,NA,NA],[NA,NA,NA],[NA,6.5,3]])
cleaned = data.dropna()
data
cleaned
cleaned = data.dropna(how='all')
cleaned
data[4]=NA
data
data.dropna(axis=1,how='all')
df = DataFrame(np.random.randn(7,3))
df.ix[:4,1]=NA
df.ix[:2,2] =NA
df
df.dropna(thresh=3)
'/Users/xiangliu/Desktop/CSC560 Data/pollution_us_2000_2016.csv')
data.shape
# In[3]:
data.head(3)
# In[4]:
le = data['CO AQI']
le[le.isnull()]
# In[5]:
##Look Into each value
data = data.dropna()
data.to_csv("/Users/xiangliu/Desktop/CSC560 Data/pollution_AQI.csv",
index=True,
sep=',')
# In[6]:
data = pd.read_csv('/Users/xiangliu/Desktop/CSC560 Data/pollution_AQI.csv')
data.shape
# In[7]:
data.head(3)
# In[8]:
def initialize(startdate, enddate, traintestchangedate, listticker):
data = yf.download(listticker, start=startdate, end=enddate)['Adj Close']
data.dropna(axis=0, inplace=True)
train = data[data.index < traintestchangedate]
test = data[data.index >= traintestchangedate]
return train, test
obj.value_counts()
pd.value_counts(obj.values, sort=False)
mask = obj.isin(['b', 'c'])
obj[mask]
data = DataFrame({
'Qu1': [1, 3, 4, 3, 4],
'Qu2': [2, 3, 1, 2, 3],
'Qu3': [1, 5, 2, 4, 4]
})
data.apply(pd.value_counts).fillna(0)
string_data = Series(['aardvark', 'artichoke', np.nan, 'avocado'])
string_data.isnull()
data = Series([1, NA, 3.5, NA, 7])
data.dropna()
data[data.notnull()]
data = DataFrame([[1, 6.5, 3], [1, NA, NA], [NA, NA, NA], [NA, 6.5, 3]])
data.dropna()
data.dropna(how='all')
data[4] = NA
data.dropna(axis=1, how='all')
df = DataFrame(np.random.randn(7, 3))
df.ix[:4, 1] = NA
df.ix[:2, 2] = NA
df.dropna(thresh=3)
df.fillna(0)
df.fillna({1: 0.5})
data = Series(np.random.randn(10),
index=[['a', 'a', 'a', 'b', 'b', 'b', 'c', 'c', 'd', 'd'],
'LIN.DE',
'LXS.DE',
'MRK.DE',
'MUV2.DE',
'RWE.DE',
'SAP.DE',
'SDF.DE',
'SIE.DE',
'TKA.DE',
'VOW3.DE',
'^GDAXI',
] #DAX30指数各个股票的代码以及德国３０指数代码
data = pd.DataFrame()
for sym in symbols: #获取数据
data[sym] = web.DataReader(sym, data_source='google')['Close']
data = data.dropna() #丢弃缺失值
dax = pd.DataFrame(data.pop('^GDAXI')) #将指数数据单独拿出来，采用pop在获取的时候已经从原来的地方删除这一列数据了
scale_function = lambda x: (x - x.mean()) / x.std()
pca = KernelPCA().fit(
data.apply(scale_function)) #这里用到了apply函数，做ＰＣＡ前我们要对数据做标准化
get_we = lambda x: x / x.sum()
print(get_we(pca.lambdas_))[:10]
pca = KernelPCA(n_components=1).fit(data.apply(scale_function))
dax['PCA_1'] = pca.transform(data)
dax.apply(scale_function).plot(figsize=(8, 4))
pca = KernelPCA(n_components=5).fit(data.apply(scale_function))
weights = get_we(pca.lambdas_)
dax['PCA_5'] = np.dot(pca.transform(data), weights)
plt.figure(figsize=(8, 4))
SP500.columns = ['GSPC.O'] raw = SP500 symbol = ['GSPC.O'] data = (pd.DataFrame(raw[symbol]).dropna()) SMA1 = 42 SMA2 = 252 data['SMA1'] = data[symbol].rolling(SMA1).mean() data['SMA2'] = data[symbol].rolling(SMA2).mean() data.plot(figsize=(10, 6)) data.dropna(inplace=True) data['Position'] = np.where(data['SMA1'] > data['SMA2'], 1, -1) data.tail() ax = data.plot(secondary_y='Position', figsize=(10, 6)) ax.get_legend().set_bbox_to_anchor((0.25, 0.85)) data['Returns'] = np.log(data[symbol] / data[symbol].shift(1)) data['Strategy'] = data['Position'].shift(1) * data['Returns'] data.round(4).head() data.dropna(inplace=True)