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()
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data" if not os.path.isfile(filename): if os.path.isfile(temp_filename): os.remove(temp_filename) download_file(url, temp_filename) os.rename(temp_filename, filename) # We use pyspark to filter empty lines sc = pyspark.SparkContext(master='local[*]', appName='iris') data = sc.textFile('iris.data') filtered_data = data.filter(lambda d: len(d) > 0) # Define Input Schema input_schema = Schema() input_schema.add_double_column('Sepal length') input_schema.add_double_column('Sepal width') input_schema.add_double_column('Petal length') input_schema.add_double_column('Petal width') input_schema.add_categorical_column( "Species", ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]) # Define Transform Process tp = TransformProcess(input_schema) tp.one_hot("Species") # Do the transformation on spark and convert to numpy output = tp(filtered_data) np_array = np.array([[float(i) for i in x.split(',')] for x in output]) x = np_array[:, :-3] y = np_array[:, -3:]
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 tp = TransformProcess(input_schema) # Let's remove some column we don't need tp.remove_column("CustomerID") tp.remove_column("MerchantID")