diff --git a/README.md b/README.md
index a8816b1..59d297b 100644
--- a/README.md
+++ b/README.md
@@ -23,9 +23,9 @@ AI Plot data: https://machinelearningmastery.com/visualize-machine-learning-data
 ## Analysis
 
 - [X] Train models with just 20000 "GALAXY" class (has an impact?)
-- [ ] Which model is the best, ratio learn_time/precision
-- [ ] Can we drop more categories and have same results (useless data?)
-- [ ] Compare prediction with y_test that were false
+- [X] Which model is the best, ratio learn_time/precision
+- [X] Can we drop more categories and have same results (useless data?)
+- [X] Compare prediction with y_test that were false
 
 ## Dataset
 Nous avons décidé de prendre un dataset sur le site Kaggle, il contient 100 000 lignes qui réprésentent
@@ -111,10 +111,10 @@ de 98%.
 
 Voici les résultats obtenu sur l'ensemble des modèles:
 
-- KNN (70,724%)
-- Decision Tree (96,82%)
+- KNN (accuracy: 70,724%, f1: 61.35%)
+- Decision Tree (accuracy: 96,82%, f1: 96,32%) 
 - Linear SVC (n'a jamais fini)
-- Random Forest (98.012%)
-- Multi-Layer Perceptron (59.22%)
-- Nearest Centroid (36.328%)
-- SGD (18.972%)
+- Random Forest (accuracy: 98.012%, f1: 97,61%)
+- Multi-Layer Perceptron (accuracy: 59.22%, f1: 24.7%)
+- Nearest Centroid (accuracy: 36.328%, f1: 36,85%)
+- SGD (accuracy: 21%, f1: 11%)
diff --git a/src/main.py b/src/main.py
index 91e4bd5..201015a 100755
--- a/src/main.py
+++ b/src/main.py
@@ -30,6 +30,7 @@ import matplotlib.pyplot as plt
 import pandas
 from pandas.plotting import scatter_matrix
 from sklearn.metrics import confusion_matrix
+from sklearn.metrics import f1_score
 
 # main
 def main():
@@ -88,7 +89,7 @@ def model_switch(choice):
     elif (choice == 7):
         model = NearestCentroid()
     elif (choice == 8):
-        model = MLPClassifier(solver='adam', alpha=1e-5, random_state=1, activation="logistic", hidden_layer_sizes=(1000, 300, 100, 30, 10, 3))
+        model = MLPClassifier(solver='adam', alpha=1e-5, random_state=1, activation="logistic", hidden_layer_sizes=(5, 9, 5, 5, 3))
     else:
         raise Exception('Wrong entry')       
     
@@ -151,7 +152,8 @@ def training(model, x, y):
             printPredictedValues(ypredict,ytest)
         elif res == 3:
             os.system("clear")
-            print(accuracy_score(ytest, ypredict))
+            print("Accuracy: ", accuracy_score(ytest, ypredict))
+            print("F1: ", f1_score(ytest, ypredict, average="macro"))
         elif res == 0:
             break
         else:
@@ -176,17 +178,18 @@ def showData(df):
     plt.pie(x, labels = ['GALAXY', 'QSO', 'Star'])
     plt.legend()
 
+# N'a jamais fini pour cause de puissance
 def rfecv_test(x, y, model):
     rfe = RFECV(estimator=model)
     pipeline = Pipeline(steps=[('s',rfe),('m',model)])
     
-    # evaluate model
+    # Evaluation du modele
     cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
     n_scores = cross_val_score(pipeline, x, y, scoring='accuracy', cv=cv, n_jobs=-1, error_score='raise', verbose=3)
     
-    # report performance
     print('Accuracy: %.3f (%.3f)' % (max(n_scores), std(n_scores)))
 
+    # Affiche la pertinence des colonnes dans l'entrainement
     rfe.fit(x,y)
     for i in range(x.shape[1]):
         print('Column: %d, Selected %s, Rank: %.3f' % (i, rfe.support_[i], rfe.ranking_[i]))
@@ -297,6 +300,7 @@ def bestModel(datas):
     print("Best model : ",model," columns : ",res[0]," Accuracy : ", res[1][model])
     print("Worst model : ",modelMin," columns : ",resMin[0]," Accuracy : ", resMin[1][model])
 
+# Test auto-sklearn
 def auto_sklearn():
     df = read_dataset('data.csv')
     X_train, X_test, y_train, ytest = train_test_split(x, y,test_size=0.25, random_state=0)
@@ -313,6 +317,7 @@ def auto_sklearn():
     y_hat = predictions = cls.predict(X_test)
     print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_hat))
 
+# Affiche tout les plots
 def plotAll():
     x,df,y = read_dataset('data.csv')