Python机器学习应用之基于LightGBM的分类预测篇解读

目录

• 一、Introduction
• 1 LightGBM的优点
• 2 LightGBM的缺点
• 二、实现过程
• 1 数据集介绍
• 2 Coding
• 三、Keys
• LightGBM的重要参数
• 基本参数调整
• 针对训练速度的参数调整
• 针对准确率的参数调整
• 针对过拟合的参数调整

#导入基本库
import numpy as np 
import pandas as pd

## 绘图函数库
import matplotlib.pyplot as plt
import seaborn as sns
#%%　数据读入：利用Pandas自带的read_csv函数读取并转化为DataFrame格式
df = pd.read_csv("D:PythonMLdatahigh_diamond_ranked_10min.csv")
y = df.blueWins
#%%查看样本数据
#print(y.value_counts())
#标注特征列
drop_cols=["gameId","blueWins"]
x=df.drop(drop_cols,axis=1)
#对数字特征进行统计描述
x_des=x.describe()

#%%去除冗余数据，因为红蓝为竞争关系，只需知道一方的情况，对方相反因此去除红方的数据信息
drop_cols = ["redFirstBlood","redKills","redDeaths"
             ,"redGoldDiff","redExperienceDiff", "blueCSPerMin",
            "blueGoldPerMin","redCSPerMin","redGoldPerMin"]
x.drop(drop_cols, axis=1, inplace=True)
#%%可视化描述。为了有一个好的呈现方式，分两张小提琴图展示前九个特征和中间九个特征，后面的相同不再赘述
data = x
data_std = (data - data.mean()) / data.std()
data = pd.concat([y, data_std.iloc[:, 0:9]], axis=1)#将标签与前九列拼接此时的到的data是（9879*10）的metric
data = pd.melt(data, id_vars="blueWins", var_name="Features", value_name="Values")#将上面的数据melt成（88911*3）的metric

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

# 绘制小提琴图
sns.violinplot(x="Features", y="Values", hue="blueWins", data=data, split=True,
               inner="quart", ax=ax[0], palette="Blues")
fig.autofmt_xdate(rotation=45)#改变x轴坐标的现实方法，可以斜着表示（倾斜45度），不用平着挤成一堆

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")

# 绘制小提琴图
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()

#%%画出各个特征之间的相关性热力图
fig,ax=plt.subplots(figsize=(15,18))
sns.heatmap(round(x.corr(),2),cmap="Blues",annot=True)
fig.autofmt_xdate(rotation=45)
plt.show()

#%%根据上述特征图，剔除相关性较强的冗余特征（redAvgLevel，blueAvgLevel）
# 去除冗余特征
drop_cols = ["redAvgLevel","blueAvgLevel"]
x.drop(drop_cols, axis=1, inplace=True)

sns.set(, palette="muted")

# 构造两个新特征
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()

#%%由上图插眼数量的离散图，可以发现插眼数量与游戏胜负之间的显著规律，游戏前十分钟插眼与否对最终的胜负影响不大，故将这些特征去除
## 去除和眼位相关的特征
drop_cols = ["blueWardsPlaced","blueWardsDestroyed","wardsPlacedDiff",
            "wardsDestroyedDiff","redWardsPlaced","redWardsDestroyed"]
x.drop(drop_cols, axis=1, inplace=True)
#%%击杀、死亡与助攻数的数据分布差别不大，但是击杀减去死亡、助攻减去死亡的分布与缘分不差别较大，构造两个新的特征
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()

#%%一些特征两两组合后对于数据的划分有提升
x["dragonsDiff"] = x["blueDragons"] - x["redDragons"]#拿到龙
x["heraldsDiff"] = x["blueHeralds"] - x["redHeralds"]#拿到峡谷先锋
x["eliteDiff"] = x["blueEliteMonsters"] - x["redEliteMonsters"]#击杀大型野怪
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()

#%%推塔数量与游戏胜负
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进行训练和预测
## 为了正确评估模型性能，将数据划分为训练集和测试集，并在训练集上训练模型，在测试集上验证模型性能。
from sklearn.model_selection import train_test_split
## 选择其类别为0和1的样本 （不包括类别为2的样本）
data_target_part = y
data_features_part = x
## 测试集大小为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)
#%%## 导入LightGBM模型
from lightgbm.sklearn import LGBMClassifier
## 定义 LightGBM 模型 
clf = LGBMClassifier()
# 在训练集上训练LightGBM模型
clf.fit(x_train, y_train)

#%%在训练集和测试集上分别利用训练好的模型进行预测
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
from sklearn import metrics

## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
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))

## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print("The confusion matrix result:
",confusion_matrix_result)

# 利用热力图对于结果进行可视化
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进行特征选择，同样可以用属性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，还可以使用LightGBM中的其他属性进行评估(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))

#%%调整参数，获得更好的效果
## 从sklearn库中导入网格调参函数
from sklearn.model_selection import GridSearchCV

## 定义参数取值范围
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)

## 进行网格搜索
clf = GridSearchCV(model, parameters, cv=3, scoring="accuracy",verbose=3, n_jobs=-1)
clf = clf.fit(x_train, y_train)
#%%查看最好的参数值分别是多少
print(clf.best_params_)

#%%查看最好的参数值分别是多少
print(clf.best_params_)
#%% 在训练集和测试集上分布利用最好的模型参数进行预测
## 定义带参数的 LightGBM模型 
clf = LGBMClassifier(feature_fraction = 1,
                    learning_rate = 0.1,
                    max_depth= 3,
                    num_leaves = 16)
# 在训练集上训练LightGBM模型
clf.fit(x_train, y_train)

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

## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
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))

## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print("The confusion matrix result:
",confusion_matrix_result)

# 利用热力图对于结果进行可视化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap="Blues")
plt.xlabel("Predicted labels")
plt.ylabel("True labels")
plt.show()