Validation 27/03/22 - 21h21

master
ChérifBALDE 2022-03-27 21:39:44 +02:00 committed by cherif
parent f97f9e2a6f
commit 5035c1c26d
6 changed files with 13144 additions and 30 deletions

File diff suppressed because it is too large Load Diff

View File

@ -887,27 +887,16 @@ def get_class(diction):
'''
Statistique : Insertion du recherche - resultat '''
ret_val_tmp = coll_search_result.insert_one(mydict_combined)
if (ret_val_tmp is False):
mycommon.myprint(str(inspect.stack()[0][3]) + " - Impossible de mettre à jour la table des resultat"
" d'une recherche de formation. Voir _id = ")
if (ret_val_tmp is False):
mycommon.myprint(str(inspect.stack()[0][3]) + " - Impossible de mettre à jour la table des resultat"
" d'une recherche de formation. Voir _id = ")
return False, "Impossible de faire un affichage detaillé "
mycommon.myprint(str(retVal))
user = retVal
RetObject.append(JSONEncoder().encode(user))
return True, RetObject

View File

@ -1,9 +1,42 @@
,index,mots,occurence,moyenne,id_formation,source_field
0,0,renforc,1,0.11,8866,default
1,1,comptabilit,1,0.11,8866,default
2,2,fondamental,1,0.11,8866,default
3,3,semain,2,0.22,8866,default
4,4,programm,1,0.11,8866,default
5,5,def,1,0.11,8866,default
6,6,7,1,0.11,8866,default
7,7,publiqu,1,0.11,8866,default
0,0,"
",1,0.02,mysy_ytubes_04,default
1,1,analys,1,0.02,mysy_ytubes_04,default
2,2,bt,1,0.02,mysy_ytubes_04,default
3,3,licenc,1,0.02,mysy_ytubes_04,default
4,4,charg,1,0.02,mysy_ytubes_04,default
5,5,notion,1,0.02,mysy_ytubes_04,default
6,6,cout,3,0.05,mysy_ytubes_04,default
7,7,analyt,1,0.02,mysy_ytubes_04,default
8,8,ge,3,0.05,mysy_ytubes_04,default
9,9,gratuit,1,0.02,mysy_ytubes_04,default
10,10,depart,1,0.02,mysy_ytubes_04,default
11,11,iut,1,0.02,mysy_ytubes_04,default
12,12,comptabilit,6,0.1,mysy_ytubes_04,default
13,13,different,1,0.02,mysy_ytubes_04,default
14,14,niveau,1,0.02,mysy_ytubes_04,default
15,15,prix,1,0.02,mysy_ytubes_04,default
16,16,professeur,1,0.02,mysy_ytubes_04,default
17,17,sorbon,1,0.02,mysy_ytubes_04,default
18,18,introduct,1,0.02,mysy_ytubes_04,default
19,19,nord,1,0.02,mysy_ytubes_04,default
20,20,cour,3,0.05,mysy_ytubes_04,default
21,21,incorpore,1,0.02,mysy_ytubes_04,default
22,22,lign,1,0.02,mysy_ytubes_04,default
23,23,universit,1,0.02,mysy_ytubes_04,default
24,24,stmg,1,0.02,mysy_ytubes_04,default
25,25,villetan,1,0.02,mysy_ytubes_04,default
26,26,dcg,1,0.02,mysy_ytubes_04,default
27,27,marg,1,0.02,mysy_ytubes_04,default
28,28,general,1,0.02,mysy_ytubes_04,default
29,29,paris,1,0.02,mysy_ytubes_04,default
30,30,corinn,1,0.02,mysy_ytubes_04,default
31,31,debut,1,0.02,mysy_ytubes_04,default
32,32,calcul,1,0.02,mysy_ytubes_04,default
33,33,1,2,0.03,mysy_ytubes_04,default
34,34,gestion,4,0.07,mysy_ytubes_04,default
35,35,"
",8,0.13,mysy_ytubes_04,default
36,36,zambotto,1,0.02,mysy_ytubes_04,default
37,37,resultat,1,0.02,mysy_ytubes_04,default

1 index mots occurence moyenne id_formation source_field
2 0 0 renforc 1 0.11 0.02 8866 mysy_ytubes_04 default
3 1 1 comptabilit analys 1 0.11 0.02 8866 mysy_ytubes_04 default
4 2 2 fondamental bt 1 0.11 0.02 8866 mysy_ytubes_04 default
5 3 3 semain licenc 2 1 0.22 0.02 8866 mysy_ytubes_04 default
6 4 4 programm charg 1 0.11 0.02 8866 mysy_ytubes_04 default
7 5 5 def notion 1 0.11 0.02 8866 mysy_ytubes_04 default
8 6 6 7 cout 1 3 0.11 0.05 8866 mysy_ytubes_04 default
9 7 7 publiqu analyt 1 0.11 0.02 8866 mysy_ytubes_04 default
10 8 8 ge 3 0.05 mysy_ytubes_04 default
11 9 9 gratuit 1 0.02 mysy_ytubes_04 default
12 10 10 depart 1 0.02 mysy_ytubes_04 default
13 11 11 iut 1 0.02 mysy_ytubes_04 default
14 12 12 comptabilit 6 0.1 mysy_ytubes_04 default
15 13 13 different 1 0.02 mysy_ytubes_04 default
16 14 14 niveau 1 0.02 mysy_ytubes_04 default
17 15 15 prix 1 0.02 mysy_ytubes_04 default
18 16 16 professeur 1 0.02 mysy_ytubes_04 default
19 17 17 sorbon 1 0.02 mysy_ytubes_04 default
20 18 18 introduct 1 0.02 mysy_ytubes_04 default
21 19 19 nord 1 0.02 mysy_ytubes_04 default
22 20 20 cour 3 0.05 mysy_ytubes_04 default
23 21 21 incorpore 1 0.02 mysy_ytubes_04 default
24 22 22 lign 1 0.02 mysy_ytubes_04 default
25 23 23 universit 1 0.02 mysy_ytubes_04 default
26 24 24 stmg 1 0.02 mysy_ytubes_04 default
27 25 25 villetan 1 0.02 mysy_ytubes_04 default
28 26 26 dcg 1 0.02 mysy_ytubes_04 default
29 27 27 marg 1 0.02 mysy_ytubes_04 default
30 28 28 general 1 0.02 mysy_ytubes_04 default
31 29 29 paris 1 0.02 mysy_ytubes_04 default
32 30 30 corinn 1 0.02 mysy_ytubes_04 default
33 31 31 debut 1 0.02 mysy_ytubes_04 default
34 32 32 calcul 1 0.02 mysy_ytubes_04 default
35 33 33 1 2 0.03 mysy_ytubes_04 default
36 34 34 gestion 4 0.07 mysy_ytubes_04 default
37 35 35 8 0.13 mysy_ytubes_04 default
38 36 36 zambotto 1 0.02 mysy_ytubes_04 default
39 37 37 resultat 1 0.02 mysy_ytubes_04 default
40
41
42

View File

@ -423,6 +423,17 @@ def ela_recherche_tokens(sentence):
tab_tokens = ls.Ela_Tokenize(sentence)
tab_tokens2 = ls.Ela_remove_stop_words(tab_tokens)
tab_tokens3 = ls.Ela_remove_pronoun(tab_tokens2)
'''
note : 26/03 : Faire evolution la fonction ici pour
gerer les mots qui ne doivent pas etre racinisé comme le cas du mot "Responsive"
De manière plus globale, il faudrait exclure certains mot de la racinisation.
'''
print(" VERIF : "+str(tab_tokens3))
for mot in tab_tokens3:
mycommon.check_word_in_fr_dict(str(mot))
tab_tokens4 = ls.Ela_stemmize(tab_tokens3)
tab_tokens4.sort()
@ -437,7 +448,7 @@ def ela_recherche_tokens(sentence):
for token in tab_tokens4:
print(token)
print(" #### Le tooken recherché est : "+str(token))
for doc in collection.find({"mots":token, "source_field":"default"}):
#print(" Trouvé dans le cours N° "+str(doc["id_formation"]))
if str(doc["id_formation"]) not in tab_training_id :
@ -490,7 +501,7 @@ def ela_recherche_tokens_source_field(sentence, source_fied=""):
for token in tab_tokens4:
print(token)
print(" #### Token rechercher dans l'index est : "+str(token))
for doc in collection.find({"mots":token, "source_field":source_fied}):
#print(" Trouvé dans le cours N° "+str(doc["id_formation"]))
if str(doc["id_formation"]) not in tab_training_id :

View File

@ -1,9 +1,39 @@
mots occurence moyenne id_formation source_field
0 renforc 1 0.11 8866 default
1 comptabilit 1 0.11 8866 default
2 fondamental 1 0.11 8866 default
3 semain 2 0.22 8866 default
4 programm 1 0.11 8866 default
5 def 1 0.11 8866 default
6 7 1 0.11 8866 default
7 publiqu 1 0.11 8866 default
mots occurence moyenne id_formation source_field
0 \n\n 1 0.02 mysy_ytubes_04 default
1 analys 1 0.02 mysy_ytubes_04 default
2 bt 1 0.02 mysy_ytubes_04 default
3 licenc 1 0.02 mysy_ytubes_04 default
4 charg 1 0.02 mysy_ytubes_04 default
5 notion 1 0.02 mysy_ytubes_04 default
6 cout 3 0.05 mysy_ytubes_04 default
7 analyt 1 0.02 mysy_ytubes_04 default
8 ge 3 0.05 mysy_ytubes_04 default
9 gratuit 1 0.02 mysy_ytubes_04 default
10 depart 1 0.02 mysy_ytubes_04 default
11 iut 1 0.02 mysy_ytubes_04 default
12 comptabilit 6 0.1 mysy_ytubes_04 default
13 different 1 0.02 mysy_ytubes_04 default
14 niveau 1 0.02 mysy_ytubes_04 default
15 prix 1 0.02 mysy_ytubes_04 default
16 professeur 1 0.02 mysy_ytubes_04 default
17 sorbon 1 0.02 mysy_ytubes_04 default
18 introduct 1 0.02 mysy_ytubes_04 default
19 nord 1 0.02 mysy_ytubes_04 default
20 cour 3 0.05 mysy_ytubes_04 default
21 incorpore 1 0.02 mysy_ytubes_04 default
22 lign 1 0.02 mysy_ytubes_04 default
23 universit 1 0.02 mysy_ytubes_04 default
24 stmg 1 0.02 mysy_ytubes_04 default
25 villetan 1 0.02 mysy_ytubes_04 default
26 dcg 1 0.02 mysy_ytubes_04 default
27 marg 1 0.02 mysy_ytubes_04 default
28 general 1 0.02 mysy_ytubes_04 default
29 paris 1 0.02 mysy_ytubes_04 default
30 corinn 1 0.02 mysy_ytubes_04 default
31 debut 1 0.02 mysy_ytubes_04 default
32 calcul 1 0.02 mysy_ytubes_04 default
33 1 2 0.03 mysy_ytubes_04 default
34 gestion 4 0.07 mysy_ytubes_04 default
35 \n 8 0.13 mysy_ytubes_04 default
36 zambotto 1 0.02 mysy_ytubes_04 default
37 resultat 1 0.02 mysy_ytubes_04 default

View File

@ -277,3 +277,37 @@ def tryInt(val):
return myfloat
except ValueError:
return 0
'''
Cette fonction verifie si un mot est dans le dictionnaire français - une table interne
si non, le mot est enregistré dans une table pour traitement utérieur
'''
def check_word_in_fr_dict(mot=None):
try:
print("#### analuse du mot "+str(mot))
col_name = dbname["list_mots_fr"]
col_name_not_fr = dbname["list_mots_not_fr"]
mydata = {}
val_tmp = col_name.count_documents({'mot': str(mot)})
if (val_tmp <= 0):
myprint(" Le mot '" + mot + "' n'existe pas dans le dictionnaire")
mydata['mot'] = mot
mydata['treated'] = int("0")
mydata['update_date'] = datetime.now()
ret_val_tmp = col_name_not_fr.insert_one(mydata)
if (ret_val_tmp is False):
print(" Impossible d'enregistrer le '" + mot + "'")
return False
return False
return True
except Exception as e:
exc_type, exc_obj, exc_tb = sys.exc_info()
myprint(str(inspect.stack()[0][3]) + " -" + str(e) + " - Line : " + str(exc_tb.tb_lineno))
return False