def setUp(self):
data = [Row(to_index="to_index%d" % i, value=i) for i in range(10)]
self.data = data
self.session = create_spark_for_test()
self.data_rdd = self.session.sparkContext \
.parallelize(range(len(data))) \
.map(lambda x: data[x])
def setUp(self):
self.session = create_spark_for_test()
df = DocumentFrequencies().construct(10, {str(i): i for i in range(1, 5)})
self.docs = df.docs
self.tfidf = TFIDF(df, df.docs, self.session.sparkContext)
class Columns:
"""
Stores column names for return value.
"""
token = "t"
document = "d"
value = "v"
self.tfidf.Columns = Columns
def setUp(self):
self.sc = create_spark_for_test()
self.bag2tf = BagFeatures2TermFreq()
def setUp(self):
self.sc = create_spark_for_test()
def setUp(self):
self.sc = create_spark_for_test()
self.bag2df = BagFeatures2DocFreq()