doczyai-pipelines/fieldExtraction/tests/postprocessing_funcs_test.py

import pytest
import pandas as pd
import numpy as np
from src.postprocessing_funcs import (
    InvalidDateException,
    yn_fixes,
    convert_to_us_date_format,
)


class TestPostprocessingFuncs:
    @pytest.fixture
    def valid_dates(self):
        return [
            ("2023-12-01", "12/01/2023"),
            ("2023-01-12", "01/12/2023"),
            ("2023-13-01", "01/13/2023"),
        ]

    @pytest.fixture
    def invalid_dates(self):
        return ["2023-13-32", "2023-00-01", "2023-12-00", "2023-12-32", "2023-13-13"]

    @pytest.fixture
    def empty_dates(self):
        return ["", "N/A", "null", "none"]

    @pytest.fixture
    def invalid_format_dates(self):
        return ["2023/12/01", "12-01-2023", "2023.12.01"]

    @pytest.fixture
    def invalid_type_dates(self):
        return [None]

    def test_convert_to_us_date_format(
        self,
        valid_dates,
        invalid_dates,
        empty_dates,
        invalid_format_dates,
        invalid_type_dates,
    ):
        for input_date, expected_output in valid_dates:
            assert convert_to_us_date_format(input_date) == expected_output

        for input_date in invalid_dates:
            with pytest.raises(InvalidDateException):
                convert_to_us_date_format(input_date)

        for input_date in empty_dates:
            with pytest.raises(InvalidDateException):
                convert_to_us_date_format(input_date)

        for input_date in invalid_format_dates:
            with pytest.raises(InvalidDateException):
                convert_to_us_date_format(input_date)

        for input_date in invalid_type_dates:
            with pytest.raises(TypeError):
                convert_to_us_date_format(input_date)

    @pytest.fixture
    def sample_answer_dicts(self):
        return [
            {
                "FULL_SERVICE": "This is a test statement containing keyword 'Lease'",
                "FULL_METHODOLOGY": "PMPM",
            },
            {"FULL_SERVICE": "unspecified", "FULL_METHODOLOGY": "valid"},
            {
                "FULL_SERVICE": "This is an example of clean dict",
                "FULL_METHODOLOGY": "Will be effective for 30 days",
            },
        ]

    @pytest.fixture
    def sample_df(self):
        data = {
            "FULL_SERVICE": ["Service A", "Service B", "Invalid Service"],
            "FULL_METHODOLOGY": [
                "Methodology X",
                "Methodology Y",
                "Invalid Methodology",
            ],
            "LESSER": ["N", "Y", "N"],
            "LESSER_RATE": [100, 200, 300],
            "RATE_STANDARD": [150, 250, 350],
            "DEFAULT_TERM": ["Outpatient", "Inpatient", "Invalid"],
            "DEFAULT_RATE": ["AC", "BC", "Invalid"],
            "IP_OP": ["OP", "IP", "OP"],
            "PROV_TYPE_LEVEL_2": ["", "Type A", "Type B"],
            "TERM_CLAUSE": [
                "IL-4 Termination",
                "bonus payment shall be effective",
                "No term or termination",
            ],
            "CONTRACT_AUTO_RENEWAL_IND": ["Y", "N", "Y"],
            "CONTRACT_TERMINATION_DT": [np.nan, "2023-12-31", np.nan],
            "PROV_GROUP_NPI": ["1234567890", "123", "N/A"],
            "NETWORK_ACCESS_FEES_IND": ["Yes", "No", "Yes"],
            "PAYER_NAME": ["Illini Health", "Superior HealthPlan", "Other Payer"],
            "HEALTH_PLAN_STATE": ["IL", "TX", "CA"],
            "NOTICE_PROVIDER_NAME": ["Superior HealthPlan", "Provider A", "Provider B"],
            "NOTICE_PROVIDER_ADDRESS": ["Address A", "Address B", "Address C"],
            "POLICIES_AND_PROCEDURES": ["Policy A", "Procedure B", "Invalid"],
            "PROV_GROUP_TIN": ["12-3456789", "123456789", "N/A"],
            "ADD_ON_REIMBURSEMENT_LANGUAGE": [
                "in no event includ",
                "forward payments",
                "N/A",
            ],
            "ADD_ON_REIMBURSEMENT_IND": ["Y", "N", "Y"],
            "FLAT_FEE_STANDARD": ["$100", "$200", "$300"],
            "CONTRACT_LOB": ["LOB A", "LOB B", "LOB C"],
            "Parent Agreement Code": ["1234", "5678", "91011"],
            "RATE_SHORT": ["$100", "$200", "$300"],
            "DUMMY_COL(Y/N)": ["Yes", "No", ""],
        }
        return pd.DataFrame(data)

    def test_yn_fixes(self, sample_df):
        cleaned_df = yn_fixes(sample_df)
        assert cleaned_df.loc[1, "ADD_ON_REIMBURSEMENT_LANGUAGE"] == ""
        assert cleaned_df["DUMMY_COL(Y/N)"].tolist() == ["Y", "N", "N"]