def get_risk_contribution(cls, factors_rets: SimpleReturnsDataFrame,
weigths_of_assets: QFSeries,
portfolio_rets: SimpleReturnsSeries) -> QFSeries:
"""
Calculates risk contribution of different factors to the portfolio. Risk is defined as volatility.
Uses x-sigma-rho formula (MSCI Bara paper).
Parameters
----------
factors_rets
dataframe consisted of returns for different assets
weigths_of_assets
series of weights of each asset. It's indexed with names of assets.
portfolio_rets
return of the whole portfolio
Returns
-------
pandas.Series
Series of risk contributions (one for each asset) to the portfolio. It's indexed with names of assets.
"""
volatility_of_returns = factors_rets.std(axis=0)
correlation_asset_portfolio = factors_rets.apply(
lambda series: series.corr(portfolio_rets))
risk_contribution = weigths_of_assets * volatility_of_returns * correlation_asset_portfolio
normalized_risk_contribution_msci = risk_contribution / risk_contribution.sum(
)
return normalized_risk_contribution_msci
def setUp(self):
self.dates = pd.date_range(start='2015-05-13', periods=5)
self.column_names = ['a', 'b', 'c', 'd', 'e']
self.prices_values = [[1., 1., 1., 1, 1.], [2., 2., 2., 2., 2.],
[3., 3., 3., 3., 3.], [4., 4., 4., 4., 4.],
[5., 5., 5., 5., 5.]]
self.test_prices_df = PricesDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
self.log_returns_values = [
[0.693147, 0.693147, 0.693147, 0.693147, 0.693147],
[0.405465, 0.405465, 0.405465, 0.405465, 0.405465],
[0.287682, 0.287682, 0.287682, 0.287682, 0.287682],
[0.223144, 0.223144, 0.223144, 0.223144, 0.223144]
]
self.test_log_returns_df = LogReturnsDataFrame(
data=self.log_returns_values,
index=self.dates[1:],
columns=self.column_names)
self.simple_returns_values = [
[1.000000, 1.000000, 1.000000, 1.000000, 1.000000],
[0.500000, 0.500000, 0.500000, 0.500000, 0.500000],
[0.333333, 0.333333, 0.333333, 0.333333, 0.333333],
[0.250000, 0.250000, 0.250000, 0.250000, 0.250000]
]
self.test_simple_returns_df = SimpleReturnsDataFrame(
data=self.simple_returns_values,
index=self.dates[1:],
columns=self.column_names)
def setUp(self):
portfolio_rets = [0.01, 0.02, -0.03, 0.04, -0.05, 0.06]
asset_1_rets = [0.011, 0.035, -0.028, 0.039, -0.044, 0.061]
asset_2_rets = [0.02, 0.04, -0.06, 0.08, -0.1, 0.12]
dates = pd.date_range(start='2015-02-01', periods=6)
self.portfolio_tms = SimpleReturnsSeries(portfolio_rets, dates)
returns_array = np.array([asset_1_rets, asset_2_rets]).T
self.factors_df = SimpleReturnsDataFrame(data=returns_array, index=dates, columns=['a', 'b'])
def test_aggregate_by_year(self):
dates = pd.DatetimeIndex(['2015-06-01', '2015-12-30', '2016-01-01', '2016-05-01'])
test_dataframe = SimpleReturnsDataFrame(data=self.simple_returns_values, index=dates)
expected_aggregated_rets = [[2.000000, 2.000000, 2.000000, 2.000000, 2.000000],
[0.666666, 0.666666, 0.666666, 0.666666, 0.666666]]
expected_dataframe = SimpleReturnsDataFrame(data=expected_aggregated_rets,
index=pd.DatetimeIndex(['2015-12-31', '2016-12-31']))
actual_dataframe = test_dataframe.aggregate_by_year()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def get_analysed_tms_and_regressors(dates_span: int = 1000, num_of_regressors: int = 7,
start_date: datetime.datetime = str_to_date('2016-01-01'),
mean_return: float = 0.001, std_of_returns: float = 0.02,
a_coeff: float = -0.25, b_coeff: float = 1.25, intercept: float = 0.004)\
-> Tuple[SimpleReturnsSeries, SimpleReturnsDataFrame]:
"""
Creates a dataframe with simple returns of sample timeseries (regressors). Then creates a series which linearly
depends on regressors 'a' and 'b'.
"""
dates = pd.bdate_range(start=start_date, periods=dates_span)
regressors_names = generate_sample_column_names(
num_of_columns=num_of_regressors)
np.random.seed(
5
) # init random number generator with a fixed number, so that results are always the same
regressors_data = np.random.normal(mean_return, std_of_returns,
(dates_span, num_of_regressors))
regressors_df = SimpleReturnsDataFrame(data=regressors_data,
index=dates,
columns=regressors_names)
analyzed_data = a_coeff * regressors_data[:, 0] + b_coeff * regressors_data[:, 1] + \
np.random.normal(0, 0.02, dates_span) + intercept
analysed_tms = SimpleReturnsSeries(data=analyzed_data,
index=dates,
name='Fund')
return analysed_tms, regressors_df
def convert_dataframe_frequency(
dataframe: QFDataFrame,
frequency: Frequency) -> SimpleReturnsDataFrame:
"""
Converts each column in the dataframe to the specified frequency.
ValueError is raised when a column has a lower frequency than the one we are converting to.
"""
# Verify that all columns in the dataframe have a lower frequency.
data_frequencies = dataframe.get_frequency()
for column, col_frequency in data_frequencies.items():
if col_frequency < frequency:
raise ValueError(
"Column '{}' cannot be converted to '{}' frequency because its frequency is '{}'."
.format(column, frequency, col_frequency))
if frequency == Frequency.DAILY:
return dataframe.to_simple_returns()
filled_df = dataframe.to_prices().fillna(method="ffill")
new_columns = {}
for column in filled_df:
new_columns[column] = get_aggregate_returns(filled_df[column],
frequency)
return SimpleReturnsDataFrame(new_columns)
def setUp(self):
dates_span = 100
regressor_names = ['a', 'b', 'c']
dates = pd.date_range(start='2015-01-01', periods=dates_span, freq='D')
fund_returns_tms = SimpleReturnsSeries(
data=[i / 100 for i in range(1, dates_span + 1)], index=dates)
deviation = 0.005
fit_returns_tms = SimpleReturnsSeries(data=(fund_returns_tms.values +
deviation),
index=dates)
regressors_returns_df = SimpleReturnsDataFrame(data=np.array([
fund_returns_tms, fund_returns_tms + deviation,
fund_returns_tms - deviation
]).T,
index=dates,
columns=regressor_names)
coefficients = QFSeries(index=regressor_names, data=[1.0, 1.0, 1.0])
self.fund_returns_tms = fund_returns_tms
self.fit_returns_tms = fit_returns_tms
self.regressors_returns_df = regressors_returns_df
self.coefficients = coefficients
self.alpha = 0.005
def generate_random_paths(sample_len: int,
sample_size: int,
mean: float,
std: float,
leverage: float = 1.0):
""" Generates random paths.
Parameters
------------
sample_len: int
length of each path of data, equivalent to time
sample_size: int
Number of paths simulated
mean: float
mean simle return
std: float
standard deviation of returns
leverage: float
leverage used in the simulated investment process
Returns
-----------
SimpleReturnsDataFrame
indexed by steps with paths as columns
"""
mean = mean * leverage
std = std * leverage
time = np.arange(1, 1 + sample_len)
returns_vector = np.random.normal(loc=mean,
scale=std,
size=(sample_len * sample_size, 1))
returns = np.reshape(returns_vector, (sample_len, sample_size))
return SimpleReturnsDataFrame(data=returns, index=time)
def make_scenarios(self, trade_rets: Sequence[float], scenarios_length: int = 100, num_of_scenarios: int = 10000) \
-> SimpleReturnsDataFrame:
"""
Utility function to generate different trades scenarios, where each scenario is a series of returns for a given
investment strategy.
The scenarios of a given length are created by randomly choosing (with replacement) returns from the original
sequence of a Trade's returns. The result is the SimpleReturnsDataFrame which is indexed by the Trade's
ordinal number and has a scenario in each column.
Parameters
----------
trade_rets: Sequence[float]
sequence of floats which represent the returns on Trades performed by some investment strategy
scenarios_length: int
number of Trades which should simulated for each scenario
num_of_scenarios: int
number of scenarios which should be generated
Returns
-------
SimpleReturnsDataFrame
data frame of size scenarios_length (rows) by num_of_scenarios (columns). It contains float numbers.
"""
values = np.random.choice(trade_rets,
scenarios_length * num_of_scenarios)
values = np.reshape(values, (scenarios_length, num_of_scenarios))
return SimpleReturnsDataFrame(values)
def _calculate_box(
asset_returns_df: SimpleReturnsDataFrame) -> SimpleReturnsSeries:
portfolio = EqualRiskContributionPortfolio(asset_returns_df.cov())
weights = portfolio.get_weights()
portfolio_rets, _ = Portfolio.constant_weights(asset_returns_df,
weights)
return portfolio_rets
def drifting_weights(cls, assets_rets_df: SimpleReturnsDataFrame, weights: pd.Series) \
-> Tuple[SimpleReturnsSeries, QFDataFrame]:
"""
Calculates the time series of portfolio returns (given the initial weights of portfolio's assets).
Weights of assets change over time because there is no rebalancing.
The method also calculates the allocation matrix which shows what portfolio consists of on each date.
Parameters
----------
assets_rets_df
simple returns of assets which create the portfolio
weights
weights of assets which create the portfolio
Returns
-------
portfolio_rets_tms
timeseries of portfolio's returns
allocation_df
dataframe indexed with dates and showing allocations in time (one column per asset)
"""
assert len(weights) == assets_rets_df.num_of_columns
weights_sum = weights.sum()
if abs(weights_sum - 1.0) > cls.EPSILON:
cls.logger().warning(
"Sum of all weights is not equal to 1.0: sum(weights) = {:f}".
format(weights_sum))
# create a data frame with cumulative returns with a row of zeroes at the beginning
assets_prices_df = assets_rets_df.to_prices(
initial_prices=weights.values)
portfolio_total_value_tms = cast_series(assets_prices_df.sum(axis=1),
PricesSeries)
portfolio_rets = portfolio_total_value_tms.to_simple_returns()
portfolio_rets *= weights_sum # scale returns so that they correspond to the level of investment
# to get an allocation matrix one needs to divide each row of assets' prices by the cumulative
# portfolio return at that time
portfolio_total_values = portfolio_total_value_tms.values.reshape(
(-1, 1)) # make it a vertical vector
normalizing_factor = np.tile(portfolio_total_values,
(1, assets_prices_df.num_of_columns))
allocation_matrix = assets_prices_df.values / normalizing_factor
# to keep the correct level of investment values in allocation matrix need to be multiplied by the sum
# of weights
allocation_matrix *= weights_sum
allocation_matrix = allocation_matrix[:-1, :]
allocation_df = QFDataFrame(index=assets_rets_df.index.copy(),
columns=assets_rets_df.columns.copy(),
data=allocation_matrix)
return portfolio_rets, allocation_df
def _create_test_dataframe(cls):
values = [[np.nan, 0.0, 0.0, 0.0, 0.0], [1.0, np.nan, 1.0, 1.0, 1.0],
[2.0, np.nan, np.nan, 2.0, 2.0],
[3.0, 3.0, 3.0, np.nan, 3.0], [4.0, 4.0, 4.0, 4.0, 4.0],
[5.0, 5.0, 5.0, 5.0, 5.0]]
index = pd.date_range(start='2015-01-01', periods=6)
columns = ['a', 'b', 'c', 'd', 'e']
dataframe = SimpleReturnsDataFrame(data=values,
index=index,
columns=columns)
return dataframe
def test_proxy_using_values(self):
expected_values = [[0.0, 0.0, 0.0, 0.0], [1.0, 1.0, 1.0, 1.0],
[2.0, 0.0, 2.0, 2.0], [3.0, 3.0, 0.0, 3.0],
[4.0, 4.0, 4.0, 4.0], [5.0, 5.0, 5.0, 5.0]]
expected_columns = ['a', 'c', 'd', 'e']
expected_dates = self.test_dataframe.index.copy()
expected_dataframe = SimpleReturnsDataFrame(data=expected_values,
columns=expected_columns,
index=expected_dates)
self.data_cleaner.threshold = 0.2
actual_dataframe = self.data_cleaner.proxy_using_value(proxy_value=0.0)
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_proxy_using_regression(self):
expected_values = [[np.nan, 0.0, 0.0, 0.0], [1.0, 1.0, 1.0, 1.0],
[2.0, 2.0, 2.0, 2.0], [3.0, 3.0, 3.0, 3.0],
[4.0, 4.0, 4.0, 4.0], [5.0, 5.0, 5.0, 5.0]]
expected_columns = ['a', 'c', 'd', 'e']
expected_dates = self.test_dataframe.index.copy()
expected_dataframe = SimpleReturnsDataFrame(data=expected_values,
columns=expected_columns,
index=expected_dates)
self.data_cleaner.threshold = 0.2
actual_dataframe = self.data_cleaner.proxy_using_regression(
benchmark_tms=self.test_benchmark,
columns_type=SimpleReturnsSeries)
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def form_different_is_and_oos_sets(
self, multiple_returns_timeseries: QFDataFrame) -> Tuple:
"""
Splits slices into two groups of equal sizes for all possible combinations.
Returns an list of tuples. 1st element of the tuple contains the In-Sample set and the 2nd one contains the
Out-Of-Sample set (both in form of QFDataFrames). Each tuple contains one of possible combinations
of slices forming IS and OOS sets. E.g. if there are 4 slices: A,B,C,D then one of possible
combinations is IS: A,B and OOS: C,D. The given example will be one of rows of the result list.
A and B (C and D) will be concatenated (so that there will be one timeseries AB),
and so will be one CD timeseries.
"""
# Drop all rows not aligned to num_of_slices. E.g if the df has 233 rows and the num_of_slices is 50,
# then last 33 rows of the original matrix will be dropped
rows_to_keep = (multiple_returns_timeseries.num_of_rows //
self.num_of_slices) * self.num_of_slices
aligned_df = multiple_returns_timeseries.iloc[:rows_to_keep]
if aligned_df.empty:
raise ValueError("Too few rows in the data frame.")
size_of_slices = aligned_df.num_of_rows // self.num_of_slices
df_slices = [
SimpleReturnsDataFrame(aligned_df.iloc[i:i + size_of_slices, :])
for i in range(0, len(aligned_df), size_of_slices)
]
# The index order of the original data frame should be preserved in both IS and OOS dfs
new_index = aligned_df.index[:len(aligned_df) // 2]
is_dfs = [
pd.concat(slices) for slices in itertools.combinations(
df_slices, self.num_of_slices // 2)
]
oos_dfs = [
aligned_df.loc[aligned_df.index.difference(df.index)]
for df in is_dfs
]
# Adjust the indices at the end, after the oos_dfs and is_dfs are already computed
for df in itertools.chain(is_dfs, oos_dfs):
df.index = new_index
return is_dfs, oos_dfs
def get_risk_contribution_optimised(
cls, assets_rets: SimpleReturnsDataFrame,
weights_of_assets: QFSeries) -> QFSeries:
"""
Calculates risk contribution of each asset of the portfolio.
Parameters
----------
assets_rets
returns of assets building the portfolio (each assets in a separate column)
weights_of_assets
Series of weights (one for each asset). It's indexed with names of assets.
Returns
-------
Series of risk contributions (one for each asset). It's indexed with names of assets
"""
assets_covariance = assets_rets.cov()
risk_contribution = cls._get_normalized_risk_contribution(
assets_covariance, weights_of_assets)
return risk_contribution
class TestDataFrames(TestCase):
def setUp(self):
self.dates = pd.date_range(start='2015-05-13', periods=5)
self.column_names = ['a', 'b', 'c', 'd', 'e']
self.prices_values = [[1, 1, 1, 1, 1], [2, 2, 2, 2,
2], [3, 3, 3, 3, 3],
[4, 4, 4, 4, 4], [5, 5, 5, 5, 5]]
self.test_prices_df = PricesDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
self.log_returns_values = [
[0.693147, 0.693147, 0.693147, 0.693147, 0.693147],
[0.405465, 0.405465, 0.405465, 0.405465, 0.405465],
[0.287682, 0.287682, 0.287682, 0.287682, 0.287682],
[0.223144, 0.223144, 0.223144, 0.223144, 0.223144]
]
self.test_log_returns_df = LogReturnsDataFrame(
data=self.log_returns_values,
index=self.dates[1:],
columns=self.column_names)
self.simple_returns_values = [
[1.000000, 1.000000, 1.000000, 1.000000, 1.000000],
[0.500000, 0.500000, 0.500000, 0.500000, 0.500000],
[0.333333, 0.333333, 0.333333, 0.333333, 0.333333],
[0.250000, 0.250000, 0.250000, 0.250000, 0.250000]
]
self.test_simple_returns_df = SimpleReturnsDataFrame(
data=self.simple_returns_values,
index=self.dates[1:],
columns=self.column_names)
def test_num_of_columns(self):
self.assertEqual(self.test_prices_df.num_of_columns, 5)
def test_prices_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_prices_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_simple_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_simple_returns_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_log_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_log_returns_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_log_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_log_returns_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_simple_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_simple_returns_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_prices_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_prices_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_log_returns_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_log_returns_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_simple_returns_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_simple_returns_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_prices_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_prices_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_min_max_normalized(self):
normalized_prices = [[0.00, 0.00, 0.00, 0.00, 0.00],
[0.25, 0.25, 0.25, 0.25, 0.25],
[0.50, 0.50, 0.50, 0.50, 0.50],
[0.75, 0.75, 0.75, 0.75, 0.75],
[1.00, 1.00, 1.00, 1.00, 1.00]]
expected_dataframe = PricesDataFrame(data=normalized_prices,
index=self.dates,
columns=self.column_names)
actual_dataframe = self.test_prices_df.min_max_normalized()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_exponential_average(self):
smoothed_values = [[1.000000, 1.000000, 1.000000, 1.000000, 1.000000],
[1.940000, 1.940000, 1.940000, 1.940000, 1.940000],
[2.936400, 2.936400, 2.936400, 2.936400, 2.936400],
[3.936184, 3.936184, 3.936184, 3.936184, 3.936184],
[4.936171, 4.936171, 4.936171, 4.936171, 4.936171]]
expected_dataframe = PricesDataFrame(data=smoothed_values,
index=self.dates,
columns=self.column_names)
actual_dataframe = self.test_prices_df.exponential_average()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_aggregate_by_year(self):
dates = pd.DatetimeIndex(
['2015-06-01', '2015-12-30', '2016-01-01', '2016-05-01'])
test_dataframe = SimpleReturnsDataFrame(
data=self.simple_returns_values, index=dates)
expected_aggregated_rets = [[
2.000000, 2.000000, 2.000000, 2.000000, 2.000000
], [0.666666, 0.666666, 0.666666, 0.666666, 0.666666]]
expected_dataframe = SimpleReturnsDataFrame(
data=expected_aggregated_rets,
index=pd.DatetimeIndex(['2015-12-31', '2016-12-31']))
actual_dataframe = test_dataframe.aggregate_by_year()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_rolling_time_window(self):
actual_result = self.test_prices_df.rolling_time_window(
window_length=2, step=1, func=lambda x: x.mean())
expected_values = [[1.5, 1.5, 1.5, 1.5,
1.5], [2.5, 2.5, 2.5, 2.5, 2.5],
[3.5, 3.5, 3.5, 3.5, 3.5],
[4.5, 4.5, 4.5, 4.5, 4.5]]
expected_index = self.test_prices_df.index[-4:].copy(deep=True)
expected_columns = ['a', 'b', 'c', 'd', 'e']
expected_result = QFDataFrame(expected_values, expected_index,
expected_columns)
assert_dataframes_equal(expected_result,
actual_result,
absolute_tolerance=1e-20)
actual_result = self.test_prices_df.rolling_time_window(
window_length=2, step=1, func=lambda x: x.mean().mean())
expected_values = [1.5, 2.5, 3.5, 4.5]
expected_index = self.test_prices_df.index[-4:].copy(deep=True)
expected_result = QFSeries(expected_values, expected_index)
assert_series_equal(expected_result,
actual_result,
absolute_tolerance=1e-20)
def test_total_cumulative_return(self):
actual_result = self.test_prices_df.total_cumulative_return()
expected_result = pd.Series(index=self.test_prices_df.columns,
data=[4.0, 4.0, 4.0, 4.0, 4.0])
assert_series_equal(expected_result, actual_result)
class TestRiskContributionAnalysis(TestCase):
def setUp(self):
portfolio_rets = [0.01, 0.02, -0.03, 0.04, -0.05, 0.06]
asset_1_rets = [0.011, 0.035, -0.028, 0.039, -0.044, 0.061]
asset_2_rets = [0.02, 0.04, -0.06, 0.08, -0.1, 0.12]
dates = pd.date_range(start='2015-02-01', periods=6)
self.portfolio_tms = SimpleReturnsSeries(portfolio_rets, dates)
returns_array = np.array([asset_1_rets, asset_2_rets]).T
self.factors_df = SimpleReturnsDataFrame(data=returns_array, index=dates, columns=['a', 'b'])
def test_get_risk_contribution(self):
weights = pd.Series([0.5, 0.5], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_risk_contribution(factors_rets=self.factors_df,
weigths_of_assets=weights,
portfolio_rets=self.portfolio_tms)
expected_result = pd.Series([0.32739478440485410, 0.672605215595146], index=self.factors_df.columns)
assert_series_equal(expected_result, actual_result)
weights = pd.Series([0.25, 0.75], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_risk_contribution(factors_rets=self.factors_df,
weigths_of_assets=weights,
portfolio_rets=self.portfolio_tms)
expected_result = pd.Series([0.139601453264340, 0.860398546735660], index=self.factors_df.columns)
assert_series_equal(expected_result, actual_result)
def test_get_risk_contribution_optimised(self):
weights = pd.Series([0.5, 0.5], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_risk_contribution_optimised(assets_rets=self.factors_df,
weights_of_assets=weights)
expected_result = pd.Series([0.328845104104390, 0.671154895895610], index=self.factors_df.columns)
assert_series_equal(expected_result, actual_result)
weights = pd.Series([0.25, 0.75], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_risk_contribution_optimised(assets_rets=self.factors_df,
weights_of_assets=weights)
expected_result = pd.Series([0.139939367445589, 0.860060632554411], index=self.factors_df.columns)
assert_series_equal(expected_result, actual_result)
def test_get_distance_to_equal_risk_contrib(self):
factors_covariance = self.factors_df.cov()
weights = pd.Series([0.5, 0.5], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_distance_to_equal_risk_contrib(factors_covariance, weights)
expected_result = 0.342309791791
self.assertAlmostEqual(actual_result, expected_result, places=10)
weights = pd.Series([0.25, 0.75], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.get_distance_to_equal_risk_contrib(factors_covariance, weights)
expected_result = 0.72012126510882146
self.assertAlmostEqual(actual_result, expected_result, places=10)
def test_is_equal_risk_contribution(self):
asset_a_tms = self.factors_df.loc[:, 'a']
factors_df = pd.concat((asset_a_tms, asset_a_tms), axis=1)
factors_df = cast_dataframe(factors_df, SimpleReturnsDataFrame)
factors_df.columns = ['a', 'b']
factors_covariance = factors_df.cov()
weights = pd.Series([0.25, 0.75], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.is_equal_risk_contribution(factors_covariance, weights)
self.assertFalse(actual_result)
weights = pd.Series([0.5, 0.5], index=self.factors_df.columns)
actual_result = RiskContributionAnalysis.is_equal_risk_contribution(factors_covariance, weights)
self.assertTrue(actual_result)
class TestDataFrames(TestCase):
def setUp(self):
self.dates = pd.date_range(start='2015-05-13', periods=5)
self.column_names = ['a', 'b', 'c', 'd', 'e']
self.prices_values = [[1., 1., 1., 1, 1.], [2., 2., 2., 2., 2.],
[3., 3., 3., 3., 3.], [4., 4., 4., 4., 4.],
[5., 5., 5., 5., 5.]]
self.test_prices_df = PricesDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
self.log_returns_values = [
[0.693147, 0.693147, 0.693147, 0.693147, 0.693147],
[0.405465, 0.405465, 0.405465, 0.405465, 0.405465],
[0.287682, 0.287682, 0.287682, 0.287682, 0.287682],
[0.223144, 0.223144, 0.223144, 0.223144, 0.223144]
]
self.test_log_returns_df = LogReturnsDataFrame(
data=self.log_returns_values,
index=self.dates[1:],
columns=self.column_names)
self.simple_returns_values = [
[1.000000, 1.000000, 1.000000, 1.000000, 1.000000],
[0.500000, 0.500000, 0.500000, 0.500000, 0.500000],
[0.333333, 0.333333, 0.333333, 0.333333, 0.333333],
[0.250000, 0.250000, 0.250000, 0.250000, 0.250000]
]
self.test_simple_returns_df = SimpleReturnsDataFrame(
data=self.simple_returns_values,
index=self.dates[1:],
columns=self.column_names)
def test_num_of_columns(self):
self.assertEqual(self.test_prices_df.num_of_columns, 5)
def test_prices_dataframe_dtypes(self):
dtypes = self.test_prices_df.dtypes
self.assertEqual({dtype("float64")}, set(dtypes))
def test_log_returns_dataframe_dtypes(self):
dtypes = self.test_log_returns_df.dtypes
self.assertEqual({dtype("float64")}, set(dtypes))
def test_simple_returns_dataframe_dtypes(self):
dtypes = self.test_simple_returns_df.dtypes
self.assertEqual({dtype("float64")}, set(dtypes))
def test_prices_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_prices_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_simple_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_simple_returns_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_log_to_log_returns(self):
expected_dataframe = self.test_log_returns_df
actual_dataframe = self.test_log_returns_df.to_log_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_log_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_log_returns_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_simple_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_simple_returns_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_prices_to_simple_returns(self):
expected_dataframe = self.test_simple_returns_df
actual_dataframe = self.test_prices_df.to_simple_returns()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_log_returns_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_log_returns_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_simple_returns_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_simple_returns_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_prices_to_prices(self):
expected_dataframe = self.test_prices_df
actual_dataframe = self.test_prices_df.to_prices()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_min_max_normalized(self):
normalized_prices = [[0.00, 0.00, 0.00, 0.00, 0.00],
[0.25, 0.25, 0.25, 0.25, 0.25],
[0.50, 0.50, 0.50, 0.50, 0.50],
[0.75, 0.75, 0.75, 0.75, 0.75],
[1.00, 1.00, 1.00, 1.00, 1.00]]
expected_dataframe = PricesDataFrame(data=normalized_prices,
index=self.dates,
columns=self.column_names)
actual_dataframe = self.test_prices_df.min_max_normalized()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_exponential_average(self):
smoothed_values = [[1.000000, 1.000000, 1.000000, 1.000000, 1.000000],
[1.940000, 1.940000, 1.940000, 1.940000, 1.940000],
[2.936400, 2.936400, 2.936400, 2.936400, 2.936400],
[3.936184, 3.936184, 3.936184, 3.936184, 3.936184],
[4.936171, 4.936171, 4.936171, 4.936171, 4.936171]]
expected_dataframe = PricesDataFrame(data=smoothed_values,
index=self.dates,
columns=self.column_names)
actual_dataframe = self.test_prices_df.exponential_average()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_aggregate_by_year(self):
dates = pd.DatetimeIndex(
['2015-06-01', '2015-12-30', '2016-01-01', '2016-05-01'])
test_dataframe = SimpleReturnsDataFrame(
data=self.simple_returns_values, index=dates)
expected_aggregated_rets = [[
2.000000, 2.000000, 2.000000, 2.000000, 2.000000
], [0.666666, 0.666666, 0.666666, 0.666666, 0.666666]]
expected_dataframe = SimpleReturnsDataFrame(
data=expected_aggregated_rets,
index=pd.DatetimeIndex(['2015-12-31', '2016-12-31']))
actual_dataframe = test_dataframe.aggregate_by_year()
assert_dataframes_equal(expected_dataframe, actual_dataframe)
self.assertEqual({dtype("float64")}, set(actual_dataframe.dtypes))
def test_rolling_time_window(self):
actual_result = self.test_prices_df.rolling_time_window(
window_length=2, step=1, func=lambda x: x.mean())
expected_values = [[1.5, 1.5, 1.5, 1.5,
1.5], [2.5, 2.5, 2.5, 2.5, 2.5],
[3.5, 3.5, 3.5, 3.5, 3.5],
[4.5, 4.5, 4.5, 4.5, 4.5]]
expected_index = self.test_prices_df.index[-4:].copy(deep=True)
expected_columns = ['a', 'b', 'c', 'd', 'e']
expected_result = QFDataFrame(expected_values, expected_index,
expected_columns)
assert_dataframes_equal(expected_result,
actual_result,
absolute_tolerance=1e-20)
actual_result = self.test_prices_df.rolling_time_window(
window_length=2, step=1, func=lambda x: x.mean().mean())
expected_values = [1.5, 2.5, 3.5, 4.5]
expected_index = self.test_prices_df.index[-4:].copy(deep=True)
expected_result = QFSeries(expected_values, expected_index)
assert_series_equal(expected_result,
actual_result,
absolute_tolerance=1e-20)
self.assertEqual(dtype("float64"), actual_result.dtypes)
def test_total_cumulative_return(self):
actual_result = self.test_prices_df.total_cumulative_return()
expected_result = PricesSeries(index=self.test_prices_df.columns,
data=[4.0, 4.0, 4.0, 4.0, 4.0])
assert_series_equal(expected_result, actual_result)
self.assertEqual(dtype("float64"), actual_result.dtypes)
def test_stats_functions(self):
qf_df = QFDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
max_qf_df = qf_df.max()
expected_max = QFSeries([5, 5, 5, 5, 5],
index=['a', 'b', 'c', 'd', 'e'])
self.assertEqual(type(max_qf_df), QFSeries)
assert_series_equal(max_qf_df, expected_max)
self.assertEqual(dtype("float64"), max_qf_df.dtypes)
def test_squeeze(self):
qf_df = QFDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
self.assertEqual(type(qf_df[['a']]), QFDataFrame)
self.assertEqual({dtype("float64")}, set(qf_df[['a']].dtypes))
self.assertEqual(type(qf_df[['a']].squeeze()), QFSeries)
self.assertEqual(dtype("float64"), qf_df[['a']].squeeze().dtypes)
self.assertEqual(type(qf_df[['a', 'b']].squeeze()), QFDataFrame)
self.assertEqual({dtype("float64")},
set(qf_df[['a', 'b']].squeeze().dtypes))
self.assertEqual(type(qf_df.iloc[[0]]), QFDataFrame)
self.assertEqual({dtype("float64")}, set(qf_df.iloc[[0]].dtypes))
self.assertEqual(type(qf_df.iloc[[0]].squeeze()), QFSeries)
self.assertEqual("float64", qf_df.iloc[[0]].squeeze().dtypes)
def test_concat(self):
full_df = QFDataFrame(data=self.prices_values,
index=self.dates,
columns=self.column_names)
# Concatenate along index (axis = 0)
number_of_rows = len(full_df)
half_df = full_df.iloc[:number_of_rows // 2]
second_half_df = full_df.iloc[number_of_rows // 2:]
concatenated_df = pd.concat([half_df, second_half_df])
self.assertEqual(type(concatenated_df), QFDataFrame)
self.assertEqual({dtype("float64")}, set(concatenated_df.dtypes))
assert_dataframes_equal(concatenated_df, full_df)
# Concatenate along columns (axis = 1)
number_of_columns = full_df.num_of_columns
half_df = full_df.loc[:, full_df.columns[:number_of_columns // 2]]
second_half_df = full_df.loc[:,
full_df.columns[number_of_columns // 2:]]
concatenated_df = pd.concat([half_df, second_half_df], axis=1)
self.assertEqual(type(concatenated_df), QFDataFrame)
self.assertEqual({dtype("float64")}, set(concatenated_df.dtypes))
assert_dataframes_equal(concatenated_df, full_df)
def test_concat_series(self):
index = [1, 2, 3]
series_1 = QFSeries(data=[17., 15., 16.], index=index)
series_2 = QFSeries(data=[18., 19., 20.], index=index)
df = pd.concat([series_1, series_2], axis=1)
self.assertEqual(type(df), QFDataFrame)
self.assertEqual({s.dtypes
for s in [series_1, series_2]}, set(df.dtypes))
series = pd.concat([series_1, series_2], axis=0)
self.assertEqual(type(series), QFSeries)
self.assertEqual("float64", series.dtypes)
self.assertEqual({s.dtypes
for s in [series_1, series_2]}, {series.dtypes})