def test_reduce_1():
reductions = ['sum', 'mean', 'std', 'var', 'prod']
for red in reductions:
schema = Schema()
schema.add_string_column('name')
schema.add_double_column('amount')
schema.add_integer_column('hours')
tp = TransformProcess(schema)
tp.reduce('name', red)
tp.to_java()
def test_reduce_1():
reductions = ['sum', 'mean', 'std', 'var', 'prod']
for red in reductions:
schema = Schema()
schema.add_string_column('name')
schema.add_double_column('amount')
schema.add_integer_column('hours')
tp = TransformProcess(schema)
tp.reduce('name', red)
tp.to_java()
def test_schema():
schema = Schema()
schema.add_string_column('str1')
schema.add_string_column('str2')
schema.add_integer_column('int1')
schema.add_integer_column('int2')
schema.add_double_column('dbl1')
schema.add_double_column('dbl2')
schema.add_float_column('flt1')
schema.add_float_column('flt2')
schema.add_categorical_column('cat1', ['A', 'B', 'C'])
schema.add_categorical_column('cat2', ['A', 'B', 'C'])
schema.to_java()
def test_schema():
schema = Schema()
schema.add_string_column('str1')
schema.add_string_column('str2')
schema.add_integer_column('int1')
schema.add_integer_column('int2')
schema.add_double_column('dbl1')
schema.add_double_column('dbl2')
schema.add_float_column('flt1')
schema.add_float_column('flt2')
schema.add_categorical_column('cat1', ['A', 'B', 'C'])
schema.add_categorical_column('cat2', ['A', 'B', 'C'])
schema.to_java()
# Basic example
from pydatavec import Schema, TransformProcess
from pydatavec import NotInSet, LessThan
# Let's define the schema of the data that we want to import
# The order in which columns are defined here should match the order in which they appear in the input data
input_schema = Schema()
input_schema.add_string_column("DateTimeString")
input_schema.add_string_column("CustomerID")
input_schema.add_string_column("MerchantID")
input_schema.add_integer_column("NumItemsInTransaction")
input_schema.add_categorical_column("MerchantCountryCode",
["USA", "CAN", "FR", "MX"])
# Some columns have restrictions on the allowable values, that we consider valid:
input_schema.add_double_column(
"TransactionAmountUSD", 0.0, None, False,
False) # $0.0 or more, no maximum limit, no NaN and no Infinite values
input_schema.add_categorical_column("FraudLabel", ["Fraud", "Legit"])
# Lets define some operations to execute on the data...
# We do this by defining a TransformProcess
# At each step, we identify column by the name we gave them in the input data schema, above
