def run_day_of_month_analysis(self, strat):
from pythalesians.economics.seasonality.seasonality import Seasonality
from pythalesians.timeseries.calcs.timeseriescalcs import TimeSeriesCalcs
tsc = TimeSeriesCalcs()
seas = Seasonality()
strat.construct_strategy()
pnl = strat.get_strategy_pnl()
# get seasonality by day of the month
pnl = pnl.resample('B').mean()
rets = tsc.calculate_returns(pnl)
bus_day = seas.bus_day_of_month_seasonality(rets, add_average = True)
# get seasonality by month
pnl = pnl.resample('BM').mean()
rets = tsc.calculate_returns(pnl)
month = seas.monthly_seasonality(rets)
self.logger.info("About to plot seasonality...")
gp = GraphProperties()
pf = PlotFactory()
# Plotting spot over day of month/month of year
gp.color = 'Blues'
gp.scale_factor = self.SCALE_FACTOR
gp.file_output = self.DUMP_PATH + strat.FINAL_STRATEGY + ' seasonality day of month.png'
gp.html_file_output = self.DUMP_PATH + strat.FINAL_STRATEGY + ' seasonality day of month.html'
gp.title = strat.FINAL_STRATEGY + ' day of month seasonality'
gp.display_legend = False
gp.color_2_series = [bus_day.columns[-1]]
gp.color_2 = ['red'] # red, pink
gp.linewidth_2 = 4
gp.linewidth_2_series = [bus_day.columns[-1]]
gp.y_axis_2_series = [bus_day.columns[-1]]
pf.plot_line_graph(bus_day, adapter = self.DEFAULT_PLOT_ENGINE, gp = gp)
gp = GraphProperties()
gp.scale_factor = self.SCALE_FACTOR
gp.file_output = self.DUMP_PATH + strat.FINAL_STRATEGY + ' seasonality month of year.png'
gp.html_file_output = self.DUMP_PATH + strat.FINAL_STRATEGY + ' seasonality month of year.html'
gp.title = strat.FINAL_STRATEGY + ' month of year seasonality'
pf.plot_line_graph(month, adapter = self.DEFAULT_PLOT_ENGINE, gp = gp)
return month
def plot_single_var_regression(self, y, x, y_variable_names, x_variable_names, statistic,
tag = 'stats',
title = None,
pretty_index = None, output_path = None,
scale_factor = Constants.plotfactory_scale_factor,
silent_plot = False,
shift=[0]):
if not(isinstance(statistic, list)):
statistic = [statistic]
# TODO optimise loop so that we are calculating each regression *once* at present calculating it
# for each statistic, which is redundant
for st in statistic:
stats_df = []
for sh in shift:
x_sh = x.shift(sh)
stats_temp = self.report_single_var_regression(y, x_sh, y_variable_names, x_variable_names, st,
pretty_index)
stats_temp.columns = [ x + "_" + str(sh) for x in stats_temp.columns]
stats_df.append(stats_temp)
stats_df = pandas.concat(stats_df, axis=1)
stats_df = stats_df.dropna(how='all')
if silent_plot: return stats_df
pf = PlotFactory()
gp = GraphProperties()
if title is None: title = statistic
gp.title = title
gp.display_legend = True
gp.scale_factor = scale_factor
# gp.color = ['red', 'blue', 'purple', 'gray', 'yellow', 'green', 'pink']
if output_path is not None:
gp.file_output = output_path + ' (' + tag + ' ' + st + ').png'
pf.plot_bar_graph(stats_df, adapter = 'pythalesians', gp = gp)
return stats_df
def create_graph_properties(self, title, file_add):
gp = GraphProperties()
gp.title = self.FINAL_STRATEGY + " " + title
gp.display_legend = True
gp.scale_factor = self.SCALE_FACTOR
if self.DEFAULT_PLOT_ENGINE != 'cufflinks':
gp.file_output = self.DUMP_PATH + self.FINAL_STRATEGY + ' (' + file_add + ') ' + str(gp.scale_factor) + '.png'
gp.html_file_output = self.DUMP_PATH + self.FINAL_STRATEGY + ' (' + file_add + ') ' + str(gp.scale_factor) + '.html'
try:
gp.silent_display = self.SILENT_DISPLAY
except: pass
return gp
df = ltsf.harvest_time_series(time_series_request)
df.columns = [x.replace('.close', '') for x in df.columns.values]
df = tsc.calculate_returns(df) * 100
df = df.dropna()
df_sorted = tsc.get_bottom_valued_sorted(df, "USDBRL", n = 20)
# df = tsc.get_top_valued_sorted(df, "USDBRL", n = 20) # get biggest up moves
# get values on day after
df2 = df.shift(-1)
df2 = df2.ix[df_sorted.index]
df2.columns = ['T+1']
df_sorted.columns = ['T']
df_sorted = df_sorted.join(df2)
df_sorted.index = [str(x.year) + '/' + str(x.month) + '/' + str(x.day) for x in df_sorted.index]
gp = GraphProperties()
gp.title = 'Largest daily falls in USDBRL'
gp.scale_factor = 3
gp.display_legend = True
gp.chart_type = 'bar'
gp.x_title = 'Dates'
gp.y_title = 'Pc'
gp.file_output = "usdbrl-biggest-downmoves.png"
pf = PlotFactory()
pf.plot_line_graph(df_sorted, adapter = 'pythalesians', gp=gp)
from pythalesians.economics.events.eventstudy import EventStudy
es = EventStudy()
# work out cumulative asset price moves moves over the event
df_event = es.get_intraday_moves_over_custom_event(df, df_event_times)
# create an average move
df_event['Avg'] = df_event.mean(axis=1)
# plotting spot over economic data event
gp = GraphProperties()
gp.scale_factor = 3
gp.title = 'USDJPY spot moves over recent NFP'
# plot in shades of blue (so earlier releases are lighter, later releases are darker)
gp.color = 'Blues'
gp.color_2 = []
gp.y_axis_2_series = []
gp.display_legend = False
# last release will be in red, average move in orange
gp.color_2_series = [df_event.columns[-2], df_event.columns[-1]]
gp.color_2 = ['red', 'orange'] # red, pink
gp.linewidth_2 = 2
gp.linewidth_2_series = gp.color_2_series
pf = PlotFactory()
pf.plot_line_graph(df_event * 100, adapter='pythalesians', gp=gp)
df_event_times.index = df_event_times.index.tz_localize(utc_time) # work in UTC time
from pythalesians.economics.events.eventstudy import EventStudy
es = EventStudy()
# work out cumulative asset price moves moves over the event
df_event = es.get_intraday_moves_over_custom_event(df, df_event_times)
# create an average move
df_event['Avg'] = df_event.mean(axis = 1)
# plotting spot over economic data event
gp = GraphProperties()
gp.scale_factor = 3
gp.title = 'USDJPY spot moves over recent NFP'
# plot in shades of blue (so earlier releases are lighter, later releases are darker)
gp.color = 'Blues'; gp.color_2 = []
gp.y_axis_2_series = []
gp.display_legend = False
# last release will be in red, average move in orange
gp.color_2_series = [df_event.columns[-2], df_event.columns[-1]]
gp.color_2 = ['red', 'orange'] # red, pink
gp.linewidth_2 = 2
gp.linewidth_2_series = gp.color_2_series
pf = PlotFactory()
pf.plot_line_graph(df_event * 100, adapter = 'pythalesians', gp = gp)
vendor_tickers = ['aapl', 'spy'], # ticker (Google)
vendor_fields = ['Close'], # which Bloomberg fields to download
cache_algo = 'internet_load_return') # how to return data
ltsf = LightTimeSeriesFactory()
tsc = TimeSeriesCalcs()
df = tsc.create_mult_index_from_prices(ltsf.harvest_time_series(time_series_request))
gp = GraphProperties()
gp.html_file_output = "output_data/apple.htm"
gp.title = "S&P500 vs Apple"
# plot first with PyThalesians and then Bokeh
# just needs 1 word to change
gp.display_legend = False
pf = PlotFactory()
pf.plot_generic_graph(df, type = 'line', adapter = 'pythalesians', gp = gp)
pf.plot_generic_graph(df, type = 'line', adapter = 'bokeh', gp = gp)
# test simple Bokeh bar charts - monthly returns over past 6 months
if True:
from datetime import timedelta
ltsf = LightTimeSeriesFactory()
end = datetime.datetime.utcnow()
start = end - timedelta(days=180)
tickers = ['S&P500', 'FTSE', 'Nikkei']
vendor_tickers = ['SPX Index', 'UKX Index', 'NKY Index']
short_dates = df[["EURUSDV1M", "USDJPYV1M"]]
long_dates = df[["EURUSDV1Y", "USDJPYV1Y"]]
short_dates, long_dates = short_dates.align(long_dates,
join='left',
axis=0)
slope = pandas.DataFrame(data=short_dates.values - long_dates.values,
index=short_dates.index,
columns=["EURUSDV1M-1Y", "USDJPYV1M-1Y"])
# resample fand calculate average over month
slope_monthly = slope.resample('M').mean()
slope_monthly.index = [
str(x.year) + '/' + str(x.month) for x in slope_monthly.index
]
pf = PlotFactory()
gp = GraphProperties()
gp.source = 'Thalesians/BBG'
gp.title = 'Vol slopes in EUR/USD and USD/JPY recently'
gp.scale_factor = 2
gp.display_legend = True
gp.chart_type = 'bar'
gp.x_title = 'Dates'
gp.y_title = 'Pc'
# plot using Cufflinks
pf.plot_bar_graph(slope_monthly, adapter='cufflinks', gp=gp)