Python pandas.dataframe方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def has_all_feature_columns(self, dset_df):
        """
        Compare the columns in dataframe dset_df against the feature columns required by
        the current featurization and descriptor_type param. Returns True if dset_df contains
        all the required columns.
        
        Args:
            dset_df (DataFrame): Feature matrix
        
        Returns:
            (Boolean): boolean specifying whether there are any missing columns in dset_df
        """
        missing_cols = set(self.featurization.get_feature_columns()) - set(dset_df.columns.values)
        return (len(missing_cols) == 0)

    # ************************************************************************************* 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def load_featurized_data(self):
        """Loads prefeaturized data from the filesystem. Returns a data frame,
        which is then passed to featurization.extract_prefeaturized_data() for processing.
        
        Returns:
            featurized_dset_df (pd.DataFrame): dataframe of the prefeaturized data, needs futher processing
        """
        # First check to set if dataset already has the feature columns we need
        dset_df = self.load_full_dataset()
        if self.has_all_feature_columns(dset_df):
            self.dataset_key = self.params.dataset_key
            return dset_df

        # Otherwise, generate the expected path for the featurized dataset
        featurized_dset_name = self.featurization.get_featurized_dset_name(self.dataset_name)
        dataset_dir = os.path.dirname(self.params.dataset_key)
        data_dir = os.path.join(dataset_dir, self.featurization.get_featurized_data_subdir())
        featurized_dset_path = os.path.join(data_dir, featurized_dset_name)
        featurized_dset_df = pd.read_csv(featurized_dset_path)
        self.dataset_key = featurized_dset_path
        return featurized_dset_df

    # **************************************************************************************** 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_account(self, format=""):
        """
            return pd.dataframe
        """
        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("oms.query_account", rpc_params)

        return utils.extract_result(cr, data_format=data_format, class_name="Account") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_position(self, mode="all", securities="", format=""):
        """
            securities: seperate by ","
            return pd.dataframe
        """

        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {"mode"       : mode,
                      "security"   : securities}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("oms.query_position", rpc_params)

        return utils.extract_result(cr, data_format=data_format, class_name="Position") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_net_position(self, mode="all", securities="", format=""):
        """
            securities: seperate by ","
            return pd.dataframe
        """

        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {"mode"       : mode,
                      "security"   : securities}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("oms.query_net_position", rpc_params)

        return utils.extract_result(cr, data_format=data_format, class_name="NetPosition") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_task(self, task_id=-1, format=""):
        """
            task_id: -1 -- all
            return pd.dataframe
        """

        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {"task_id": task_id}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("oms.query_task", rpc_params)

        return utils.extract_result(cr, data_format=data_format, class_name="Task") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_trade(self, task_id=-1, format=""):
        """
            task_id: -1 -- all
            return pd.dataframe
        """

        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {"task_id": task_id}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("oms.query_trade", rpc_params)

        return utils.extract_result(cr, data_format=data_format, class_name="Trade") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def query_portfolio(self, format=""):
        """
            return pd.dataframe
        """

        r, msg = self._check_session()
        if not r: return (None, msg)

        rpc_params = {}

        data_format = self._get_format(format, "pandas")
        if data_format == "pandas":
            rpc_params["format"] = "columnset"

        cr = self._remote.call("pms.query_portfolio", rpc_params)

        return utils.extract_result(cr, index_column="security", data_format=data_format, class_name="NetPosition") 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def calc_worst_hour(latitude, weather_data, solar_window_solstice):
    """
    Calculate the first hour of solar window of the winter solstice for panel spacing.
    http://www.affordable-solar.com/learning-center/building-a-system/calculating-tilted-array-spacing/

    :param latitude: latitude of the site [degree]
    :type latitude: float
    :param weather_data: weather data of the site
    :type weather_data: pd.dataframe
    :param solar_window_solstice: the desired hour of shade-free solar window on the winter solstice.
    :type solar_window_solstice: floar
    :return worst_hour: the hour to calculate minimum spacing
    :rtype worst_hour: float


    """
    if latitude > 0:
        northern_solstice = weather_data.query('month == 12 & day == 21')
        worst_hour = northern_solstice[northern_solstice.hour == (12 - round(solar_window_solstice / 2))].index[0]
    else:
        southern_solstice = weather_data.query('month == 6 & day == 21')
        worst_hour = southern_solstice[southern_solstice.hour == (12 - round(solar_window_solstice / 2))].index[0]

    return worst_hour 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def transform(self, X, end_index_list = None):
        if end_index_list is None:
            end_index_list = self.end_index_list # in case the end_index_list was set as meta_data

        if end_index_list is None:
            return X
        else:
            voted_labels = []
            prev_index = 0
            if not isinstance(X, np.ndarray):
                if isinstance(X, list):
                    X = np.array(X)
                elif isinstance(X, pd.dataframe):
                    X = X.as_matrix()
            for index in end_index_list:
                labels = X[prev_index:index]
                (values,counts) = np.unique(labels,return_counts=True)
                ind=np.argmax(counts) #If two labels are in majority, this will pick the first one.
                voted_labels.append(ind)
            return np.array(voted_labels) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def from_dict_of_values_to_df(data_dict, ts_index, columns=None):
    """
    Turn a set of fixed values into a pd.dataframe

    :param data_dict: A dict of scalars
    :param ts_index: A timeseries index
    :param columns: (optional) A list of str to align the column names to [must have entries in data_dict keys]
    :return: pd.dataframe, column names from data_dict, values repeated scalars
    """

    if columns is None:
        columns = data_dict.keys()

    columns_as_list = list(columns)

    numeric_values = dict([(keyname, [data_dict[keyname]] * len(ts_index))
                           for keyname in columns_as_list])

    pd_dataframe = pd.DataFrame(numeric_values, ts_index)

    return pd_dataframe 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def dataframe_pad(starting_df, column_list, padwith=0.0):
    """
    Takes a dataframe and adds extra columns if neccessary so we end up with columns named column_list

    :param starting_df: A pd.dataframe with named columns
    :param column_list: A list of column names
    :param padwith: The value to pad missing columns with
    :return: pd.Dataframe
    """

    def _pad_column(column_name, starting_df, padwith):
        if column_name in starting_df.columns:
            return starting_df[column_name]
        else:
            return pd.Series([0.0] * len(starting_df.index), starting_df.index)

    new_data = [
        _pad_column(column_name, starting_df, padwith)
        for column_name in column_list
    ]

    new_df = pd.concat(new_data, axis=1)
    new_df.columns = column_list

    return new_df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def check_params_with_data(self, df, actual_field, predicted_field):
        """ Check parameters against ground-truth values.

        Handle errors regarding cardinality of ground-truth labels
        and check pos_label param, if applicable. Assumed data has already
        been cleaned and made categorical. Overwritten as needed.

        Args:
            df (pd.dataframe): input dataframe
            actual_field (str): name of ground-truth field
            predicted_field (str): name of predicted field

        Raises:
            RuntimeError if params are incompatible with passed data
        """
        msg = 'Scoring method {} does not support "check_params_with_data" method.'
        raise MLSPLNotImplementedError(msg.format(self.scoring_name)) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def score(self, df, options):
        """ Compute the score.

        Args:
            df (pd.DataFrame): input dataframe
            options (dict): passed options

        Returns:
            df_output (pd.dataframe): output dataframe
        """
        # Prepare ground-truth and predicted labels
        y_actual, y_predicted = self.prepare_input_data(df, self.actual_field, self.predicted_field, options)
        # Get the scoring result
        result = self.scoring_function(y_actual, y_predicted, **self.params)
        # Create the output df
        df_output = self.create_output(self.scoring_name, result)
        return df_output 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import dataframe [as 别名]
def create_output(self, scoring_name, result):
        """ Create output dataframe

        Args:
            scoring_name (str): scoring function name
            result (float, dict or array): output of sklearn scoring function

        Returns:
            output_df (pd.DataFrame): output dataframe
        """

        labels = self.params.get('labels', None)

        if labels is not None:  # labels is union of predicted & actual classes. (eg. average=none, confusion matrix)
            output_df = pd.DataFrame(data=[result], columns=labels)
        else:  # otherwise, use scoring name
            output_df = pd.DataFrame(data=[result], columns=[scoring_name])
        return output_df