[CG] : nettoyages des données Vertébré
This commit is contained in:
parent
b787fe6fa5
commit
090822ccd7
@ -52,6 +52,18 @@ def form_complx_grp(data):
|
||||
data.loc[data.nom_new.notna(),'nom_latin'] = data[data.nom_new.notna()].nom_new
|
||||
data.drop(columns='nom_new',inplace=True)
|
||||
|
||||
def correct_taxonomie(data):
|
||||
dict_taxo = {
|
||||
444440:'Pelophylax kl\. esculentus \(Linnaeus, 1758\)'
|
||||
}
|
||||
for k,v in dict_taxo.items():
|
||||
is_saisie = data.rmq_observation.str.contains(v,na=False)
|
||||
if not is_saisie.any():
|
||||
continue
|
||||
data.loc[is_saisie,'nom_latin'] = v
|
||||
data.loc[is_saisie,'cd_nom'] = k
|
||||
data.loc[is_saisie,'cd_ref'] = k
|
||||
|
||||
def form_precision(data):
|
||||
dict_pre = {
|
||||
'GPS':0,
|
||||
@ -79,6 +91,37 @@ def form_effectif(data):
|
||||
data.effectif = data.effectif.astype('Int64')
|
||||
data.effectif_max = data.effectif_max.astype('Int64')
|
||||
|
||||
t1 = data.effectif_min < data.effectif
|
||||
data.loc[t1,'effectif_max'] = data[t1].effectif
|
||||
data.loc[t1,'effectif'] = data[t1].effectif_min
|
||||
|
||||
|
||||
# Est trop incertain... Les effectifs récupérés sont < aux effectifs déclarés
|
||||
# ==> Incompréhansion, Ne sera pas utilisé
|
||||
def recup_faune_eff(data):
|
||||
# Récupération des effectifs standardisés du champ rmq_observation
|
||||
ismixte = data.rmq_observation.str.contains('\\d.00 Mâle\(s\) et \\d.00 Femelle\(s\)',na=False)
|
||||
ismal = data.rmq_observation.str.contains('\\d.00 Mâle\(s\) et \? Femelle\(s\)',na=False)
|
||||
isfem = data.rmq_observation.str.contains('\? Mâle\(s\) et \\d.00 Femelle\(s\)',na=False)
|
||||
data.loc[ismixte,'extract_eff'] = (data[ismixte].rmq_observation
|
||||
.str.extract('(\d+).00 Mâle\(s\) et (\d+).00 Femelle\(s\)').astype(int).sum(axis=1))
|
||||
data.loc[ismal,'extract_eff'] = (data[ismal].rmq_observation
|
||||
.str.extract('(\d+).00 Mâle\(s\) et \? Femelle\(s\)').astype(int).sum(axis=1))
|
||||
data.loc[isfem,'extract_eff'] = (data[isfem].rmq_observation
|
||||
.str.extract('\? Mâle\(s\) et (\d+).00 Femelle\(s\)').astype(int).sum(axis=1))
|
||||
|
||||
extr = data.extract_eff.notna()
|
||||
extr_sup = data.effectif < data.extract_eff
|
||||
data[extr_sup]
|
||||
age_na = data.age_faune.isna()
|
||||
no_0 = data.extract_eff > 0
|
||||
if any(age_na&no_0&ismixte):
|
||||
data.loc[age_na&no_0&ismixte,'age_faune'] = 'mixte'
|
||||
if any(age_na&no_0&ismal):
|
||||
data.loc[age_na&no_0&ismal,'age_faune'] = 'male'
|
||||
if any(age_na&no_0&isfem):
|
||||
data.loc[age_na&no_0&isfem,'age_faune'] = 'femelle'
|
||||
|
||||
def form_date(data):
|
||||
cols = data.columns[data.columns.str.contains('date')]
|
||||
for col in cols:
|
||||
@ -108,6 +151,7 @@ def recup_stadevie(data):
|
||||
|
||||
d2.age_faune = d2.age_faune.str.replace('Imago, adulte','Adulte')
|
||||
d2.age_faune = d2.age_faune.str.replace('Nymphe, immature','Immature')
|
||||
d2.id_obs = ('9999'+d2.id_obs.astype(str)).astype(int)
|
||||
|
||||
data = gpd.pd.concat([data,d2])
|
||||
|
||||
@ -137,24 +181,115 @@ def recup_stadevie(data):
|
||||
# Amphibiens
|
||||
is_amphi = data.group2_inpn == 'Amphibiens'
|
||||
is_larve = data.rmq_observation.str.contains('larve',na=False)
|
||||
is_ponte = data.rmq_observation.str.contains('ponte',na=False)
|
||||
is_tetar = data.rmq_observation.replace('ê','e',regex=True).str.contains('ponte',na=False)
|
||||
is_ponte = data.rmq_observation.str.contains('ponte|Ponte',na=False)
|
||||
is_tetar = data.rmq_observation.replace(['ê','é'],'e',regex=True).str.contains('tetard',na=False)
|
||||
is_urode = data.ordre=='Urodela'
|
||||
is_anure = data.ordre=='Anura'
|
||||
rmq_na = data.rmq_observation.isna()
|
||||
if 'obj_denombre' not in data.columns:
|
||||
data['obj_denombre'] = None
|
||||
data.loc[t3&is_amphi&is_larve,'age_faune'] = 'Larve'
|
||||
data.loc[t3&is_amphi&is_ponte,'age_faune'] = 'Oeufs'
|
||||
data.loc[t3&is_amphi&is_ponte,'obj_denombre'] = 'Ponte'
|
||||
data.loc[t3&is_amphi&is_tetar,'age_faune'] = 'Têtard'
|
||||
data.loc[t3&is_amphi&is_urode&rmq_na,'age_faune'] = 'Larve'
|
||||
data.loc[t3&is_amphi&is_anure&rmq_na,'age_faune'] = 'Ponte'
|
||||
# Corresction de 3 données de Nicolas Biron
|
||||
t3 = data.age_faune=='Oeuf/ponte/larve/nymphe/chenille...'
|
||||
data.loc[t3&(is_urode|is_anure),'age_faune'] = 'Ponte'
|
||||
# Correction de la dernière donnée restante (Marjorie Simean)
|
||||
t3 = data.age_faune=='Oeuf/ponte/larve/nymphe/chenille...'
|
||||
data.loc[t3,'age_faune'] = 'Oeufs'
|
||||
|
||||
# Définition de l'objet du dénombrement si ponte
|
||||
if 'obj_denombre' not in data.columns:
|
||||
data['obj_denombre'] = None
|
||||
isnot_ponte = ~data.rmq_observation.str.contains('nbre pontes:0',na=False)
|
||||
data.loc[is_amphi&is_ponte&isnot_ponte,'obj_denombre'] = 'Ponte'
|
||||
|
||||
# Récup stade_vie derrirère le terme @NSA
|
||||
age_isna = data.age_faune.isna()
|
||||
as_nsa = data.rmq_observation.str.contains('@NSA',na=False)
|
||||
# data.loc[age_isna&as_nsa,'test'] = (data[age_isna&as_nsa].rmq_observation
|
||||
# .str.split('@NSA :|@NSA:')
|
||||
# .str[1]
|
||||
# .str.split('/|;')
|
||||
# .str[0]
|
||||
# .str.strip())
|
||||
data.loc[age_isna&as_nsa,'age_faune'] = (data[age_isna&as_nsa].rmq_observation
|
||||
.str.split('@NSA :|@NSA:')
|
||||
.str[1]
|
||||
.str.split('/|;')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
.str.lower()
|
||||
.str.extract('(imm|juv|ad|jeune|larve)')[0])
|
||||
|
||||
# Récup stade_vie derrirère le terme Commentaires
|
||||
age_isna = data.age_faune.isna()
|
||||
as_com = data.rmq_observation.str.contains('Commentaires : \\d',na=False)
|
||||
data.loc[age_isna&as_com,'age_faune'] = (data[age_isna&as_com].rmq_observation
|
||||
.str.split('[,(.]|Code Atlas')
|
||||
.str[0].str.strip()
|
||||
.str.lower()
|
||||
.replace(
|
||||
{'femelles':'femelle','mâles':'mâle','adultes':'adulte',
|
||||
'jeunes':'jeune','juvéniles':'juvénile','larves':'larve',
|
||||
'couples':'couple','x':''},regex=True)
|
||||
.str.extract('[Commentaires : \d+ ](jeune volant|juvénile|juv|couple|adulte|ad|crapelet|femelle adulte|larve|mâle juvénile|mâle adulte|subadulte|larve \/ têtard)$')[0])
|
||||
age_isna = data.age_faune.isna()
|
||||
data.loc[age_isna&as_com,'age_faune'] = (data[age_isna&as_com].rmq_observation
|
||||
.str.split('[,(.]|Code Atlas')
|
||||
.str[0].str.strip()
|
||||
.str.lower()
|
||||
.replace(
|
||||
{'femelles':'femelle','mâles':'mâle','adultes':'adulte',
|
||||
'jeunes':'jeune','juvéniles':'juvénile','larves':'larve',
|
||||
'têtards':'têtard','couples':'couple','x':''},regex=True)
|
||||
.str.extract('[Commentaires : \d+](jeune volant|juvénile|juv|couple|adulte|ad|crapelet|femelle adulte|larve|mâle adulte|subadulte|larve / têtard)$')[0])
|
||||
|
||||
# Précision de larve / têtard
|
||||
is_impreci = data.age_faune=='larve / têtard'
|
||||
data.loc[is_impreci&is_anure,'age_faune'] = 'têtard'
|
||||
data.loc[is_impreci&is_urode,'age_faune'] = 'larve'
|
||||
|
||||
data.age_faune = (data.age_faune
|
||||
.replace({
|
||||
'ad':'Adulte',
|
||||
'Oeufs':'Oeuf',
|
||||
'imm':'Immature',
|
||||
'jeune':'Jeune',
|
||||
'juv':'Juvénile',
|
||||
'subadulte':'Sub-adulte',
|
||||
'Subadulte':'Sub-adulte',})
|
||||
.str.capitalize()
|
||||
)
|
||||
|
||||
sex_isna = data.sexe_faune.isna()
|
||||
is_male = data.age_faune.str.contains('Mâle',na=False)
|
||||
is_feml = data.age_faune.str.contains('Femelle',na=False)
|
||||
is_copl = data.age_faune.str.contains('Couple',na=False)
|
||||
is_immat = data.age_faune.str.contains('Immature',na=False)
|
||||
data.loc[sex_isna&is_male,'sexe_faune'] = 'Mâle'
|
||||
data.loc[sex_isna&is_feml,'sexe_faune'] = 'Femelle'
|
||||
data.loc[sex_isna&is_copl,'sexe_faune'] = 'Couple'
|
||||
data.loc[sex_isna&is_immat,'sexe_faune'] = 'Immature'
|
||||
|
||||
return data
|
||||
|
||||
def complete_objdenomb(data):
|
||||
asnot_denomb = data.obj_denombre.isna()
|
||||
isnot_dead = data.etat_bio != 'mort'
|
||||
as_statbio = data.statut_bio.notna()
|
||||
as_compt = data.comportement.notna()
|
||||
as_atlas = data.code_atlas.notna()
|
||||
as_age = data.age_faune.notna()
|
||||
as_sexe = data.sexe_faune.notna()
|
||||
as_repro = data.reprostatut_faune.notna()
|
||||
as_determ = data.determination.notna()
|
||||
data.loc[asnot_denomb&isnot_dead&(as_statbio|as_compt|as_atlas|as_age|as_sexe|as_repro|as_determ),'obj_denombre'] = 'individu'
|
||||
return data
|
||||
|
||||
def recup_comptmt(data):
|
||||
if 'reprostatut_faune' in data.columns:
|
||||
# Récupération du comportement après `Comp. ind` dans la colonne `rmq_observation`
|
||||
compt_isna = data.reprostatut_faune.isna()
|
||||
in_rmq = data.rmq_observation.str.contains('Comp. ind')
|
||||
data.loc[compt_isna&in_rmq,'comportement'] = (data[compt_isna&in_rmq].rmq_observation
|
||||
@ -163,41 +298,411 @@ def recup_comptmt(data):
|
||||
.str.split('|')
|
||||
.str[0]
|
||||
.str.strip())
|
||||
|
||||
# Récupération du comportement dans la colonne `reprostatut_faune`
|
||||
sex_isna = data.sexe_faune.isna()
|
||||
comp_isna = data.comportement.isna()
|
||||
lst_comp = ['ODO_Tandem','ODO_Territorial','INV_Accouplement','INV_Chant (orthoptères)','ODO_Ponte']
|
||||
t3 = (~compt_isna)&comp_isna&sex_isna&(data.reprostatut_faune.isin(lst_comp))
|
||||
lst_comp_inv = [
|
||||
'ODO_Tandem','ODO_Territorial','INV_Accouplement','INV_Chant (orthoptères)','ODO_Ponte']
|
||||
lst_comp_ver = ['OIS_Reproduction certaine (patrim)','MAM_Fécès - épreinte - urine', 'OIS_Nid avec jeune(s)',
|
||||
'OIS_Couvaison', 'CHIR_Hivernant', 'AMP_Mise bas - ponte','CHIR_Lethargie', 'OIS_Chant', # 'AMP_Indéterminé',
|
||||
'AMP_Chant','CHIR_Estivant', 'CHIR_Transit', 'OIS_Reproduction possible',
|
||||
'MAM_Alarme', 'AMP_Accouplement', 'OIS_Fuite - envol','OIS_Accouplement']
|
||||
if data.reprostatut_faune.isin(lst_comp_inv).any():
|
||||
t3 = (~compt_isna)&comp_isna&sex_isna&(data.reprostatut_faune.isin(lst_comp_inv))
|
||||
elif data.reprostatut_faune.isin(lst_comp_ver).any():
|
||||
t3 = (~compt_isna)&comp_isna&(data.reprostatut_faune.isin(lst_comp_ver))
|
||||
data.loc[t3,'comportement'] = data[t3].reprostatut_faune
|
||||
|
||||
# Récupération du comportement après `Comp. ind` dans la colonne `rmq_observation`
|
||||
# dictionnaire des transports
|
||||
dict_transport = {
|
||||
**dict.fromkeys(['transport de branche','transport de matériaux','transport de brindille','transporte une branche',"transport d'une branche",'transportant des matériaux','transportant une branche','transporte des feuilles'],'transport matériaux'),
|
||||
**dict.fromkeys(['transport de nourriture','transport nourriture','transport de poisson','transportant nourriture','Transporte une proie','transport de proie'],'transport nourriture'),
|
||||
}
|
||||
lst_rmq_comp = "chant|houspille|en chasse|{}|en vol|en survol|posé|parade|s'envole|se nourrit|se pose|tambourinage|vol migratoire|hivernage|nourrissage|couveur|nourrit|cht|cris|estivant|hivernant|Construction de nid|alarme|migration active".format('|'.join(dict_transport.keys()))
|
||||
comp_isna = data.comportement.isna()
|
||||
in_rmq = data.rmq_observation.str.contains('[%s]'%lst_rmq_comp,case=False,na=False)
|
||||
data.loc[comp_isna&in_rmq,'comportement'] = (data[comp_isna&in_rmq].rmq_observation
|
||||
.str.lower()
|
||||
.str.extract('(%s)'%lst_rmq_comp)[0]
|
||||
.replace(dict_transport))
|
||||
|
||||
def isole_rnngl():
|
||||
return
|
||||
comp_isna = data.comportement.isna()
|
||||
envol = data.rmq_observation.str.contains('Statut:Passage.')
|
||||
if any(comp_isna&envol):
|
||||
data.loc[comp_isna&envol,'comportement'] = 'en vol'
|
||||
|
||||
comp_isna = data.comportement.isna()
|
||||
data.loc[comp_isna,'comportement'] = (data[comp_isna].rmq_observation
|
||||
.replace({'x',''},regex=True)
|
||||
.str.lower()
|
||||
.str.extract('[détails : \d+ ]\((en transit)\)')[0])
|
||||
|
||||
def _get_gn_atlas():
|
||||
sch = 'ref_nomenclatures'
|
||||
tab = ['t_nomenclatures','bib_nomenclatures_types']
|
||||
bib_mnemo='CODE_ATLAS'
|
||||
sql = """
|
||||
SELECT
|
||||
a.id_nomenclature,
|
||||
a.cd_nomenclature,
|
||||
a.mnemonique mnemo,
|
||||
a.label_default as label,
|
||||
a.label_fr,
|
||||
a.definition_default definition,
|
||||
a.definition_fr def_fr,
|
||||
b.mnemonique bib_mnemo,
|
||||
b.label_default bib_label,
|
||||
b.definition_default bib_def,
|
||||
a.active
|
||||
FROM {sch}.{tab0} a
|
||||
JOIN {sch}.{tab1} b USING (id_type)
|
||||
""".format(sch=sch,tab0=tab[0],tab1=tab[1])
|
||||
if bib_mnemo is not None:
|
||||
sql += " WHERE "
|
||||
sql += "b.mnemonique = '%s'"%bib_mnemo
|
||||
return gpd.pd.read_sql_query(sql,con_gn)
|
||||
|
||||
|
||||
def recup_atlas(data):
|
||||
is_atlas = data.rmq_observation.str.contains('Code atlas',na=False)
|
||||
# is_atlas = data.rmq_observation.str.contains('Code atlas :',na=False)
|
||||
|
||||
if any(is_atlas):
|
||||
atlas = _get_gn_atlas()
|
||||
dict_code = dict(zip(atlas.cd_nomenclature.astype(int).astype(str),atlas.label_fr))
|
||||
dict_label = dict(zip(atlas.label.str.removesuffix('.'),atlas.label_fr))
|
||||
dict_autre = {
|
||||
'Mâle chanteur (ou cris de nidification) ou tambourinage en période de reproduction':'Mâle chanteur présent en période de nidification, cris nuptiaux ou tambourinage entendus, mâle vu en parade',
|
||||
'Jeunes fraîchement envolés (espèces nidicoles) ou poussins (espèces nidifuges)':'Jeunes en duvet ou jeunes venant de quitter le nid et incapables de soutenir le vol sur de longues distances'
|
||||
}
|
||||
data.loc[is_atlas,'code_atlas'] = (data[is_atlas].rmq_observation
|
||||
.str.split('Code atlas')
|
||||
.str[1]
|
||||
# .str.split('\||@|;|\(')
|
||||
.str.split(r'[|@;]')
|
||||
.str[0]
|
||||
.replace({
|
||||
**dict.fromkeys([':','Nidification possible \(','Nidification certaine \(','Nidification probable \('],''),
|
||||
'\s+':' ',
|
||||
' - ':'; '},regex=True)
|
||||
.str.strip()
|
||||
.str.replace('nuptial parades','nuptial: parades')
|
||||
.str.removesuffix(')')
|
||||
.replace('',None)
|
||||
.replace(dict_code)
|
||||
.replace(dict_autre)
|
||||
.replace(dict_label))
|
||||
|
||||
data.loc[is_atlas,'rmq1'] = (data[is_atlas].rmq_observation
|
||||
.str.split('Code atlas')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
.replace(dict.fromkeys(['Commentaires :','Remarques :','Détails : @','','nan'],None))
|
||||
)
|
||||
data.loc[is_atlas,'rmq2'] = (data[is_atlas].rmq_observation
|
||||
.str.split('Code atlas')
|
||||
.str[1]
|
||||
.str.split(r'[|@;]')
|
||||
.str[1]
|
||||
.str.strip()
|
||||
.str.removesuffix(';')
|
||||
.str.strip()
|
||||
.replace(dict.fromkeys(['','nan'],None))
|
||||
)
|
||||
data.loc[is_atlas,'rmq_observation'] = [
|
||||
' ; '.join([x,y]) if not gpd.pd.isna(y) and not gpd.pd.isna(x)
|
||||
else y if gpd.pd.isna(x)
|
||||
else x
|
||||
for x,y in zip(data[is_atlas].rmq1,data[is_atlas].rmq2)
|
||||
]
|
||||
data.rmq_observation.replace('nan',None,inplace=True)
|
||||
data.drop(columns=['rmq1','rmq2'],inplace=True)
|
||||
|
||||
atlas_isna = data.code_atlas.isna()
|
||||
rmq_atlas = {
|
||||
'2':"Observation de l'espèce pendant la période de nidification dans un biotope adéquat",
|
||||
'2':"Observation de l'espèce pendant la période de nidification",
|
||||
'4':'Couple pendant la période de nidification dans un biotope adéquat',
|
||||
}
|
||||
for k,v in rmq_atlas.items():
|
||||
as_atlas = data.rmq_observation.str.contains(v,na=False)
|
||||
data.loc[atlas_isna&as_atlas,'code_atlas'] = dict_code[k]
|
||||
|
||||
# Récupération du code atlas 99
|
||||
for i in ['99','1.00','2','3.00','3 ','4 ','4.00','5.00','5 ',
|
||||
'6','7','8','9.00','9 ','10','11 ','12 ','12.00','13',
|
||||
'14.00','14 ','15.00','16','17','18','19']:
|
||||
is_atlas = data.rmq_observation.str.contains('Code Atlas : %s'%i,na=False)
|
||||
atlas_isna = data.code_atlas.isna()
|
||||
if is_atlas.any():
|
||||
data.loc[is_atlas&atlas_isna,'code_atlas'] = str(int(float('%s'%i)))
|
||||
data.loc[is_atlas&atlas_isna,'code_atlas'] = data[is_atlas&atlas_isna].code_atlas.replace(dict_code)
|
||||
|
||||
# définition du code_atlas par le statut repro
|
||||
lst_repro = [
|
||||
'Reproduction possible','Reproduction probable','Reproduction confirmée','Nicheur possible'
|
||||
]
|
||||
|
||||
atlas_isna = data.code_atlas.isna()
|
||||
is_aves = data.group2_inpn == 'Oiseaux'
|
||||
is_repro = data.statut_bio.isin(lst_repro)
|
||||
if any(is_aves&is_repro&atlas_isna):
|
||||
data.loc[is_aves&is_repro&atlas_isna,'code_atlas'] = (data[is_aves&is_repro&atlas_isna].statut_bio
|
||||
.replace(['Reproduction','Nicheur'],'Nidification')
|
||||
.replace(dict_label))
|
||||
|
||||
# définition du code atlas par le statut repro
|
||||
atlas_isna = data.code_atlas.isna()
|
||||
dict_repro = {
|
||||
**dict.fromkeys(['couvaison','couveur','ois_couvaison'],'18'),
|
||||
**dict.fromkeys(['accouplement','ois_accouplement','parade'],'6'),
|
||||
**dict.fromkeys(['alarme'],'8'),
|
||||
**dict.fromkeys(['chant','cht','ois_chant'],'3'),
|
||||
**dict.fromkeys(['nourrissage','nourrissage des jeunes'],'16'),
|
||||
**dict.fromkeys(['ois_nid avec jeune(s)'],'19'),
|
||||
**dict.fromkeys(['ois_reproduction certaine (patrim)'],'50'),
|
||||
**dict.fromkeys(['ois_reproduction possible'],'30'),
|
||||
**dict.fromkeys(['transport matériaux'],'10'),
|
||||
}
|
||||
for k,v in dict_repro.items():
|
||||
is_repro = data.comportement.str.lower()==k
|
||||
if any(is_repro&atlas_isna):
|
||||
data.loc[is_repro&is_aves&atlas_isna,'code_atlas'] = dict_code[v]
|
||||
|
||||
# Suppression des codes atlas érronés
|
||||
is_dead = data.etat_bio=='mort'
|
||||
atlas_notna = data.code_atlas.notna()
|
||||
if any(is_dead&atlas_notna):
|
||||
data.loc[is_dead&atlas_notna,'code_atlas'] = None
|
||||
|
||||
|
||||
def form_observator(data):
|
||||
return data.observateurs_v2.replace({
|
||||
' \(CEN Isère\) \(CEN Isère\)':'',
|
||||
' \(GRPLS\) \(GRPLS\)':'',
|
||||
' \(CD Isère\) \(CD Isère\)':'',
|
||||
' \(BIOTOPE\) \(BIOTOPE\)':'',
|
||||
' \(Ecosphère\) \(Ecosphère\)':'',
|
||||
' \(FMBDS\) \(FMBDS\)':'',
|
||||
' \(Lo Parvi\) \(Lo Parvi\)':'',
|
||||
' \(LPO Rhône\) \(LPO Rhône\)':'',
|
||||
' \(Personnel\) \(Personnel\)':'',
|
||||
' \(ONCFS\) \(ONCFS\)':'',
|
||||
' \(Nature et Vie Sociale\) \(Nature et Vie Sociale\)':'',
|
||||
' \(Conservatoire d’Espaces Naturels Isère\) \(Conservatoire d’Espaces Naturels Isère\)':'',
|
||||
' \(Société Batrachologique de France\) \(Société Batrachologique de France\)':'',
|
||||
'CEN Isère':'Conservatoire d’Espaces Naturels Isère',
|
||||
},regex=True)
|
||||
|
||||
def form_coord(data):
|
||||
t1 = data.longitude_x > 10
|
||||
t2 = data.latitude_y > 50
|
||||
data.loc[t1,'longitude_x'] = data[t1].to_crs(epsg=4326).geom.x
|
||||
data.loc[t2,'latitude_y'] = data[t2].to_crs(epsg=4326).geom.y
|
||||
|
||||
def form_rmqobs(data):
|
||||
data.rmq_observation.replace({
|
||||
'Commentaires : Détails :':'Détails :',
|
||||
'Commentaires : , localisation :':'localisation :',
|
||||
},inplace=True,regex=True)
|
||||
|
||||
def recup_determ(data):
|
||||
determ_isna = data.determination.isna()
|
||||
is_statut = data.rmq_observation.str.contains('Indice de présence')
|
||||
if is_statut.any():
|
||||
data.loc[determ_isna&is_statut,'determination'] = 'Indice de présence'
|
||||
data.loc[determ_isna&is_statut,'preuve_detrm'] = (data[determ_isna&is_statut].rmq_observation
|
||||
.str.split('Indice de présence')
|
||||
.str[1]
|
||||
.str.split('|')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
.str.extract('.*\((.*)\).*')[0]
|
||||
)
|
||||
|
||||
determ_isna = data.determination.isna()
|
||||
data.loc[determ_isna,'determination'] = (data[determ_isna].rmq_observation
|
||||
.str.extract('.*\((en main|observation indirecte|vu|contact auditif|analyse de pelotes)\).*')[0]
|
||||
)
|
||||
|
||||
# determ_isna = data.determination.isna()
|
||||
# in_hand = data.rmq_observation.str.contains('\(en main\)')
|
||||
# if any(determ_isna&in_hand):
|
||||
# data.loc[determ_isna&in_hand,'determination'] = 'en main'
|
||||
|
||||
determ_isna = data.determination.isna()
|
||||
vu = data.rmq_observation.str.contains('Individu vu|Vu vivant|Commentaires \: Vu')
|
||||
if any(determ_isna&vu):
|
||||
data.loc[determ_isna&vu,'determination'] = 'Individu vu'
|
||||
|
||||
determ_isna = data.determination.isna()
|
||||
entendu = data.rmq_observation.str.contains('Individu entendu')
|
||||
if any(determ_isna&entendu):
|
||||
data.loc[determ_isna&entendu,'determination'] = 'Individu entendu'
|
||||
|
||||
determ_isna = data.determination.isna()
|
||||
photo = data.rmq_observation.str.contains('piège photo')
|
||||
if any(determ_isna&photo):
|
||||
data.loc[determ_isna&photo,'determination'] = 'Observation par piège photographique'
|
||||
|
||||
def recup_statutbio(data):
|
||||
data['statut_bio'] = None
|
||||
is_stat1 = data.rmq_observation.str.contains('Caractéristique',na=False)
|
||||
if is_stat1.any():
|
||||
statbio_isna = data.statut_bio.isna()
|
||||
data.loc[statbio_isna&is_stat1,'statut_bio'] = (data[statbio_isna&is_stat1].rmq_observation
|
||||
.str.split('Caractéristique :')
|
||||
.str[1]
|
||||
.str.split('\|')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
)
|
||||
is_stat2 = data.rmq_observation.str.contains('Statut',na=False)
|
||||
if is_stat2.any():
|
||||
statbio_isna = data.statut_bio.isna()
|
||||
data.loc[statbio_isna&is_stat2,'statut_bio'] = (data[statbio_isna&is_stat2].rmq_observation
|
||||
.str.split('Statut')
|
||||
.str[1]
|
||||
.str.strip()
|
||||
.str.removeprefix(':').str.strip()
|
||||
.str.split('\||/|;')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
.str.extract('(Migrateur|Estivage|Reproduction probable|Reproduction certaine|Reproduction possible|Hivernant)')[0]
|
||||
)
|
||||
is_stat3 = data.rmq_observation.str.contains('Critere',na=False)
|
||||
if is_stat3.any():
|
||||
statbio_isna = data.statut_bio.isna()
|
||||
data.loc[statbio_isna&is_stat3,'statut_bio'] = (data[statbio_isna&is_stat3].rmq_observation
|
||||
.str.split('Critere')
|
||||
.str[1]
|
||||
.str.strip()
|
||||
.str.removeprefix(':').str.strip()
|
||||
.str.split('\||/|;')
|
||||
.str[0]
|
||||
.str.strip()
|
||||
.str.extract('(nicheurs possibles|reproducteur)')[0]
|
||||
)
|
||||
is_stat4 = data.rmq_observation.str.contains('Commentaires',na=False)
|
||||
if is_stat4.any():
|
||||
statbio_isna = data.statut_bio.isna()
|
||||
data.loc[statbio_isna&is_stat4,'statut_bio'] = (data[statbio_isna&is_stat4].rmq_observation
|
||||
.str.split('Commentaires')
|
||||
.str[1]
|
||||
.str.strip()
|
||||
.str.removeprefix(':').str.strip()
|
||||
.str.lower()
|
||||
.str.extract('(estivant|nicheur certain|nicheur probable|nicheur|semble nicher|niche|Reproduction probable|Reproduction certaine|Reproduction possible)')[0]
|
||||
)
|
||||
|
||||
def recup_etatbio(data):
|
||||
data['etat_bio'] = None
|
||||
# Récupération de la mortalité dans le champs rmq_observation
|
||||
is_dead1 = (data.rmq_observation
|
||||
.str.lower()
|
||||
.str.contains('individu mort|trouvé mort|mort : oui',na=False))
|
||||
if is_dead1.any():
|
||||
data.loc[is_dead1,'etat_bio'] = 'mort'
|
||||
|
||||
is_dead2 = data.comportement.str.lower()=='cadavre'
|
||||
if is_dead2.any():
|
||||
data.loc[is_dead2,'etat_bio'] = 'mort'
|
||||
|
||||
# nettoyage des comportements si individu mort
|
||||
is_dead = is_dead1|is_dead2
|
||||
compt_notna = data.comportement.notna()
|
||||
if any(is_dead&compt_notna):
|
||||
data.loc[is_dead&compt_notna,'comportement'] = None
|
||||
|
||||
# adaptation de la détermination
|
||||
detm_hand = data.determination=='en main'
|
||||
if any(detm_hand&is_dead):
|
||||
data.loc[detm_hand&is_dead,'comportement'] = 'cadavre en main'
|
||||
|
||||
def recup_sexefaune(data):
|
||||
is_male = data.rmq_observation.replace({'[x.0s]':''},regex=True).str.lower().str.contains('\\d mâle',na=False)
|
||||
is_feml = data.rmq_observation.replace({'[x.0s]':''},regex=True).str.lower().str.contains('\\d femelle',na=False)
|
||||
sexe_isna = data.sexe_faune.isna()
|
||||
data.loc[sexe_isna&is_male&~is_feml,'sexe_faune'] = 'mâle'
|
||||
data.loc[sexe_isna&~is_male&is_feml,'sexe_faune'] = 'femelle'
|
||||
data.loc[sexe_isna&is_male&is_feml,'sexe_faune'] = 'mixte'
|
||||
|
||||
def format_faune(data):
|
||||
recup_sexefaune(data)
|
||||
recup_comptmt(data)
|
||||
return recup_stadevie(data)
|
||||
recup_etatbio(data)
|
||||
recup_statutbio(data)
|
||||
recup_atlas(data)
|
||||
res = recup_stadevie(data)
|
||||
return complete_objdenomb(res)
|
||||
|
||||
def format_data(data):
|
||||
form_rmqobs(data)
|
||||
data.observateurs_v2 = form_observator(data)
|
||||
form_precision(data)
|
||||
form_effectif(data)
|
||||
correct_taxonomie(data)
|
||||
form_cdnom(data)
|
||||
form_date(data)
|
||||
form_coord(data)
|
||||
form_complx_grp(data)
|
||||
recup_determ(data)
|
||||
return format_faune(data)
|
||||
|
||||
def export(path_name, data, format='csv'):
|
||||
detect_date = data.columns[data.columns.str.startswith('date')]
|
||||
data[detect_date] = data[detect_date].astype(str)
|
||||
df = data.to_wkt().drop(columns='geom',errors='ignore')
|
||||
def _export(path_name, data, format='csv'):
|
||||
if format=='xlsx':
|
||||
df.to_excel(path_name+'.%s'%format)
|
||||
data.to_excel(path_name+'.%s'%format)
|
||||
elif format=='csv':
|
||||
df.to_csv(path_name+'.%s'%format)
|
||||
data.to_csv(path_name+'.%s'%format)
|
||||
else:
|
||||
raise('format non prévu')
|
||||
|
||||
|
||||
def _filter_diffusable(path_name,data):
|
||||
if any(data.diffusable=='non'):
|
||||
no_diff = data[data.diffusable=='non'].copy()
|
||||
diff = data[data.diffusable=='oui'].copy()
|
||||
to_export = {
|
||||
path_name+'_diff':diff,
|
||||
path_name+'_no_diff':no_diff
|
||||
}
|
||||
else:
|
||||
to_export = {
|
||||
path_name:data
|
||||
}
|
||||
return to_export
|
||||
|
||||
|
||||
def _filter_uuid_sinp(to_export):
|
||||
res = {}
|
||||
for k,v in to_export.items():
|
||||
if 'unique_id_sinp' in v.columns:
|
||||
uuid_sinp = v[v.unique_id_sinp.notna()]
|
||||
not_uuid = v[v.unique_id_sinp.isna()]
|
||||
res |= {
|
||||
k+'_uuid':uuid_sinp,
|
||||
k+'_not_uuid':not_uuid
|
||||
}
|
||||
else:
|
||||
res |= {
|
||||
k:v
|
||||
}
|
||||
return res
|
||||
|
||||
def export(path_name, data, format='csv'):
|
||||
# Formatage des dates avant écriture
|
||||
detect_date = data.columns[data.columns.str.startswith('date')]
|
||||
data.loc[:,detect_date] = data[detect_date].astype(str)
|
||||
# Suppression de la colonne geom
|
||||
df = data.to_wkt().drop(columns='geom',errors='ignore')
|
||||
# Export
|
||||
_to_export = _filter_diffusable(path_name,df)
|
||||
to_export = _filter_uuid_sinp(_to_export)
|
||||
for k,v in to_export.items():
|
||||
if v.empty:
|
||||
continue
|
||||
_export(k,v,format)
|
||||
|
||||
def serena_rnngl_site():
|
||||
from sqlalchemy import create_engine # pour lecture de la bd
|
||||
from sqlalchemy.engine import URL
|
||||
@ -224,6 +729,7 @@ def serena_rnngl_site():
|
||||
.to_crs(2154)
|
||||
.dropna(subset=['geom']))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
v_synthese_invertebre = 'v_synthese_invertebre'
|
||||
@ -231,43 +737,101 @@ if __name__ == "__main__":
|
||||
v_synthese_flore = 'v_synthese_flore'
|
||||
|
||||
sit_rnngl = serena_rnngl_site()
|
||||
sql_exclude_rnngl = " (rmq_localisation NOT ILIKE '%%lemps%%' OR NOT ST_INTERSECTS(geom,'SRID=2154;{}'))".format(sit_rnngl.unary_union)
|
||||
# sql_exclude_rnngl = " (rmq_localisation NOT ILIKE '%%lemps%%' OR NOT ST_INTERSECTS(geom,'SRID=2154;{}'))".format(sit_rnngl.unary_union)
|
||||
sql_exclude_rnngl = " rmq_localisation NOT ILIKE '%%grand%%lemps%%'"
|
||||
sql_rmqloc_null = " rmq_localisation IS NULL"
|
||||
|
||||
sql_inv = "SELECT * FROM saisie.%s WHERE cd_nom <> '9999081'"%v_synthese_invertebre # 9999081 : Heterocera sp.
|
||||
v_inv = gpd.read_postgis(sql_inv+" AND"+sql_exclude_rnngl,con_sicen)
|
||||
sql_ver = "SELECT * FROM saisie.%s WHERE cd_nom <> '9999056'"%v_synthese_vertebre # 9999056 : Micromammalia sp.
|
||||
v_ver = gpd.read_postgis(sql_ver+" AND"+sql_exclude_rnngl,con_sicen)
|
||||
v_inv = gpd.read_postgis(sql_inv+" AND"+sql_exclude_rnngl,con_sicen).dropna(how='all',axis=1)
|
||||
v_inv_autre = gpd.read_postgis(sql_inv+" AND"+sql_rmqloc_null,con_sicen).dropna(how='all',axis=1)
|
||||
v_inv = gpd.pd.concat([v_inv,v_inv_autre],ignore_index=True).reset_index(drop=True)
|
||||
v_inv_rnngl = gpd.read_postgis(sql_inv+" AND"+sql_exclude_rnngl.replace('NOT ',''),con_sicen).dropna(how='all',axis=1)
|
||||
t1_inv = v_inv_rnngl.etude.str.contains('Haute Bourbre 2014')
|
||||
t2_inv = v_inv_rnngl.observateurs_v2.isin(['ZARADZKI Lise (CEN Isère)','BIRON Nicolas (CEN Isère)'])
|
||||
t3_inv = v_inv.observateurs_v2=='LUCAS Jérémie (CEN Isère)'
|
||||
t4_inv = v_inv.etude!='Echange de données - GRPLS'
|
||||
hb_inv = v_inv_rnngl[t1_inv|t2_inv].copy()
|
||||
no_stg = v_inv[t3_inv&t4_inv].copy()
|
||||
v_inv = gpd.pd.concat([v_inv,hb_inv],ignore_index=True).drop_duplicates()
|
||||
v_inv_rnngl.drop(hb_inv.index,inplace=True)
|
||||
v_inv_rnngl = gpd.pd.concat([v_inv_rnngl,no_stg],ignore_index=True).drop_duplicates()
|
||||
v_inv.drop(no_stg.index,inplace=True)
|
||||
#v_synthese_invertebre = 37915
|
||||
#v_inv.shape[0]+v_inv_rnngl.shape[0] = 37914
|
||||
#différence de 1 donnée. Correspond au taxon 9999081 dans la bdd
|
||||
|
||||
sql_ver = "SELECT * FROM saisie.%s WHERE cd_nom <> '9999056'"%v_synthese_vertebre # 9999056 : Micromammalia sp. (17 données)
|
||||
v_ver = gpd.read_postgis(sql_ver+" AND"+sql_exclude_rnngl,con_sicen).dropna(how='all',axis=1)
|
||||
v_ver_autre = gpd.read_postgis(sql_ver+" AND"+sql_rmqloc_null,con_sicen).dropna(how='all',axis=1)
|
||||
v_ver = gpd.pd.concat([v_ver,v_ver_autre],ignore_index=True).reset_index(drop=True)
|
||||
v_ver_rnngl = gpd.read_postgis(sql_ver+" AND"+sql_exclude_rnngl.replace('NOT ',''),con_sicen).dropna(how='all',axis=1)
|
||||
t1_ver = v_ver_rnngl.etude.str.contains('Haute Bourbre 2014')
|
||||
t2_ver = v_ver_rnngl.observateurs_v2.isin(['ZARADZKI Lise (CEN Isère)','BIRON Nicolas (CEN Isère)'])
|
||||
t3_ver = v_ver.observateurs_v2.isin(['LUCAS Jérémie (CEN Isère)','PRUNIER Jérôme (Personnel)', 'MAILLET Grégory (CEN Isère)','LAFON Arnaud (CEN Isère)'])
|
||||
t4_ver = v_ver.etude!='Echange de données - GRPLS'
|
||||
hb_ver = v_ver_rnngl[t1_ver|t2_ver].copy()
|
||||
sg_ver = v_ver[t3_ver&t4_ver].copy()
|
||||
v_ver = gpd.pd.concat([v_ver,hb_ver],ignore_index=True).drop_duplicates()
|
||||
v_ver_rnngl.drop(hb_ver.index,inplace=True)
|
||||
v_ver_rnngl = gpd.pd.concat([v_ver_rnngl,sg_ver],ignore_index=True).drop_duplicates()
|
||||
v_ver.drop(sg_ver.index,inplace=True)
|
||||
#v_synthese_vertebre = 102175
|
||||
#v_ver.shape[0]+v_ver_rnngl.shape[0] = 102158
|
||||
#différence de 17 donnée. Correspond au taxon 9999056 dans la bdd
|
||||
|
||||
sql_flo = 'SELECT * FROM saisie.%s'%v_synthese_flore
|
||||
v_flo = gpd.read_postgis(sql_flo+" WHERE"+sql_exclude_rnngl,con_sicen).dropna(how='all',axis=1)
|
||||
v_flo_autre = gpd.read_postgis(sql_flo+" AND"+sql_rmqloc_null,con_sicen).dropna(how='all',axis=1)
|
||||
v_flo = gpd.pd.concat([v_flo,v_flo_autre],ignore_index=True).reset_index(drop=True)
|
||||
v_flo_rnngl = gpd.read_postgis(sql_flo+" WHERE"+sql_exclude_rnngl.replace('NOT ',''),con_sicen).dropna(how='all',axis=1)
|
||||
t1_flo = v_flo_rnngl.etude.str.contains('Haute Bourbre 2014')
|
||||
t2_flo = v_flo_rnngl.observateurs_v2=='ZARADZKI Lise (CEN Isère)'
|
||||
t3_flo = v_flo.observateurs_v2=='LUCAS Jérémie (CEN Isère)'
|
||||
t4_flo = v_flo.etude!='Echange de données - GRPLS'
|
||||
hb_flo = v_flo_rnngl[t1_flo|t2_flo].copy()
|
||||
sg_flo = v_flo[t3_flo&t4_flo].copy()
|
||||
v_flo = gpd.pd.concat([v_flo,hb_flo],ignore_index=True).drop_duplicates()
|
||||
v_flo_rnngl.drop(hb_flo.index,inplace=True)
|
||||
idflo_drop = v_flo[v_flo.id_obs.isin(v_flo_rnngl.id_obs)].index
|
||||
v_flo.drop(idflo_drop,inplace=True)
|
||||
v_flo_rnngl = gpd.pd.concat([v_flo_rnngl,sg_flo],ignore_index=True).drop_duplicates()
|
||||
v_flo.drop(sg_flo.index,inplace=True)
|
||||
#v_synthese_flore = 113556
|
||||
#v_flo.shape[0]+v_flo_rnngl.shape[0] = 113556
|
||||
|
||||
v_inv = format_data(v_inv)
|
||||
format_data(v_ver)
|
||||
v_inv_explode = format_data(v_inv)
|
||||
V_VER = v_ver.copy()
|
||||
v_ver = V_VER.copy()
|
||||
v_ver_explode = format_data(v_ver)
|
||||
format_data(v_flo)
|
||||
|
||||
inv_uuid = (gpd.pd.read_csv(os.path.join(DIR,'INVERTEBRE/','ORB_UUID','donnees_importees_cen38.csv'),sep=';')
|
||||
.rename(columns={'entity_source_pk_value':'id_obs'}))
|
||||
v_inv_explode = v_inv_explode.merge(inv_uuid[['id_obs', 'unique_id_sinp']],how='left',on='id_obs')
|
||||
# list_inv = v_inv_explode[v_inv_explode.unique_id_sinp.notna()].etude.unique()
|
||||
# INVERTEBRE
|
||||
for etude in v_inv.etude.unique():
|
||||
exp_inv = v_inv[v_inv.etude==etude].copy()
|
||||
for etude in v_inv_explode.etude.unique():
|
||||
exp_inv = v_inv_explode[v_inv_explode.etude==etude].copy()
|
||||
exp_inv.dropna(how='all',inplace=True,axis=1)
|
||||
if 'complexe_groupe' in exp_inv.columns:
|
||||
exp_inv1 = exp_inv[exp_inv.complexe_groupe.notna()]
|
||||
exp_inv2 = exp_inv[exp_inv.complexe_groupe.isna()].dropna(how='all',axis=1)
|
||||
export(os.path.join(DIR,'INVERTEBRE',etude+'_GRP'),exp_inv1,format='csv')
|
||||
export(os.path.join(DIR,'INVERTEBRE',etude),exp_inv2,format='csv')
|
||||
export(os.path.join(DIR,'INVERTEBRE','INV_'+etude+'_GRP'),exp_inv1,format='csv')
|
||||
export(os.path.join(DIR,'INVERTEBRE','INV_'+etude),exp_inv2,format='csv')
|
||||
else :
|
||||
export(os.path.join(DIR,'INVERTEBRE',etude),exp_inv,format='csv')
|
||||
|
||||
export(os.path.join(DIR,'INVERTEBRE','INV_'+etude),exp_inv,format='csv')
|
||||
|
||||
# VERTEBRE
|
||||
for etude in v_ver.etude.unique():
|
||||
exp_ver = v_ver[v_ver.etude==etude].copy()
|
||||
for etude in v_ver_explode.etude.unique():
|
||||
exp_ver = v_ver_explode[v_ver_explode.etude==etude].copy()
|
||||
exp_ver.dropna(how='all',inplace=True,axis=1)
|
||||
if 'complexe_groupe' in exp_ver.columns:
|
||||
exp_ver1 = exp_ver[exp_ver.complexe_groupe.notna()]
|
||||
exp_ver2 = exp_ver[exp_ver.complexe_groupe.isna()].dropna(how='all',axis=1)
|
||||
export(os.path.join(DIR,'VERTEBRE',etude+'_GRP'),exp_ver1,format='csv')
|
||||
export(os.path.join(DIR,'VERTEBRE',etude),exp_ver2,format='csv')
|
||||
export(os.path.join(DIR,'VERTEBRE','VER_'+etude+'_GRP'),exp_ver1,format='csv')
|
||||
export(os.path.join(DIR,'VERTEBRE','VER_'+etude),exp_ver2,format='csv')
|
||||
else :
|
||||
export(os.path.join(DIR,'VERTEBRE',etude),exp_ver,format='csv')
|
||||
export(os.path.join(DIR,'VERTEBRE','VER_'+etude),exp_ver,format='csv')
|
||||
|
||||
# FLORE
|
||||
for etude in v_flo.etude.unique():
|
||||
@ -276,17 +840,18 @@ if __name__ == "__main__":
|
||||
if 'complexe_groupe' in exp_flo.columns:
|
||||
exp_flo1 = exp_flo[exp_flo.complexe_groupe.notna()]
|
||||
exp_flo2 = exp_flo[exp_flo.complexe_groupe.isna()].dropna(how='all',axis=1)
|
||||
export(os.path.join(DIR,'FLORE',etude+'_GRP'),exp_flo1,format='csv')
|
||||
export(os.path.join(DIR,'FLORE',etude),exp_flo2,format='csv')
|
||||
export(os.path.join(DIR,'FLORE','FLO_'+etude+'_locNULL'+'_GRP'),exp_flo1,format='csv')
|
||||
export(os.path.join(DIR,'FLORE','FLO_'+etude+'_locNULL'),exp_flo2,format='csv')
|
||||
else :
|
||||
export(os.path.join(DIR,'FLORE',etude),exp_flo,format='csv')
|
||||
export(os.path.join(DIR,'FLORE','FLO_'+etude+'_locNULL'),exp_flo,format='csv')
|
||||
|
||||
|
||||
# export(os.path.join(DIR,v_synthese_invertebre+'2'),v_inv.dropna(how='all',axis=1))
|
||||
# export(os.path.join(DIR,v_synthese_vertebre),v_ver.dropna(how='all',axis=1))
|
||||
# export(os.path.join(DIR,v_synthese_flore),v_flo)
|
||||
# _export(os.path.join(DIR,v_synthese_invertebre+'2'),v_inv_explode.dropna(how='all',axis=1))
|
||||
# _export(os.path.join(DIR,v_synthese_invertebre),v_inv.dropna(how='all',axis=1))
|
||||
# _export(os.path.join(DIR,v_synthese_vertebre+'2'),v_ver_explode.dropna(how='all',axis=1))
|
||||
# _export(os.path.join(DIR,v_synthese_vertebre),v_ver.dropna(how='all',axis=1))
|
||||
# _export(os.path.join(DIR,v_synthese_flore),v_flo)
|
||||
|
||||
# v_ver.etude.unique()
|
||||
# v_ver.protocole.unique()
|
||||
# v_ver.lot_donnee.unique()
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user