def nyse_dates_advanced(self):
'''
Tests the dates between two dates with the lookBack and lookForward parameters
'''
# Test: with lookbackDays without lookforwardDays
start = datetime(2009, 1, 1)
end = datetime(2011, 1, 1)
dates = DateUtils.nyse_dates(start=start, end=end,
lookbackDays=10, lookforwardDays=0)
self.assertEquals(dates[0], datetime(2008, 12, 17))
self.assertEquals(dates[-1], datetime(2010, 12, 31))
# Test: without lookbackDays with lookforwardDays
start = datetime(2009, 1, 1)
end = datetime(2011, 1, 1)
dates = DateUtils.nyse_dates(start=start, end=end,
lookbackDays=0, lookforwardDays=10)
self.assertEquals(dates[0], datetime(2009, 1, 2))
self.assertEquals(dates[-1], datetime(2011, 1, 14))
# Test: with lookbackDays with lookforwardDays
start = datetime(2009, 1, 1)
end = datetime(2011, 1, 1)
dates = DateUtils.nyse_dates(start=start, end=end,
lookbackDays=10, lookforwardDays=10)
self.assertEquals(dates[0], datetime(2008, 12, 17))
self.assertEquals(dates[-1], datetime(2011, 1, 14))
def search(self, oneEventPerEquity=True, useCache=True, save=True):
self.oneEventPerEquity = oneEventPerEquity
# 1. Load the data if requested and available
self.matrix = self.data_access.load(self.generate_filename(),
'.evt_matrix')
if useCache and self.matrix is not None:
pass
else:
# 2. Data was not loaded
# 2.1 Get the dates, and Download/Import the data
nyse_dates = DateUtils.nyse_dates(start=self.start_date,
end=self.end_date)
data = self.data_access.get_data(self.symbols, nyse_dates[0],
nyse_dates[-1], self.field)
# Special case
if len(data.columns) == 1:
data.columns = self.symbols
# 2.2 Create and fill the matrix of events
data = data[self.start_date:self.end_date]
self.matrix = pd.DataFrame(index=data.index, columns=self.symbols)
for symbol in self.symbols:
i = 0
for item in data[symbol][1:]:
e = self.condition.function(i, item, data[symbol][1:])
if e:
self.matrix[symbol][i + 1] = 1
if oneEventPerEquity == True:
break
i = i + 1
# 3. Calculate other results and save if requested
# Reduce Matrix: Sum each row and columns: if is greater than 0 there is an event
self.matrix = self.matrix[self.matrix.fillna(value=0).sum(axis=1) > 0]
valid_cols = self.matrix.columns[self.matrix.fillna(value=0).sum(
axis=0) > 0].values
self.matrix = self.matrix[valid_cols]
# 3.2 Create list of events
self.list = pd.Series(index=self.matrix.index,
name='Equity',
dtype=str)
for idx, row in self.matrix.iterrows():
equity = row[row == 1].index[0]
self.list.ix[idx] = equity
# 3.3 Save
self.num_events = len(self.list)
if save:
self.data_access.save(self.matrix, self.generate_filename(),
'.evt_matrix')
def search(self, oneEventPerEquity=True, useCache=True, save=True):
self.oneEventPerEquity = oneEventPerEquity
# 1. Load the data if requested and available
self.matrix = self.data_access.load(self.generate_filename(), '.evt_matrix')
if useCache and self.matrix is not None:
pass
else:
# 2. Data was not loaded
# 2.1 Get the dates, and Download/Import the data
nyse_dates = DateUtils.nyse_dates(start=self.start_date, end=self.end_date)
data = self.data_access.get_data(self.symbols, nyse_dates[0], nyse_dates[-1], self.field)
# Special case
if len(data.columns) == 1:
data.columns = self.symbols
# 2.2 Create and fill the matrix of events
data = data[self.start_date:self.end_date]
self.matrix = pd.DataFrame(index=data.index, columns=self.symbols)
for symbol in self.symbols:
i = 0
for item in data[symbol][1:]:
e = self.condition.function(i, item, data[symbol][1:])
if e:
self.matrix[symbol][i+1] = 1
if oneEventPerEquity == True:
break
i = i + 1
# 3. Calculate other results and save if requested
# Reduce Matrix: Sum each row and columns: if is greater than 0 there is an event
self.matrix = self.matrix[self.matrix.fillna(value=0).sum(axis=1) > 0]
valid_cols = self.matrix.columns[self.matrix.fillna(value=0).sum(axis=0) > 0].values
self.matrix = self.matrix[valid_cols]
# 3.2 Create list of events
self.list = pd.Series(index=self.matrix.index, name='Equity')
for idx, row in self.matrix.iterrows():
equity = row[row == 1].index[0]
self.list.loc[idx] = equity
# 3.3 Save
self.num_events = len(self.list)
if save:
self.data_access.save(self.matrix, self.generate_filename(), '.evt_matrix')
from datetime import datetime from finance.utils import DateUtils all_dates = DateUtils.nyse_dates() print(all_dates) print(DateUtils.nyse_dates(start=datetime(2008,1,1))) index = DateUtils.search_closer_date(datetime(2009,1,1), all_dates) print(index, all_dates[index])
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'
def nyse_dates_basic(self):
'''
Tests the dates without the lookBack and lookForward parameters
'''
# We assume this works: because sometime today is not and open day
today = datetime(datetime.today().year, datetime.today().month, datetime.today().day)
dates = DateUtils.nyse_dates()
today = DateUtils.search_closer_date(today, dates)
today = dates[today]
# End of assumssion
# Test: Returns a list
dates = DateUtils.nyse_dates()
self.assertEquals(type(dates), list)
# Test: Returns a pd.Series if requested
dates = DateUtils.nyse_dates(series=True)
self.assertEquals(type(dates), pd.TimeSeries)
# Test: Default startdate is 2007-1-1
dates = DateUtils.nyse_dates()
ans = dates[0]
self.assertEquals(ans, datetime(2007,1,3))
# Test: Default enddate is today
ans = dates[-1]
self.assertEquals(ans, today)
# Test: Values: start date after 2007-1-1
start = datetime(2008, 1, 1)
# Test: returns list
dates = DateUtils.nyse_dates(start=start)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(2008, 1, 2))
self.assertEquals(dates[-1], today)
# Test: returns pd.Series
dates = DateUtils.nyse_dates(start=start, series=True)
self.assertEquals(type(dates), pd.TimeSeries)
self.assertEquals(dates[0], datetime(2008, 1, 2))
self.assertEquals(dates[-1], today)
# Test: Values: start date before 2007-1-1
start = datetime(1995, 1, 1)
# Test: with list
dates = DateUtils.nyse_dates(start=start)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(1995, 1, 3))
self.assertEquals(dates[-1], today)
# Test: with pd.Series
dates = DateUtils.nyse_dates(start=start, series=True)
self.assertEquals(type(dates), pd.TimeSeries)
self.assertEquals(dates[0], datetime(1995, 1, 3))
self.assertEquals(dates[-1], today)
# Test: end date after 2007-1-1
end = datetime(2009, 6, 6)
dates = DateUtils.nyse_dates(end=end)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(2007, 1, 3))
self.assertEquals(dates[-1], datetime(2009, 6, 5))
# Test: end date before 2007-1-1
end = datetime(2005, 6, 6)
dates = DateUtils.nyse_dates(end=end)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(1962, 7, 5))
self.assertEquals(dates[-1], datetime(2005, 6, 6))
# Test: Values and lenght between 2 dates - No. 1
start = datetime(2000, 1, 1)
end = datetime(2002, 1, 1)
# Test: with list
dates = DateUtils.nyse_dates(start=start, end=end)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(2000, 1, 3))
self.assertEquals(dates[-1], datetime(2001, 12, 31))
self.assertEquals(len(dates), 500)
# Test: with pd.Series
dates = DateUtils.nyse_dates(start=start, end=end, series=True)
self.assertEquals(type(dates), pd.TimeSeries)
self.assertEquals(dates[0], datetime(2000, 1, 3))
self.assertEquals(dates[-1], datetime(2001, 12, 31))
self.assertEquals(len(dates), 500)
# Test: Values and lenght between 2 dates - No. 2
start = datetime(2009, 1, 1)
end = datetime(2011, 1, 1)
# Test: Lenght: Section - list
dates = DateUtils.nyse_dates(start=start, end=end)
self.assertEquals(type(dates), list)
self.assertEquals(dates[0], datetime(2009, 1, 2))
self.assertEquals(dates[-1], datetime(2010, 12, 31))
self.assertEquals(len(dates), 504)
# Test: Lenght: Section - pd.Series
dates = DateUtils.nyse_dates(start=start, end=end, series=True)
self.assertEquals(type(dates), pd.TimeSeries)
self.assertEquals(dates[0], datetime(2009, 1, 2))
self.assertEquals(dates[-1], datetime(2010, 12, 31))
self.assertEquals(len(dates), 504)
from datetime import datetime from finance.utils import DateUtils all_dates = DateUtils.nyse_dates() print(all_dates) print(DateUtils.nyse_dates(start=datetime(2015,1,1))) index = DateUtils.search_closer_date(datetime(2017,1,1), all_dates) print(index, all_dates[index])