决策树算法预测NBA赛事结果

决策树算法介绍

决策树（decision tree）是一个树结构（可以是二叉树或非二叉树）。
其每个非叶节点表示一个特征属性上的测试，每个分支代表这个特征属性在某个值域上的输出，而每个叶节点存放一个类别。

使用决策树进行决策的过程就是从根节点开始，测试待分类项中相应的特征属性，并按照其值选择输出分支，直到到达叶子节点，将叶子节点存放的类别作为决策结果。

总结来说：

决策树模型核心是下面几部分：

• 结点和有向边组成
• 结点有内部结点和叶结点俩种类型
• 内部结点表示一个特征，叶节点表示一个类

加载数据集

import numpy as np
import pandas as pd
file = "NBA2014.csv"
data = pd.read_csv(file)
data.iloc[:5]

数据预处理

# Don't read the first row,as it is blank. Parse the date column as a date
data = pd.read_csv(file,parse_dates=[0])
data.columns = ["Date","Start","Visitor Team","VisitorPts","Home Team","HomePts","Score Type","OT?","Attend","Notes"]
data.iloc[:5]

data["Home Win"] = data["VisitorPts"] < data["HomePts"]
y_true = data["Home Win"].values
data.iloc[:5]
print("Home Team Win Percentage: {0:.1f}%".format(np.mean(y_true)*100))

data["HomeLastWin"] = False
data["VisitorLastWin"] = False
data.iloc[:5]
# create a dict to store the team last result
from collections import defaultdict
won_last = defaultdict(int)
for index,row in data.iterrows():
    home_team = row["Home Team"]
    visitor_team = row["Visitor Team"]
    row["HomeLastWin"] = won_last[home_team]
    row["VisitorLastWin"] = won_last[visitor_team]
    data.iloc[index] = row
    # set the current win
    won_last[home_team] = row["Home Win"]
    won_last[visitor_team] = not row["Home Win"]
data.iloc[20:25]

模型建立

from sklearn.tree import DecisionTreeClassifier
from sklearn.cross_validation import cross_val_score
clf = DecisionTreeClassifier(random_state = 14)
# create the dataset
X_win = data[["HomeLastWin","VisitorLastWin"]].values
scores = cross_val_score(clf,X_win,y_true,scoring="accuracy")
print("Accuracy: {0:.1f}%".format(np.mean(scores)*100))

引入新的特征：赛季排名

import chardet
file = "NBA2013_expanded-standings.csv"
with open(file, 'rb') as f:
    print(f)
    result = chardet.detect(f.read())  # or readline if the file is large 

standings = pd.read_csv(file,skiprows=[0],encoding=result['encoding'])

# create a new feature:HomeTeamRankHigher
data["HomeTeamRankHigher"] = 0
for index,row in data.iterrows():
    home_team = row["Home Team"]
    visitor_team = row["Visitor Team"]
    if home_team == "New Orleans Pelicans":
        home_team = "New Orleans Hornets"
    elif visitor_team == "New Orleans Pelicans":
        visitor_team = "New Orleans Hornets"
    home_rank = standings[standings["Team"] == home_team]['Rk'].values[0]
    visitor_rank = standings[standings["Team"] == visitor_team]["Rk"].values[0]
    row["HomeTeamRankHigher"] = int(home_rank > visitor_rank)
    data.iloc[index] = row
data.iloc[:5]

# create the train set
X_homehigher = data[["HomeLastWin","VisitorLastWin","HomeTeamRankHigher"]].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))

# who won the last match
last_match_winer = defaultdict(int)
data["HomeTeamWonLast"] = 0

for index,row in data.iterrows():
    home_team = row["Home Team"]
    visitor_team = row["Visitor Team"]
    #sort the team names
    teams = tuple(sorted([home_team,visitor_team]))
    # who won the last game
    row["HomeTeamWonLast"] = 1 if last_match_winer == row["Home Team"] else 0
    data.iloc[index] = row
    
    winner = row["Home Team"] if row["Home Win"] else row["Visitor Team"]
    last_match_winer = winner
data.iloc[:5]

# create the dataset
X_lastwinner = data[["HomeTeamRankHigher","HomeTeamWonLast"]].values
clf = DecisionTreeClassifier(random_state=14)
scores = cross_val_score(clf,X_lastwinner,y_true,scoring="accuracy")
print("Accuracy: {0:.1f}%".format(np.mean(scores)*100))

# convert the string names to into integers
from sklearn.preprocessing import LabelEncoder
encoding = LabelEncoder()
encoding.fit(data["Home Team"].values)

home_teams = encoding.transform(data["Home Team"].values)
visitor_teams = encoding.transform(data["Visitor Team"].values)
X_teams = np.vstack([home_teams,visitor_teams]).T
# encode these integers into a number if binary features
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))

新模型：随机森林

# use random_forest
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(random_state=14)
scores = cross_val_score(clf,X_teams_expanded,y_true,scoring='accuracy')
print("Accuracy: {0:.1f}%".format(np.mean(scores)*100))

X_all = np.hstack([X_lastwinner,X_teams_expanded])
print("X_all shape: {0}".format(X_all.shape))
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))

from sklearn.grid_search import GridSearchCV
#n_estimators=10, criterion='gini', max_depth=None, 
#min_samples_split=2, min_samples_leaf=1,
#max_features='auto',
#max_leaf_nodes=None, bootstrap=True,
#oob_score=False, n_jobs=1,
#random_state=None, verbose=0, min_density=None, compute_importances=None
parameter_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))