update code

0_FONCIER/grant_table.py

@@ -46,7 +46,7 @@ def revoke_all_table(con,sch):
     
 
 if __name__ == "__main__":
-    sch_cad = '38_202501'
+    sch_cad = '26_202504'
-    sch_old = '42_202207'
+    sch_old = '38_202501'
     grant_all_table(con_cad,sch_cad)
     # revoke_all_table(con_cad,sch_old)

3_AZALEE/insert_ps.py

@@ -106,7 +106,7 @@ def format_date(df):
     df.date = pd.to_datetime(df.date,format='%d%b%Y')
 
   if table == '"PS_BIEVRE_CEN38_2016"':
-    df.date = df.date.astype(str).replace('\.','',regex=True)
+    df.date = df.date.astype(str).replace(r'\.','',regex=True)
     df.date = df.date.str.rsplit(' ',1).str[0]\
       .replace(['avr','mai','juin','juil'],['apr','may','jun','jul'],regex=True)
     df.date = pd.to_datetime(df.date,format='%d %b %Y')
@@ -541,7 +541,7 @@ def normalize_formatIdsite(id_site):
   import re
   df = pd.DataFrame({'id_site':id_site})
   df['dept'] = '38'
-  df[['org','num','other']] = [re.split('(\d+)',s) for s in [*df.id_site]]
+  df[['org','num','other']] = [re.split(r'(\d+)',s) for s in [*df.id_site]]
   del df['other']
   df.loc[df.num.str.len() == 1,'num'] = '000'+ df.loc[df.num.str.len() == 1,'num']
   df.loc[df.num.str.len() == 2,'num'] = '00' + df.loc[df.num.str.len() == 2,'num']
@@ -601,7 +601,7 @@ def normalize_pratiques(prat):
   p = normalize_paturage(p)
   p = p.replace(dic)
   p.fillna('N.D', inplace=True)
-  p[p.str.contains('\?| ou ',na=False)] = 'incertain'
+  p[p.str.contains(r'\?| ou ',na=False)] = 'incertain'
   pp = p.str.split(',',expand=True)
   pp.columns = 'p' + pp.columns.astype(str)
   for c in pp.columns:
@@ -903,7 +903,7 @@ def insert_attrsPS(df,ps_statut='actif'):
     del df['pratiques']
 
   for col in params:
-    df[col] = df[col].astype(str).replace(['\.0'],[''],regex=True)
+    df[col] = df[col].astype(str).replace([r'\.0'],[''],regex=True)
 
   if 'niv_embrous' in df.columns:
     df.niv_embrous.replace(['nan'],['N.D'],inplace=True)
@@ -971,9 +971,9 @@ def insert_attrsPS(df,ps_statut='actif'):
 
 def split_codehab(lst_codehab):
   lst = lst_codehab.copy()
-  lst = lst.str.split('x|X|,|&|/|\(|et',expand=True) \
+  lst = lst.str.split(r'x|X|,|&|/|\(|et',expand=True) \
     .stack().str.strip() \
-    .str.replace('\)','',regex=True)\
+    .str.replace(r'\)','',regex=True)\
     .droplevel(-1).reset_index(drop=False)
   return lst
 
@@ -994,7 +994,7 @@ def format_codehab2insert(lst_codehab):
   suspect = lst.code_hab.str.split('(',expand=True)
   if suspect.shape[1] > 1:
     suspect[0] = suspect[0].str.strip()
-    suspect[1] = suspect[1].str.replace('\)','',regex=True)
+    suspect[1] = suspect[1].str.replace(r'\)','',regex=True)
     suspect.columns = ['code_hab','suspect']
     del lst['code_hab']
     # raise Exception('habitat suspecté en développement')
@@ -1011,7 +1011,7 @@ def insert_cbPS(df):
   drop_col = ['auteur','structure']
   df = df.copy()
   df.date = df.date.astype(str)
-  df.code_hab = df.code_hab.replace(['\*'],[''],regex=True).str.strip()
+  df.code_hab = df.code_hab.replace([r'\*'],[''],regex=True).str.strip()
   df.code_hab = df.code_hab.replace(['None','nan','0'],[None,None,None])
   df.dropna(subset=['code_hab'],inplace=True)
   ids = select_ID(df[df.columns.drop(['code_hab',*drop_col])],sch=pycen.ps.schema,tab='r_site_habitat')
@@ -1061,7 +1061,7 @@ def insert_habPS(df,ps_statut='actif'):
   #   df[t] = df[t].astype(str)
   df = df.stack().reset_index(-1)
   df.columns = ['param','value']
-  df[['param','index','other']] = [re.split('(\d+)',s) for s in [*df.param]]
+  df[['param','index','other']] = [re.split(r'(\d+)',s) for s in [*df.param]]
   del df['other']
   df['index'] = df['index'].astype(int)
   df['value'] = df['value'].replace(['-'],[None])
@@ -1137,7 +1137,7 @@ def filter_saisierror(df):
   tmp.set_index([*cc], inplace=True)
   tmp = tmp.stack().reset_index(-1)
   tmp.columns = ['param','value']
-  tmp[['param','index','other']] = [re.split('(\d+)',s) for s in [*tmp.param]]
+  tmp[['param','index','other']] = [re.split(r'(\d+)',s) for s in [*tmp.param]]
   del tmp['other']
   tmp['index'] = tmp['index'].astype(int)
   tmp['value'] = tmp['value'].replace(['-'],[None])
@@ -1180,7 +1180,7 @@ def filter_saisierror(df):
 
 
   cb = pycen.ref_hab().get_CB()
-  tmp.code_hab = tmp.code_hab.replace(['\*'],[''],regex=True).str.strip()
+  tmp.code_hab = tmp.code_hab.replace([r'\*'],[''],regex=True).str.strip()
   tmp.code_hab = tmp.code_hab.replace(['0'],[None])
   tmp.dropna(subset=['code_hab'], inplace=True)
   tmpp = tmp[['id_site','index','code_hab']].copy()
@@ -1303,8 +1303,9 @@ if __name__ == "__main__":
   ]
   # from_table = '"cr_ECRIN_habitats_CBNA_2014"'
   from_table = None
-  from_file  = 'PS38_modifs_AG_2024.gpkg'
+  from_file  = 'PS prioritaire.geojson'
-  path0 = '/home/colas/Documents/9_PROJETS/2_PS/TO IMPORT/2024/'
+  from_tab = 'Tableau_saisie_PS_2026.xlsx'
+  path0 = '/home/colas/Documents/9_PROJETS/2_PS/TO IMPORT/2026/'
 
   # org = from_file.split('/')[1]
   tutu = pd.DataFrame()

5_GEONATURE/EXPORT/v_synthese_zones_humides.py

@@ -1,9 +1,6 @@
 from pycen import con_gn
 
-sql = '''
+sql0 = '''
-DROP VIEW IF EXISTS gn_exports.v_synthese_zones_humides;
-
-CREATE VIEW gn_exports.v_synthese_zones_humides AS
 with habitats as (
     SELECT 
 	    zh_uuid,
@@ -25,8 +22,7 @@ with habitats as (
 	FROM pr_zh.t_zh 
 	LEFT JOIN pr_zh.cor_zh_lim_fs USING (id_zh)
 	group by 1 order by 1
-), activ_hum AS (
+), v_activity AS (
-    WITH v_activity AS (
         SELECT
             id_zh, 
             json_agg(ref_nomenclatures.get_nomenclature_label(cor_impact_types.id_impact)) impacts
@@ -34,38 +30,60 @@ with habitats as (
         LEFT JOIN pr_zh.cor_impact_list USING (id_impact_list)
         LEFT JOIN pr_zh.cor_impact_types USING (id_cor_impact_types)
         group by 1 order by 1
-    )
+), activ_hum AS (
     SELECT 
         zh_uuid,
-        json_agg(json_build_object(
+        json_agg(CASE WHEN t_activity.id_activity IS NULL
-            'activite', ref_nomenclatures.get_nomenclature_label(t_activity.id_activity),
+            THEN NULL
-            'position', ref_nomenclatures.get_nomenclature_label(t_activity.id_position),
+            ELSE json_build_object(
-            'impact', v_activity.impacts,
+                'activite', ref_nomenclatures.get_nomenclature_label(t_activity.id_activity),
-            'rmq_activ', t_activity.remark_activity
+                'position', ref_nomenclatures.get_nomenclature_label(t_activity.id_position),
-        )) AS activ_hum
+                'impact', v_activity.impacts,
+                'rmq_activ', t_activity.remark_activity
+            ) 
+        END) AS activ_hum
     FROM pr_zh.t_zh 
     LEFT JOIN pr_zh.t_activity USING (id_zh)
     LEFT JOIN v_activity USING (id_zh)
     group by zh_uuid order by 1
+--), activ_hum_test AS (
+--    SELECT 
+--        zh_uuid,
+--        CASE WHEN t_activity.id_activity IS NOT NULL
+--        	THEN jsonb_build_object(
+--	            ref_nomenclatures.get_nomenclature_label(t_activity.id_activity), v_activity.impacts
+--	        ) 
+--	       ELSE NULL 
+--        END AS activ_hum_test
+--    FROM pr_zh.t_zh 
+--    LEFT JOIN pr_zh.t_activity USING (id_zh)
+--    LEFT JOIN v_activity USING (id_zh)
+--    --group by zh_uuid order by 1
 ), inflow as (
     SELECT 
         zh_uuid,
-        json_agg(json_build_object(
+        json_agg(CASE WHEN t_inflow.id_inflow IS NULL
+            THEN NULL
+            ELSE json_build_object(
             'entree_eau', ref_nomenclatures.get_nomenclature_label(t_inflow.id_inflow),
             'perm', ref_nomenclatures.get_nomenclature_label(t_inflow.id_permanance),
             'topo', t_inflow.topo
-        )) AS entree_eau
+            ) 
+        END) AS entree_eau
     FROM pr_zh.t_zh 
     LEFT JOIN pr_zh.t_inflow USING (id_zh)
     group by zh_uuid
 ), outflow as (
     SELECT 
         zh_uuid,
-        json_agg(json_build_object(
+        json_agg(CASE WHEN t_outflow.id_outflow IS NULL
-            'sortie_eau', ref_nomenclatures.get_nomenclature_label(t_outflow.id_outflow),
+            THEN NULL
-            'perm', ref_nomenclatures.get_nomenclature_label(t_outflow.id_permanance),
+            ELSE json_build_object(
-            'topo', t_outflow.topo
+                'sortie_eau', ref_nomenclatures.get_nomenclature_label(t_outflow.id_outflow),
-        )) AS sortie_eau
+                'perm', ref_nomenclatures.get_nomenclature_label(t_outflow.id_permanance),
+                'topo', t_outflow.topo
+            ) 
+        END) AS sortie_eau
     FROM pr_zh.t_zh 
     LEFT JOIN pr_zh.t_outflow USING (id_zh)
     group by zh_uuid
@@ -247,11 +265,13 @@ SELECT
     zh_uuid,
     code,
     main_name,
-    CONCAT(crea_role.nom_role, ' ', crea_role.prenom_role) crea_author,
+    --concat(crea_role.nom_role, ' ', crea_role.prenom_role) AS crea_author,
-    CONCAT(updt_role.nom_role, ' ', updt_role.prenom_role) updt_author,
+    --bib_org.name AS organisme,
-    bib_org.name organisme,
+    --concat(updt_role.nom_role, ' ', updt_role.prenom_role) AS updt_author,
+    bib_org_user_updt.nom_organisme as org_updt,
     create_date crea_date,
     update_date updt_date,
+    --ST_TRANSFORM(geom,2154)::geometry(geometry,2154) geom,
     geom,
     area surface,
     rb.river_bassin,
@@ -259,27 +279,43 @@ SELECT
     zh_area_com.commune,
     ref_nomenclatures.get_nomenclature_label(id_sdage) sdage,
 	ref_nomenclatures.get_nomenclature_label(id_sage) sage,
-    habitats.habitats,
+    CASE WHEN habitats.habitats::text = '[null]'
+        THEN NULL
+        ELSE habitats.habitats
+    END AS habitats,
     remark_pres descript,
     crit_delim.crit_delim,
     remark_lim rmq_delilm,
-    esp_fs.crit_esp_fs,
+    CASE WHEN esp_fs.crit_esp_fs::text = '[null]'
+        THEN NULL
+        ELSE esp_fs.crit_esp_fs
+    END AS crit_esp_fs,
     remark_lim_fs rmq_esp_fs,
-    ef_area,
+    --ef_area,
-    v_habref v_hab,
+    --v_habref v_hab,
-    activ_hum.activ_hum,
+    CASE WHEN activ_hum.activ_hum::text = '[null]'
+        THEN NULL
+        ELSE activ_hum.activ_hum::text
+    END AS activ_hum,
+--    activ_hum_test.activ_hum_test,
     ref_nomenclatures.get_nomenclature_label(id_thread) bilan_menace,
-    inflow.entree_eau,
+    CASE WHEN inflow.entree_eau::text = '[null]'
-    outflow.sortie_eau,
+        THEN NULL
+        ELSE inflow.entree_eau::text
+    END AS entree_eau,
+    CASE WHEN outflow.sortie_eau::text = '[null]'
+        THEN NULL
+        ELSE outflow.sortie_eau::text
+    END AS sortie_eau,
     ref_nomenclatures.get_nomenclature_label(id_frequency) freq_sub,
     ref_nomenclatures.get_nomenclature_label(id_spread) extend_sub,
     ref_nomenclatures.get_nomenclature_label(id_connexion) connex,
     ref_nomenclatures.get_nomenclature_label(id_diag_hydro) diag_hydro,
     ref_nomenclatures.get_nomenclature_label(id_diag_bio) diag_bio,
-    functions.hydro,
+    functions.hydro::text,
-    functions.bio,
+    functions.bio::text,
-    functions.int_patrim,
+    functions.int_patrim::text,
-    functions.val_socio,
+    functions.val_socio::text,
     remark_eval_functions eval_fcts,
     remark_eval_heritage eval_heritage,
     remark_eval_thread eval_menace,
@@ -293,19 +329,21 @@ SELECT
     especes.nb_flora nb_flora_sp,
     especes.nb_vertebrates nb_vertebrate_sp,
     especes.nb_invertebrates nb_invertebrate_sp,
-    inventaire.inventaire,
+    inventaire.inventaire::text,
-    actions.prio_actions,
+    actions.prio_actions::text,
-    instrument.instrument,
+    instrument.instrument::text,
-    urba.docs_urba
+    urba.docs_urba::text
     --remark_is_other_inventory
 FROM pr_zh.t_zh
 JOIN utilisateurs.t_roles crea_role ON t_zh.create_author = crea_role.id_role
 LEFT JOIN utilisateurs.t_roles updt_role ON t_zh.update_author = updt_role.id_role
+LEFT JOIN utilisateurs.bib_organismes bib_org_user_updt on updt_role.id_organisme = bib_org_user_updt.id_organisme
 LEFT JOIN pr_zh.bib_organismes bib_org USING (id_org) 
 LEFT JOIN habitats USING (zh_uuid)
 LEFT JOIN crit_delim USING (zh_uuid)
 LEFT JOIN esp_fs USING (zh_uuid)
 LEFT JOIN activ_hum USING (zh_uuid)
+--LEFT JOIN activ_hum_test USING (zh_uuid)
 LEFT JOIN inflow USING (zh_uuid)
 LEFT JOIN outflow USING (zh_uuid)
 LEFT JOIN functions USING (zh_uuid)
@@ -317,11 +355,37 @@ LEFT JOIN actions USING (id_zh)
 LEFT JOIN zh_area_com USING (id_zh)
 LEFT JOIN dep USING (id_zh)
 LEFT JOIN inventaire USING (id_zh)
+'''
+
+sql_zh_all = '''
+DROP VIEW IF EXISTS gn_exports.v_synthese_zones_humides;
+
+CREATE VIEW gn_exports.v_synthese_zones_humides AS
+''' + sql0 + '''
 --group BY zh_uuid
-WHERE code not like '38CENIS%%'
+WHERE code not like '38CENIS%%' 
+    AND ref_nomenclatures.get_cd_nomenclature(id_sdage)::int > 0
+    --id_sdage > 0
 order by code
 ;
 '''
 
 with con_gn.begin() as cnx:
-    cnx.execute(sql)
+    cnx.execute(sql_zh_all)
+
+
+sql_zh_38 = '''
+DROP VIEW IF EXISTS gn_exports.v_synthese_zones_humides_isere;
+
+CREATE VIEW gn_exports.v_synthese_zones_humides_isere AS
+''' + sql0 + '''
+--group BY zh_uuid
+WHERE code not like '38CENIS%%' 
+    AND dep.departement::jsonb @> '"Isère"'
+    AND ref_nomenclatures.get_cd_nomenclature(id_sdage)::int > 0
+order by code
+;
+'''
+
+with con_gn.begin() as cnx:
+    cnx.execute(sql_zh_38)

5_GEONATURE/pivot_bdc_status_v2.py

@@ -24,6 +24,7 @@ def get_status(lst,con):
             t.nom_valide,
             t.lb_nom,
             --s.*
+            s.cd_sig,
             s.rq_statut,
             s.code_statut,
             s.cd_type_statut,
@@ -202,12 +203,65 @@ def get_taxon_status(lst,api):
     }
     return pd.DataFrame({**phylo,**cd_status})
 
+
+def filter_bio_geo(df,zone_bio):
+    idNotBioGeo = []
+    # Filtre du dommaine biogeographique sur la plaine Rhodanienne et Alpine
+    test_rhod = df.rq_statut.str.contains('rhodanienne : Non déterminante',na=False)
+    test_alpi = df.rq_statut.str.contains('Alpine : Non déterminante',na=False)
+    
+    if zone_bio == 'rhod':
+        idNotBioGeo = df[test_rhod].index
+    elif zone_bio == 'alpi':
+        idNotBioGeo = df[test_alpi].index
+    elif zone_bio == 'all':
+        idNotBioGeo = df[test_rhod&test_alpi].index
+
+    if not idNotBioGeo.empty:
+        df.drop(idNotBioGeo, inplace=True)
+
+    return df
+
+
+def form_territoire(df,terr):
+    is_dep = df.cd_sig.str.contains('INSEED')
+    dep = (
+        ['38','42','07','26'] if terr == 'platiere' else
+        ['38','69','01'] if terr == 'negria' else ['38']
+    )
+    keep_not = df[is_dep&(~df.cd_sig.str[-2:].isin(dep))].index
+    df.drop(keep_not,inplace=True)
+    
+    is_dep = df.cd_sig.str.contains('INSEED')
+    is_38  = df.cd_sig=='INSEED38'
+
+    if terr == 'isere':
+        filter_id = df[is_dep&(~is_38)].index
+        df.drop(filter_id,inplace=True)
+    else:
+        lst_stat = df[is_dep&(~is_38)].cd_type_statut.unique()
+        # is_lst = df.cd_type_statut.isin(lst_stat)
+        df.loc[is_dep&(~is_38),'cd_type_statut'] = ( df[is_dep&(~is_38)]
+            .cd_type_statut + '_' + df[is_dep&(~is_38)].cd_sig.str.strip('INSEED')    
+        )
+        df.loc[is_38,'cd_type_statut'] = ( df[is_38]
+            .cd_type_statut + '_38'    
+        )
+
+    return df
+
+
 dict_dep = {
     '38':'Isère',
     '42':'Loire',
     '07':'Ardèche',
     '26':'Drôme',
 }
+
+
+cols_rename = {
+    'nom_vernaculaire': 'nom_vern'
+}
     
 
 if __name__ == "__main__":
@@ -219,19 +273,33 @@ if __name__ == "__main__":
     # Paramètres de chargement du fichier des taxons
     PATH0 = '/home/cgeier/Téléchargements'
     PATH = ''
-    file = 'CHASS_synthese_observations_2026-01-28.xlsx'
+    file = 'synthese_observations_2026-04-23.xlsx'
-    sheet = 'liste sp'
+    sheet = 'observations'
+    zone_bio_znieff = 'rhod' # ['rhod', 'alpi', 'all']
+    territoire = 'negria' # ['isere', 'platiere','negria']
+    # [GEOMETRY PARAMS]
+    keep_geomtype = None # ['polygon', 'point', 'ligne', None]
+    geom_col = 'geometrie_wkt_4326'
 
     # Liste des CD_NOM en entrée
-    cd_col = 'cd_ref'   # Nom de la colonne à utiliser dans le feuillet ``sheet``
+    cd_col = 'cd_nom'   # Nom de la colonne à utiliser dans le feuillet ``sheet``
+
 
     # Lecture des données
     taxlist = pd.read_excel(os.path.join(PATH0,PATH,file),sheet,usecols=[cd_col],header=0)
     tab_sp = pd.read_excel(os.path.join(PATH0,PATH,file),sheet,index_col=cd_col)
+    tab_sp.rename(columns=cols_rename,inplace=True)
+
+    # Exclusion d'un type de géométrie
+    if keep_geomtype is not None:
+        as_geom = tab_sp[geom_col].str.contains(keep_geomtype.upper(),na=False)
+        tab_sp = tab_sp[as_geom]
+        taxlist = taxlist[taxlist.cd_nom.isin(tab_sp.index.tolist())]
+
     lst =  taxlist[cd_col]
     
     # Récupération des statuts
-    df = get_status(taxlist[cd_col].astype(str),con_gn)
+    df = get_status(taxlist[cd_col].astype(str).unique(),con_gn)
     typ = get_type_status(con_gn)
     typ = typ[typ.cd_type_statut.isin(df.cd_type_statut.unique())]
 
@@ -241,32 +309,70 @@ if __name__ == "__main__":
     df.loc[is_lrr & (df.niveau_admin == 'Ancienne région'),'cd_type_statut'] = 'LRR_RA'
     del df['niveau_admin']
 
-    for c in ['cd_ref','cd_nom','lb_nom']:
+    # Filtre du dommaine biogeographique sur la plaine Rhodanienne et Alpine
-        if c in tab_sp.columns:
+    df = filter_bio_geo(df,zone_bio_znieff)
-        # if 'cd_nom' not in df.columns and c == 'cd_ref': continue
-            tab_sp.drop(c,axis=1,inplace=True)
 
-    pivot = pd.pivot_table(
+    # Filtre des statuts vis à vis du territoire d'intérêts
+    # Conservation des statuts Adrèche, Drôme et Loire pour la Platière
+    df = form_territoire(df,territoire)
+
+    # for c in ['cd_ref','cd_nom','lb_nom']:
+    #     if c in tab_sp.columns:
+    #     # if 'cd_nom' not in df.columns and c == 'cd_ref': continue
+    #         tab_sp.drop(c,axis=1,inplace=True)
+
+    keep_cols = same_col = df.columns[df.columns.isin(tab_sp.reset_index(drop=False).columns)]
+    as_vern = keep_cols.str.contains('vern').any()
+    as_numb = keep_cols.str.contains('nombre').any()
+    if not as_vern:
+        keep_cols = [*keep_cols,'nom_vern']
+    if not as_numb:
+        keep_cols = [*keep_cols,'nombre_min','nombre_max']
+    else:
+        same_col = [x for x in keep_cols if x not in ['nombre_min','nombre_max']]
+
+    piv = pd.pivot_table(
         df,
         values='code_statut',
-        index=['cd_nom', 'cd_ref','lb_nom'#,'niveau_admin','lb_adm_tr'
+        index=['cd_nom', 'cd_ref','lb_nom','nom_vern'#,'niveau_admin','lb_adm_tr'
         ],
         columns=['cd_type_statut'],
         aggfunc=list,fill_value=None)
 
-    for c in pivot.columns:
+    for c in piv.columns:
-        pivot[c] = [x[0] if x is not np.NaN and len(x)==1 else x for x in pivot[c]]
+        piv[c] = [x[0] if x is not np.NaN and len(x)==1 else x for x in piv[c]]
-    if 'DH' in pivot.columns:
+    if 'DH' in piv.columns:
-        pivot['DH'] = [','.join(x) if (x is not np.NaN) and (len(x)==2) else x for x in pivot['DH']]
+        piv['DH'] = [','.join(x) if (x is not np.NaN) and (len(x)==2) else x for x in piv['DH']]
-        pivot.DH.replace({'CDH':''},regex=True,inplace=True)
+        piv.DH.replace({'CDH':''},regex=True,inplace=True)
+    # piv.reset_index(-1, inplace=True)
 
-    pivot = tab_sp.merge(pivot,on=[cd_col],how='left')
+    # tabsp_nb = tab_sp.reset_index(drop=False)[[*same_col,'nombre_min','nombre_max']].groupby([*same_col]).sum()
+    tabsp_nb = (
+        tab_sp.reset_index(drop=False)[same_col]
+        .drop_duplicates()
+        .merge(
+            tab_sp.reset_index(drop=False)[[cd_col,'nombre_min','nombre_max','date_debut','date_fin']]
+            .groupby([cd_col])
+            .agg({
+                'nombre_min':'sum',
+                'nombre_max':'sum',
+                'date_debut':'min',
+                'date_fin':'max'
+            }),
+            on = cd_col
+        )
+    )
+    tabsp_nb.set_index(cd_col,inplace=True)
+    tabsp_nb.sort_index(inplace=True)
+    
+    # pivot = tab_sp.merge(piv,on=[cd_col],how='left')
+    pivot = tabsp_nb.merge(piv,on=[cd_col],how='left')
 
     pivlib = pd.pivot_table(
         df,
         values='label_statut',
         index=[
-            'cd_nom', 'cd_ref','lb_nom'#,'niveau_admin','lb_adm_tr'
+            'cd_nom', 'cd_ref','lb_nom','nom_vern'#,'niveau_admin','lb_adm_tr'
         ],
         columns=['cd_type_statut'],
         aggfunc=list,fill_value=None)
@@ -276,10 +382,18 @@ if __name__ == "__main__":
         pivlib['DH'] = [','.join(x) if (x is not np.NaN) and (len(x)==2) else x for x in pivlib['DH']]
         pivlib.DH.replace({'CDH':''},regex=True,inplace=True)
 
-    pivlib = tab_sp.merge(pivlib,on=[cd_col],how='left')
+    # pivlib = tab_sp.merge(pivlib,on=[cd_col],how='left')
+    pivotlib = tabsp_nb.merge(pivlib,on=[cd_col],how='left')
+
+    tx_nb_missing = df[~df.cd_nom.isin(tabsp_nb.index)].shape[0]
+    if tx_nb_missing > 0:
+        print('WARNING : %i taxon(s) is MISING !! \n'%tx_nb_missing)
 
     print('INIT writer')
     NAME_OUT = os.path.join('~/',sheet+'_status.xlsx')
+    if keep_geomtype is not None:
+        NAME_OUT = NAME_OUT[:-5]+' (%s only).xlsx'%keep_geomtype.lower()
+
     with pd.ExcelWriter(NAME_OUT) as writer:
         df.to_excel(
             writer,sheet_name='v_bdc_status',index=False
@@ -291,7 +405,7 @@ if __name__ == "__main__":
             )
         # writer.save()
         print('pivot_table OK !')
-        pivlib.to_excel(
+        pivotlib.to_excel(
             writer,sheet_name='pivot_libel'
             )
         # writer.save()
@@ -301,3 +415,5 @@ if __name__ == "__main__":
             )
         # writer.save()
         print('dic_type_statut OK !')
+    print('END writing %s'%NAME_OUT)
+