✨ Percent classification

mmix.py

@@ -0,0 +1,43 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.metrics import accuracy_score
+from sklearn import metrics
+from sklearn.model_selection import train_test_split
+
+
+dataframe = pd.read_csv("archive/data.csv")
+
+# Change bool values to int (0/1)
+dataframe = dataframe.rename(columns={'Winner': 'Blue_Corner_Win'})
+dataframe['Blue_Corner_Win'] = (dataframe['Blue_Corner_Win'] == 'Blue').astype(int)
+dataframe['title_bout'] = dataframe['title_bout'].astype(int)
+
+# Select datas for Yi (blue corner win ?) and columns for stat
+Yi = dataframe[["Blue_Corner_Win"]]
+colonnes = ['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_TD_att', 'R_avg_opp_GROUND_att', 
+                   'R_avg_opp_SIG_STR_landed', 'B_age', 'R_age']
+                   
+Xi = dataframe[colonnes]
+
+Xtrain, Xtest, ytrain, ytest = train_test_split(Xi, Yi,test_size=0.20, random_state=42)
+print(Xtrain.shape)
+print(Xtest.shape)
+
+Arbre_decision = DecisionTreeClassifier(random_state=0, max_depth=20)
+clf = Arbre_decision.fit(Xi, Yi)
+
+ypredit = clf.predict(Xtest)
+accuracy_score(ytest, ypredit)
+matriceConfusion=metrics.confusion_matrix(ytest, ypredit)
+
+incorrect=matriceConfusion[0][1] + matriceConfusion[1][0]
+total = matriceConfusion.sum()
+
+print("\nNumber of incorrect classifications: " + str(incorrect))
+print("Number of classifications total: " + str(total))
+
+print("Percent: "+ str((total-incorrect)/total*100))