Entity Annotation

from synthesized.model.models.person import all_supported_country_codes
all_supported_country_codes()

# Dictionary mapping country codes to locales
{'AR': ['es_AR'],
 'AM': ['hy_AM'],
 'AT': ['de_AT'],
 'AZ': ['az_AZ'],
 'BE': ['nl_BE', 'fr_BE'],...
 }

from synthesized.model.models.person import all_supported_country_names
all_supported_country_names()

# Dictionary mapping country codes to associated locales
{'argentina': ['es_AR'],
 'armenia': ['hy_AM'],
 'austria': ['de_AT'],
 'azerbaijan': ['az_AZ'],
 'belgium': ['nl_BE', 'fr_BE'],...
}

from synthesized.model.models.person import all_supported_locales
all_supported_locales()

# List of all supported locales
['ar_AA',
 'ar_PS',
 'ar_SA',
 'az_AZ',
 'bg_BG',...
]

synthesizer = HighDimSynthesizer(df_meta=df_meta)
synthesizer.learn(...)
df_synthesized = synthesizer.synthesize(num_rows=...)

import pandas as pd
from synthesized.metadata.value import Person
from synthesized.config import PersonLabels
from synthesized import MetaExtractor, HighDimSynthesizer

orig_df = pd.DataFrame({
        "title": ["Mr", "Ms", "Mrs"],
        "gender": ["M", "F", "F"],
        "firstname": ["John", "Jane", "Alice"],
        "lastname": ["Smith", "Doe", "Smith"],
        "email": [
            "j.smith@gmail.com",
            "jane.doe@blah.com",
            "A.S.Smith@synth.io",
        ],
        "country": ["US", "GB", "FR"],
    })

person = Person(
    name='person',
    labels=PersonLabels(
        title="title",
        gender="gender",
        firstname="firstname",
        lastname="lastname",
        email="email",
        country="country",
    )
)

df_meta = MetaExtractor.extract(df=orig_df, annotations=[person])

synthesizer = HighDimSynthesizer(df_meta=df_meta)
synthesizer.learn(orig_df)
df_synthesized = synthesizer.synthesize(num_rows=10)
df_synthesized

  title gender firstname   lastname                           email country
0    Mr      M     Peter     Harvey       peter.harvey14@davies.net      GB
1    Ms      F    Audrey  Couturier  audrey_couturier37@bonneau.com      FR
2    Mr      M    Joshua    Marquez   joshua.marquez77@mckinney.com      US
3    Mr      M    Ashley       Hall          ashley_hall@ingram.com      GB
4   Mrs      F   Melanie     Bryant       melaniebryant14@bruce.biz      GB

[5 rows x 6 columns]

import pandas as pd
from synthesized.metadata.value import Person
from synthesized.config import PersonLabels
from synthesized import MetaExtractor, HighDimSynthesizer

orig_df = pd.DataFrame({
        "title": ["Mr", "Ms", "Mrs"],
        "gender": ["M", "F", "F"],
        "firstname": ["John", "Jane", "Alice"],
        "lastname": ["Smith", "Doe", "Smith"],
        "email": [
            "j.smith@gmail.com",
            "jane.doe@blah.com",
            "A.S.Smith@synth.io",
        ],
    })

person = Person(
    name='person',
    labels=PersonLabels(
        title="title",
        gender="gender",
        firstname="firstname",
        lastname="lastname",
        email="email",
    ),
    locales=["ru_RU", "ja_JP", "it_IT"]
)

df_meta = MetaExtractor.extract(df=orig_df, annotations=[person])

synthesizer = HighDimSynthesizer(df_meta=df_meta)
synthesizer.learn(orig_df)
df_synthesized = synthesizer.synthesize(num_rows=5)
df_synthesized

  title gender  firstname lastname                           email
0    Mr      M    Леонтий  Рыбаков  леонтий.рыбаков1@yakusheva.biz
1    Ms      F   Serafina    Balbi      serafina_balbi30@sagese.it
2    Mr      M         稔      山口                稔.山口76@kato.jp
3    Mr      M  Francesco      Foa        francesco_foa@collodi.eu
4    Mr      M  Pierluigi    Roero    pierluigi.roero12@bertoni.it

[5 rows x 6 columns]

from synthesized.metadata.value import Address
from synthesized.config import AddressLabels, AddressModelConfig
from synthesized.model.models import AddressModel

config = AddressModelConfig(addresses_file=None, learn_postcodes=False)
df = pd.DataFrame({
    'postcode': ["" for _ in range(10)],
    'street': ["" for _ in range(10)],
    'full_address': ["" for _ in range(10)],
    'city': ["" for _ in range(10)]
})

annotations = [Address(
    name='Address',
    nan_freq=0.3,
    labels=AddressLabels(
        postcode='postcode', city='city',
        street='street', full_address='full_address'
    )
)]
meta = MetaExtractor.extract(df, annotations=annotations)
model = AddressModel(meta['Address'], config=config)
model.meta.revert_df_from_children(df)
model.fit(df)
model.sample(n=3)

from faker import Faker
from synthesized.metadata.value import Address
from synthesized.config import AddressLabels, AddressModelConfig
from synthesized.model.models import AddressModel

address_file_path = 'data/addresses.jsonl.gz'
config = AddressModelConfig(addresses_file=address_file_path, learn_postcodes=True)
fkr = Faker('en_GB')
df = pd.DataFrame({
    'postcode': [fkr.postcode() for _ in range(10)],
    'street': [fkr.street_name() for _ in range(10)],
    'full_address': [fkr.address() for _ in range(10)],
    'city': [fkr.city() for _ in range(10)]
})

annotations = [Address(name='Address', nan_freq=0.3,
                labels=AddressLabels(postcode='postcode', city='city',
                                    street='street', full_address='full_address'))]
meta = MetaExtractor.extract(df, annotations=annotations)
model = AddressModel(meta['Address'], config=config)
model.meta.revert_df_from_children(df)
model.fit(df)
model.sample(n=3)