SMS स्पैम पाइपलाइन

from pyspark.ml.feature import Tokenizer, StopWordsRemover, HashingTF, IDF

# Break text into tokens at non-word characters
tokenizer = ____(inputCol='text', outputCol='words')

# Remove stop words
remover = ____(inputCol=____, outputCol='terms')

# Apply the hashing trick and transform to TF-IDF
hasher = ____(inputCol=____, outputCol="hash")
idf = ____(inputCol=____, outputCol="features")

# Create a logistic regression object and add everything to a pipeline
logistic = LogisticRegression()
pipeline = Pipeline(stages=[____, ____, ____, ____, logistic])