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

csv_detective/detect_labels/other/email/__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 = [
-        'email',
-        'mail',
-        'courriel',
-        'contact',
-        'mel',
-        'lieucourriel',
-        'coordinates.emailcontact',
-        'e mail',
-        'mo mail',
-        'adresse mail',
-        'adresse email'
-    ]
-    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/float/__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 = ['part', 'ratio']
-    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/int/__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 = ['nb', 'nombre', 'nbre']
-    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/money/__init__.py

@@ -1,11 +0,0 @@
-PROPORTION = 0.5
-
-
-def _is(header):
-    '''
-    Returns 1 if at least one of the mentionned words is in the label, else 0
-    '''
-
-    words_list = ['budget', 'salaire', 'euro', 'euros', 'prêt', 'montant']
-
-    return float(any([word in header.lower() for word in words_list]))

csv_detective/detect_labels/other/money/check_col_name.py

@@ -1,8 +0,0 @@
-def is_col_name_related_to_money(name):
-    # TODO : make this a little bit more clever (spacy ?)
-    col_name_related_to_money = False
-    money_themes = ['budget', 'salaire', 'euro', 'euros', 'prêt', 'montant']
-    # TODO attention 'européeen' est détecté OK
-    for theme in money_themes:
-        col_name_related_to_money = col_name_related_to_money or (theme in name)
-    return col_name_related_to_money

csv_detective/detect_labels/other/mongo_object_id/__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 = ['id', 'objectid']
-    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/twitter/__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 = ['twitter', 'twitter account', 'twitter username']
-    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/url/__init__.py

@@ -1,48 +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 = [
-        'url',
-        'url source',
-        'site web',
-        'source url',
-        'site internet',
-        'remote url',
-        'web',
-        'site',
-        'lien',
-        'site data',
-        'lien url',
-        'lien vers le fichier',
-        'sitweb',
-        'interneturl'
-    ]
-    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/uuid/__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 = ['id', 'uuid', 'guid']
-    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/temp/date/__init__.py

@@ -1,51 +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 = [
-        'date',
-        'jour',
-        'date de mise a jour',
-        'sns date',
-        'date maj',
-        'rem date',
-        'periode',
-        'date de publication',
-        'dpc',
-        'extract date',
-        'date immatriculation',
-        'date jeu donnees',
-        'datemaj',
-        'dateouv',
-        'date der maj',
-        'dmaj',
-        'jour'
-    ]
-    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/temp/datetime_iso/__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 = [
-        'datetime iso',
-        'datetime',
-        'timestamp',
-        'osm_timestamp',
-        'date',
-        'created at',
-        'last update',
-        'date maj',
-        'createdat',
-        'date naissance',
-        'date donnees'
-    ]
-    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/temp/datetime_rfc822/__init__.py

@@ -1,44 +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 = [
-        'datetime',
-        'timestamp',
-        'osm_timestamp',
-        'date',
-        'created at',
-        'last update',
-        'date maj',
-        'createdat',
-        'date naissance',
-        'date donnees'
-    ]  # Almost same as IS0, no example in data
-    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/temp/year/__init__.py

@@ -1,44 +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 = [
-        'year',
-        'annee',
-        'annee depot',
-        'an nais',
-        'exercice',
-        'data year',
-        'annee de publication',
-        'exercice comptable',
-        'annee de naissance',
-        'annee ouverture'
-    ]
-    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)