def test_more_keys(self):
old = {1: ['APPLE', 'ARTICHOKE'], 2: ['BOAT', 'BALLERINA']}
expected = {
'apple': 1,
'artichoke': 1,
'boat': 2,
'ballerina': 2
}
self.assertEqual(expected, etl.transform(old))
def test_multiple_scores_with_differing_numbers_of_letters(self):
legacy_data = {
1: ["A", "E", "I", "O", "U", "L", "N", "R", "S", "T"],
2: ["D", "G"],
3: ["B", "C", "M", "P"],
4: ["F", "H", "V", "W", "Y"],
5: ["K"],
8: ["J", "X"],
10: ["Q", "Z"]
}
data = {
"a": 1, "b": 3, "c": 3, "d": 2, "e": 1, "f": 4,
"g": 2, "h": 4, "i": 1, "j": 8, "k": 5, "l": 1,
"m": 3, "n": 1, "o": 1, "p": 3, "q": 10, "r": 1,
"s": 1, "t": 1, "u": 1, "v": 4, "w": 4, "x": 8,
"y": 4, "z": 10
}
self.assertEqual(transform(legacy_data), data)
def test_full_dataset(self):
old = {
1: "AEIOULNRST",
2: "DG",
3: "BCMP",
4: "FHVWY",
5: "K",
8: "JX",
10: "QZ",
}
expected = {
"a": 1, "b": 3, "c": 3, "d": 2, "e": 1,
"f": 4, "g": 2, "h": 4, "i": 1, "j": 8,
"k": 5, "l": 1, "m": 3, "n": 1, "o": 1,
"p": 3, "q": 10, "r": 1, "s": 1, "t": 1,
"u": 1, "v": 4, "w": 4, "x": 8, "y": 4,
"z": 10
}
self.assertEqual(expected, etl.transform(old))
def test_single_letter(self):
legacy_data = {1: ["A"]}
data = {"a": 1}
self.assertEqual(transform(legacy_data), data)
def test_multiple_scores_with_multiple_letters(self):
legacy_data = {1: ["A", "E"], 2: ["D", "G"]}
data = {"a": 1, "d": 2, "e": 1, "g": 2}
self.assertEqual(transform(legacy_data), data)
def test_single_score_with_multiple_letters(self):
legacy_data = {1: ["A", "E", "I", "O", "U"]}
data = {"a": 1, "e": 1, "i": 1, "o": 1, "u": 1}
self.assertEqual(transform(legacy_data), data)
def test_transform_pivot_legacy_score():
legacy_score = {1: ['A', 'B'], 2: ['C']}
expected_score = {'a': 1, 'b': 1, 'c': 2}
assert_that(transform(legacy_score), equal_to(expected_score))
import etl
import metricas
import constants
import pandas as pd
# df, clients = etl.extract()
payments_df, clientes_df = etl.extract()
# df, clients = etl.extract()
payments_df, clientes_df, metricsPerClient = etl.transform(payments_df, clientes_df)
metricas, metricsPerClient = metricas.metricsCalculator(clientes_df, metricsPerClient)
payments_df.to_csv('D:\ETL-TechnicalEvaluation\ETL-TechnicalEvaluation\docs\pagamentos.csv',index=True)
clientes_df.to_csv('D:\ETL-TechnicalEvaluation\ETL-TechnicalEvaluation\docs\clients.csv', index=True)
metricsPerClient.to_csv('D:\ETL-TechnicalEvaluation\ETL-TechnicalEvaluation\docs\metricasCliente.csv',index=True)
metricas.to_csv('D:\ETL-TechnicalEvaluation\ETL-TechnicalEvaluation\docs\metricas.csv',index=True)
def etl(cfg):
return transform(pseudo_data_generation(), cfg)
def test_a_single_letter(self):
self.assertEqual(transform({1: ['A']}), {'a': 1})
def test_multiple_scores_with_multiple_letters(self):
legacy_data = {1: ["A", "E"], 2: ["D", "G"]}
data = {"a": 1, "d": 2, "e": 1, "g": 2}
self.assertEqual(transform(legacy_data), data)
def test_single_score_with_multiple_letters(self):
legacy_data = {1: ["A", "E", "I", "O", "U"]}
data = {"a": 1, "e": 1, "i": 1, "o": 1, "u": 1}
self.assertEqual(transform(legacy_data), data)
def test_transform_one_value(self):
old = {1: ['WORLD']}
expected = {'world': 1}
self.assertEqual(expected, etl.transform(old))
def test_more_keys(self):
old = {1: ['APPLE', 'ARTICHOKE'], 2: ['BOAT', 'BALLERINA']}
expected = {'apple': 1, 'artichoke': 1, 'boat': 2, 'ballerina': 2}
self.assertEqual(expected, etl.transform(old))
def test_transform_more_values(self):
old = {1: ['WORLD', 'GSCHOOLERS']}
expected = {'world': 1, 'gschoolers': 1}
self.assertEqual(expected, etl.transform(old))
def test_transform_more_values(self):
old = {1: ['WORLD', 'GSCHOOLERS']}
expected = {'world': 1, 'gschoolers': 1}
self.assertEqual(expected, etl.transform(old))
def test_a_single_letter(self):
self.assertEqual(transform({1: ['A']}), {'a': 1})
def test_transform(self):
opec_orb_transform_data = transform(extract_data)
assert (transform_data == opec_orb_transform_data)
def test_transform_one_value(self):
old = {1: ['WORLD']}
expected = {'world': 1}
self.assertEqual(expected, etl.transform(old))
from etl import transform
SCORE_CHAR = {
1: ['A', 'E', 'I', 'O', 'U', 'L', 'N', 'R', 'S', 'T'],
2: ['D', 'G'],
3: ['B', 'C', 'M', 'P'],
4: ['F', 'H', 'V', 'W', 'Y'],
5: ['K'],
8: ['J', 'X'],
10: ['Q', 'Z']
}
CHAR_SCORE = transform(SCORE_CHAR)
def score(input):
def to_score(char):
return CHAR_SCORE[char.lower()] if char.lower() in CHAR_SCORE else 0
return sum(map(to_score, input))
