marketdata.py 文件源码

def _standardize_index(
            self, df_in: pd.DataFrame, symbol: str=None, datatype: str=None,
            barsize: str=None, tz: str=None):
        """Normalize input DataFrame index to MarketDataBlock standard.
        """
        # Add or starndardize index names in the input.
        if isinstance(df_in.index, pd.MultiIndex):
            df_in.reset_index(inplace=True)

        # Rename ambiguous column names.
        df_in.columns = [
            col_rename.get(col.strip().lower(), col.strip().lower())
            for col in df_in.columns]

        # Insert Symbol, DataType, Barsize columns from arguments if not
        # found in the input dataframe.
        for col in MarketDataBlock.data_index:
            if col not in df_in.columns:
                if locals().get(col.lower(), None) is None:
                    raise KeyError(
                        'No {0} argument and no {0} column in the DataFrame.'
                        .format(col))
                df_in.insert(0, col, locals()[col.lower()])

        # Convert datetime strings to pandas DatetimeIndex
        df_in['TickerTime'] = pd.DatetimeIndex(
            df_in['TickerTime'].apply(pd.Timestamp))

        # Standardize BarSize strings
        df_in['BarSize'] = df_in['BarSize'].map(timedur_standardize)

        # Set index to class-defined MultiIndex
        df_in.set_index(MarketDataBlock.data_index, inplace=True)

        # Set time zone so all DatetimeIndex are tz-aware
        df_in_tz = df_in.index.levels[self.__class__.dtlevel].tz
        if df_in_tz is None or isinstance(df_in_tz, timezone) or \
           isinstance(df_in_tz, pytz._FixedOffset):
            # Input df has naive time index, or tzinfo is not pytz.timezone()
            if tz is None:
                raise ValueError(
                    'Argument tz=None, and TickerTime.tzinfo is None(naive),'
                    'datetime.timezone, or pytz._FixedOffset.')
            if df_in_tz is None:
                df_in = df_in.tz_localize(tz, level=self.__class__.dtlevel)
            else:
                df_in = df_in.tz_convert(tz, level=self.__class__.dtlevel)

        return df_in