csv-detective 0.6.7__py3-none-any.whl → 0.9.3.dev2438__py3-none-any.whl

csv_detective/detect_labels/FR/other/siren/__init__.py

@@ -1,41 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'siren',
-        'siren organisme designe',
-        'siren organisme designant',
-        'n° siren',
-        'siren organisme',
-        'siren titulaire',
-        'numero siren'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/FR/other/siret/__init__.py

@@ -1,40 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'siret',
-        'siret d',
-        'num siret',
-        'siretacheteur',
-        'n° siret',
-        'coll siret'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/FR/other/tel_fr/__init__.py

@@ -1,45 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'telephone',
-        'tel',
-        'tel1',
-        'tel2',
-        'phone',
-        'num tel',
-        'tel mob',
-        'telephone sav',
-        'telephone1',
-        'coordinates.phone',
-        'telephone du lieu'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/FR/other/uai/__init__.py

@@ -1,50 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'uai',
-        'code etablissement',
-        'code uai',
-        'uai - identifiant',
-        'numero uai',
-        'rne',
-        "numero de l'etablissement",
-        'code rne',
-        'codeetab',
-        "code uai de l'etablissement",
-        'ref uai',
-        'cd rne',
-        'numerouai',
-        'numero d etablissement',
-        'code etablissement',
-        'numero etablissement'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py

@@ -1,41 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'jour semaine',
-        'type jour',
-        'jour de la semaine',
-        'saufjour',
-        'nomjour',
-        'jour',
-        'jour de fermeture'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py

@@ -1,33 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = ['mois de annee', 'mois']
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/__init__.py

@@ -1,43 +0,0 @@
-# flake8: noqa
-from .FR.geo import (
-    adresse,
-    code_commune_insee,
-    code_departement,
-    code_fantoir,
-    code_postal,
-    code_region,
-    commune,
-    departement,
-    insee_canton,
-    latitude_l93,
-    latitude_wgs_fr_metropole,
-    longitude_l93,
-    longitude_wgs_fr_metropole,
-    pays,
-    region
-)
-from .FR.other import (
-    code_csp_insee,
-    code_rna,
-    code_waldec,
-    csp_insee,
-    date_fr,
-    insee_ape700,
-    sexe,
-    siren,
-    siret,
-    tel_fr,
-    uai
-)
-from .FR.temp import jour_de_la_semaine, mois_de_annee
-from .geo import (
-    iso_country_code_alpha2,
-    iso_country_code_alpha3,
-    iso_country_code_numeric,
-    json_geojson,
-    latitude_wgs,
-    latlon_wgs,
-    longitude_wgs
-)
-from .other import booleen, email, float, int, money, mongo_object_id, twitter, url, uuid
-from .temp import date, datetime_iso, datetime_rfc822, year

csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py

@@ -1,41 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py

@@ -1,41 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py

@@ -1,41 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/json_geojson/__init__.py

@@ -1,42 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'json geojson',
-        'json',
-        'geojson',
-        'geo shape',
-        'geom',
-        'geometry',
-        'geo shape',
-        'geoshape'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/latitude_wgs/__init__.py

@@ -1,55 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'latitude',
-        'lat',
-        'y',
-        'yf',
-        'yd',
-        'coordonnee y',
-        'coord y',
-        'ycoord',
-        'geocodage y gps',
-        'location latitude',
-        'ylatitude',
-        'ylat',
-        'latitude (y)',
-        'latitudeorg',
-        'coordinates.latitude',
-        'googlemap latitude',
-        'latitudelieu',
-        'latitude googlemap',
-        'latitude wgs84',
-        'y wgs84',
-        'latitude (wgs84)'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/latlon_wgs/__init__.py

@@ -1,67 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = [
-        'latlon wgs',
-        'latlon',
-        'geo point',
-        'geo point 2d',
-        'wgs84',
-        'geolocalisation',
-        'geo',
-        'coordonnees finales',
-        'coordonnees',
-        'coordonnees ban',
-        'xy',
-        'geometry x y',
-        'coordonnees insee',
-        'coordonnees geographiques',
-        'position',
-        'coordonnes gps',
-        'geopoint',
-        'geom x y',
-        'coord gps',
-        'latlong',
-        'position geographique',
-        'c geo',
-        'coordonnes geoloc',
-        'lat lon',
-        'code geo',
-        'geo localisation',
-        'coordonnes geo',
-        'geo cp',
-        'x y',
-        'geo coordinates',
-        'point geo',
-        'point geo insee',
-        'coordonnees geoloc',
-        'coordonnees xy'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/geo/longitude_wgs/__init__.py

@@ -1,45 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-    #  Does not detect CRS
-    words_combinations_list = [
-        'longitude',
-        'lon',
-        'long',
-        'geocodage x gps',
-        'location longitude',
-        'xlongitude',
-        'lng',
-        'xlong',
-        'x',
-        'xf',
-        'xd'
-    ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/detect_labels/other/booleen/__init__.py

@@ -1,34 +0,0 @@
-from csv_detective.utils import full_word_strictly_inside_string
-from csv_detective.process_text import _process_text
-
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    #  Not relevant to make it match with specific words (find other rules)
-    words_combinations_list = []
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                full_word_strictly_inside_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)