Python pyspark.sql.types.FloatType() Examples

def _convert_precision(df, dtype):
    if dtype is None:
        return df

    if dtype != "float32" and dtype != "float64":
        raise ValueError("dtype {} is not supported. \
            Use 'float32' or float64".format(dtype))

    source_type, target_type = (DoubleType, FloatType) \
        if dtype == "float32" else (FloatType, DoubleType)

    logger.warning("Converting floating-point columns to %s", dtype)

    for field in df.schema:
        col_name = field.name
        if isinstance(field.dataType, source_type):
            df = df.withColumn(col_name, df[col_name].cast(target_type()))
        elif isinstance(field.dataType, ArrayType) and \
                isinstance(field.dataType.elementType, source_type):
            df = df.withColumn(col_name, df[col_name].cast(ArrayType(target_type())))
    return df 

def register_udfs(self, sess, sc):
        """Register UDFs to be used in SQL queries.

        :type sess: `pyspark.sql.SparkSession`
        :param sess: Session used in Spark for SQL queries.

        :type sc: `pyspark.SparkContext`
        :param sc: Spark Context to run Spark jobs.
        """ 
        sess.udf.register("SQUARED", self.squared, returnType=(
            stypes.ArrayType(stypes.StructType(
            fields=[stypes.StructField('sku0', stypes.StringType()),
            stypes.StructField('norm', stypes.FloatType())]))))

        sess.udf.register('INTERSECTIONS',self.process_intersections,
            returnType=stypes.ArrayType(stypes.StructType(fields=[
            stypes.StructField('sku0', stypes.StringType()),
            stypes.StructField('sku1', stypes.StringType()),
            stypes.StructField('cor', stypes.FloatType())]))) 

def _decodeOutputAsPredictions(self, df):
        # If we start having different weights than imagenet, we'll need to
        # move this logic to individual model building in NamedImageTransformer.
        # Also, we could put the computation directly in the main computation
        # graph or use a scala UDF for potentially better performance.
        topK = self.getOrDefault(self.topK)

        def decode(predictions):
            pred_arr = np.expand_dims(np.array(predictions), axis=0)
            decoded = decode_predictions(pred_arr, top=topK)[0]
            # convert numpy dtypes to python native types
            return [(t[0], t[1], t[2].item()) for t in decoded]

        decodedSchema = ArrayType(
            StructType([
                StructField("class", StringType(), False),
                StructField("description", StringType(), False),
                StructField("probability", FloatType(), False)
            ]))
        decodeUDF = udf(decode, decodedSchema)
        interim_output = self._getIntermediateOutputCol()
        return df \
            .withColumn(self.getOutputCol(), decodeUDF(df[interim_output])) \
            .drop(interim_output) 

def register_udfs(self, sess, sc):
        """Register UDFs to be used in SQL queries.

        :type sess: `pyspark.sql.SparkSession`
        :param sess: Session used in Spark for SQL queries.

        :type sc: `pyspark.SparkContext`
        :param sc: Spark Context to run Spark jobs.
        """ 
        sess.udf.register("SQUARED", self.squared, returnType=(
            stypes.ArrayType(stypes.StructType(
            fields=[stypes.StructField('sku0', stypes.StringType()),
            stypes.StructField('norm', stypes.FloatType())]))))

        sess.udf.register('INTERSECTIONS',self.process_intersections,
            returnType=stypes.ArrayType(stypes.StructType(fields=[
            stypes.StructField('sku0', stypes.StringType()),
            stypes.StructField('sku1', stypes.StringType()),
            stypes.StructField('cor', stypes.FloatType())]))) 

def as_spark_type(tpe) -> types.DataType:
    """
    Given a python type, returns the equivalent spark type.
    Accepts:
    - the built-in types in python
    - the built-in types in numpy
    - list of pairs of (field_name, type)
    - dictionaries of field_name -> type
    - python3's typing system
    """
    if tpe in (str, "str", "string"):
        return types.StringType()
    elif tpe in (bytes,):
        return types.BinaryType()
    elif tpe in (np.int8, "int8", "byte"):
        return types.ByteType()
    elif tpe in (np.int16, "int16", "short"):
        return types.ShortType()
    elif tpe in (int, "int", np.int, np.int32):
        return types.IntegerType()
    elif tpe in (np.int64, "int64", "long", "bigint"):
        return types.LongType()
    elif tpe in (float, "float", np.float):
        return types.FloatType()
    elif tpe in (np.float64, "float64", "double"):
        return types.DoubleType()
    elif tpe in (datetime.datetime, np.datetime64):
        return types.TimestampType()
    elif tpe in (datetime.date,):
        return types.DateType()
    elif tpe in (bool, "boolean", "bool", np.bool):
        return types.BooleanType()
    elif tpe in (np.ndarray,):
        # TODO: support other child types
        return types.ArrayType(types.StringType())
    else:
        raise TypeError("Type %s was not understood." % tpe) 

def test_spark_udf(spark, model_path):
    mlflow.pyfunc.save_model(
        path=model_path,
        loader_module=__name__,
        code_path=[os.path.dirname(tests.__file__)],
    )
    reloaded_pyfunc_model = mlflow.pyfunc.load_pyfunc(model_path)

    pandas_df = pd.DataFrame(data=np.ones((10, 10)), columns=[str(i) for i in range(10)])
    spark_df = spark.createDataFrame(pandas_df)

    # Test all supported return types
    type_map = {"float": (FloatType(), np.number),
                "int": (IntegerType(), np.int32),
                "double": (DoubleType(), np.number),
                "long": (LongType(), np.int),
                "string": (StringType(), None)}

    for tname, tdef in type_map.items():
        spark_type, np_type = tdef
        prediction_df = reloaded_pyfunc_model.predict(pandas_df)
        for is_array in [True, False]:
            t = ArrayType(spark_type) if is_array else spark_type
            if tname == "string":
                expected = prediction_df.applymap(str)
            else:
                expected = prediction_df.select_dtypes(np_type)
                if tname == "float":
                    expected = expected.astype(np.float32)

            expected = [list(row[1]) if is_array else row[1][0] for row in expected.iterrows()]
            pyfunc_udf = spark_udf(spark, model_path, result_type=t)
            new_df = spark_df.withColumn("prediction", pyfunc_udf(*pandas_df.columns))
            actual = list(new_df.select("prediction").toPandas()['prediction'])
            assert expected == actual
            if not is_array:
                pyfunc_udf = spark_udf(spark, model_path, result_type=tname)
                new_df = spark_df.withColumn("prediction", pyfunc_udf(*pandas_df.columns))
                actual = list(new_df.select("prediction").toPandas()['prediction'])
                assert expected == actual 

def test_load_neighbor_schema(self):
        klass = self.get_target_klass()()
        result = klass.load_neighbor_schema()
        expected = stypes.StructType(fields=[
                stypes.StructField("item", stypes.StringType()),
                 stypes.StructField("similarity_items", stypes.ArrayType(
                  stypes.StructType(fields=[
                   stypes.StructField("item", stypes.StringType()),
                    stypes.StructField("similarity", stypes.FloatType())])))])
        self.assertEqual(expected, result) 

def test_load_users_schema(self):
        klass = self.get_target_klass()()
        expected = stypes.StructType(fields=[
        	stypes.StructField("user", stypes.StringType()),
        	 stypes.StructField('interactions', stypes.ArrayType(
        	  stypes.StructType(fields=[stypes.StructField('item', 
        	   stypes.StringType()), stypes.StructField('score', 
        	    stypes.FloatType())])))])
        result = klass.load_users_schema()
        self.assertEqual(result, expected) 

def load_users_schema():
        """Loads schema with data type [user, [(sku, score), (sku, score)]]

        :rtype: `pyspark.sql.type.StructType`
        :returns: schema speficiation for user -> (sku, score) data.
        """
        return stypes.StructType(fields=[
        	stypes.StructField("user", stypes.StringType()),
        	 stypes.StructField('interactions', stypes.ArrayType(
        	  stypes.StructType(fields=[stypes.StructField('item', 
        	   stypes.StringType()), stypes.StructField('score', 
        	    stypes.FloatType())])))]) 

def load_neighbor_schema(self):
        """Loads neighborhood schema for similarity matrix

        :rtype: `pyspark.sql.types.StructField`
        :returns: schema of type ["key", [("key", "value")]]
        """
        return stypes.StructType(fields=[
                stypes.StructField("item", stypes.StringType()),
                 stypes.StructField("similarity_items", stypes.ArrayType(
                  stypes.StructType(fields=[
                   stypes.StructField("item", stypes.StringType()),
                    stypes.StructField("similarity", stypes.FloatType())])))]) 

def load_users_schema():
        """Loads schema with data type [user, [(sku, score), (sku, score)]]

        :rtype: `pyspark.sql.type.StructType`
        :returns: schema speficiation for user -> (sku, score) data.
        """
        return stypes.StructType(fields=[
        	stypes.StructField("user", stypes.StringType()),
        	 stypes.StructField('interactions', stypes.ArrayType(
        	  stypes.StructType(fields=[stypes.StructField('item', 
        	   stypes.StringType()), stypes.StructField('score', 
        	    stypes.FloatType())])))]) 

def isnull(self):
        """
        Detect existing (non-missing) values.

        Return a boolean same-sized object indicating if the values are NA.
        NA values, such as None or numpy.NaN, gets mapped to True values.
        Everything else gets mapped to False values. Characters such as empty strings '' or
        numpy.inf are not considered NA values
        (unless you set pandas.options.mode.use_inf_as_na = True).

        Returns
        -------
        Series : Mask of bool values for each element in Series
            that indicates whether an element is not an NA value.

        Examples
        --------
        >>> ser = ks.Series([5, 6, np.NaN])
        >>> ser.isna()  # doctest: +NORMALIZE_WHITESPACE
        0    False
        1    False
        2     True
        Name: 0, dtype: bool

        >>> ser.rename("a").to_frame().set_index("a").index.isna()
        Index([False, False, True], dtype='object', name='a')
        """
        from databricks.koalas.indexes import MultiIndex

        if isinstance(self, MultiIndex):
            raise NotImplementedError("isna is not defined for MultiIndex")
        if isinstance(self.spark.data_type, (FloatType, DoubleType)):
            return self._with_new_scol(
                self.spark.column.isNull() | F.isnan(self.spark.column)
            ).rename(self.name)
        else:
            return self._with_new_scol(self.spark.column.isNull()).rename(self.name) 

def _count_expr(col: spark.Column, spark_type: DataType) -> spark.Column:
        # Special handle floating point types because Spark's count treats nan as a valid value,
        # whereas pandas count doesn't include nan.
        if isinstance(spark_type, (FloatType, DoubleType)):
            return F.count(F.nanvl(col, F.lit(None)))
        else:
            return F.count(col) 

def test_fromFile(self):
        f = os.path.join(SmvSchemaTest.resourceTestDir(), "data/a.schema")
        s = SmvSchema.fromFile(f)
        fields = s.spark_schema.fields
        assert(len(fields) == 2)
        assert(fields[0] == st.StructField('a', st.StringType()))
        assert(fields[1] == st.StructField('b', st.FloatType())) 

def encode(self, unischema_field, value):
        # Lazy loading pyspark to avoid creating pyspark dependency on data reading code path
        # (currently works only with make_batch_reader). We should move all pyspark related code into a separate module
        import pyspark.sql.types as sql_types

        # We treat ndarrays with shape=() as scalars
        unsized_numpy_array = isinstance(value, np.ndarray) and value.shape == ()
        # Validate the input to be a scalar (or an unsized numpy array)
        if not unsized_numpy_array and hasattr(value, '__len__') and (not isinstance(value, str)):
            raise TypeError('Expected a scalar as a value for field \'{}\'. '
                            'Got a non-numpy type\'{}\''.format(unischema_field.name, type(value)))

        if unischema_field.shape:
            raise ValueError('The shape field of unischema_field \'%s\' must be an empty tuple (i.e. \'()\' '
                             'to indicate a scalar. However, the actual shape is %s',
                             unischema_field.name, unischema_field.shape)
        if isinstance(self._spark_type, (sql_types.ByteType, sql_types.ShortType, sql_types.IntegerType,
                                         sql_types.LongType)):
            return int(value)
        if isinstance(self._spark_type, (sql_types.FloatType, sql_types.DoubleType)):
            return float(value)
        if isinstance(self._spark_type, sql_types.BooleanType):
            return bool(value)
        if isinstance(self._spark_type, sql_types.StringType):
            if not isinstance(value, str):
                raise ValueError(
                    'Expected a string value for field {}. Got type {}'.format(unischema_field.name, type(value)))
            return str(value)

        return value 

def _numpy_to_spark_mapping():
    """Returns a mapping from numpy to pyspark.sql type. Caches the mapping dictionary inorder to avoid instantiation
    of multiple objects in each call."""

    # Refer to the attribute of the function we use to cache the map using a name in the variable instead of a 'dot'
    # notation to avoid copy/paste/typo mistakes
    cache_attr_name = 'cached_numpy_to_pyspark_types_map'
    if not hasattr(_numpy_to_spark_mapping, cache_attr_name):
        import pyspark.sql.types as T

        setattr(_numpy_to_spark_mapping, cache_attr_name,
                {
                    np.int8: T.ByteType(),
                    np.uint8: T.ShortType(),
                    np.int16: T.ShortType(),
                    np.uint16: T.IntegerType(),
                    np.int32: T.IntegerType(),
                    np.int64: T.LongType(),
                    np.float32: T.FloatType(),
                    np.float64: T.DoubleType(),
                    np.string_: T.StringType(),
                    np.str_: T.StringType(),
                    np.unicode_: T.StringType(),
                    np.bool_: T.BooleanType(),
                })

    return getattr(_numpy_to_spark_mapping, cache_attr_name)


# TODO: Changing fields in this class or the UnischemaField will break reading due to the schema being pickled next to
# the dataset on disk 

def get_petastorm_column(df_column):

        column_type = df_column.type
        column_name = df_column.name
        column_is_nullable = df_column.is_nullable
        column_array_dimensions = df_column.array_dimensions

        # Reference:
        # https://github.com/uber/petastorm/blob/master/petastorm/
        # tests/test_common.py

        petastorm_column = None
        if column_type == ColumnType.INTEGER:
            petastorm_column = UnischemaField(column_name,
                                              np.int32,
                                              (),
                                              ScalarCodec(IntegerType()),
                                              column_is_nullable)
        elif column_type == ColumnType.FLOAT:
            petastorm_column = UnischemaField(column_name,
                                              np.float64,
                                              (),
                                              ScalarCodec(FloatType()),
                                              column_is_nullable)
        elif column_type == ColumnType.TEXT:
            petastorm_column = UnischemaField(column_name,
                                              np.string_,
                                              (),
                                              ScalarCodec(StringType()),
                                              column_is_nullable)
        elif column_type == ColumnType.NDARRAY:
            petastorm_column = UnischemaField(column_name,
                                              np.uint8,
                                              column_array_dimensions,
                                              NdarrayCodec(),
                                              column_is_nullable)
        else:
            LoggingManager().log("Invalid column type: " + str(column_type),
                                 LoggingLevel.ERROR)

        return petastorm_column