PySparkMethods/pysparkmethod.py at main · SoldatovDaniil/PySparkMethods · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
from pyspark.sql import DataFrame, SparkSession
from pyspark.sql.functions import col, when, lit, count
from pyspark.sql.types import StructType, StructField, StringType, IntegerType
import unittest

def get_products_with_categories(products_df, categories_df, relations_df):
    products_with_relations = products_df.join(relations_df, "product_id", "left")
    result_df = products_with_relations.join(categories_df, "category_id", "left").select("product_name", "category_name")

    return result_df

class TestProductsCategories(unittest.TestCase):

    @classmethod
    def setUpClass(cls):
        cls.spark = SparkSession.builder \
            .appName("ProductsCategoriesTest") \
            .master("local[2]") \
            .getOrCreate()

        cls.products_schema = StructType([
            StructField("product_id", IntegerType(), True),
            StructField("product_name", StringType(), True)
        ])

        cls.categories_schema = StructType([
            StructField("category_id", IntegerType(), True),
            StructField("category_name", StringType(), True)
        ])

        cls.relations_schema = StructType([
            StructField("product_id", IntegerType(), True),
            StructField("category_id", IntegerType(), True)
        ])

    @classmethod
    def tearDownClass(cls):
        cls.spark.stop()

    def test_basic_functional(self):
        products_data = [
            (1, "Laptop"),
            (2, "Mouse"),
            (3, "Keyboard"),
            (4, "Monitor"),
            (5, "Headphones")
        ]

        categories_data = [
            (1, "Electronics"),
            (2, "Peripherals"),
            (3, "Audio")
        ]

        relations_data = [
            (1, 1),
            (2, 2),
            (3, 2),
            (5, 3),
        ]

        products_df = self.spark.createDataFrame(products_data, self.products_schema)
        categories_df = self.spark.createDataFrame(categories_data, self.categories_schema)
        relations_df = self.spark.createDataFrame(relations_data, self.relations_schema)

        result_df = get_products_with_categories(products_df, categories_df, relations_df)

        self.assertEqual(result_df.count(), 5)

        result_list = [(row.product_name, row.category_name) for row in result_df.collect()]

        expected_pairs = [
            ("Laptop", "Electronics"),
            ("Mouse", "Peripherals"),
            ("Keyboard", "Peripherals"),
            ("Monitor", None),
            ("Headphones", "Audio")
        ]

        result_list.sort()
        expected_pairs.sort()

        self.assertEqual(result_list, expected_pairs)

    def test_products_multiple_categories(self):
        products_data = [
            (1, "Smartphone"),
            (2, "Tablet")
        ]

        categories_data = [
            (1, "Electronics"),
            (2, "Mobile"),
            (3, "Computing")
        ]

        relations_data = [
            (1, 1),
            (1, 2),
            (2, 1),
            (2, 3),
        ]

        products_df = self.spark.createDataFrame(products_data, self.products_schema)
        categories_df = self.spark.createDataFrame(categories_data, self.categories_schema)
        relations_df = self.spark.createDataFrame(relations_data, self.relations_schema)

        result_df = get_products_with_categories(products_df, categories_df, relations_df)

        self.assertEqual(result_df.count(), 4)

        result_pairs = [(row.product_name, row.category_name) for row in result_df.collect()]
        expected_pairs = [
            ("Smartphone", "Electronics"),
            ("Smartphone", "Mobile"),
            ("Tablet", "Electronics"),
            ("Tablet", "Computing")
        ]

        self.assertCountEqual(result_pairs, expected_pairs)

    def test_empty_datasets(self):
        empty_products = self.spark.createDataFrame([], self.products_schema)
        empty_categories = self.spark.createDataFrame([], self.categories_schema)
        empty_relations = self.spark.createDataFrame([], self.relations_schema)

        result_df = get_products_with_categories(empty_products, empty_categories, empty_relations)

        self.assertEqual(result_df.count(), 0)

    def test_categories_without_products(self):
        products_data = [
            (1, "Laptop")
        ]

        categories_data = [
            (1, "Electronics"),
            (2, "Books"),
            (3, "Clothing")
        ]

        relations_data = [
            (1, 1)
        ]

        products_df = self.spark.createDataFrame(products_data, self.products_schema)
        categories_df = self.spark.createDataFrame(categories_data, self.categories_schema)
        relations_df = self.spark.createDataFrame(relations_data, self.relations_schema)

        result_df = get_products_with_categories(products_df, categories_df, relations_df)

        self.assertEqual(result_df.count(), 1)

        result_pair = [(row.product_name, row.category_name) for row in result_df.collect()]
        expected_pair = [("Laptop", "Electronics")]

        self.assertEqual(result_pair, expected_pair)

if __name__ == '__main__':
    loader = unittest.TestLoader()
    suite = loader.loadTestsFromTestCase(TestProductsCategories)

    runner = unittest.TextTestRunner(verbosity=2)
    result = runner.run(suite)