4 (jupiter)

 import csv

def mapper(tags): return [(r['movieId'], r['tag']) for r in tags]

def reducer(vals): return list(set(vals))

def map_reduce(tags):

    g = {}

    for k,v in mapper(tags): g.setdefault(k, []).append(v)

    return {k: reducer(v) for k,v in g.items()}

def load_csv(f): return list(csv.DictReader(open(f)))

def get_titles(rows): return {r['movieId']: r['title'] for r in rows}

tags = load_csv('tags.csv')

movies = get_titles(load_csv('movies.csv'))

for m,t in map_reduce(tags).items():

    print(f"Movie: {movies[m]}, Tags: {', '.join(t)}")

.....................................................................................................................
def mapper(tags): 
    return [(r['movieId'], r['tag']) for r in tags]
def reducer(values): 
    return list(set(values))
def map_reduce(tags):
    grouped = {}
    for k, v in mapper(tags): 
        grouped.setdefault(k, []).append(v)
    return {k: reducer(v) for k, v in grouped.items()}
def main():
    tags = [
        {'movieId': '1', 'tag': 'funny'},
        {'movieId': '1', 'tag': 'action'},
        {'movieId': '2', 'tag': 'drama'},
        {'movieId': '2', 'tag': 'romance'},
        {'movieId': '1', 'tag': 'funny'}
    ]
    movies = {
        '1': 'Movie One',
        '2': 'Movie Two'
    }
    result = map_reduce(tags)
    for mid, tgs in result.items():
        print(f"Movie: {movies[mid]}, Tags: {', '.join(tgs)}")
if __name__ == "__main__":
    main()

Comments

Post a Comment

Popular posts from this blog

7

 hive CREATE DATABASE employee_db; USE employee_db; CREATE TABLE employees (     emp_id INT,     name STRING,     age INT,     dept_id INT,     salary FLOAT ) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' STORED AS TEXTFILE; LOAD DATA INPATH '/user/cloudera/employees.txt' INTO TABLE employees; ALTER TABLE employees ADD COLUMNS (email STRING); ALTER TABLE employees RENAME TO employees_new; DROP TABLE employees_new; CREATE VIEW high_salary_employees AS SELECT emp_id, name, salary FROM employees WHERE salary > 50000; ALTER VIEW high_salary_employees AS SELECT emp_id, name, age, salary FROM employees WHERE salary > 60000; DROP VIEW high_salary_employees; SHOW TABLES; DESCRIBE employees; SELECT * FROM employees LIMIT 5; -=
Read more

8

 nano wordcount_sim.py text = """ Hadoop MapReduce is a software framework for easily writing applications which process vast amounts """ def mapper(line):     words = line.strip().split()     return [(word, 1) for word in words] from collections import defaultdict # Map phase mapped = [] for line in text.strip().split('\n'):     mapped.extend(mapper(line)) # Shuffle and sort phase shuffle_sort = defaultdict(list) for word, count in mapped:     shuffle_sort[word].append(count) # Reduce phase def reducer(shuffled_data):     reduced = {}     for word, counts in shuffled_data.items():         reduced[word] = sum(counts)     return reduced word_counts = reducer(shuffle_sort) # Output for word, count in word_counts.items():     print(f"{word}\t{count}") ctrl+o python3 wordcount_sim.py (or)python wordcount_sim.py
Read more

6

 pig -x local students = LOAD '/home/cloudera/Desktop/students.txt' USING PigStorage(',')  AS (id:int, name:chararray, dept:chararray, marks:int); departments = LOAD '/home/cloudera/Desktop/departments.txt' USING PigStorage(',')  AS (dept_code:chararray, dept_name:chararray); high_scorers = FILTER students BY marks > 70; DUMP high_scorers; projected = FOREACH high_scorers GENERATE name, marks; DUMP projected; grouped_by_dept = GROUP students BY dept; DUMP grouped_by_dept; avg_marks = FOREACH grouped_by_dept GENERATE group AS department, AVG(students.marks) AS average_marks; DUMP avg_marks; joined = JOIN students BY dept, departments BY dept_code; DUMP joined; sorted = ORDER students BY marks DESC; DUMP sorted;
Read more