def market_return(self):
# 1. Linear Regression: On the estimation_period
dr_data = Calculator.returns(self.data)
dr_market = Calculator.returns(self.market)
c_name = dr_data.columns[0]
x = dr_market[c_name][self.start_period:self.end_period]
y = dr_data[c_name][self.start_period:self.end_period]
slope, intercept, r_value, p_value, std_error = stats.linregress(x, y)
er = lambda x: x * slope + intercept
# 2. Analysis on the event window
# Expexted Return:
self.er = dr_market[self.start_window:self.end_window].apply(
er)[c_name]
self.er.name = 'Expected return'
# Abnormal return: Return of the data - expected return
self.ar = dr_data[c_name][self.start_window:self.end_window] - self.er
self.ar.name = 'Abnormal return'
# Cumulative abnormal return
self.car = self.ar.cumsum()
self.car.name = 'Cum abnormal return'
# t-test
t_test_calc = lambda x: x / std_error
self.t_test = self.ar.apply(t_test_calc)
self.t_test.name = 't-test'
self.prob = self.t_test.apply(stats.norm.cdf)
self.prob.name = 'Probability'
def test_tvm(self):
'''
Tests
-----
1. FV w/ PV, R, n, m and ret_list=False
2. PV w/ PV, R, n, m and ret_list=False
3. R w/ PV, FV, n, m
4. n w/ PV, FV, R, m
5. ear w/ R, m
'''
self_dir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
tests = ['Calculator_TVM_1.csv', 'Calculator_TVM_2.csv',
'Calculator_TVM_3.csv']
tests = [os.path.join(self_dir, 'docs',test) for test in tests]
for test_file in tests:
# Set up
solution = pd.read_csv(test_file)
for idx, row in solution.iterrows():
# Test 1
FV = Calculator.FV(PV=row['PV'], R=row['R'], n=row['n'], m=row['m'])
self.assertAlmostEquals(FV, row['FV'], 4)
# Test 2
PV = Calculator.PV(FV=row['FV'], R=row['R'], n=row['n'], m=row['m'])
self.assertAlmostEquals(PV, row['PV'], 4)
# Test 3
R = Calculator.R(PV=row['PV'], FV=row['FV'], n=row['n'], m=row['m'])
self.assertAlmostEquals(R, row['R'], 4)
# Test 4
n = Calculator.n(PV=row['PV'], FV=row['FV'], R=row['R'], m=row['m'])
self.assertAlmostEquals(n, row['n'], 4)
# Test 5
ear = Calculator.eff_ret(R=row['R'], m=row['m'])
self.assertAlmostEquals(ear, row['EAR'], 4, "R(%s),m(%s)" % (row['R'], row['m']))
def market_return(self):
# 1. Linear Regression: On the estimation_period
dr_data = Calculator.returns(self.data)
dr_market = Calculator.returns(self.market)
c_name = dr_data.columns[0]
x = dr_market[c_name][self.start_period:self.end_period]
y = dr_data[c_name][self.start_period:self.end_period]
slope, intercept, r_value, p_value, std_error = stats.linregress(x, y)
er = lambda x: x * slope + intercept
# 2. Analysis on the event window
# Expexted Return:
self.er = dr_market[self.start_window:self.end_window].apply(er)[c_name]
self.er.name = 'Expected return'
# Abnormal return: Return of the data - expected return
self.ar = dr_data[c_name][self.start_window:self.end_window] - self.er
self.ar.name = 'Abnormal return'
# Cumulative abnormal return
self.car = self.ar.cumsum()
self.car.name = 'Cum abnormal return'
# t-test
t_test_calc = lambda x: x / std_error
self.t_test = self.ar.apply(t_test_calc)
self.t_test.name = 't-test'
self.prob = self.t_test.apply(stats.norm.cdf)
self.prob.name = 'Probability'
def test_tvm(self):
'''
Tests
-----
1. FV w/ PV, R, n, m and ret_list=False
2. PV w/ PV, R, n, m and ret_list=False
3. R w/ PV, FV, n, m
4. n w/ PV, FV, R, m
5. ear w/ R, m
'''
self_dir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
tests = ['Calculator_TVM_1.csv', 'Calculator_TVM_2.csv',
'Calculator_TVM_3.csv']
tests = [os.path.join(self_dir, 'docs',test) for test in tests]
for test_file in tests:
# Set up
solution = pd.read_csv(test_file)
for idx, row in solution.iterrows():
# Test 1
FV = Calculator.FV(PV=row['PV'], R=row['R'], n=row['n'], m=row['m'])
self.assertAlmostEqual(FV, row['FV'], 4)
# Test 2
PV = Calculator.PV(FV=row['FV'], R=row['R'], n=row['n'], m=row['m'])
self.assertAlmostEqual(PV, row['PV'], 4)
# Test 3
R = Calculator.R(PV=row['PV'], FV=row['FV'], n=row['n'], m=row['m'])
self.assertAlmostEqual(R, row['R'], 4)
# Test 4
n = Calculator.n(PV=row['PV'], FV=row['FV'], R=row['R'], m=row['m'])
self.assertAlmostEqual(n, row['n'], 4)
# Test 5
ear = Calculator.eff_ret(R=row['R'], m=row['m'])
self.assertAlmostEqual(ear, row['EAR'], 4, "R(%s),m(%s)" % (row['R'], row['m']))
def test_assets(self):
'''
Tests
-----
1. Calculator.returns w/ basedOn=1 cc=False
2. Calculator.returns w/ basedOn=1 cc=True
3. Calculator.returns w/ basedOn=2 cc=False
4. Calculator.returns w/ basedOn=2 cc=True
5. Calculator.FV w/ R=list ret_list=True
6. Calculator.PV w/ R=list ret_list=True
'''
# Load Data
self_dir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
tests = ['Calculator_Assets_1.csv']
tests = [os.path.join(self_dir, 'docs', test) for test in tests]
for test_file in tests:
# Set up
solution = pd.read_csv(test_file).set_index('Date').fillna(value=0)
data = solution['Adj. Close']
# Test 1
simple_returns = Calculator.returns(data)
self.assertEqual(solution['Adj. Close returns'], simple_returns)
# Test 2
cc_returns = Calculator.returns(data, cc=True)
self.assertEqual(solution['Adj. Close CC returns'], cc_returns)
# Test 3
simple_returns_2 = Calculator.returns(data, basedOn=2)
self.assertEqual(solution['Adj. Close returns (2)'], simple_returns_2)
# Test 4
cc_returns_2 = Calculator.returns(data, basedOn=2, cc=True)
self.assertEqual(solution['Adj. Close CC returns (2)'], cc_returns_2)
# Test 5
fv = Calculator.FV(PV=1, R=simple_returns, ret_list=True)
self.assertEqual(solution['Future value'], fv)
# Test 6
pv = Calculator.PV(FV=fv[-1], R=simple_returns, ret_list=True)
pv_sol = solution['Future value']
pv_sol.name = 'Present value'
self.assertEqual(solution['Future value'], pv)
def test_sharpe_ratio(self):
array = np.array([1, 1.5, 3, 4, 4.3])
array_2 = np.array([5, 4.3, 3, 3.5, 1])
matrix = np.array([array, array_2]).T
series = pd.Series(array)
time_series = pd.Series(array_2)
df = pd.DataFrame(matrix, columns=['c1', 'c2'])
# Input is np.array of 1 dimmension => float
ans = Calculator.sharpe_ratio(array)
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# Input is np.array of 2 dimmensions => array
ans = Calculator.sharpe_ratio(matrix)
self.assertArray(ans)
sol = np.array([2.38842482, -1.4708528])
self.assertEqual(ans, sol, 5)
# Input is pandas.Series => float
ans = Calculator.sharpe_ratio(series)
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# Input is pandas.TimeSeries => float
ans = Calculator.sharpe_ratio(time_series)
self.assertFloat(ans)
self.assertAlmostEquals(ans, -1.4708528, 5)
# Input is pandas.DataFrame with col parameter => float
ans = Calculator.sharpe_ratio(df, col='c1')
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# --
ans = Calculator.sharpe_ratio(df, col='c2')
self.assertFloat(ans)
self.assertAlmostEqual(ans, -1.4708528, 5)
# Input is pandas.DataFrame without col parameter => pd.Series
ans = Calculator.sharpe_ratio(df)
self.assertSeries(ans)
sol = pd.Series([2.38842482, -1.4708528],
index=['c1', 'c2'],
name='Sharpe Ratios')
self.assertEqual(ans, sol)
def test_ret(self):
# Variables
array = np.array([1, 2, 3, 4, 5])
array_2 = np.array([5, 4, 3, 2, 1])
matrix = np.array([array, array_2]).T
series = pd.Series(array, index=[5, 7, 8, 10, 11])
time_series = pd.Series(array)
df = pd.DataFrame(matrix,
columns=['c1', 'c2'],
index=[5, 7, 8, 10, 11])
# Input is numpy.ndarray of 1 dimmension => float
ans = Calculator.ret(array)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is numpy.ndarray of 2 dimmensions => np.ndarray
ans = Calculator.ret(matrix)
self.assertArray(ans)
self.assertEqual(ans, np.array([4, -0.8]))
# Input is pandas.Series => float
ans = Calculator.ret(series)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is pandas.TimeSeries => float
ans = Calculator.ret(time_series)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is pandas.DataFrame with col parameter => float
ans = Calculator.ret(df, col='c1')
self.assertFloat(ans)
self.assertEqual(ans, 4)
# --
ans = Calculator.ret(df, col='c2')
self.assertFloat(ans)
self.assertEqual(ans, -0.8)
# Input is pandas.DataFrame without col parameter => Return pd.Series
ans = Calculator.ret(df)
self.assertSeries(ans)
sol = pd.Series([4, -0.8], index=['c1', 'c2'], name='Total Returns')
self.assertEqual(ans, sol)
def test_sharpe_ratio(self):
array = np.array([1,1.5,3,4,4.3])
array_2 = np.array([5,4.3,3,3.5,1])
matrix = np.array([array, array_2]).T
series = pd.Series(array)
time_series = pd.Series(array_2)
df = pd.DataFrame(matrix, columns=['c1', 'c2'])
# Input is np.array of 1 dimmension => float
ans = Calculator.sharpe_ratio(array)
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# Input is np.array of 2 dimmensions => array
ans = Calculator.sharpe_ratio(matrix)
self.assertArray(ans)
sol = np.array([2.38842482, -1.4708528])
self.assertEqual(ans, sol, 5)
# Input is pandas.Series => float
ans = Calculator.sharpe_ratio(series)
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# Input is pandas.TimeSeries => float
ans = Calculator.sharpe_ratio(time_series)
self.assertFloat(ans)
self.assertAlmostEquals(ans, -1.4708528, 5)
# Input is pandas.DataFrame with col parameter => float
ans = Calculator.sharpe_ratio(df, col='c1')
self.assertFloat(ans)
self.assertAlmostEquals(ans, 2.38842, 5)
# --
ans = Calculator.sharpe_ratio(df, col='c2')
self.assertFloat(ans)
self.assertAlmostEqual(ans, -1.4708528, 5)
# Input is pandas.DataFrame without col parameter => pd.Series
ans = Calculator.sharpe_ratio(df)
self.assertSeries(ans)
sol = pd.Series([2.38842482, -1.4708528], index=['c1', 'c2'], name='Sharpe Ratios')
self.assertEqual(ans, sol)
def test_ret(self):
# Variables
array = np.array([1,2,3,4,5])
array_2 = np.array([5,4,3,2,1])
matrix = np.array([array, array_2]).T
series = pd.Series(array, index=[5,7,8,10,11])
time_series = pd.Series(array)
df = pd.DataFrame(matrix, columns=['c1', 'c2'], index=[5,7,8,10,11])
# Input is numpy.ndarray of 1 dimmension => float
ans = Calculator.ret(array)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is numpy.ndarray of 2 dimmensions => np.ndarray
ans = Calculator.ret(matrix)
self.assertArray(ans)
self.assertEqual(ans, np.array([4, -0.8]))
# Input is pandas.Series => float
ans = Calculator.ret(series)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is pandas.TimeSeries => float
ans = Calculator.ret(time_series)
self.assertFloat(ans)
self.assertEqual(ans, 4)
# Input is pandas.DataFrame with col parameter => float
ans = Calculator.ret(df, col='c1')
self.assertFloat(ans)
self.assertEqual(ans, 4)
# --
ans = Calculator.ret(df, col='c2')
self.assertFloat(ans)
self.assertEqual(ans, -0.8)
# Input is pandas.DataFrame without col parameter => Return pd.Series
ans = Calculator.ret(df)
self.assertSeries(ans)
sol = pd.Series([4, -0.8], index=['c1', 'c2'], name='Total Returns')
self.assertEqual(ans, sol)
def test_assets(self):
'''
Tests
-----
1. Calculator.returns w/ basedOn=1 cc=False
2. Calculator.returns w/ basedOn=1 cc=True
3. Calculator.returns w/ basedOn=2 cc=False
4. Calculator.returns w/ basedOn=2 cc=True
5. Calculator.FV w/ R=list ret_list=True
6. Calculator.PV w/ R=list ret_list=True
'''
# Load Data
self_dir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
tests = ['Calculator_Assets_1.csv']
tests = [os.path.join(self_dir, 'docs', test) for test in tests]
for test_file in tests:
# Set up
solution = pd.read_csv(test_file).set_index('Date').fillna(value=0)
data = solution['Adj. Close']
# Test 1
simple_returns = Calculator.returns(data)
self.assertEqual(solution['Adj. Close returns'], simple_returns)
# Test 2
cc_returns = Calculator.returns(data, cc=True)
self.assertEqual(solution['Adj. Close CC returns'], cc_returns)
# Test 3
simple_returns_2 = Calculator.returns(data, basedOn=2)
self.assertEqual(solution['Adj. Close returns (2)'], simple_returns_2)
# Test 4
cc_returns_2 = Calculator.returns(data, basedOn=2, cc=True)
self.assertEqual(solution['Adj. Close CC returns (2)'], cc_returns_2)
# Test 5
fv = Calculator.FV(PV=1, R=simple_returns, ret_list=True)
self.assertEqual(solution['Future value'], fv)
# Test 6
pv = Calculator.PV(FV=fv[-1], R=simple_returns, ret_list=True)
pv_sol = solution['Future value']
pv_sol.name = 'Present value'
self.assertEqual(solution['Future value'], pv)
def test_returns(self):
# Variables
array_1 = np.array([1, 1.5, 3, 4, 4.3])
array_2 = np.array([5, 4.3, 3, 3.5, 1])
matrix = np.array([array_1, array_2]).T
ser = pd.Series(array_1, name='TEST')
df = pd.DataFrame(matrix, columns=['c1', 'c2'])
sol_array_1 = np.array([0, 0.5, 1, 0.33333333, 0.075])
sol_array_2 = np.array(
[0., -0.14, -0.30232558, 0.16666667, -0.71428571])
sol_matrix = np.array([sol_array_1, sol_array_2]).T
# Input is numpy.array of 1 dimmension => np.ndarray
ans = Calculator.returns(array_1)
self.assertArray(ans)
self.assertEqual(ans, sol_array_1, 5)
# Input is numpy.ndarray of 2 dimmension 2 => np.ndarray
ans = Calculator.returns(matrix)
self.assertArray(ans)
self.assertEqual(ans, sol_matrix, 5)
# Input is pandas.Series => pd.Series
ans = Calculator.returns(ser)
self.assertSeries(ans)
sol = pd.Series(sol_array_1, index=ser.index, name='TEST returns')
self.assertEqual(ans, sol)
# Input is pandas.DataFrame with col parameter => pd.Series
ans = Calculator.returns(df, col='c1')
self.assertSeries(ans)
sol = pd.Series(sol_array_1, index=df.index, name='c1 returns')
self.assertEqual(ans, sol)
# --
ans = Calculator.returns(df, col='c2')
self.assertSeries(ans)
sol = pd.Series(sol_array_2, index=df.index, name='c2 returns')
self.assertEqual(ans, sol)
# Test: Input is pandas.DataFrame without col parameter => pd.DataFrame
ans = Calculator.returns(df)
sol = pd.DataFrame(sol_matrix, index=df.index, columns=df.columns)
self.assertEqual(ans, sol)
def test_returns(self):
# Variables
array_1 = np.array([1,1.5,3,4,4.3])
array_2 = np.array([5,4.3,3,3.5,1])
matrix = np.array([array_1, array_2]).T
ser = pd.Series(array_1, name='TEST')
df = pd.DataFrame(matrix, columns=['c1', 'c2'])
sol_array_1 = np.array([0, 0.5, 1, 0.33333333, 0.075])
sol_array_2 = np.array([ 0., -0.14, -0.30232558, 0.16666667, -0.71428571])
sol_matrix = np.array([sol_array_1, sol_array_2]).T
# Input is numpy.array of 1 dimmension => np.ndarray
ans = Calculator.returns(array_1)
self.assertArray(ans)
self.assertEqual(ans, sol_array_1, 5)
# Input is numpy.ndarray of 2 dimmension 2 => np.ndarray
ans = Calculator.returns(matrix)
self.assertArray(ans)
self.assertEqual(ans, sol_matrix, 5)
# Input is pandas.Series => pd.Series
ans = Calculator.returns(ser)
self.assertSeries(ans)
sol = pd.Series(sol_array_1, index=ser.index, name='TEST returns')
self.assertEqual(ans, sol)
# Input is pandas.DataFrame with col parameter => pd.Series
ans = Calculator.returns(df, col='c1')
self.assertSeries(ans)
sol = pd.Series(sol_array_1, index=df.index, name='c1 returns')
self.assertEqual(ans, sol)
# --
ans = Calculator.returns(df, col='c2')
self.assertSeries(ans)
sol = pd.Series(sol_array_2, index=df.index, name='c2 returns')
self.assertEqual(ans, sol)
# Test: Input is pandas.DataFrame without col parameter => pd.DataFrame
ans = Calculator.returns(df)
sol = pd.DataFrame(sol_matrix, index=df.index, columns=df.columns)
self.assertEqual(ans, sol)
plt.show() # Question 9 W0 = 100000 R = stats.norm(loc=0.04, scale=0.09) print(9, W0 * R.ppf(0.01), W0 * R.ppf(0.05)) # Question 10 W0 = 100000 r = stats.norm(loc=0.04, scale=0.09) r_1, r_5 = r.ppf(0.01), r.ppf(0.05) R_1, R_5 = math.exp(r_1) - 1, math.exp(r_5) - 1 print(10, W0 * R_1, W0 * R_5) # Question 11 q11_amzn = Calculator.ret([38.23, 41.29]) # q11_amzn = Calculator.R(PV=38.23, FV=41.29) # Other option q11_cost = Calculator.ret([41.11, 41.74]) print(11, q11_amzn, q11_cost) # Question 12 q12_amzn = Calculator.ret([38.23, 41.29], cc=True) q12_cost = Calculator.ret([41.11, 41.74], cc=True) print(12, q12_amzn, q12_cost) # Question 13 q13_amzn = Calculator.ret([38.23, 41.29], dividends=[0, 0.1]) print(13, q13_amzn, 0.1/41.29) print(13, (41.29 + 0.1)/38.23 - 1, 0.1/41.29) # Question 14
da = DataAccess()
# Question 1
symbols = ['SBUX']
start_date = datetime(1993, 3, 31)
end_date = datetime(2008, 3, 31)
fields = "Adj Close"
data = da.get_data(symbols, start_date, end_date, fields)
monthly = data.asfreq('M', method='ffill')
monthly.plot()
plt.title('Montly Data')
plt.draw()
# Question 2 and 3
total_return = Calculator.ret(data)
q2 = Calculator.FV(PV=10000, R=total_return)
print(2, q2)
# Question 3
q3 = Calculator.ann_ret(R=total_return, m=1 / 15)
print(3, q3)
# Question 4
monthly_ln = monthly.apply(np.log)
monthly_ln.plot()
plt.title('Montly Natural Logarithm')
plt.draw()
# Question 5
monthly_returns = Calculator.returns(monthly)
# Create the data
data = [['December, 2004', 31.18], ['January, 2005', 27.00],['February, 2005', 25.91],
['March, 2005', 25.83],['April, 2005', 24.76],['May, 2005', 27.40],
['June, 2005', 25.83],['July, 2005', 26.27],['August, 2005', 24.51],
['September, 2005', 25.05],['October, 2005', 28.28],['November, 2005', 30.45],
['December, 2005', 30.51]]
starbucks = pd.DataFrame(data, columns=['Date', 'Value']).set_index('Date')['Value']
'''
Question 1: Using the data in the table, what is the simple monthly return between the
end of December 2004 and the end of January 2005?
Ans: -13.40%
'''
q1 = Calculator.ret(starbucks, pos=1)
# q1 = Calculator.R(PV=data[0][1], FV=data[1][1]) # Other option
print(1, q1)
'''
Question 2: If you invested $10,000 in Starbucks at the end of December 2004, how much
would the investment be worth at the end of January 2005?
Ans: $8659.39
'''
q2 = Calculator.FV(PV=10000, R=q1)
print(2, q2)
'''
Question 3: Using the data in the table, what is the continuously compounded monthly
return between December 2004 and January 2005?
Ans: -14.39%
'''
da = DataAccess()
# Question 1
symbols = ['SBUX']
start_date = datetime(1993, 3, 31)
end_date = datetime(2008, 3, 31)
fields = 'adjusted_close'
data = da.get_data(symbols, start_date, end_date, fields)
monthly = data.asfreq('M', method='ffill')
monthly.plot()
plt.title('Montly Data')
plt.draw()
# Question 2 and 3
total_return = Calculator.ret(data)
q2 = Calculator.FV(PV=10000, R=total_return)
print(2, q2)
# Question 3
q3 = Calculator.ann_ret(R=total_return, m=1/15)
print(3, q3)
# Question 4
monthly_ln = monthly.apply(np.log)
monthly_ln.plot()
plt.title('Montly Natural Logarithm')
plt.draw()
# Question 5
monthly_returns = Calculator.returns(monthly)
def run(self):
'''
Assess the events
|-----100-----|-------20-------|-|--------20--------|
estimation lookback event lookforward
Prerequisites
-------------
self.matrix
self.market = 'SPY'
self.lookback_days = 20
self.lookforward_days = 20
self.estimation_period = 200
self.field = 'Adj Close'
'''
# 0. Get the dates and Download/Import the data
symbols = list(set(self.list))
start_date = self.list.index[0]
end_date = self.list.index[-1]
nyse_dates = DateUtils.nyse_dates(
start=start_date,
end=end_date,
lookbackDays=self.lookback_days + self.estimation_period + 1,
lookforwardDays=self.lookforward_days)
data = self.data_access.get_data(symbols, nyse_dates[0],
nyse_dates[-1], self.field)
market = self.data_access.get_data(self.market, nyse_dates[0],
nyse_dates[-1], self.field)
if len(data.columns) == 1:
data.columns = symbols
if len(data) > len(market):
market = market.reindex(data.index)
market.columns = [self.field]
data = data.fillna(method='ffill').fillna(method='bfill')
market = market.fillna(method='ffill').fillna(method='bfill')
# 1. Create DataFrames with the data of each event
windows_indexes = range(-self.lookback_days, self.lookforward_days + 1)
estimation_indexes = range(
-self.estimation_period - self.lookback_days, -self.lookback_days)
self.equities_window = pd.DataFrame(index=windows_indexes)
self.equities_estimation = pd.DataFrame(index=estimation_indexes)
self.market_window = pd.DataFrame(index=windows_indexes)
self.market_estimation = pd.DataFrame(index=estimation_indexes)
dr_data = Calculator.returns(data)
dr_market = Calculator.returns(market)
self.dr_equities_window = pd.DataFrame(index=windows_indexes)
self.dr_equities_estimation = pd.DataFrame(index=estimation_indexes)
self.dr_market_window = pd.DataFrame(index=windows_indexes)
self.dr_market_estimation = pd.DataFrame(index=estimation_indexes)
# 2. Iterate over the list of events and fill the DataFrames
for i in range(len(self.list)):
symbol = self.list[i]
evt_date = self.list.index[i].to_pydatetime()
col_name = symbol + ' ' + evt_date.strftime('%Y-%m-%d')
evt_idx = DateUtils.search_closer_date(evt_date,
data[symbol].index,
exact=True)
# 1.1 Data on the estimation period: self.equities_estimation
start_idx = evt_idx - self.lookback_days - self.estimation_period # estimation start idx on self.data
end_idx = evt_idx - self.lookback_days # estimation end idx on self.data
new_equities_estimation = data[symbol][start_idx:end_idx]
new_equities_estimation.index = self.equities_estimation.index
self.equities_estimation[col_name] = new_equities_estimation
# Daily return of the equities on the estimation period
new_dr_equities_estimation = dr_data[symbol][start_idx:end_idx]
new_dr_equities_estimation.index = self.dr_equities_estimation.index
self.dr_equities_estimation[col_name] = new_dr_equities_estimation
# 1.4 Market on the estimation period: self.market_estimation
new_market_estimation = market[self.field][start_idx:end_idx]
new_market_estimation.index = self.market_estimation.index
self.market_estimation[col_name] = new_market_estimation
# Daily return of the market on the estimation period
new_dr_market_estimation = dr_market[start_idx:end_idx]
new_dr_market_estimation.index = self.dr_market_estimation.index
self.dr_market_estimation[col_name] = new_dr_market_estimation
# 1.3 Equities on the event window: self.equities_window
start_idx = evt_idx - self.lookback_days # window start idx on self.data
end_idx = evt_idx + self.lookforward_days + 1 # window end idx on self.data
new_equities_window = data[symbol][start_idx:end_idx]
new_equities_window.index = self.equities_window.index
self.equities_window[col_name] = new_equities_window
# Daily return of the equities on the event window
new_dr_equities_window = dr_data[symbol][start_idx:end_idx]
new_dr_equities_window.index = self.dr_equities_window.index
self.dr_equities_window[col_name] = new_dr_equities_window
# 1.4 Market on the event window: self.market_window
new_market_window = market[self.field][start_idx:end_idx]
new_market_window.index = self.market_window.index
self.market_window[col_name] = new_market_window
# Daily return of the market on the event window
new_dr_market_window = dr_market[start_idx:end_idx]
new_dr_market_window.index = self.dr_market_window.index
self.dr_market_window[col_name] = new_dr_market_window
# 3. Calculate the linear regression -> expected return
self.reg_estimation = pd.DataFrame(
index=self.dr_market_estimation.columns,
columns=['Intercept', 'Slope', 'Std Error'])
self.er = pd.DataFrame(index=self.dr_market_window.index,
columns=self.dr_market_window.columns)
# For each column (event) on the estimation period
for col in self.dr_market_estimation.columns:
# 3.1 Calculate the regression
x = self.dr_market_estimation[col]
y = self.dr_equities_estimation[col]
slope, intercept, r_value, p_value, slope_std_error = stats.linregress(
x, y)
self.reg_estimation['Slope'][col] = slope
self.reg_estimation['Intercept'][col] = intercept
self.reg_estimation['Std Error'][col] = slope_std_error
# 3.2 Calculate the expected return of each date using the regression
self.er[col] = intercept + self.dr_market_window[col] * slope
# 4. Final results
self.er.columns.name = 'Expected return'
self.mean_er = self.er.mean(axis=1)
self.mean_er.name = 'Mean ER'
self.std_er = self.er.std(axis=1)
self.std_er.name = 'Std ER'
self.ar = self.dr_equities_window - self.er
self.ar.columns.name = 'Abnormal return'
self.mean_ar = self.ar.mean(axis=1)
self.mean_ar.name = 'Mean AR'
self.std_ar = self.ar.std(axis=1)
self.std_ar.name = 'Std AR'
self.car = self.ar.apply(np.cumsum)
self.car.columns.name = 'Cum Abnormal Return'
self.mean_car = self.car.mean(axis=1)
self.mean_car.name = 'Mean CAR'
self.std_car = self.car.std(axis=1)
self.mean_car.name = 'Mean CAR'
def run(self):
"""
Assess the events
|-----100-----|-------20-------|-|--------20--------|
estimation lookback event lookforward
Prerequisites
-------------
self.matrix
self.market = 'SPY'
self.lookback_days = 20
self.lookforward_days = 20
self.estimation_period = 200
self.field = 'Adj Close'
"""
# 0. Get the dates and Download/Import the data
symbols = list(set(self.list))
start_date = self.list.index[0]
end_date = self.list.index[-1]
nyse_dates = DateUtils.nyse_dates(
start=start_date,
end=end_date,
lookbackDays=self.lookback_days + self.estimation_period + 1,
lookforwardDays=self.lookforward_days,
)
data = self.data_access.get_data(symbols, nyse_dates[0], nyse_dates[-1], self.field)
market = self.data_access.get_data(self.market, nyse_dates[0], nyse_dates[-1], self.field)
if len(data.columns) == 1:
data.columns = symbols
if len(data) > len(market):
market = market.reindex(data.index)
market.columns = [self.field]
data = data.fillna(method="ffill").fillna(method="bfill")
market = market.fillna(method="ffill").fillna(method="bfill")
# 1. Create DataFrames with the data of each event
windows_indexes = range(-self.lookback_days, self.lookforward_days + 1)
estimation_indexes = range(-self.estimation_period - self.lookback_days, -self.lookback_days)
self.equities_window = pd.DataFrame(index=windows_indexes)
self.equities_estimation = pd.DataFrame(index=estimation_indexes)
self.market_window = pd.DataFrame(index=windows_indexes)
self.market_estimation = pd.DataFrame(index=estimation_indexes)
dr_data = Calculator.returns(data)
dr_market = Calculator.returns(market)
self.dr_equities_window = pd.DataFrame(index=windows_indexes)
self.dr_equities_estimation = pd.DataFrame(index=estimation_indexes)
self.dr_market_window = pd.DataFrame(index=windows_indexes)
self.dr_market_estimation = pd.DataFrame(index=estimation_indexes)
# 2. Iterate over the list of events and fill the DataFrames
for i in range(len(self.list)):
symbol = self.list[i]
evt_date = self.list.index[i].to_pydatetime()
col_name = symbol + " " + evt_date.strftime("%Y-%m-%d")
evt_idx = DateUtils.search_closer_date(evt_date, data[symbol].index, exact=True)
# 1.1 Data on the estimation period: self.equities_estimation
start_idx = evt_idx - self.lookback_days - self.estimation_period # estimation start idx on self.data
end_idx = evt_idx - self.lookback_days # estimation end idx on self.data
new_equities_estimation = data[symbol][start_idx:end_idx]
new_equities_estimation.index = self.equities_estimation.index
self.equities_estimation[col_name] = new_equities_estimation
# Daily return of the equities on the estimation period
new_dr_equities_estimation = dr_data[symbol][start_idx:end_idx]
new_dr_equities_estimation.index = self.dr_equities_estimation.index
self.dr_equities_estimation[col_name] = new_dr_equities_estimation
# 1.4 Market on the estimation period: self.market_estimation
new_market_estimation = market[self.field][start_idx:end_idx]
new_market_estimation.index = self.market_estimation.index
self.market_estimation[col_name] = new_market_estimation
# Daily return of the market on the estimation period
new_dr_market_estimation = dr_market[start_idx:end_idx]
new_dr_market_estimation.index = self.dr_market_estimation.index
self.dr_market_estimation[col_name] = new_dr_market_estimation
# 1.3 Equities on the event window: self.equities_window
start_idx = evt_idx - self.lookback_days # window start idx on self.data
end_idx = evt_idx + self.lookforward_days + 1 # window end idx on self.data
new_equities_window = data[symbol][start_idx:end_idx]
new_equities_window.index = self.equities_window.index
self.equities_window[col_name] = new_equities_window
# Daily return of the equities on the event window
new_dr_equities_window = dr_data[symbol][start_idx:end_idx]
new_dr_equities_window.index = self.dr_equities_window.index
self.dr_equities_window[col_name] = new_dr_equities_window
# 1.4 Market on the event window: self.market_window
new_market_window = market[self.field][start_idx:end_idx]
new_market_window.index = self.market_window.index
self.market_window[col_name] = new_market_window
# Daily return of the market on the event window
new_dr_market_window = dr_market[start_idx:end_idx]
new_dr_market_window.index = self.dr_market_window.index
self.dr_market_window[col_name] = new_dr_market_window
# 3. Calculate the linear regression -> expected return
self.reg_estimation = pd.DataFrame(
index=self.dr_market_estimation.columns, columns=["Intercept", "Slope", "Std Error"]
)
self.er = pd.DataFrame(index=self.dr_market_window.index, columns=self.dr_market_window.columns)
# For each column (event) on the estimation period
for col in self.dr_market_estimation.columns:
# 3.1 Calculate the regression
x = self.dr_market_estimation[col]
y = self.dr_equities_estimation[col]
slope, intercept, r_value, p_value, slope_std_error = stats.linregress(x, y)
self.reg_estimation["Slope"][col] = slope
self.reg_estimation["Intercept"][col] = intercept
self.reg_estimation["Std Error"][col] = slope_std_error
# 3.2 Calculate the expected return of each date using the regression
self.er[col] = intercept + self.dr_market_window[col] * slope
# 4. Final results
self.er.columns.name = "Expected return"
self.mean_er = self.er.mean(axis=1)
self.mean_er.name = "Mean ER"
self.std_er = self.er.std(axis=1)
self.std_er.name = "Std ER"
self.ar = self.dr_equities_window - self.er
self.ar.columns.name = "Abnormal return"
self.mean_ar = self.ar.mean(axis=1)
self.mean_ar.name = "Mean AR"
self.std_ar = self.ar.std(axis=1)
self.std_ar.name = "Std AR"
self.car = self.ar.apply(np.cumsum)
self.car.columns.name = "Cum Abnormal Return"
self.mean_car = self.car.mean(axis=1)
self.mean_car.name = "Mean CAR"
self.std_car = self.car.std(axis=1)
self.mean_car.name = "Mean CAR"
plt.show() # Question 9 W0 = 100000 R = stats.norm(loc=0.04, scale=0.09) print(9, W0 * R.ppf(0.01), W0 * R.ppf(0.05)) # Question 10 W0 = 100000 r = stats.norm(loc=0.04, scale=0.09) r_1, r_5 = r.ppf(0.01), r.ppf(0.05) R_1, R_5 = math.exp(r_1) - 1, math.exp(r_5) - 1 print(10, W0 * R_1, W0 * R_5) # Question 11 q11_amzn = Calculator.ret([38.23, 41.29]) # q11_amzn = Calculator.R(PV=38.23, FV=41.29) # Other option q11_cost = Calculator.ret([41.11, 41.74]) print(11, q11_amzn, q11_cost) # Question 12 q12_amzn = Calculator.ret([38.23, 41.29], cc=True) q12_cost = Calculator.ret([41.11, 41.74], cc=True) print(12, q12_amzn, q12_cost) # Question 13 q13_amzn = Calculator.ret([38.23, 41.29], dividends=[0, 0.1]) print(13, q13_amzn, 0.1 / 41.29) print(13, (41.29 + 0.1) / 38.23 - 1, 0.1 / 41.29) # Question 14
from datetime import datetime
import matplotlib.pyplot as plt
from finance.utils import Calculator
from finance.sim import MarketSimulator
# from finance.utils import DataAccess
# DataAccess.path = 'data'
sim = MarketSimulator()
sim.initial_cash = 1000000
sim.load_trades("MarketSimulator_orders.csv")
sim.simulate()
print(sim.portfolio[0:10])
print('Total Return:', Calculator.ret(sim.portfolio))
print(Calculator.sharpe_ratio(sim.portfolio))
sim.portfolio.plot()
# plt.grid(True)
plt.show()
data = [['December, 2004', 31.18], ['January, 2005', 27.00],
['February, 2005', 25.91], ['March, 2005', 25.83],
['April, 2005', 24.76], ['May, 2005', 27.40], ['June, 2005', 25.83],
['July, 2005', 26.27], ['August, 2005', 24.51],
['September, 2005', 25.05], ['October, 2005', 28.28],
['November, 2005', 30.45], ['December, 2005', 30.51]]
starbucks = pd.DataFrame(data, columns=['Date',
'Value']).set_index('Date')['Value']
'''
Question 1: Using the data in the table, what is the simple monthly return between the
end of December 2004 and the end of January 2005?
Ans: -13.40%
'''
q1 = Calculator.ret(starbucks, pos=1)
# q1 = Calculator.R(PV=data[0][1], FV=data[1][1]) # Other option
print(1, q1)
'''
Question 2: If you invested $10,000 in Starbucks at the end of December 2004, how much
would the investment be worth at the end of January 2005?
Ans: $8659.39
'''
q2 = Calculator.FV(PV=10000, R=q1)
print(2, q2)
'''
Question 3: Using the data in the table, what is the continuously compounded monthly
return between December 2004 and January 2005?
Ans: -14.39%
'''
q3 = Calculator.ret(starbucks, pos=1, cc=True)