Python genutils.str2Bool函数代码示例

    def _use_fixed_weights(self):
        if str2Bool(self.parent.config.use_forecast_scale_estimates):
            fixed_flavour = True
        else:
            fixed_flavour = False

        return fixed_flavour

def forecast_scalar(cs_forecasts, window=250000, min_periods=500, backfill=True):
    """
    Work out the scaling factor for xcross such that T*x has an abs value of 10 (or whatever the average absolute forecast is)

    :param cs_forecasts: forecasts, cross sectionally
    :type cs_forecasts: pd.DataFrame TxN

    :param span:
    :type span: int

    :param min_periods:


    :returns: pd.DataFrame
    """
    backfill = str2Bool(backfill)  # in yaml will come in as text
    # We don't allow this to be changed in config
    target_abs_forecast = system_defaults['average_absolute_forecast']

    # Take CS average first
    # we do this before we get the final TS average otherwise get jumps in
    # scalar when new markets introduced
    if cs_forecasts.shape[1] == 1:
        x = cs_forecasts.abs().iloc[:, 0]
    else:
        x = cs_forecasts.ffill().abs().median(axis=1)

    # now the TS
    avg_abs_value = x.rolling(window=window, min_periods=min_periods).mean()
    scaling_factor = target_abs_forecast / avg_abs_value

    if backfill:
        scaling_factor = scaling_factor.fillna(method="bfill")

    return scaling_factor

    def __init__(self,  log=logtoscreen("optimiser"), frequency="W", date_method="expanding", 
                         rollyears=20, method="bootstrap", cleaning=True, 
                         cost_multiplier=1.0, apply_cost_weight=True, 
                         ann_target_SR=TARGET_ANN_SR, equalise_gross=False,
                         **passed_params):
                
        cleaning=str2Bool(cleaning)
        optimise_params=copy(passed_params)
        ann_dict=dict(D=BUSINESS_DAYS_IN_YEAR, W=WEEKS_IN_YEAR, M=MONTHS_IN_YEAR, Y=1.0)
        annualisation=ann_dict.get(frequency, 1.0)
        period_target_SR=ann_target_SR/(annualisation**.5)        
        moments_estimator=momentsEstimator(optimise_params, annualisation,  ann_target_SR)
        optimiser=optimiserWithParams(method, optimise_params, moments_estimator)

        setattr(self, "optimiser", optimiser)
        setattr(self, "log", log)
        setattr(self, "frequency", frequency)
        setattr(self, "method", method)
        setattr(self, "equalise_gross", equalise_gross)
        setattr(self, "cost_multiplier", cost_multiplier)
        setattr(self, "annualisation", annualisation)
        setattr(self, "period_target_SR", period_target_SR)
        setattr(self, "date_method", date_method)
        setattr(self, "rollyears", rollyears)
        setattr(self, "cleaning", cleaning)
        setattr(self, "apply_cost_weight", apply_cost_weight)

    def forecast_turnover(self, instrument_code, rule_variation_name):
        """
        Get the annualised turnover for a forecast/rule combination

        :param instrument_code: instrument to get values for
        :type instrument_code: str

        :param rule_variation_name: rule to get values for
        :type rule_variation_name: str

        :returns: float


        """

        use_pooled_turnover = str2Bool(
            self.parent.config.forecast_cost_estimates['use_pooled_turnover'])

        if use_pooled_turnover:
            instrument_code_list = self.has_same_rules_as_code(instrument_code)
        else:
            instrument_code_list = [instrument_code]

        turnover_for_SR = self.forecast_turnover_for_list(
            instrument_code_list, rule_variation_name)

        return turnover_for_SR

def forecast_scalar(xcross, window=250000, min_periods=500, backfill=True):
    """
    Work out the scaling factor for xcross such that T*x has an abs value of 10
    
    :param x: 
    :type x: pd.DataFrame TxN
    
    :param span:
    :type span: int
    
    :param min_periods:
    
    
    :returns: pd.DataFrame 
    """
    backfill=str2Bool(backfill) ## in yaml will come in as text
    ##We don't allow this to be changed in config
    target_abs_forecast = system_defaults['average_absolute_forecast']

    ## Take CS average first
    ## we do this before we get the final TS average otherwise get jumps in scalar
    if xcross.shape[1]==1:
        x=xcross.abs().iloc[:,0]
    else:
        x=xcross.ffill().abs().median(axis=1)
    
    ## now the TS 
    avg_abs_value=pd.rolling_mean(x, window=window, min_periods=min_periods)
    scaling_factor=target_abs_forecast/avg_abs_value

    
    if backfill:
        scaling_factor=scaling_factor.fillna(method="bfill")

    return scaling_factor

def correlation_single_period(data_for_estimate,
                              using_exponent=True, min_periods=20, ew_lookback=250,
                              floor_at_zero=True):
    """
    We generate a correlation from eithier a pd.DataFrame, or a list of them if we're pooling

    It's important that forward filling, or index / ffill / diff has been done before we begin

    also that we're on the right time frame, eg weekly if that's what we're doing

    :param data_for_estimate: Data to get correlations from
    :type data_for_estimate: pd.DataFrame

    :param using_exponent: Should we use exponential weighting?
    :type using_exponent: bool

    :param ew_lookback: Lookback, in periods, for exp. weighting
    :type ew_lookback: int

    :param min_periods: Minimum periods before we get a correlation
    :type min_periods: int

    :param floor_at_zero: remove negative correlations before proceeding
    :type floor_at_zero: bool or str

    :returns: 2-dim square np.array


    """
    # These may come from config as str
    using_exponent = str2Bool(using_exponent)

    if using_exponent:
        # If we stack there will be duplicate dates
        # So we massage the span so it's correct
        # This assumes the index is at least daily and on same timestamp
        # This is an artifact of how we prepare the data
        dindex = data_for_estimate.index
        dlenadj = float(len(dindex)) / len(set(list(dindex)))
        # Usual use for IDM, FDM calculation when whole data set is used
        corrmat = pd.ewmcorr(
            data_for_estimate,
            span=int(
                ew_lookback *
                dlenadj),
            min_periods=min_periods)

        # only want the final one
        corrmat = corrmat.values[-1]
    else:
        # Use normal correlation
        # Usual use for bootstrapping when only have sub sample
        corrmat = data_for_estimate.corr(min_periods=min_periods)
        corrmat = corrmat.values

    if floor_at_zero:
        corrmat[corrmat < 0] = 0.0

    return corrmat

 def calculation_of_raw_forecast_weights(self, instrument_code):
     """
     returns the forecast weights for a given instrument code
     
     Checks to see if there are pooled forecasts
     """
     
     ## Get some useful stuff from the config
     ## do we pool our estimation?
     pooling_returns = str2Bool(self.parent.config.forecast_weight_estimate["pool_gross_returns"])
     pooling_costs = str2Bool(self.parent.config.forecast_cost_estimates["use_pooled_costs"])
     
     if (pooling_returns & pooling_costs):
         return self.calculation_of_pooled_raw_forecast_weights(instrument_code)
     else:
         ## could still be using pooled returns 
         return self.calculation_of_raw_forecast_weights_for_instrument(instrument_code)

    def __init__(self,
                 data_as_df,
                 length_of_data=1,
                 ew_lookback=250,
                 boring_offdiag=0.99,
                 cleaning=True,
                 floor_at_zero=True,
                 **kwargs):
        """
        Create an object to calculate correlations

        We set up one of these with a set of data and parameters, and then call repeatedly

        :param data_as_df: The dataframe of correlations
        :param boring_offdiag: The off diagonal element to put into the matrix if data is absent
        :param cleaning: Should we include fake values in the matrix so we don't need a warm up period?
        :param floor_at_zero: Should we remove negative correlations?
        :param ew_lookback: Lookback to use if exponential calculation used
        :param length_of_data: Original length of data passed in (to correct for stacking of dataframe)

        :return: np.array of correlation matrix
        """

        self.cleaning = str2Bool(cleaning)
        self.floor_at_zero = str2Bool(floor_at_zero)

        ## correct the lookback if we're jamming stuff together
        self.ew_lookback_corrected = length_of_data * ew_lookback

        size = data_as_df.shape[1]
        self.corr_with_no_data = boring_corr_matrix(size, offdiag=np.nan)
        self.corr_for_cleaning = boring_corr_matrix(
            size, offdiag=boring_offdiag)

        self.kwargs = kwargs
        self.data_as_df = data_as_df

    def get_costs(self, instrument_code):
        """
        Get the relevant kinds of cost for an instrument

        :param instrument_code: instrument to value for
        :type instrument_code: str

        :returns: 2 tuple
        """

        use_SR_costs = str2Bool(self.parent.config.use_SR_costs)

        if use_SR_costs:
            return (self.get_SR_cost(instrument_code), None)
        else:
            return (None, self.get_cash_costs(instrument_code))

def correlation_calculator(data_for_estimate,
                           using_exponent=True,
                           min_periods=20,
                           ew_lookback=250):
    """
    We generate a correlation from a pd.DataFrame, which could have been stacked up

    :param data_for_estimate: simData to get correlations from
    :type data_for_estimate: pd.DataFrame

    :param using_exponent: Should we use exponential weighting? If not every item is weighted equally
    :type using_exponent: bool

    :param ew_lookback: Lookback, in periods, for exp. weighting
    :type ew_lookback: int

    :param min_periods: Minimum periods before we get a correlation
    :type min_periods: int

    :returns: 2-dim square np.array

    """
    # These may come from config as str

    using_exponent = str2Bool(using_exponent)

    if using_exponent:
        # If we have stacked there will be duplicate dates
        # So we massage the span so it's correct
        # This assumes the index is at least daily and on same timestamp
        # This is an artifact of how we prepare the data
        # Usual use for IDM, FDM calculation when whole data set is used
        corrmat = data_for_estimate.ewm(
            span=ew_lookback, min_periods=min_periods).corr(pairwise=True)

        number_of_items=data_for_estimate.shape[1]
        # only want the final one
        corrmat = corrmat.iloc[-number_of_items:,].values
    else:
        # Use normal correlation
        # Usual use for bootstrapping when only have sub sample
        corrmat = data_for_estimate.corr(min_periods=min_periods)
        corrmat = corrmat.values

    return corrmat

    def _system_init(self, system):
        """
        When we add this stage object to a system, this code will be run
        
        It will determine if we use an estimate or a fixed class of object
        """
        if str2Bool(system.config.use_instrument_weight_estimates):
            fixed_flavour=False
        else:
            fixed_flavour=True    
        
        if fixed_flavour:
            self.__class__= PortfoliosFixed
            self.__init__()
            setattr(self, "parent", system)

        else:
            self.__class__= PortfoliosEstimated
            self.__init__()
            setattr(self, "parent", system)

    def _system_init(self, system):
        """
        When we add this stage object to a system, this code will be run
        
        It will determine if we use an estimate or a fixed class of object
        """
        if str2Bool(system.config.use_forecast_scale_estimates):
            fixed_flavour=False
        else:
            fixed_flavour=True    
        
        if fixed_flavour:
            self.__class__=ForecastScaleCapFixed
            self.__init__()
            setattr(self, "parent", system)

        else:
            self.__class__=ForecastScaleCapEstimated
            self.__init__()
            setattr(self, "parent", system)

    def __init__(self, data_gross, data_costs, log=logtoscreen("optimiser"), frequency="W", date_method="expanding", 
                         rollyears=20, fit_method="bootstrap", cleaning=True, equalise_gross=False,
                         cost_multiplier=1.0, apply_cost_weight=True, ceiling_cost_SR=0.13,
                         ann_target_SR=TARGET_ANN_SR,
                         **passed_params):
        
        """
    
        Optimise weights over some returns data
        
        :param data_gross: Returns data for gross returns
        :type data_gross: pd.DataFrame or list if pooling

        :param data_net: Returns data for costs
        :type data_net: pd.DataFrame or list if pooling
    
        :param frequency: Downsampling frequency. Must be "D", "W" or bigger
        :type frequency: str
    
        :param date_method: Method to pass to generate_fitting_dates 
        :type date_method: str
    
        :param roll_years: If date_method is "rolling", number of years in window
        :type roll_years: int
    
        :param fit_method: Method used for fitting, one of 'bootstrap', 'shrinkage', 'one_period'
        :type fit_method: str
    
        :param equalise_gross: Should we equalise expected gross returns so that only costs affect weightings?
        :type equalise_gross: bool

        :param cost_multiplier: Multiply costs by this number
        :type cost_multiplier: float

        :param apply_cost_weight: Should we adjust our weightings to reflect costs?
        :type apply_cost_weight: bool

        :param ceiling_cost_SR: What is the maximum SR cost beyond which I don't allocate to an asset. Set to 999 to avoid using.
        :type ceiling_cost_SR: float
    
        :param *_estimate_params: dicts of **kwargs to pass to moments estimation, and optimisation functions
        
        :returns: pd.DataFrame of weights
        """

        ## Because interaction of parameters is complex, display warnings         
        display_warnings(log, cost_multiplier, equalise_gross, apply_cost_weight, **passed_params)
        
        cleaning=str2Bool(cleaning)
        optimise_params=copy(passed_params)

        ## annualisation
        ann_dict=dict(D=BUSINESS_DAYS_IN_YEAR, W=WEEKS_IN_YEAR, M=MONTHS_IN_YEAR, Y=1.0)
        annualisation=ann_dict.get(frequency, 1.0)

        period_target_SR=ann_target_SR/(annualisation**.5)
        ceiling_cost_SR_period=ceiling_cost_SR/(annualisation**.5)
        
        ## A moments estimator works out the mean, vol, correlation
        ## Also stores annualisation factor and target SR (used for shrinkage and equalising)
        moments_estimator=momentsEstimator(optimise_params, annualisation,  ann_target_SR)

        ## The optimiser instance will do the optimation once we have the appropriate data
        optimiser=optimiserWithParams(optimise_params, moments_estimator)
    
    
        ## resample, indexing before and differencing after (returns, remember)
        data_gross = [data_item.cumsum().resample(frequency, how="last").diff() for
                       data_item in data_gross]
        
        data_costs = [data_item.cumsum().resample(frequency, how="last").diff() for
                      data_item in data_costs]

        ## stack de-pool pooled data    
        data_gross=df_from_list(data_gross)    
        data_costs=df_from_list(data_costs)    
        
        ## net gross and costs
        if equalise_gross:
            log.terse("Setting all gross returns to be identical - optimisation driven only by costs")
        if cost_multiplier!=1.0:
            log.terse("Using cost multiplier on optimisation of %.2f" % cost_multiplier)
        
        
        data = work_out_net(data_gross, data_costs, annualisation=annualisation,
                            equalise_gross=equalise_gross, cost_multiplier=cost_multiplier,
                            ceiling_cost_ann_SR=ceiling_cost_SR, 
                            period_target_SR=period_target_SR)
            
        fit_dates = generate_fitting_dates(data, date_method=date_method, rollyears=rollyears)
        setattr(self, "fit_dates", fit_dates)
    
        ## Now for each time period, estimate weights
        ## create a list of weight vectors
        weight_list=[]
        
        ## create a class object for each period
        opt_results=[]
        
        log.terse("Optimising...")
#.........这里部分代码省略.........

    def calculation_of_pooled_raw_forecast_weights(self, instrument_code):
        """
        Estimate the forecast weights for this instrument

        We store this intermediate step to expose the calculation object
        
        :param instrument_code:
        :type str:

        :returns: TxK pd.DataFrame containing weights, columns are trading rule variation names, T covers all
        """

        def _calculation_of_pooled_raw_forecast_weights(system, instrument_code_ref, this_stage, 
                                      codes_to_use, weighting_func,  **weighting_params):

            print(__file__ + ":" + str(inspect.getframeinfo(inspect.currentframe())[:3][1]) + ":" +"Calculating pooled raw forecast weights over instruments: %s" % instrument_code_ref)


            rule_list = self.apply_cost_weighting(instrument_code)

            weight_func=weighting_func(log=self.log.setup(call="weighting"), **weighting_params)
            if weight_func.need_data():
    
                ## returns a list of accountCurveGroups
                ## cost pooling will already have been applied

                pandl_forecasts=[this_stage.get_returns_for_optimisation(code)
                        for code in codes_to_use]
                
                ## have to decode these
                ## returns two lists of pd.DataFrames
                (pandl_forecasts_gross, pandl_forecasts_costs) = decompose_group_pandl(pandl_forecasts, pool_costs=True)

                ## The weighting function requires two lists of pd.DataFrames, one gross, one for costs
                
                weight_func.set_up_data(data_gross = pandl_forecasts_gross, data_costs = pandl_forecasts_costs)
            else:
                ## in the case of equal weights, don't need data
                
                forecasts = this_stage.get_all_forecasts(instrument_code, rule_list)
                weight_func.set_up_data(weight_matrix=forecasts)

            SR_cost_list = [this_stage.get_SR_cost_for_instrument_forecast(instrument_code, rule_variation_name)
                             for rule_variation_name in rule_list]
            
            weight_func.optimise(ann_SR_costs=SR_cost_list)

            return weight_func


        ## Get some useful stuff from the config
        weighting_params=copy(self.parent.config.forecast_weight_estimate)  

        ## do we pool our estimation?
        pooling_returns = str2Bool(weighting_params.pop("pool_gross_returns"))
        pooling_costs = self.parent.config.forecast_cost_estimates['use_pooled_costs'] 
        
        assert pooling_returns and pooling_costs
        
        ## which function to use for calculation
        weighting_func=resolve_function(weighting_params.pop("func"))
        
        codes_to_use=self.has_same_cheap_rules_as_code(instrument_code)
            
        instrument_code_ref ="_".join(codes_to_use) ## ensures we don't repeat optimisation
        
        ##
        ## _get_raw_forecast_weights: function to call if we don't find in cache
        ## self: this_system stage object
        ## codes_to_use: instrument codes to get data for 
        ## weighting_func: function to call to calculate weights
        ## **weighting_params: parameters to pass to weighting function
        ##
        raw_forecast_weights_calcs = self.parent.calc_or_cache(
            'calculation_of_raw_forecast_weights', instrument_code_ref, 
            _calculation_of_pooled_raw_forecast_weights,
             self, codes_to_use, weighting_func, **weighting_params)

        return raw_forecast_weights_calcs

    def get_forecast_correlation_matrices(self, instrument_code):
        """
        Returns a correlationList object which contains a history of correlation matricies
        
        :param instrument_code:
        :type str:

        :returns: correlation_list object

        >>> from systems.tests.testdata import get_test_object_futures_with_rules_and_capping_estimate
        >>> from systems.basesystem import System
        >>> (accounts, fcs, rules, rawdata, data, config)=get_test_object_futures_with_rules_and_capping_estimate()
        >>> system=System([rawdata, rules, fcs, accounts, ForecastCombineEstimated()], data, config)
        >>> ans=system.combForecast.get_forecast_correlation_matrices("EDOLLAR")
        >>> ans.corr_list[-1]
        array([[ 1.        ,  0.1168699 ,  0.08038547],
               [ 0.1168699 ,  1.        ,  0.86907623],
               [ 0.08038547,  0.86907623,  1.        ]])
        >>> print(ans.columns)
        ['carry', 'ewmac16', 'ewmac8']
        """
        def _get_forecast_correlation_matrices(system, NotUsed1, NotUsed2, this_stage, 
                                               codes_to_use, corr_func, **corr_params):
            print(__file__ + ":" + str(inspect.getframeinfo(inspect.currentframe())[:3][1]) + ":" +"Calculating forecast correlations over %s" % ", ".join(codes_to_use))

            forecast_data=[this_stage.get_all_forecasts(instr_code, this_stage.apply_cost_weighting(instr_code)) for instr_code in codes_to_use]
            
            ## if we're not pooling passes a list of one
            forecast_data=[forecast_ts.ffill() for forecast_ts in forecast_data]

            return corr_func(forecast_data, log=self.log.setup(call="correlation"), **corr_params)
                            
        ## Get some useful stuff from the config
        corr_params=copy(self.parent.config.forecast_correlation_estimate)

        ## do we pool our estimation?
        pooling=str2Bool(corr_params.pop("pool_instruments"))
        
        ## which function to use for calculation
        corr_func=resolve_function(corr_params.pop("func"))
        
        if pooling:
            ## find set of instruments with same trading rules as I have
            codes_to_use=self.has_same_cheap_rules_as_code(instrument_code)
            instrument_code_ref=ALL_KEYNAME
            
            ## We 
            label='_'.join(codes_to_use)
            
        else:

            codes_to_use=[instrument_code]
            label=instrument_code
            instrument_code_ref=instrument_code
        ##
        ## label: how we identify this thing in the cache
        ## instrument_code_ref: eithier the instrument code, or 'all markets' if pooling
        ## _get_forecast_correlation_matrices: function to call if we don't find in cache
        ## self: this_system stage object
        ## codes_to_use: instrument codes 
        ## func: function to call to calculate correlations
        ## **corr_params: parameters to pass to correlation function
        ##

        forecast_corr_list = self.parent.calc_or_cache_nested(
            'get_forecast_correlation_matrices', instrument_code_ref, label, 
            _get_forecast_correlation_matrices,
             self, codes_to_use, corr_func, **corr_params)
        
        return forecast_corr_list