#數據導入 import pandas as pddata_filename="datasets.csv" dataset=pd.read_csv(data_filename) #dataset.loc[:5]#數據清洗 dataset=pd.read_csv(data_filename, parse_dates=["Date"]) #dataset.loc[:5]#方法1：上場比賽情況特征提取，并用其進行預測#主隊獲勝情況提取 from collections import defaultdictdataset["HomeWin"]=dataset["VisitorPTS"]<dataset["HomePTS"] y_true=dataset["HomeWin"].values#隊伍上一次比賽情況記錄 won_last=defaultdict(int)#HomeLastWin && VisitorLastWint填充 dataset["HomeLastWin"]=0 dataset["VisitorLastWin"]=0 for index, row in dataset.sort_values("Date").iterrows():home_team=row["Home Team"]visitor_team=row["Visitor Team"]row["HomeLastWin"]=won_last[home_team]row["VisitorLastWin"]=won_last[visitor_team]dataset.loc[index]=rowwon_last[home_team]=int(row["HomeWin"])won_last[visitor_team]=1-int(row["HomeWin"])#決策樹 交叉驗證 from sklearn.tree import DecisionTreeClassifier from sklearn.model_selection import cross_val_score import numpy as np clf=DecisionTreeClassifier(random_state=14) X_previouswins=dataset[["HomeLastWin","VisitorLastWin"]].valuesscores=cross_val_score(clf,X_previouswins,y_true,scoring="accuracy") #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))#方法2：上場比賽情況 && 球隊排名用于預測#雙方相對排名提取 standings = pd.read_csv("standings.csv") dataset["HomeTeamRanksHigher"]=0 for index,row in dataset.iterrows():home_team=row["Home Team"]visitor_team=row["Visitor Team"]home_rank=standings[standings["Team"]==home_team]["Rk"].values[0]visitor_rank=standings[standings["Team"]==visitor_team]["Rk"].values[0]row["HomeTeamRankingHigher"]=int(home_rank>visitor_rank)# 決策樹 交叉驗證 X_homehigher = dataset[["HomeLastWin", "VisitorLastWin", "HomeTeamRanksHigher"]].values clf=DecisionTreeClassifier(random_state=14)scores=cross_val_score(clf,X_homehigher,y_true,scoring="accuracy") #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))# 方法3 忽略主客場，記錄最后的勝利last_match_winner = defaultdict(int) dataset["HomeTeamWonLast"] = 0 for index, row in dataset.iterrows():home_team = row["Home Team"]visitor_team = row["Visitor Team"]teams = tuple(sorted([home_team, visitor_team]))row["HomeTeamWonLast"] = 1 if last_match_winner[teams] == home_team else 0dataset.loc[index] = rowwinner = row["Home Team"] if row["HomeWin"] else row["Visitor Team"]last_match_winner[teams] = winner# 決策樹 交叉驗證 clf=DecisionTreeClassifier(random_state=14) X_lastwinner=dataset[["HomeLastWin","VisitorLastWin"]].valuesscores=cross_val_score(clf,X_lastwinner,y_true,scoring="accuracy") #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))#方法4 球隊姓名數字化from sklearn.preprocessing import LabelEncoder encoding = LabelEncoder()#轉換為整型 encoding.fit(dataset["Home Team"].values)#球隊名數據接收 home_teams = encoding.transform(dataset["Home Team"].values) visitor_teams = encoding.transform(dataset["Visitor Team"].values)#拼接 X_teams = np.vstack([home_teams, visitor_teams]).T#print(X_teams)#獨熱編碼 from sklearn.preprocessing import OneHotEncoder onehot = OneHotEncoder() X_teams_expanded = onehot.fit_transform(X_teams).todense()clf = DecisionTreeClassifier(random_state=14) scores = cross_val_score(clf, X_teams_expanded, y_true, scoring='accuracy') #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))#隨機森林# 僅用隊名 from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(random_state=14) scores = cross_val_score(clf, X_teams, y_true, scoring='accuracy') #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100)) # 隊名 && 上一場勝者 #X_previouswins X_all = np.hstack([X_previouswins, X_teams]) clf = RandomForestClassifier(random_state=14) scores = cross_val_score(clf, X_all, y_true, scoring='accuracy') #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))# GridSearchCV搜索最佳參數 from sklearn.model_selection import GridSearchCVparameter_space = { "max_features": [2, 10, 'auto'], "n_estimators": [100,], "criterion": ["gini", "entropy"], "min_samples_leaf": [2, 4, 6], } clf = RandomForestClassifier(random_state=14) grid = GridSearchCV(clf, parameter_space) grid.fit(X_all, y_true) #print("Accuracy: {0:.1f}%".format(grid.best_score_ * 100))#隨機森林 正確率最高的模型參數 clf = RandomForestClassifier(bootstrap=True,criterion='entropy', max_depth=None, max_features=2,max_leaf_nodes=None, min_samples_leaf=6,min_samples_split=2, n_estimators=100, n_jobs=1,oob_score=False, random_state=14, verbose=0) scores = cross_val_score(clf, X_all, y_true, scoring='accuracy') #print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))

總結

以上是生活随笔為你收集整理的比赛结果预测_决策树_随机森林(通用 数据挖掘入门与实践-实验5)的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。