✨ Random Blue corner and Red Corner

cleanData.py

@@ -7,33 +7,49 @@ from sklearn.impute import SimpleImputer
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
 from models import *
+import random
 from analise import *
 
+columns = ['B_fighter','R_fighter','title_bout',
+                    'B_avg_BODY_landed', 'B_avg_HEAD_landed', 'B_avg_TD_att', 'B_avg_TOTAL_STR_landed', 
+                'B_avg_opp_BODY_att', 'B_avg_opp_HEAD_landed', 'B_avg_opp_LEG_landed', 
+                'B_avg_opp_SIG_STR_att', 'B_avg_opp_TOTAL_STR_att',
+                
+                'R_avg_BODY_landed', 'R_avg_HEAD_landed', 'R_avg_TD_att', 'R_avg_TOTAL_STR_landed', 
+                'R_avg_opp_BODY_att', 'R_avg_opp_HEAD_landed', 'R_avg_opp_LEG_landed', 
+                'R_avg_opp_SIG_STR_att', 'R_avg_opp_TOTAL_STR_att',
+
+                'B_age', 'R_age','date','Winner','weight_class','B_Stance','R_Stance'] 
+
+def swap_values(row):
+    if random.random() > 0.5:
+        for column in columns:
+            if column.startswith('B_'):
+                opposite_column = 'R_' + column[2:]
+                row[column], row[opposite_column] = row[opposite_column], row[column]
+            if column.startswith('Winner'):
+                print(row[column])
+                if row[column] == 0:
+                    row[column] = 2
+                elif row[column] == 2:
+                    row[column] = 0
+                print(row[column])
+        return row
+    return row
 
 def getData():
     df = pd.read_csv('archive/data.csv')
-    columns = ['B_fighter','R_fighter','title_bout',
-                        'B_avg_BODY_landed', 'B_avg_HEAD_landed', 'B_avg_TD_att', 'B_avg_TOTAL_STR_landed', 
-                    'B_avg_opp_BODY_att', 'B_avg_opp_HEAD_landed', 'B_avg_opp_LEG_landed', 
-                    'B_avg_opp_SIG_STR_att', 'B_avg_opp_TOTAL_STR_att',
-                    
-                    'R_avg_BODY_landed', 'R_avg_HEAD_landed', 'R_avg_TD_att', 'R_avg_TOTAL_STR_landed', 
-                    'R_avg_opp_BODY_att', 'R_avg_opp_HEAD_landed', 'R_avg_opp_LEG_landed', 
-                    'R_avg_opp_SIG_STR_att', 'R_avg_opp_TOTAL_STR_att',
-
-                    'B_age', 'R_age','date','Winner','weight_class','B_Stance','R_Stance'] 
-
-
 
     limit_date = '2001-04-01'
     df = df.loc[df['date'] > limit_date, columns]
 
     label_encoder = LabelEncoder()
-
     # Convertir les chaînes de caractères en nombres
     for column in df.select_dtypes(include=['object']).columns:
         df[column] = label_encoder.fit_transform(df[column])
 
+    df = df.apply(swap_values, axis=1)
+
     median_values = df.median()
     df.fillna(median_values, inplace=True)
 

main.py

@@ -6,7 +6,12 @@ X,y=getData()
 X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.30, random_state=50)
 
 startRandomForest(X_train,X_test,y_train,y_test)
-startKNN(X_train,X_test,y_train,y_test)
+#startKNN(X_train,X_test,y_train,y_test)
-startSVM(X_train,X_test,y_train,y_test)
+#startSVM(X_train,X_test,y_train,y_test)
-startDecisionTree(X_train,X_test,y_train,y_test)
+#startDecisionTree(X_train,X_test,y_train,y_test)
-startLogisticRegression(X_train,X_test,y_train,y_test)
+#startLogisticRegression(X_train,X_test,y_train,y_test)
+
+#startLinearSVC(X_train,X_test,y_train,y_test)
+#startNaiveBayes(X_train,X_test,y_train,y_test)
+
+# https://scikit-learn.org/stable/_static/ml_map.png

models.py

@@ -4,6 +4,9 @@ from sklearn.linear_model import LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.linear_model import SGDClassifier
 from sklearn import svm
+from sklearn.svm import LinearSVC
+from sklearn.naive_bayes import GaussianNB
+
 
 def RandomForest(X_train, X_test, y_train):
     random_forest = RandomForestClassifier(n_estimators=100, 
@@ -35,3 +38,13 @@ def LogisticRegress(X_train, X_test, y_train):
     logistic = LogisticRegression()
     logistic.fit(X_train,y_train)
     return logistic.predict(X_test),logistic
+
+def Linearsvc(X_train, X_test, y_train):
+    svc = LinearSVC(C=1.0, dual=False, verbose=True, loss="squared_hinge", multi_class="crammer_singer")
+    svc.fit(X_train,y_train)
+    return svc.predict(X_test),svc
+
+def GaussianNaiveBayes(X_train, X_test, y_train):
+    gnb = GaussianNB()
+    gnb.fit(X_train, y_train)
+    return gnb.predict(X_test),gnb

runModel.py

@@ -45,4 +45,20 @@ def startLogisticRegression(X_train,X_test,y_train,y_test):
     report(lr_ac, lr_matrix, lr_class_report)
     seeMatrix(lr_matrix, lr.classes_)
     #rocCurve(y_test, y_pred)
-    #seeRocCurve(rf, X_train, y_train, 10)
+    #seeRocCurve(rf, X_train, y_train, 10)
+
+def startLinearSVC(X_train,X_test,y_train,y_test):
+    y_pred, svc = Linearsvc(X_train, X_test, y_train)
+    svc_ac, svc_matrix, svc_class_report = calculateMatrix(y_test, y_pred)
+    report(svc_ac, svc_matrix, svc_class_report)
+    seeMatrix(svc_matrix, svc.classes_)
+    #rocCurve(y_test, y_pred)
+    #seeRocCurve(rf, X_train, y_train, 10)
+
+def startNaiveBayes(X_train,X_test,y_train,y_test):
+    y_pred, gnb = GaussianNaiveBayes(X_train, X_test, y_train)
+    gnb_ac, gnb_matrix, gnb_class_report = calculateMatrix(y_test, y_pred)
+    report(gnb_ac, gnb_matrix, gnb_class_report)
+    seeMatrix(gnb_matrix, gnb.classes_)
+    #rocCurve(y_test, y_pred)
+    #seeRocCurve(rf, X_train, y_train, 10)