feat(basic): 添加基本的 Spark 用例

- 新增 basic_re.py 文件，实现了一个简单的 Spark 应用程序
- 该程序从 HDFS 读取电影评分数据，进行基本的数据处理和统计
- 演示了如何使用 Spark RDD 进行数据转换和操作
- 验证了数据排序和比较的功能

basic_re.py

@@ -0,0 +1,68 @@
+from pyspark import SparkContext, SparkConf
+import os
+os.environ['JAVA_HOME'] = "/opt/module/jdk1.8.0_171"
+os.environ["PYSPARK_PYTHON"]="/usr/bin/python3"
+os.environ["PYSPARK_DRIVER_PYTHON"]="/usr/bin/python3"
+def get_ratings_tuple(entry):
+    items = entry.split('::')
+    return int(items[0]), int(items[1]), float(items[2])
+
+def get_movie_tuple(entry):
+    items = entry.split('::')
+    return int(items[0]), items[1]
+
+def sortFunction(tuple):
+    key = str('%06.3f' % tuple[0])
+    value = tuple[1]
+    return (key + ' ' + value)
+
+def init_rdds(sc):
+    ratingsFilename = "hdfs://master:9000/user/root/als_movie/ratings.txt"
+    moviesFilename = "hdfs://master:9000/user/root/als_movie/movies.dat"
+    numPartitions = 2
+    rawRatings = sc.textFile(ratingsFilename).repartition(numPartitions)
+    rawMovies = sc.textFile(moviesFilename)
+    ratingsRDD = rawRatings.map(get_ratings_tuple).cache()
+    moviesRDD = rawMovies.map(get_movie_tuple).cache()
+    return ratingsRDD, moviesRDD
+
+if __name__ == "__main__":
+    import sys, os
+    os.environ["PYSPARK_PYTHON"] = "/usr/bin/python3"
+    os.environ["PYSPARK_DRIVER_PYTHON"] = "/usr/bin/python3"
+
+    conf = SparkConf().setMaster("spark://master:7077").setAppName("als_movie")
+    sc = SparkContext.getOrCreate(conf)
+    sc.setLogLevel("ERROR")
+
+    ratingsRDD, moviesRDD = init_rdds(sc)
+
+    ratingsCount = ratingsRDD.count()
+    moviesCount = moviesRDD.count()
+
+    print('There are %s ratings and %s movies in the datasets' % (ratingsCount, moviesCount))
+    print('Ratings: %s' % ratingsRDD.take(3))
+    print('Movies: %s' % moviesRDD.take(3))
+
+    tmp1 = [(1, u'alpha'), (2, u'alpha'), (2, u'beta'), (3, u'alpha'), (1, u'epsilon'), (1, u'delta')]
+    tmp2 = [(1, u'delta'), (2, u'alpha'), (2, u'beta'), (3, u'alpha'), (1, u'epsilon'), (1, u'alpha')]
+
+    oneRDD = sc.parallelize(tmp1)
+    twoRDD = sc.parallelize(tmp2)
+    oneSorted = oneRDD.sortByKey(True).collect()
+    twoSorted = twoRDD.sortByKey(True).collect()
+    print(oneSorted)
+    print(twoSorted)
+    assert set(oneSorted) == set(twoSorted)
+    assert twoSorted[0][0] < twoSorted.pop()[0]
+    assert oneSorted[0:2] != twoSorted[0:2]
+
+    print(oneRDD.sortBy(sortFunction, True).collect())
+    print(twoRDD.sortBy(sortFunction, True).collect())
+
+    oneSorted1 = oneRDD.takeOrdered(oneRDD.count(), key=sortFunction)
+    twoSorted1 = twoRDD.takeOrdered(twoRDD.count(), key=sortFunction)
+    print('one is %s' % oneSorted1)
+    print('two is %s' % twoSorted1)
+    assert oneSorted1 == twoSorted1
+    sc.stop()