from pyspark import SparkContext
 
def mapper(line):
    words = line.split()
    return [(word, 1) for word in words]
 
def reducer(word_count):
    return word_count.reduceByKey(lambda a, b: a + b)
 
if __name__ == "__main__":
    sc = SparkContext("local", "WordCount")
 
    # Read the input file
    input_file = "path/to/your/input.txt"
    lines = sc.textFile(input_file)
 
    # Apply the mapper
    word_counts = lines.flatMap(mapper)
 
    # Apply the reducer
    final_counts = reducer(word_counts)
 
    # Collect and print results
    results = final_counts.collect()
 
    for word, count in results:
        print(f"{word}: {count}")
 
    # Stop the Spark context
    sc.stop()

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