CAISO Daily Load

CAISODailyLoadISOSource

Bases: BaseISOSource

The CAISO Daily Load ISO Source is used to read daily load data from CAISO API. It supports multiple types of data. Check the load_types attribute.
API: http://oasis.caiso.com/oasisapi

Parameters:

Name Type Description Default
spark SparkSession

Spark Session instance

required
options dict

A dictionary of ISO Source specific configurations (See Attributes table below)

required

Attributes:

Name Type Description
load_types list

Must be a subset of [Demand Forecast 7-Day Ahead, Demand Forecast 2-Day Ahead, Demand Forecast Day Ahead, RTM 15Min Load Forecast, RTM 5Min Load Forecast, Total Actual Hourly Integrated Load].
Default Value - [Total Actual Hourly Integrated Load].

date str

Must be in YYYY-MM-DD format.

Please check the BaseISOSource for available methods.

BaseISOSource

BaseISOSource

Bases: SourceInterface

Base class for all the ISO Sources. It provides common functionality and helps in reducing the code redundancy.

Parameters:

Name Type Description Default
spark SparkSession

Spark Session instance

required
options dict

A dictionary of ISO Source specific configurations

required
Source code in src/sdk/python/rtdip_sdk/pipelines/sources/spark/iso/base_iso.py
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
class BaseISOSource(SourceInterface):
    """
    Base class for all the ISO Sources. It provides common functionality and helps in reducing the code redundancy.

    Parameters:
        spark (SparkSession): Spark Session instance
        options (dict): A dictionary of ISO Source specific configurations
    """

    spark: SparkSession
    options: dict
    iso_url: str = "https://"
    query_datetime_format: str = "%Y%m%d"
    required_options: list = []
    spark_schema = StructType([StructField("id", IntegerType(), True)])
    default_query_timezone: str = "UTC"

    def __init__(self, spark: SparkSession, options: dict) -> None:
        self.spark = spark
        self.options = options
        self.query_timezone = pytz.timezone(
            self.options.get("query_timezone", self.default_query_timezone)
        )
        self.current_date = datetime.now(timezone.utc).astimezone(self.query_timezone)

    def _fetch_from_url(self, url_suffix: str) -> bytes:
        """
        Gets data from external ISO API.

        Args:
            url_suffix: String to be used as suffix to iso url.

        Returns:
            Raw content of the data received.

        """
        url = f"{self.iso_url}{url_suffix}"
        logging.info(f"Requesting URL - {url}")

        response = requests.get(url)
        code = response.status_code

        if code != 200:
            raise HTTPError(
                f"Unable to access URL `{url}`."
                f" Received status code {code} with message {response.content}"
            )

        return response.content

    def _get_localized_datetime(self, datetime_str: str) -> datetime:
        """
        Converts string datetime into Python datetime object with configured format and timezone.
        Args:
            datetime_str: String to be converted into datetime.

        Returns: Timezone aware datetime object.

        """
        parsed_dt = datetime.strptime(datetime_str, self.query_datetime_format)
        parsed_dt = parsed_dt.replace(tzinfo=self.query_timezone)
        return parsed_dt

    def _pull_data(self) -> pd.DataFrame:
        """
        Hits the fetch_from_url method with certain parameters to get raw data from API.

        All the children ISO classes must override this method and call the fetch_url method
        in it.

        Returns:
             Raw DataFrame from API.
        """

        return pd.read_csv(BytesIO(self._fetch_from_url("")))

    def _prepare_data(self, df: pd.DataFrame) -> pd.DataFrame:
        """
        Performs all the basic transformations to prepare data for further processing.
        All the children ISO classes must override this method.

        Args:
            df: Raw DataFrame, received from the API.

        Returns:
             Modified DataFrame, ready for basic use.

        """
        return df

    def _sanitize_data(self, df: pd.DataFrame) -> pd.DataFrame:
        """
        Another data transformation helper method to be called after prepare data.
        Used for advance data processing such as cleaning, filtering, restructuring.
        All the children ISO classes must override this method if there is any post-processing required.

        Args:
            df: Initial modified version of DataFrame, received after preparing the data.

        Returns:
             Final version of data after all the fixes and modifications.

        """
        return df

    def _get_data(self) -> pd.DataFrame:
        """
        Entrypoint method to return the final version of DataFrame.

        Returns:
            Modified form of data for specific use case.

        """
        df = self._pull_data()
        df = self._prepare_data(df)
        df = self._sanitize_data(df)

        # Reorder columns to keep the data consistent
        df = df[self.spark_schema.names]

        return df

    @staticmethod
    def system_type():
        return SystemType.PYSPARK

    @staticmethod
    def libraries():
        libraries = Libraries()
        return libraries

    @staticmethod
    def settings() -> dict:
        return {}

    def _validate_options(self) -> bool:
        """
        Performs all the options checks. Raises exception in case of any invalid value.
        Returns:
             True if all checks are passed.

        """
        return True

    def pre_read_validation(self) -> bool:
        """
        Ensures all the required options are provided and performs other validations.
        Returns:
             True if all checks are passed.

        """
        for key in self.required_options:
            if key not in self.options:
                raise ValueError(f"Required option `{key}` is missing.")

        return self._validate_options()

    def post_read_validation(self) -> bool:
        return True

    def read_batch(self) -> DataFrame:
        """
        Spark entrypoint, It executes the entire process of pulling, transforming & fixing data.
        Returns:
             Final Spark DataFrame converted from Pandas DataFrame post-execution.

        """

        try:
            self.pre_read_validation()
            pdf = self._get_data()
            pdf = _prepare_pandas_to_convert_to_spark(pdf)

            # The below is to fix the compatibility issues between Pandas 2.0 and PySpark.
            pd.DataFrame.iteritems = pd.DataFrame.items
            df = self.spark.createDataFrame(data=pdf, schema=self.spark_schema)
            return df

        except Exception as e:
            logging.exception(str(e))
            raise e

    def read_stream(self) -> DataFrame:
        """
        By default, the streaming operation is not supported but child classes can override if ISO supports streaming.

        Returns:
             Final Spark DataFrame after all the processing.

        """

        raise NotImplementedError(
            f"{self.__class__.__name__} connector doesn't support stream operation."
        )

pre_read_validation()

Ensures all the required options are provided and performs other validations. Returns: True if all checks are passed.

Source code in src/sdk/python/rtdip_sdk/pipelines/sources/spark/iso/base_iso.py
175
176
177
178
179
180
181
182
183
184
185
186
def pre_read_validation(self) -> bool:
    """
    Ensures all the required options are provided and performs other validations.
    Returns:
         True if all checks are passed.

    """
    for key in self.required_options:
        if key not in self.options:
            raise ValueError(f"Required option `{key}` is missing.")

    return self._validate_options()

read_batch()

Spark entrypoint, It executes the entire process of pulling, transforming & fixing data. Returns: Final Spark DataFrame converted from Pandas DataFrame post-execution.

Source code in src/sdk/python/rtdip_sdk/pipelines/sources/spark/iso/base_iso.py
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
def read_batch(self) -> DataFrame:
    """
    Spark entrypoint, It executes the entire process of pulling, transforming & fixing data.
    Returns:
         Final Spark DataFrame converted from Pandas DataFrame post-execution.

    """

    try:
        self.pre_read_validation()
        pdf = self._get_data()
        pdf = _prepare_pandas_to_convert_to_spark(pdf)

        # The below is to fix the compatibility issues between Pandas 2.0 and PySpark.
        pd.DataFrame.iteritems = pd.DataFrame.items
        df = self.spark.createDataFrame(data=pdf, schema=self.spark_schema)
        return df

    except Exception as e:
        logging.exception(str(e))
        raise e

read_stream()

By default, the streaming operation is not supported but child classes can override if ISO supports streaming.

Returns:

Type Description
DataFrame

Final Spark DataFrame after all the processing.

Source code in src/sdk/python/rtdip_sdk/pipelines/sources/spark/iso/base_iso.py
213
214
215
216
217
218
219
220
221
222
223
224
def read_stream(self) -> DataFrame:
    """
    By default, the streaming operation is not supported but child classes can override if ISO supports streaming.

    Returns:
         Final Spark DataFrame after all the processing.

    """

    raise NotImplementedError(
        f"{self.__class__.__name__} connector doesn't support stream operation."
    )
Source code in src/sdk/python/rtdip_sdk/pipelines/sources/spark/iso/caiso_daily_load_iso.py
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
class CAISODailyLoadISOSource(BaseISOSource):
    """
    The CAISO Daily Load ISO Source is used to read daily load data from CAISO API.
    It supports multiple types of data. Check the `load_types` attribute.
    <br>API: <a href="http://oasis.caiso.com/oasisapi">http://oasis.caiso.com/oasisapi</a>


    Parameters:
        spark (SparkSession): Spark Session instance
        options (dict): A dictionary of ISO Source specific configurations (See Attributes table below)

    Attributes:
        load_types (list): Must be a subset of [`Demand Forecast 7-Day Ahead`, `Demand Forecast 2-Day Ahead`, `Demand Forecast Day Ahead`, `RTM 15Min Load Forecast`, `RTM 5Min Load Forecast`, `Total Actual Hourly Integrated Load`]. <br> Default Value - `[Total Actual Hourly Integrated Load]`.
        date (str): Must be in `YYYY-MM-DD` format.

    Please check the BaseISOSource for available methods.

    BaseISOSource:
        ::: src.sdk.python.rtdip_sdk.pipelines.sources.spark.iso.base_iso
    """

    spark: SparkSession
    options: dict
    iso_url: str = "https://oasis.caiso.com/oasisapi/SingleZip"
    query_datetime_format: str = "%Y%m%dT00:00-0000"
    required_options = ["load_types", "date"]
    spark_schema = CAISO_SCHEMA
    default_query_timezone = "UTC"

    def __init__(self, spark: SparkSession, options: dict) -> None:
        super().__init__(spark, options)
        self.spark = spark
        self.options = options
        self.load_types = self.options.get(
            "load_types", ["Total Actual Hourly Integrated Load"]
        )
        self.date = self.options.get("date", "").strip()
        self.user_datetime_format = "%Y-%m-%d"

        # The following to fix the Security Check Error as the CAISO API is timing out with HTTPS protocol.
        self.iso_url = self.iso_url.replace("s://", "://")

    def _pull_data(self) -> pd.DataFrame:
        """
        Pulls data from the CAISO API and parses the zip files for CSV data.

        Returns:
            Raw form of data.
        """

        logging.info(f"Getting {self.load_types} data for date {self.date}")
        start_date = datetime.strptime(self.date, self.user_datetime_format)
        end_date = start_date + timedelta(days=1)
        return self._fetch_and_parse_zip(start_date, end_date)

    def _fetch_and_parse_zip(
        self, start_date: datetime, end_date: datetime
    ) -> pd.DataFrame:
        suffix = (
            f"?resultformat=6&"
            f"queryname=SLD_FCST&"
            "version=1&"
            f"startdatetime={start_date.strftime(self.query_datetime_format)}&"
            f"enddatetime={end_date.strftime(self.query_datetime_format)}"
        )

        content = self._fetch_from_url(suffix)
        if not content:
            raise HTTPError("Empty Response was returned")
        logging.info("Unzipping the file")

        zf = ZipFile(BytesIO(content))

        csvs = list(filter(lambda name: ".csv" in name, zf.namelist()))
        if len(csvs) == 0:
            raise ValueError("No data was found in the specified interval")

        df = pd.read_csv(zf.open(csvs[0]))
        return df

    def _prepare_data(self, df: pd.DataFrame) -> pd.DataFrame:
        date_cols = ["INTERVALSTARTTIME_GMT", "INTERVALENDTIME_GMT"]
        for date_col in date_cols:
            df[date_col] = df[date_col].apply(
                lambda data: datetime.strptime(str(data)[:19], "%Y-%m-%dT%H:%M:%S")
            )

        df = df.rename(
            columns={
                "INTERVALSTARTTIME_GMT": "StartTime",
                "INTERVALENDTIME_GMT": "EndTime",
                "LOAD_TYPE": "LoadType",
                "OPR_DT": "OprDt",
                "OPR_HR": "OprHr",
                "OPR_INTERVAL": "OprInterval",
                "MARKET_RUN_ID": "MarketRunId",
                "TAC_AREA_NAME": "TacAreaName",
                "LABEL": "Label",
                "XML_DATA_ITEM": "XmlDataItem",
                "POS": "Pos",
                "MW": "Load",
                "EXECUTION_TYPE": "ExecutionType",
                "GROUP": "Group",
            }
        )

        return df

    def _sanitize_data(self, df: pd.DataFrame) -> pd.DataFrame:
        df = df[df["Label"].isin(self.load_types)]
        return df

    def _validate_options(self) -> bool:
        try:
            datetime.strptime(self.date, self.user_datetime_format)
        except ValueError:
            raise ValueError(
                f"Unable to parse date. Please specify in {self.user_datetime_format} format."
            )
        return True