Skip to content

Convert SEM Json to Process Control Data Model

SEMJsonToPCDMTransformer

Bases: TransformerInterface

Converts a Spark Dataframe column containing a json string created by SEM to the Process Control Data Model.

Example

from rtdip_sdk.pipelines.transformers import SEMJsonToPCDMTransformer

sem_json_to_pcdm_transformer = SEMJsonToPCDMTransformer(
    data=df
    source_column_name="body",
    version=10,
    status_null_value="Good",
    change_type_value="insert"
)

result = sem_json_to_pcdm_transformer.transform()

Parameters:

Name Type Description Default
data DataFrame

Dataframe containing the column with SEM data

 required
source_column_name str

Spark Dataframe column containing the Json SEM data

 required
version int

The version for the OBC field mappings. The latest version is 10.

 required
status_null_value optional str

If populated, will replace 'Good' in the Status column with the specified value.

 'Good'
change_type_value optional str

If populated, will replace 'insert' in the ChangeType column with the specified value.

 'insert'
Source code in src/sdk/python/rtdip_sdk/pipelines/transformers/spark/sem_json_to_pcdm.py 
 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
class SEMJsonToPCDMTransformer(TransformerInterface):
    """
    Converts a Spark Dataframe column containing a json string created by SEM to the Process Control Data Model.

    Example
    --------
    ```python
    from rtdip_sdk.pipelines.transformers import SEMJsonToPCDMTransformer

    sem_json_to_pcdm_transformer = SEMJsonToPCDMTransformer(
        data=df
        source_column_name="body",
        version=10,
        status_null_value="Good",
        change_type_value="insert"
    )

    result = sem_json_to_pcdm_transformer.transform()
    ```

    Parameters:
        data (DataFrame): Dataframe containing the column with SEM data
        source_column_name (str): Spark Dataframe column containing the Json SEM data
        version (int): The version for the OBC field mappings. The latest version is 10.
        status_null_value (optional str): If populated, will replace 'Good' in the Status column with the specified value.
        change_type_value (optional str): If populated, will replace 'insert' in the ChangeType column with the specified value.
    """

    data: DataFrame
    source_column_name: str
    version: int
    status_null_value: str
    change_type_value: str

    def __init__(
        self,
        data: DataFrame,
        source_column_name: str,
        version: int,
        status_null_value: str = "Good",
        change_type_value: str = "insert",
    ) -> None:
        _package_version_meets_minimum("pyspark", "3.4.0")
        self.data = data
        self.source_column_name = source_column_name
        self.version = version
        self.status_null_value = status_null_value
        self.change_type_value = change_type_value

    @staticmethod
    def system_type():
        """
        Attributes:
            SystemType (Environment): Requires PYSPARK
        """
        return SystemType.PYSPARK

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

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

    def pre_transform_validation(self):
        return True

    def post_transform_validation(self):
        return True

    def transform(self) -> DataFrame:
        """
        Returns:
            DataFrame: A dataframe with the specified column converted to PCDM
        """
        if self.version == 10:
            mapping = obc_field_mappings.OBC_FIELD_MAPPINGS_V10
            df = (
                self.data.withColumn(
                    self.source_column_name,
                    from_json(self.source_column_name, SEM_SCHEMA),
                )
                .select(self.source_column_name + ".readings")
                .melt(
                    ids=["readings.resourceName"],
                    values=["readings.value"],
                    variableColumnName="var",
                    valueColumnName="value",
                )
                .drop("var")
                .select(map_from_arrays("resourceName", "value").alias("resourceName"))
                .select("resourceName.dID", "resourceName.d", "resourceName.t")
                .select(
                    regexp_replace(col("t").cast("string"), "(\d{10})(\d+)", "$1.$2")
                    .cast("double")
                    .alias("timestamp"),
                    "dID",
                    posexplode(split(expr("substring(d, 2, length(d)-2)"), ",")),
                )
                .select(
                    to_timestamp("timestamp").alias("EventTime"),
                    col("dID"),
                    col("pos").cast("string"),
                    col("col").alias("Value"),
                )
                .withColumn(
                    "TagName",
                    concat(
                        col("dID"),
                        lit(":"),
                        udf(lambda row: mapping[row]["TagName"])(col("pos")),
                    ),
                )
                .withColumn(
                    "ValueType", udf(lambda row: mapping[row]["ValueType"])(col("pos"))
                )
                .withColumn("Status", lit(self.status_null_value))
                .withColumn("ChangeType", lit(self.change_type_value))
            )
            return df.select(
                "EventTime", "TagName", "Status", "Value", "ValueType", "ChangeType"
            )
        else:
            return logging.exception(
                "The wrong version was specified. Please use the latest version"
            )

system_type() staticmethod

Attributes:

Name Type Description
SystemType Environment

Requires PYSPARK
Source code in src/sdk/python/rtdip_sdk/pipelines/transformers/spark/sem_json_to_pcdm.py 
87
88
89
90
91
92
93
@staticmethod
def system_type():
    """
    Attributes:
        SystemType (Environment): Requires PYSPARK
    """
    return SystemType.PYSPARK

transform()

Returns:

Name Type Description
DataFrame DataFrame

A dataframe with the specified column converted to PCDM
Source code in src/sdk/python/rtdip_sdk/pipelines/transformers/spark/sem_json_to_pcdm.py 
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
def transform(self) -> DataFrame:
    """
    Returns:
        DataFrame: A dataframe with the specified column converted to PCDM
    """
    if self.version == 10:
        mapping = obc_field_mappings.OBC_FIELD_MAPPINGS_V10
        df = (
            self.data.withColumn(
                self.source_column_name,
                from_json(self.source_column_name, SEM_SCHEMA),
            )
            .select(self.source_column_name + ".readings")
            .melt(
                ids=["readings.resourceName"],
                values=["readings.value"],
                variableColumnName="var",
                valueColumnName="value",
            )
            .drop("var")
            .select(map_from_arrays("resourceName", "value").alias("resourceName"))
            .select("resourceName.dID", "resourceName.d", "resourceName.t")
            .select(
                regexp_replace(col("t").cast("string"), "(\d{10})(\d+)", "$1.$2")
                .cast("double")
                .alias("timestamp"),
                "dID",
                posexplode(split(expr("substring(d, 2, length(d)-2)"), ",")),
            )
            .select(
                to_timestamp("timestamp").alias("EventTime"),
                col("dID"),
                col("pos").cast("string"),
                col("col").alias("Value"),
            )
            .withColumn(
                "TagName",
                concat(
                    col("dID"),
                    lit(":"),
                    udf(lambda row: mapping[row]["TagName"])(col("pos")),
                ),
            )
            .withColumn(
                "ValueType", udf(lambda row: mapping[row]["ValueType"])(col("pos"))
            )
            .withColumn("Status", lit(self.status_null_value))
            .withColumn("ChangeType", lit(self.change_type_value))
        )
        return df.select(
            "EventTime", "TagName", "Status", "Value", "ValueType", "ChangeType"
        )
    else:
        return logging.exception(
            "The wrong version was specified. Please use the latest version"
        )