def _create_chart(self, df: QFDataFrame, title: str):
chart = LineChart()
# Place legend on bottom right corner of plot
legend = LegendDecoratorCustomPosition(
legend_placement=AxisLocation.LOWER_LEFT)
cmap = get_cmap("tab10", len(df.columns))
# iterate columns
for column, label, color_index in zip(df.columns, df.columns.values,
range(0, cmap.N)):
data = df.loc[:, column]
data_value_decorator = DataElementDecorator(
data, color=cmap(color_index))
chart.add_decorator(data_value_decorator)
legend.add_entry(data_value_decorator, label)
chart.add_decorator(
AxesFormatterDecorator(
x_major=DateFormatter(fmt=str(DateFormat.YEAR_DOT_MONTH)),
y_major=StrMethodFormatter("{x:.2f}"),
))
chart.add_decorator(AxesPositionDecorator(*self.axis_position))
chart.add_decorator(TitleDecorator(title))
chart.add_decorator(legend)
return chart
def __get_perf_chart(self, series_list, is_large_chart):
strategy = series_list[0].to_prices(
1) # the main strategy should be the first series
log_scale = True if strategy[
-1] > 10 else False # use log scale for returns above 1 000 %
if is_large_chart:
chart = LineChart(start_x=strategy.index[0],
end_x=strategy.index[-1],
log_scale=log_scale)
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
else:
chart = LineChart(log_scale=log_scale, rotate_x_axis=True)
line_decorator = HorizontalLineDecorator(1, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
legend = LegendDecorator()
for series in series_list:
strategy_tms = series.to_prices(1)
series_elem = DataElementDecorator(strategy_tms)
chart.add_decorator(series_elem)
legend.add_entry(series_elem, strategy_tms.name)
chart.add_decorator(legend)
title_decorator = TitleDecorator("Strategy Performance", key="title")
chart.add_decorator(title_decorator)
return chart
def _add_line_chart_element(self, series, title):
chart = self._get_line_chart(series, title)
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
chart.add_decorator(position_decorator)
self.document.add_element(ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _get_distribution_plot(self, data_series: SimpleReturnsSeries, title: str, bins: Union[int, str] = 50,
crop: bool = False):
colors = Chart.get_axes_colors()
if crop:
start_x = np.quantile(data_series, 0.01)
end_x = np.quantile(data_series, 0.99)
chart = HistogramChart(data_series, bins=bins, start_x=start_x, end_x=end_x)
else:
chart = HistogramChart(data_series, bins=bins)
# Only show whole numbers on the y-axis.
y_axis_locator = MaxNLocator(integer=True)
axes_locator_decorator = AxesLocatorDecorator(y_major=y_axis_locator, key="axes_locator")
chart.add_decorator(axes_locator_decorator)
# Add an average line.
avg_line = VerticalLineDecorator(data_series.mean(), color=colors[1],
key="average_line_decorator", linestyle="--", alpha=0.8)
chart.add_decorator(avg_line)
# Add a legend.
legend = LegendDecorator(key="legend_decorator")
legend.add_entry(avg_line, "Mean")
chart.add_decorator(legend)
# Add a title.
title_decorator = TitleDecorator(title, key="title")
chart.add_decorator(title_decorator)
chart.add_decorator(AxesLabelDecorator(title, "Occurrences"))
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
chart.add_decorator(position_decorator)
return chart
def _add_gini_coefficient_chart(self):
chart = LineChart(rotate_x_axis=False)
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
chart.add_decorator(position_decorator)
# Get the assets history
assets_history = self.backtest_result.portfolio.positions_history()
assets_history = assets_history.applymap(
lambda x: x.total_exposure if isinstance(x, BacktestPositionSummary) else 0)
def gini(group):
# Function computing the Gini coefficients for each row
group = group.abs()
ranks = group.rank(ascending=True)
mean_value = group.mean()
samples = group.size
group = group * (2 * ranks - samples - 1)
return group.sum() / (samples * samples * mean_value)
assets_history = assets_history.stack(dropna=False).groupby(level=0).apply(gini).to_frame(name="Gini "
"coefficient")
assets_history_decorator = DataElementDecorator(assets_history)
chart.add_decorator(assets_history_decorator)
# Add title
title_decorator = TitleDecorator("Concentration of assets - Gini coefficient")
chart.add_decorator(title_decorator)
self.document.add_element(ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_assets_number_in_portfolio_chart(self):
chart = LineChart(rotate_x_axis=False)
chart.add_decorator(AxesPositionDecorator(*self.full_image_axis_position))
legend = LegendDecorator(key="legend_decorator")
positions_history = self.backtest_result.portfolio.positions_history()
# Find all not NaN values (not NaN values indicate that the position was open for this contract at that time)
# and count their number for each row (for each of the dates)
number_of_contracts = positions_history.notna().sum(axis=1)
number_of_contracts_decorator = DataElementDecorator(number_of_contracts)
chart.add_decorator(number_of_contracts_decorator)
legend.add_entry(number_of_contracts_decorator, "Contracts")
# Group tickers by name and for each name and date check if there was at least one position open with any
# of the corresponding tickers. Finally sum all the assets that had a position open on a certain date.
number_of_assets = positions_history.groupby(by=lambda ticker: ticker.name, axis='columns') \
.apply(lambda x: x.notna().any(axis=1)).sum(axis=1)
number_of_assets_decorator = DataElementDecorator(number_of_assets)
chart.add_decorator(number_of_assets_decorator)
legend.add_entry(number_of_assets_decorator, "Assets")
chart.add_decorator(TitleDecorator("Number of assets in the portfolio"))
chart.add_decorator(legend)
chart.add_decorator(AxesLabelDecorator(y_label="Number of contracts / assets"))
self.document.add_element(ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_leverage_chart(self):
lev_chart = self._get_leverage_chart(self.leverage)
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
lev_chart.add_decorator(position_decorator)
self.document.add_element(
ChartElement(lev_chart, figsize=self.full_image_size,
dpi=self.dpi))
def _add_concentration_of_portfolio_chart(self, top_assets_numbers: tuple = (1, 5)):
chart = LineChart(rotate_x_axis=False)
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
chart.add_decorator(position_decorator)
# Define a legend
legend = LegendDecorator(key="legend_decorator")
# Add y label
label_decorator = AxesLabelDecorator(y_label="Mean total exposure of top assets")
chart.add_decorator(label_decorator)
# Add top asset contribution
positions_history = self.backtest_result.portfolio.positions_history()
if positions_history.empty:
raise ValueError("No positions found in positions history")
positions_history = positions_history.applymap(
lambda x: x.total_exposure if isinstance(x, BacktestPositionSummary) else 0)
# Map all the single contracts onto tickers (including future tickers) and take the maximal total exposure for
# each of the groups - in case if two contracts for a single asset will be included in the open positions in
# the portfolio at any point of time, only one (with higher total exposure) will be considered while generating
# the top assets plot
def contract_to_ticker(c: Contract):
return self.backtest_result.portfolio.contract_ticker_mapper. \
contract_to_ticker(c, strictly_to_specific_ticker=False)
assets_history = positions_history.rename(columns=contract_to_ticker)
assets_history = assets_history.groupby(level=0, axis=1).apply(func=(
lambda x: x.abs().max(axis=1).astype(float)
))
for assets_number in top_assets_numbers:
# For each date (row), find the top_assets largest assets and compute the mean value of their market value
top_assets_mean_values = assets_history.stack(dropna=False).groupby(level=0).apply(
lambda group: group.nlargest(assets_number).mean()
).resample('D').last()
# Divide the computed mean values by the portfolio value, for each of the dates
top_assets_percentage_value = top_assets_mean_values / self.backtest_result.portfolio.portfolio_eod_series()
concentration_top_asset = DataElementDecorator(top_assets_percentage_value)
chart.add_decorator(concentration_top_asset)
# Add to legend
legend.add_entry(concentration_top_asset, "TOP {} assets".format(assets_number))
# Add title
title_decorator = TitleDecorator("Concentration of assets")
chart.add_decorator(title_decorator)
# Add legend
chart.add_decorator(legend)
self.document.add_element(ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_cone_chart(self):
cone_chart = ConeChartOOS(self.strategy_series,
is_mean_return=self.is_mean_return,
is_sigma=self.is_sigma)
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
cone_chart.add_decorator(position_decorator)
chart_element = ChartElement(cone_chart, self.full_image_size, self.dpi, False)
self.document.add_element(chart_element)
def _add_leverage_chart(self):
lev_chart = self._get_leverage_chart(self.backtest_result.portfolio.leverage_series())
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
lev_chart.add_decorator(position_decorator)
# Add y label
label_decorator = AxesLabelDecorator(y_label="Leverage")
lev_chart.add_decorator(label_decorator)
self.document.add_element(ChartElement(lev_chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_rolling_alpha_and_beta(self, timeseries_list):
freq = timeseries_list[0].get_frequency()
timeseries_list = [
tms.dropna().to_simple_returns() for tms in timeseries_list
]
df = pd.concat(timeseries_list, axis=1).fillna(0)
rolling_window_len = int(freq.value / 2) # 6M rolling
step = round(freq.value / 6) # 2M shift
legend = LegendDecorator()
chart = LineChart(start_x=df.index[0], end_x=df.index[-1])
line_decorator = HorizontalLineDecorator(0, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
def alpha_function(df_in_window):
strategy_returns = df_in_window.iloc[:, 0]
benchmark_returns = df_in_window.iloc[:, 1]
beta, alpha, _, _, _ = stats.linregress(benchmark_returns,
strategy_returns)
return beta, alpha
rolling = df.rolling_time_window(rolling_window_len, step,
alpha_function)
rolling = pd.DataFrame([[b, a] for b, a in rolling.values],
columns=["beta", "alpha"],
index=rolling.index)
rolling_element = DataElementDecorator(rolling["beta"])
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, "beta")
rolling_element = DataElementDecorator(rolling["alpha"],
use_secondary_axes=True)
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, "alpha")
chart.add_decorator(legend)
chart.add_decorator(
AxesFormatterDecorator(use_secondary_axes=True,
y_major=PercentageFormatter(".1f")))
# modify axes position to make secondary scale visible
axes_position = list(self.full_image_axis_position)
axes_position[2] = axes_position[2] - 0.07
position_decorator = AxesPositionDecorator(*axes_position)
chart.add_decorator(position_decorator)
title_str = "Rolling alpha and beta [{} {} samples]".format(
rolling_window_len, freq)
title_decorator = TitleDecorator(title_str, key="title")
chart.add_decorator(title_decorator)
self.document.add_element(
ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_assets_number_in_portfolio_chart(self):
chart = LineChart(rotate_x_axis=False)
legend = LegendDecorator(key="legend_decorator")
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
positions_history = self.backtest_result.portfolio.positions_history()
# Find all not NaN values (not NaN values indicate that the position was open for this contract at that time)
# and count their number for each row (for each of the dates)
number_of_contracts = positions_history.notnull().sum(axis=1)
number_of_contracts_decorator = DataElementDecorator(
number_of_contracts)
chart.add_decorator(number_of_contracts_decorator)
legend.add_entry(number_of_contracts_decorator, "Contracts")
# Count number of assets in the portfolio (if on two contracts from same future family exist in the same time,
# e.g. during rolling day, in the portfolio, they are counted as one asset)
def contract_to_ticker(c: Contract):
return self.backtest_result.portfolio.contract_ticker_mapper. \
contract_to_ticker(c, strictly_to_specific_ticker=False)
assets_history = positions_history.rename(columns=contract_to_ticker)
assets_history = assets_history.groupby(level=0, axis=1).apply(func=(
# For each asset, group all of the corresponding columns (each of which corresponds to one contract),
# and check if at any given timestamp the "value" of any of the contracts was different than None - this
# indicates that at this point of time a position concerning the given asset was open in the portfolio
# (which in the resulting series will be denoted as 1, otherwise - 0, so that it will be possible to
# sum positions of all open assets at any given point of time)
lambda x: x.notna().any(axis=1).astype(int)))
number_of_assets = assets_history.sum(axis=1)
number_of_assets_decorator = DataElementDecorator(number_of_assets)
chart.add_decorator(number_of_assets_decorator)
legend.add_entry(number_of_assets_decorator, "Assets")
# Add title
title_decorator = TitleDecorator("Number of assets in the portfolio")
chart.add_decorator(title_decorator)
# Add legend
chart.add_decorator(legend)
# Add y label
label_decorator = AxesLabelDecorator(
y_label="Number of contracts / assets")
chart.add_decorator(label_decorator)
self.document.add_element(
ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _create_single_heat_map(self, title, result_df, min_v, max_v):
chart = HeatMapChart(data=result_df,
color_map=plt.get_cmap("coolwarm"),
min_value=min_v,
max_value=max_v)
chart.add_decorator(
AxisTickLabelsDecorator(labels=list(result_df.columns),
axis=Axis.X))
chart.add_decorator(
AxisTickLabelsDecorator(labels=list(reversed(result_df.index)),
axis=Axis.Y))
chart.add_decorator(ValuesAnnotations())
param_names = self._get_param_names()
chart.add_decorator(
AxesLabelDecorator(x_label=param_names[1], y_label=param_names[0]))
chart.add_decorator(TitleDecorator(title))
position_decorator = AxesPositionDecorator(*self.image_axis_position)
chart.add_decorator(position_decorator)
return chart
def _get_rolling_ret_and_vol_chart(self, timeseries):
freq = timeseries.get_frequency()
rolling_window_len = int(freq.value / 2) # 6M rolling
step = round(freq.value / 6) # 2M shift
tms = timeseries.to_prices(1)
chart = LineChart(start_x=tms.index[0], end_x=tms.index[-1])
line_decorator = HorizontalLineDecorator(0, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
legend = LegendDecorator()
def tot_return(window):
return PricesSeries(window).total_cumulative_return()
def volatility(window):
return get_volatility(PricesSeries(window), freq)
functions = [tot_return, volatility]
names = ['Rolling Return', 'Rolling Volatility']
for func, name in zip(functions, names):
rolling = tms.rolling_window(rolling_window_len, func, step=step)
rolling_element = DataElementDecorator(rolling)
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, name)
chart.add_decorator(legend)
chart.add_decorator(
AxesFormatterDecorator(y_major=PercentageFormatter(".0f")))
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
title_str = "Rolling Stats [{} {} samples]".format(
rolling_window_len, freq)
title_decorator = TitleDecorator(title_str, key="title")
chart.add_decorator(title_decorator)
return chart
def _add_rolling_chart(self):
days_rolling = int(252 / 2) # 6M rolling
step = round(days_rolling / 5)
strategy = self.strategy_series.to_prices(1)
chart = LineChart(start_x=strategy.index[0], end_x=strategy.index[-1])
line_decorator = HorizontalLineDecorator(0, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
legend = LegendDecorator()
def tot_return(window):
return PricesSeries(window).total_cumulative_return()
def volatility(window):
return get_volatility(PricesSeries(window), Frequency.DAILY)
functions = [tot_return, volatility]
names = ['Rolling Return', 'Rolling Volatility']
for func, name in zip(functions, names):
rolling = strategy.rolling_window(days_rolling, func, step=step)
rolling_element = DataElementDecorator(rolling)
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, name)
chart.add_decorator(legend)
chart.add_decorator(
AxesFormatterDecorator(y_major=PercentageFormatter(".0f")))
left, bottom, width, height = self.full_image_axis_position
position_decorator = AxesPositionDecorator(left, bottom, width, height)
chart.add_decorator(position_decorator)
title_decorator = TitleDecorator(
"Rolling Statistics [6 Months]".format(days_rolling), key="title")
chart.add_decorator(title_decorator)
self.document.add_element(
ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _get_rolling_chart(self, timeseries_list, rolling_function,
function_name):
freq = timeseries_list[0].get_frequency()
timeseries_list = [
tms.dropna().to_prices(1) for tms in timeseries_list
]
df = pd.concat(timeseries_list, axis=1).fillna(method='ffill')
rolling_window_len = int(freq.value / 2) # 6M rolling
step = round(freq.value / 6) # 2M shift
legend = LegendDecorator()
chart = LineChart(start_x=df.index[0], end_x=df.index[-1])
line_decorator = HorizontalLineDecorator(0, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
for _, tms in df.iteritems():
rolling = tms.rolling_window(rolling_window_len,
rolling_function,
step=step)
rolling_element = DataElementDecorator(rolling)
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, tms.name)
chart.add_decorator(legend)
chart.add_decorator(
AxesFormatterDecorator(y_major=PercentageFormatter(".0f")))
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
title_str = "{} - Rolling Stats [{} {} samples]".format(
function_name, rolling_window_len, freq)
title_decorator = TitleDecorator(title_str, key="title")
chart.add_decorator(title_decorator)
return chart
def _get_simulation_plot(self, scenarios_df: PricesDataFrame) -> Chart:
chart = LineChart(log_scale=True)
for _, scenario in scenarios_df.items():
data_element = DataElementDecorator(scenario, linewidth=0.5)
chart.add_decorator(data_element)
# Add a legend
legend = LegendDecorator(key="legend_decorator")
# Add Ensemble average
ensemble_avg = scenarios_df.mean(axis=1)
ensemble_avg_data_element = DataElementDecorator(ensemble_avg, color="#e1e5f4", linewidth=3)
chart.add_decorator(ensemble_avg_data_element)
legend.add_entry(ensemble_avg_data_element, "Ensemble average")
# Add Expectation (vol adjusted)
trade_returns = QFSeries(data=[trade.percentage_pnl for trade in self.trades])
std = trade_returns.std()
expectation_adj_series = np.ones(len(ensemble_avg)) * (trade_returns.mean() - 0.5 * std * std)
expectation_adj_series = SimpleReturnsSeries(data=expectation_adj_series, index=ensemble_avg.index)
expectation_adj_series = expectation_adj_series.to_prices()
data_element = DataElementDecorator(expectation_adj_series, color="#46474b", linewidth=2)
chart.add_decorator(data_element)
legend.add_entry(data_element, "Expectation (vol adjusted)")
# Add title
title_decorator = TitleDecorator("Monte Carlo Simulations (log scale)", key="title")
chart.add_decorator(title_decorator)
position_decorator = AxesPositionDecorator(*self.full_image_axis_position)
chart.add_decorator(position_decorator)
chart.add_decorator(legend)
return chart
def _get_rolling_chart(self, timeseries_list, rolling_function,
function_name):
days_rolling = int(BUSINESS_DAYS_PER_YEAR / 2) # 6M rolling
step = round(days_rolling / 5)
legend = LegendDecorator()
chart = None
for i, tms in enumerate(timeseries_list):
if i == 0:
chart = LineChart(start_x=tms.index[0], end_x=tms.index[-1])
line_decorator = HorizontalLineDecorator(0,
key="h_line",
linewidth=1)
chart.add_decorator(line_decorator)
tms = tms.to_prices(1)
rolling = tms.rolling_window(days_rolling,
rolling_function,
step=step)
rolling_element = DataElementDecorator(rolling)
chart.add_decorator(rolling_element)
legend.add_entry(rolling_element, tms.name)
chart.add_decorator(legend)
chart.add_decorator(
AxesFormatterDecorator(y_major=PercentageFormatter(".0f")))
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
title_str = "{} - Rolling Stats [{} days]".format(
function_name, days_rolling)
title_decorator = TitleDecorator(title_str, key="title")
chart.add_decorator(title_decorator)
return chart
def _add_concentration_of_portfolio_chart(self, top_assets_numbers: tuple = (1, 5)):
chart = LineChart(rotate_x_axis=False)
chart.add_decorator(AxesPositionDecorator(*self.full_image_axis_position))
chart.add_decorator(AxesLabelDecorator(y_label="Mean total exposure of top assets"))
chart.add_decorator(TitleDecorator("Concentration of assets"))
legend = LegendDecorator(key="legend_decorator")
chart.add_decorator(legend)
# Add top asset contribution
positions_history = self.backtest_result.portfolio.positions_history()
if positions_history.empty:
raise ValueError("No positions found in positions history")
positions_history = positions_history.applymap(
lambda x: x.total_exposure if isinstance(x, BacktestPositionSummary) else 0)
# Group all the tickers by their names and take the maximal total exposure for each of the groups - in case
# if two contracts for a single asset will be included in the open positions in the portfolio at any point of
# time, only one (with higher total exposure) will be considered while generating the top assets plot
assets_history = positions_history.groupby(by=lambda ticker: ticker.name, axis='columns').apply(
lambda x: x.abs().max(axis=1))
for assets_number in top_assets_numbers:
# For each date (row), find the top_assets largest assets and compute the mean value of their market value
top_assets_mean_values = assets_history.stack(dropna=False).groupby(level=0).apply(
lambda group: group.nlargest(assets_number).mean()
).resample('D').last()
# Divide the computed mean values by the portfolio value, for each of the dates
top_assets_percentage_value = top_assets_mean_values / self.backtest_result.portfolio.portfolio_eod_series()
concentration_top_asset = DataElementDecorator(top_assets_percentage_value)
chart.add_decorator(concentration_top_asset)
legend.add_entry(concentration_top_asset, "TOP {} assets".format(assets_number))
self.document.add_element(ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_relative_performance_chart(
self,
strategy_tms: QFSeries,
benchmark_tms: QFSeries,
chart_title: str = "Relative Performance",
legend_subtitle: str = "Strategy - Benchmark"):
diff = strategy_tms.to_simple_returns().subtract(
benchmark_tms.to_simple_returns(), fill_value=0)
diff = diff.to_prices(1) - 1
chart = LineChart(start_x=diff.index[0],
end_x=diff.index[-1],
log_scale=False)
position_decorator = AxesPositionDecorator(
*self.full_image_axis_position)
chart.add_decorator(position_decorator)
line_decorator = HorizontalLineDecorator(0, key="h_line", linewidth=1)
chart.add_decorator(line_decorator)
legend = LegendDecorator()
series_elem = DataElementDecorator(diff)
chart.add_decorator(series_elem)
legend.add_entry(series_elem, legend_subtitle)
chart.add_decorator(legend)
title_decorator = TitleDecorator(chart_title, key="title")
chart.add_decorator(title_decorator)
chart.add_decorator(
AxesFormatterDecorator(y_major=PercentageFormatter(".0f")))
fill_decorator = FillBetweenDecorator(diff)
chart.add_decorator(fill_decorator)
self.document.add_element(
ChartElement(chart, figsize=self.full_image_size, dpi=self.dpi))
def _add_axes_position_decorator(self, chart: Chart):
left, bottom, width, height = self.full_image_axis_position
position_decorator = AxesPositionDecorator(left, bottom, width, height)
chart.add_decorator(position_decorator)
def _add_line_plots(self, tickers: Sequence[Ticker]):
parameters_list = sorted(
self.backtest_evaluator.params_backtest_summary_elem_dict.keys())
title_to_plot = defaultdict(lambda: LineChart())
title_to_legend = defaultdict(
lambda: LegendDecorator(key="legend_decorator"))
for start_time, end_time in [
(self.backtest_summary.start_date, self.out_of_sample_start_date),
(self.out_of_sample_start_date, self.backtest_summary.end_date)
]:
results = []
for param_tuple in parameters_list:
trades_eval_result = self.backtest_evaluator.evaluate_params_for_tickers(
param_tuple, tickers, start_time, end_time)
results.append(trades_eval_result)
sqn_avg_nr_trades = DataElementDecorator(
[x.sqn_per_avg_nr_trades for x in results])
avg_nr_of_trades = DataElementDecorator(
[x.avg_nr_of_trades_1Y for x in results])
annualised_return = DataElementDecorator(
[x.annualised_return for x in results])
adjusted_start_time = min([x.start_date for x in results])
adjusted_end_time = max([x.end_date for x in results])
if adjusted_start_time >= adjusted_end_time:
adjusted_end_time = adjusted_start_time if adjusted_start_time <= self.backtest_summary.end_date \
else end_time
adjusted_start_time = start_time
title = "{} - {} ".format(adjusted_start_time.strftime("%Y-%m-%d"),
adjusted_end_time.strftime("%Y-%m-%d"))
title_to_plot["SQN (Arithmetic return) per year"].add_decorator(
sqn_avg_nr_trades)
title_to_legend["SQN (Arithmetic return) per year"].add_entry(
sqn_avg_nr_trades, title)
title_to_plot["Avg # trades 1Y"].add_decorator(avg_nr_of_trades)
title_to_legend["Avg # trades 1Y"].add_entry(
sqn_avg_nr_trades, title)
if len(tickers) == 1:
title_to_plot["Annualised return"].add_decorator(
annualised_return)
title_to_legend["Annualised return"].add_entry(
annualised_return, title)
tickers_used = "Many tickers" if len(tickers) > 1 else (
tickers[0].name)
for description, line_chart in title_to_plot.items():
self.document.add_element(
HeadingElement(3, "{} - {}".format(description, tickers_used)))
line_chart.add_decorator(
AxesLabelDecorator(x_label=self._get_param_names()[0],
y_label=title))
position_decorator = AxesPositionDecorator(
*self.image_axis_position)
line_chart.add_decorator(position_decorator)
legend = title_to_legend[description]
line_chart.add_decorator(legend)
self.document.add_element(
ChartElement(line_chart, figsize=self.full_image_size))
def _resize_chart(self, chart):
left, bottom, width, height = self.image_axis_position
position_decorator = AxesPositionDecorator(left, bottom, width, height)
chart.add_decorator(position_decorator)