class ExpectColumnValuesToMatchSomeRegex(RegexBasedColumnMapExpectation):
"""TODO: Add a docstring here"""
# These values will be used to configure the metric created by your expectation
regex_camel_name = "RegexName"
regex = "regex pattern"
semantic_type_name_plural = None
# These examples will be shown in the public gallery.
# They will also be executed as unit tests for your Expectation.
examples = []
# Here your regex is used to create a custom metric for this expectation
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
# This object contains metadata for display in the public Gallery
library_metadata = {
"tags": [], # Tags for this Expectation in the Gallery
"contributors":
[ # Github handles for all contributors to this Expectation.
"@your_name_here", # Don't forget to add your github handle here!
],
}
class ExpectColumnValuesToHaveValidICD10CodeFormat(
RegexBasedColumnMapExpectation):
"""Checks if each value matches a regex for ICD10 codes. Does NOT ensure
the given code actually exists in any version of the ICD10.
"""
regex_camel_name = "ICD10Codes"
regex = "[A-Za-z][0-9][A-Za-z0-9](?:\\.[A-Za-z0-9]{0,4})?\\Z"
semantic_type_name_plural = None
examples = [{
"data": {
"valid_icd10": ["Z99.0", "Z08", "J09.X2", "S22.000A"],
"invalid_icd10": ["XXX.X", "AA2.01", "2A", "S22.0000A"],
},
"tests": [
{
"title": "positive_test",
"exact_match_out": False,
"in": {
"column": "valid_icd10"
},
"out": {
"success": True
},
"include_in_gallery": True,
},
{
"title": "negative_test",
"exact_match_out": False,
"in": {
"column": "invalid_icd10"
},
"out": {
"success": False,
"unexpected_index_list": [0, 1, 2, 3]
},
},
],
"test_backends": [{
"backend": "pandas",
"dialects": None
}],
}]
# Here your regex is used to create a custom metric for this expectation
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
# This object contains metadata for display in the public Gallery
library_metadata = {
"tags": ["typed-entities", "hackathon"],
"contributors": [
"@zachlindsey",
],
}
class ExpectColumnValuesToBeValidScientificNotation(
RegexBasedColumnMapExpectation):
"""Expect values in this column to be a valid scientific notation string."""
# These values will be used to configure the metric created by your expectation
regex_camel_name = "ScientificNotation"
regex = "^[+\-]?(?=\.\d|\d)(?:0|[1-9]\d*)?(?:\.\d+)?(?:(?<=\d)(?:[eE][+\-]?\d+))?$"
semantic_type_name_plural = "scientific_notations"
# These examples will be shown in the public gallery.
# They will also be executed as unit tests for your Expectation.
examples = [{
"data": {
"valid": ["-3.14", "1.07E-10", "3.14e-12"],
"invalid": ["11.e-12", "0E+5", "007"],
"empty": ["", None, False],
},
"tests": [
{
"title": "basic_positive_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "valid"
},
"out": {
"success": True,
},
},
{
"title": "basic_negative_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "invalid",
"mostly": 1
},
"out": {
"success": False,
},
},
{
"title": "empty",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "empty",
"mostly": 1
},
"out": {
"success": False,
},
},
],
}]
# Here your regex is used to create a custom metric for this expectation
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
# This object contains metadata for display in the public Gallery
library_metadata = {
"maturity":
"experimental",
"tags": [
"scientific_notation",
"expectation",
], # Tags for this Expectation in the Gallery
"contributors":
[ # Github handles for all contributors to this Expectation.
"@rdodev", # Don't forget to add your github handle here!
],
}
class ExpectColumnValuesToBeValidGeohash(RegexBasedColumnMapExpectation):
"""Expect values in this column to be a valid geohash."""
# These values will be used to configure the metric created by your expectation
regex_camel_name = "Geohash"
regex = "^[0123456789bcdefghjkmnpqrstuvwxyz]+$"
semantic_type_name_plural = "geohashes"
# These examples will be shown in the public gallery.
# They will also be executed as unit tests for your Expectation.
examples = [{
"data": {
"valid_geohash": ["dpz8"],
"invalid_alphanumeric": ["apz8"], # "a" is an invalid geohash char
"invalid_non_alphanumeric": ["dp2-"],
"empty": [""],
},
"tests": [
{
"title": "basic_positive_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "valid_geohash"
},
"out": {
"success": True,
},
},
{
"title": "basic_negative_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "invalid_alphanumeric",
"mostly": 1
},
"out": {
"success": False,
},
},
{
"title": "invalid_non_alphanumeric",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "invalid_non_alphanumeric",
"mostly": 1
},
"out": {
"success": False,
},
},
{
"title": "empty",
"exact_match_out": False,
"include_in_gallery": True,
"in": {
"column": "empty",
"mostly": 1
},
"out": {
"success": False,
},
},
],
}]
# Here your regex is used to create a custom metric for this expectation
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
# This object contains metadata for display in the public Gallery
library_metadata = {
"tags": [
"geospatial",
"hackathon-22",
], # Tags for this Expectation in the Gallery
"contributors":
[ # Github handles for all contributors to this Expectation.
"@chrisarnold91", # Don't forget to add your github handle here!
],
}
class ExpectColumnValuesToOnlyContainVowels(RegexBasedColumnMapExpectation):
"""Values in this column should only contain vowels"""
regex_camel_name = "Vowel"
regex = "^[aeiouyAEIOUY]*$"
semantic_type_name_plural = "vowels"
examples = [{
"data": {
"only_vowels": ["a", "e", "I", "O", "U", "y", ""],
"mixed": ["A", "b", "c", "D", "E", "F", "g"],
"longer_vowels": ["aei", "YAY", "oYu", "eee", "", "aeIOUY", None],
"contains_vowels_but_also_other_stuff": [
"baa",
"aba",
"aab",
"1a1",
"a a",
" ",
"*",
],
},
"tests": [
{
"title": "positive_test",
"exact_match_out": False,
"in": {
"column": "only_vowels"
},
"out": {
"success": True,
},
"include_in_gallery": True,
},
{
"title": "negative_test",
"exact_match_out": False,
"in": {
"column": "mixed"
},
"out": {
"success": False,
"unexpected_index_list": [1, 2, 3, 5, 6],
},
"include_in_gallery": True,
},
{
"title": "another_postive_test",
"exact_match_out": False,
"in": {
"column": "longer_vowels"
},
"out": {
"success": True,
},
"include_in_gallery": True,
},
{
"title": "another_negative_test",
"exact_match_out": False,
"in": {
"column": "contains_vowels_but_also_other_stuff"
},
"out": {
"success": False,
"unexpected_index_list": [0, 1, 2, 3, 4, 5, 6],
},
"include_in_gallery": True,
},
{
"title": "mostly_positive_test",
"exact_match_out": False,
"in": {
"column": "mixed",
"mostly": 0.1
},
"out": {
"success": True,
},
"include_in_gallery": True,
},
{
"title": "mostly_negative_test",
"exact_match_out": False,
"in": {
"column": "mixed",
"mostly": 0.3
},
"out": {
"success": False,
},
"include_in_gallery": True,
},
],
"test_backends": [
{
"backend": "pandas",
"dialects": None,
},
{
"backend": "sqlalchemy",
"dialects": ["sqlite", "postgresql"],
},
{
"backend": "spark",
"dialects": None,
},
],
}]
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
library_metadata = {
"tags": ["regex"],
"contributors": ["@joegargery"],
}
class ExpectColumnValuesToBeValidArn(RegexBasedColumnMapExpectation):
"""Expect values in this column to be a valid amazon arn."""
# These values will be used to configure the metric created by your expectation
regex_camel_name = "AmazonResourceName"
regex = "^arn:(?P<Partition>[^:\n]*):(?P<Service>[^:\n]*):(?P<Region>[^:\n]*):(?P<AccountID>[^:\n]*):(?P<Ignore>(?P<ResourceType>[^:\/\n]*)[:\/])?(?P<Resource>.*)$"
semantic_type_name_plural = "arns"
# These examples will be shown in the public gallery.
# They will also be executed as unit tests for your Expectation.
examples = [
{
"data": {
"valid_arns": [
"arn:aws:s3:::my-bucket/my-object",
"arn:partition:service:region:account-id:resource",
],
"invalid_alphanumeric": [
"apz8",
"bubba:arn:123",
],
"invalid_arn": [
"arn:aws:::::::my-bucket/my-object",
"arn::::",
],
"empty": ["", None],
},
"tests": [
{
"title": "basic_positive_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {"column": "valid_arns"},
"out": {
"success": True,
},
},
{
"title": "basic_negative_test",
"exact_match_out": False,
"include_in_gallery": True,
"in": {"column": "invalid_alphanumeric", "mostly": 1},
"out": {
"success": False,
},
},
{
"title": "invalid_non_alphanumeric",
"exact_match_out": False,
"include_in_gallery": True,
"in": {"column": "invalid_arn", "mostly": 1},
"out": {
"success": False,
},
},
{
"title": "empty",
"exact_match_out": False,
"include_in_gallery": True,
"in": {"column": "empty", "mostly": 1},
"out": {
"success": False,
},
},
],
}
]
# Here your regex is used to create a custom metric for this expectation
map_metric = RegexBasedColumnMapExpectation.register_metric(
regex_camel_name=regex_camel_name,
regex_=regex,
)
# This object contains metadata for display in the public Gallery
library_metadata = {
"maturity": "experimental",
"tags": [
"amazon",
"arn",
"expectation",
], # Tags for this Expectation in the Gallery
"contributors": [ # Github handles for all contributors to this Expectation.
"@rdodev", # Don't forget to add your github handle here!
],
}