lightGBM是2017年1⽉，微软在GItHub上开源的⼀个新的梯度提升框架。
介绍链接
higgs数据集介绍：这是⼀个分类问题，⽤于区分产⽣希格斯玻⾊⼦的信号过程和不产⽣希格斯玻⾊⼦的信号过 程。
数据链接
数据链接
安装
pip3 install lightgbmlightGBM参数—— Control Parameters lightGBM参数—— Core Parameters
from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from sklearn.model_selection import GridSearchCV from sklearn.metrics import mean_squared_error import lightgbm as lgb读取数据
iris = load_iris() data = iris.data target= iris.target data
target数据基本处理
x_train,x_test,y_train,y_test = train_test_split(data,target,test_size=0.2)模型训练 模型基本训练
# 模型基本训练 gbm = lgb.LGBMRegressor(objective="regression",learning_rate=0.05,n_estimators=20) gbm.fit(x_train,y_train,eval_set=[(x_test,y_test)],eval_metric="l1",early_stopping_rounds=3) gbm.score(x_test,y_test)网格搜索进行训练
estimators = lgb.LGBMRegressor(num_leaves=31)
param_grid = {
"learning_rate":[0.01,0.1,1],
"n_estmators":[20,40,60,80]
}
gbm = GridSearchCV(estimator=estimators,param_grid=param_grid,cv=5)
gbm.fit(x_train,y_train)
gbm.best_params_
gbm = lgb.LGBMRegressor(objective="regression",learning_rate=0.1,n_estimators=20) gbm.fit(x_train,y_train,eval_set=[(x_test,y_test)],eval_metric="l1",early_stopping_rounds=3) gbm.score(x_test,y_test)lightGBM案例二：绝地求生玩家排名预测 数据集字段
创建⼀个模型，根据他们的最终统计数据预测玩家的排名，从1（第⼀名）到0（最后⼀名）。 最后结果通过平均绝对误差（MAE）进⾏评估，即通过预测的winPlacePerc和真实的winPlacePerc之间的平均绝对误差
MAE
sklearn.metrics.mean_absolute_error
import numpy as np import matplotlib.pyplot as plt import pandas as pd import seaborn as sns获取数据、基本数据信息查看
train = pd.read_csv("./data/train_V2.csv")
train.head()
# 查看一共有多少数据 train.shape #(4446966, 29) # 有多少场比赛 np.unique(train["matchId"]).shape #(47965,) # 有多少队伍 np.unique(train["groupId"]).shape #(2026745,)数据基本处理
# 数据缺失值处理 winPlacePerc有缺失值 np.any(train.isnull(),axis=0)
# 查找缺失值 train[train["winPlacePerc"].isnull()]
# 只有一行，删除即可 train = train.drop(2744604,inplace=True) train.shape #(4446965, 29)
# 特征数据规范化处理
# 查看每场比赛参加的人数
count = train.groupby("matchId")["matchId"].transform("count")
train["playersJoined"] = count
train.head()
train["playersJoined"].sort_values().head()
plt.figure(figsize=(20,8)) sns.countplot(train["playersJoined"]) plt.grid() plt.show()
plt.figure(figsize=(20,8)) sns.countplot(train[train["playersJoined"]>=75]["playersJoined"]) plt.grid() plt.show()
# 规范化输出部分数据 train["killsNorm"] = train["kills"] * ((100-train["playersJoined"])/100+1) train["damageDealtNorm"] = train["damageDealt"] * ((100-train["playersJoined"])/100+1) train["maxPlaceNorm"] = train["maxPlace"] * ((100-train["playersJoined"])/100+1) train["matchDurationNorm"] = train["matchDuration"] * ((100-train["playersJoined"])/100+1) train.head()
# 部分变量合成 train["healsandboosts"] = train["heals"] + train["boosts"] train[["heals", "boosts", "healsandboosts"]].tail(10)
# 异常值处理 删除有击杀，但是完全没有移动的玩家 train["totalDistance"] = train["rideDistance"] + train["walkDistance"] + train["swimDistance"] train.head()
train["killwithoutMoving"] = (train["kills"] > 0) & (train["totalDistance"] == 0) train[train["killwithoutMoving"] == True].head()
train[train["killwithoutMoving"] == True].shape #(1535, 37) train[train["killwithoutMoving"] == True].index
train.drop(train[train["killwithoutMoving"] == True].index, inplace=True) train.shape #(4445430, 37)
# 异常值处理：删除驾车杀敌数异常的数据 train.drop(train[train["roadKills"] > 10].index, inplace=True) train.shape #(4445426, 37)
# 异常值处理：删除玩家在一局中杀敌数超过30人的数据 train.drop(train[train["kills"] > 30].index, inplace=True) train.shape #(4445331, 37)
# 异常值处理：删除爆头率异常数据 train["headshot_rate"] = train["headshotKills"]/train["kills"] train["headshot_rate"].head()
train["headshot_rate"] = train["headshot_rate"].fillna(0) train.head()
train[(train["headshot_rate"] == 1) & (train["kills"] > 9)].head()
train.drop(train[(train["headshot_rate"] == 1) & (train["kills"] > 9)].index, inplace=True) train.shape #(4445307, 38)
# 异常值处理：删除最远杀敌距离异常数据 train.drop(train[train["longestKill"] >=1000].index, inplace=True) train.shape #(4445287, 38)
# 异常值处理：删除关于运动距离的异常值 # 行走 train.drop(train[train["walkDistance"] >=10000].index, inplace=True) train.shape #(4445068, 38) # 载具 train.drop(train[train["rideDistance"] >=20000].index, inplace=True) train.shape #(4444918, 38) # 游泳 train.drop(train[train["swimDistance"] >=20000].index, inplace=True) train.shape #(4444918, 38)
# 异常值处理：武器收集异常值处理 train.drop(train[train["weaponsAcquired"] >=80].index, inplace=True) train.shape #(4444899, 38)
# 异常值处理：删除使用治疗药品数量异常值 train.drop(train[train["heals"] >=80].index, inplace=True) train.shape #(4444898, 38)
# 类别型数据处理 # 比赛类型one-hot处理 train["matchType"].unique()
train = pd.get_dummies(train, columns=["matchType"]) train.head()
train.shape #(4444898, 53)
# 对groupId,matchId等数据进行处理 train["groupId"].head()
train["groupId"] = train["groupId"].astype("category")
train["groupId_cat"] = train["groupId"].cat.codes
train["groupId_cat"].head()
train["matchId"] = train["matchId"].astype("category")
train["matchId_cat"] = train["matchId"].cat.codes
train["matchId_cat"].head()
train.head()
train.drop(["groupId", "matchId"], axis=1, inplace=True) # 数据截取 取部分数据进行使用（100000） df_sample = train.sample(100000) df_sample.shape #(100000, 53) # 确定特征值和目标值 df = df_sample.drop(["winPlacePerc", "Id"], axis=1) y = df_sample["winPlacePerc"] df.shape #(100000, 51) y.shape #(100000,) # 分割训练集和测试集 from sklearn.model_selection import train_test_split X_train, X_valid, y_train, y_valid = train_test_split(df, y, test_size=0.2) X_train.shape #(80000, 51) y_train.shape #(80000,)模型训练/模型评估 初步使用随机森林
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
m1 = RandomForestRegressor(n_estimators=40,
min_samples_leaf=3,
max_features='sqrt',
n_jobs=-1)
m1.fit(X_train, y_train)
y_pre = m1.predict(X_valid)
m1.score(X_valid, y_valid)
mean_absolute_error(y_valid, y_pre)
再次使用随机森林，去掉不重要字段
m1.feature_importances_
imp_df = pd.Dataframe({"cols":df.columns, "imp":m1.feature_importances_})
imp_df.head()
imp_df = imp_df.sort_values("imp", ascending=False)
imp_df.head()
imp_df[:20].plot("cols", "imp", figsize=(20, 8), kind="barh")
to_keep = imp_df[imp_df.imp > 0.005].cols
to_keep.shape #(20,)
df_keep = df[to_keep]
X_train, X_valid, y_train, y_valid = train_test_split(df_keep, y, test_size=0.2)
X_train.shape #(80000, 20)
m2 = RandomForestRegressor(n_estimators=40,
min_samples_leaf=3,
max_features='sqrt',
n_jobs=-1)
m2.fit(X_train, y_train)
y_pre = m2.predict(X_valid)
m2.score(X_valid, y_valid) #0.9125654968172906
mean_absolute_error(y_valid, y_pre) #0.06408683094647326
使用lightGBM对模型进行训练
X_train, X_valid, y_train, y_valid = train_test_split(df, y, test_size=0.2)
X_train.shape #(80000, 51) import lightgbm as lgb gbm = lgb.LGBMRegressor(objective="regression", num_leaves=31, learning_rate=0.05, n_estimators=20) gbm.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], eval_metric="l1", early_stopping_rounds=5) y_pre = gbm.predict(X_valid, num_iteration=gbm.best_iteration_) mean_absolute_error(y_valid, y_pre) #0.12331524150224461使用GridSearchCV对lightGBM模型进行调优
from sklearn.model_selection import GridSearchCV
estimator = lgb.LGBMRegressor(num_leaves=31)
param_grid = {
"learning_rate":[0.01, 0.1, 1],
"n_estimators":[40, 60, 80, 100, 200, 300]
}
gbm = GridSearchCV(estimator, param_grid, cv=5, n_jobs=-1)
gbm.fit(X_train, y_train)
y_pre = gbm.predict(X_valid)
mean_absolute_error(y_valid, y_pre) #0.05685004010605751
gbm.best_params_ #{'learning_rate': 0.1, 'n_estimators': 300}
三次调优
# n_estimators
scores = []
n_estimators = [100, 300, 500, 800]
for nes in n_estimators:
lgbm = lgb.LGBMRegressor(boosting_type='gbdt',
num_leaves=31,
max_depth=5,
learning_rate=0.1,
n_estimators=nes,
min_child_samples=20,
n_jobs=-1)
lgbm.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], eval_metric="l1", early_stopping_rounds=5)
y_pre = lgbm.predict(X_valid)
mae = mean_absolute_error(y_valid, y_pre)
scores.append(mae)
print("本次结果输出的mae值是:n", mae)
plt.plot(n_estimators,scores,'o-')
plt.ylabel("mae")
plt.xlabel("n_estimator")
print("best n_estimator {}".format(n_estimators[np.argmin(scores)]))
# max_depth
scores = []
max_depth = [3, 5, 7, 9, 11]
for md in max_depth:
lgbm = lgb.LGBMRegressor(boosting_type='gbdt',
num_leaves=31,
max_depth=md,
learning_rate=0.1,
n_estimators=500,
min_child_samples=20,
n_jobs=-1)
lgbm.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], eval_metric="l1", early_stopping_rounds=5)
y_pre = lgbm.predict(X_valid)
mae = mean_absolute_error(y_valid, y_pre)
scores.append(mae)
print("本次结果输出的mae值是:n", mae)
plt.plot(max_depth,scores,'o-')
plt.ylabel("mae")
plt.xlabel("max_depths")
print("best max_depths {}".format(max_depth[np.argmin(scores)]))
scores1
