#導(dǎo)入基本庫
import numpy as np 
import pandas as pd

## 繪圖函數(shù)庫
import matplotlib.pyplot as plt
import seaborn as sns
#%%　數(shù)據(jù)讀入：利用Pandas自帶的read_csv函數(shù)讀取并轉(zhuǎn)化為DataFrame格式
df = pd.read_csv('D:\Python\ML\data\high_diamond_ranked_10min.csv')
y = df.blueWins
#%%查看樣本數(shù)據(jù)
#print(y.value_counts())
#標注特征列
drop_cols=['gameId','blueWins']
x=df.drop(drop_cols,axis=1)
#對數(shù)字特征進行統(tǒng)計描述
x_des=x.describe()

#%%去除冗余數(shù)據(jù)，因為紅藍為競爭關(guān)系，只需知道一方的情況，對方相反因此去除紅方的數(shù)據(jù)信息
drop_cols = ['redFirstBlood','redKills','redDeaths'
             ,'redGoldDiff','redExperienceDiff', 'blueCSPerMin',
            'blueGoldPerMin','redCSPerMin','redGoldPerMin']
x.drop(drop_cols, axis=1, inplace=True)
#%%可視化描述。為了有一個好的呈現(xiàn)方式，分兩張小提琴圖展示前九個特征和中間九個特征，后面的相同不再贅述
data = x
data_std = (data - data.mean()) / data.std()
data = pd.concat([y, data_std.iloc[:, 0:9]], axis=1)#將標簽與前九列拼接此時的到的data是（9879*10）的metric
data = pd.melt(data, id_vars='blueWins', var_name='Features', value_name='Values')#將上面的數(shù)據(jù)melt成（88911*3）的metric

fig, ax = plt.subplots(1,2,figsize=(15,8))

# 繪制小提琴圖
sns.violinplot(x='Features', y='Values', hue='blueWins', data=data, split=True,
               inner='quart', ax=ax[0], palette='Blues')
fig.autofmt_xdate(rotation=45)#改變x軸坐標的現(xiàn)實方法，可以斜著表示（傾斜45度），不用平著擠成一堆

data = x
data_std = (data - data.mean()) / data.std()
data = pd.concat([y, data_std.iloc[:, 9:18]], axis=1)
data = pd.melt(data, id_vars='blueWins', var_name='Features', value_name='Values')

# 繪制小提琴圖
sns.violinplot(x='Features', y='Values', hue='blueWins', 
               data=data, split=True, inner='quart', ax=ax[1], palette='Blues')
fig.autofmt_xdate(rotation=45)
plt.show()

#%%畫出各個特征之間的相關(guān)性熱力圖
fig,ax=plt.subplots(figsize=(15,18))
sns.heatmap(round(x.corr(),2),cmap='Blues',annot=True)
fig.autofmt_xdate(rotation=45)
plt.show()

#%%根據(jù)上述特征圖，剔除相關(guān)性較強的冗余特征（redAvgLevel，blueAvgLevel）
# 去除冗余特征
drop_cols = ['redAvgLevel','blueAvgLevel']
x.drop(drop_cols, axis=1, inplace=True)

sns.set(style='whitegrid', palette='muted')

# 構(gòu)造兩個新特征
x['wardsPlacedDiff'] = x['blueWardsPlaced'] - x['redWardsPlaced']
x['wardsDestroyedDiff'] = x['blueWardsDestroyed'] - x['redWardsDestroyed']

data = x[['blueWardsPlaced','blueWardsDestroyed','wardsPlacedDiff','wardsDestroyedDiff']].sample(1000)
data_std = (data - data.mean()) / data.std()
data = pd.concat([y, data_std], axis=1)
data = pd.melt(data, id_vars='blueWins', var_name='Features', value_name='Values')

plt.figure(figsize=(15,8))
sns.swarmplot(x='Features', y='Values', hue='blueWins', data=data)
plt.show()

#%%由上圖插眼數(shù)量的離散圖，可以發(fā)現(xiàn)插眼數(shù)量與游戲勝負之間的顯著規(guī)律，游戲前十分鐘插眼與否對最終的勝負影響不大，故將這些特征去除
## 去除和眼位相關(guān)的特征
drop_cols = ['blueWardsPlaced','blueWardsDestroyed','wardsPlacedDiff',
            'wardsDestroyedDiff','redWardsPlaced','redWardsDestroyed']
x.drop(drop_cols, axis=1, inplace=True)
#%%擊殺、死亡與助攻數(shù)的數(shù)據(jù)分布差別不大，但是擊殺減去死亡、助攻減去死亡的分布與緣分不差別較大，構(gòu)造兩個新的特征
x['killsDiff'] = x['blueKills'] - x['blueDeaths']
x['assistsDiff'] = x['blueAssists'] - x['redAssists']
x[['blueKills','blueDeaths','blueAssists','killsDiff','assistsDiff','redAssists']].hist(figsize=(15,8), bins=20)
plt.show()

#%%
data = x[['blueKills','blueDeaths','blueAssists','killsDiff','assistsDiff','redAssists']].sample(1000)
data_std = (data - data.mean()) / data.std()
data = pd.concat([y, data_std], axis=1)
data = pd.melt(data, id_vars='blueWins', var_name='Features', value_name='Values')

plt.figure(figsize=(10,6))
sns.swarmplot(x='Features', y='Values', hue='blueWins', data=data)
plt.xticks(rotation=45)
plt.show()

#%%
data = pd.concat([y, x], axis=1).sample(500)
sns.pairplot(data, vars=['blueKills','blueDeaths','blueAssists','killsDiff','assistsDiff','redAssists'], 
             hue='blueWins')
plt.show()

#%%一些特征兩兩組合后對于數(shù)據(jù)的劃分有提升
x['dragonsDiff'] = x['blueDragons'] - x['redDragons']#拿到龍
x['heraldsDiff'] = x['blueHeralds'] - x['redHeralds']#拿到峽谷先鋒
x['eliteDiff'] = x['blueEliteMonsters'] - x['redEliteMonsters']#擊殺大型野怪
data = pd.concat([y, x], axis=1)
eliteGroup = data.groupby(['eliteDiff'])['blueWins'].mean()
dragonGroup = data.groupby(['dragonsDiff'])['blueWins'].mean()
heraldGroup = data.groupby(['heraldsDiff'])['blueWins'].mean()
fig, ax = plt.subplots(1,3, figsize=(15,4))

eliteGroup.plot(kind='bar', ax=ax[0])
dragonGroup.plot(kind='bar', ax=ax[1])
heraldGroup.plot(kind='bar', ax=ax[2])

print(eliteGroup)
print(dragonGroup)
print(heraldGroup)

plt.show()

#%%推塔數(shù)量與游戲勝負
x['towerDiff'] = x['blueTowersDestroyed'] - x['redTowersDestroyed']
data = pd.concat([y, x], axis=1)
towerGroup = data.groupby(['towerDiff'])['blueWins']
print(towerGroup.count())
print(towerGroup.mean())

fig, ax = plt.subplots(1,2,figsize=(15,5))

towerGroup.mean().plot(kind='line', ax=ax[0])
ax[0].set_title('Proportion of Blue Wins')
ax[0].set_ylabel('Proportion')

towerGroup.count().plot(kind='line', ax=ax[1])
ax[1].set_title('Count of Towers Destroyed')
ax[1].set_ylabel('Count')

#%%利用LightGBM進行訓(xùn)練和預(yù)測
## 為了正確評估模型性能，將數(shù)據(jù)劃分為訓(xùn)練集和測試集，并在訓(xùn)練集上訓(xùn)練模型，在測試集上驗證模型性能。
from sklearn.model_selection import train_test_split
## 選擇其類別為0和1的樣本 （不包括類別為2的樣本）
data_target_part = y
data_features_part = x
## 測試集大小為20%， 80%/20%分
x_train, x_test, y_train, y_test = train_test_split(data_features_part, data_target_part, test_size = 0.2, random_state = 2020)
#%%## 導(dǎo)入LightGBM模型
from lightgbm.sklearn import LGBMClassifier
## 定義 LightGBM 模型 
clf = LGBMClassifier()
# 在訓(xùn)練集上訓(xùn)練LightGBM模型
clf.fit(x_train, y_train)

#%%在訓(xùn)練集和測試集上分別利用訓(xùn)練好的模型進行預(yù)測
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
from sklearn import metrics

## 利用accuracy（準確度）【預(yù)測正確的樣本數(shù)目占總預(yù)測樣本數(shù)目的比例】評估模型效果
print('The accuracy of the LightGBM is:',metrics.accuracy_score(y_train,train_predict))
print('The accuracy of the LightGBM is:',metrics.accuracy_score(y_test,test_predict))

## 查看混淆矩陣 (預(yù)測值和真實值的各類情況統(tǒng)計矩陣)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用熱力圖對于結(jié)果進行可視化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
plt.xlabel('Predicted labels')
plt.ylabel('True labels')
plt.show()

#%%利用lightgbm進行特征選擇，同樣可以用屬性feature_importances_查看特征的重要度
sns.barplot(y=data_features_part.columns, x=clf.feature_importances_)

#%%除feature_importances_外，還可以使用LightGBM中的其他屬性進行評估(gain,split)
from sklearn.metrics import accuracy_score
from lightgbm import plot_importance

def estimate(model,data):
    ax1=plot_importance(model,importance_type="gain")
    ax1.set_title('gain')
    ax2=plot_importance(model, importance_type="split")
    ax2.set_title('split')
    plt.show()
def classes(data,label,test):
    model=LGBMClassifier()
    model.fit(data,label)
    ans=model.predict(test)
    estimate(model, data)
    return ans
 
ans=classes(x_train,y_train,x_test)
pre=accuracy_score(y_test, ans)
print('acc=',accuracy_score(y_test,ans))

#%%調(diào)整參數(shù)，獲得更好的效果
## 從sklearn庫中導(dǎo)入網(wǎng)格調(diào)參函數(shù)
from sklearn.model_selection import GridSearchCV

## 定義參數(shù)取值范圍
learning_rate = [0.1, 0.3, 0.6]
feature_fraction = [0.5, 0.8, 1]
num_leaves = [16, 32, 64]
max_depth = [-1,3,5,8]

parameters = { 'learning_rate': learning_rate,
              'feature_fraction':feature_fraction,
              'num_leaves': num_leaves,
              'max_depth': max_depth}
model = LGBMClassifier(n_estimators = 50)

## 進行網(wǎng)格搜索
clf = GridSearchCV(model, parameters, cv=3, scoring='accuracy',verbose=3, n_jobs=-1)
clf = clf.fit(x_train, y_train)
#%%查看最好的參數(shù)值分別是多少
print(clf.best_params_)

#%%查看最好的參數(shù)值分別是多少
print(clf.best_params_)
#%% 在訓(xùn)練集和測試集上分布利用最好的模型參數(shù)進行預(yù)測
## 定義帶參數(shù)的 LightGBM模型 
clf = LGBMClassifier(feature_fraction = 1,
                    learning_rate = 0.1,
                    max_depth= 3,
                    num_leaves = 16)
# 在訓(xùn)練集上訓(xùn)練LightGBM模型
clf.fit(x_train, y_train)

train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)

## 利用accuracy（準確度）【預(yù)測正確的樣本數(shù)目占總預(yù)測樣本數(shù)目的比例】評估模型效果
print('The accuracy of the LightGBM is:',metrics.accuracy_score(y_train,train_predict))
print('The accuracy of the LightGBM is:',metrics.accuracy_score(y_test,test_predict))

## 查看混淆矩陣 (預(yù)測值和真實值的各類情況統(tǒng)計矩陣)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用熱力圖對于結(jié)果進行可視化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
plt.xlabel('Predicted labels')
plt.ylabel('True labels')
plt.show()