LightGBM分类实战

目录

❄️导入模块❄️

🌜数据处理🌛

1️⃣加载数据集

2️⃣字符变量编码

3️⃣分离数据集和标签

4️⃣超参数设置

5️⃣保存特征重要性

🔞交叉验证训练模型🔞

1️⃣可视化特征重要性

2️⃣模型预测

---

❄️导入模块❄️

import joblib
import warnings
import numpy as np
import pandas as pd
import seaborn as sns
import lightgbm as lgb
import matplotlib.pyplot as plt

from tqdm import tqdm_notebook
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import KFold, train_test_split
from sklearn.metrics import precision_recall_fscore_support, roc_auc_score

warnings.filterwarnings("ignore")

🌜数据处理🌛

1️⃣加载数据集

%%time
# 加载数据集
train = pd.read_csv("historic customer behavior.csv")
test = pd.read_csv("target customer.csv")
print("train shape : ", train.shape)
print("test shape : ", test.shape)

2️⃣字符变量编码

# 输出 object 类型的列
for col in train.columns:
    if train[col].dtype == "object":
        print(col)



# LabelEncoder
for col in tqdm_notebook(train.columns):
    if train[col].dtype == "object":
        encoder = LabelEncoder()
        encoder.fit(list(train[col].values) + list(test[col].values))
        train[col] = encoder.transform(list(train[col].values))
        test[col] = encoder.transform(list(test[col].values))

3️⃣分离数据集和标签

X = train.drop(['Risk_Flag'], axis=1)
y = train['Risk_Flag']

4️⃣超参数设置

# params 超参数设置
params = {'learning_rate':0.05, #  学习率，默认设置为0.1，一般设置在0.05-0.1之间
          'boosting_type': 'gbdt', # 'dart', 'goss', 'rf'
          'objective': 'binary', # 任务：二分类
          'metric': 'auc', # 衡量标准
          'max_depth': 8, # 默认-1 ： 不限制深度
          'num_leaves': 63, # 叶节点数量
          'lambda_l1': 1,
          'lambda_l2': 1,
          'min_child_samples': 100,
          'min_child_weight': 1,
          'feature_fraction':1,
          'bagging_fraction':1,
          'bagging_freq':2,
          "verbose" : -1, # 不显示信息
          'seed': 66, # 随机种子
          'is_unbalance':'True'
         }

5️⃣保存特征重要性

# 创建DataFrame保存特征重要性
feature_importances = pd.DataFrame(index=None)
feature_importances['features'] = X.columns

🔞交叉验证训练模型🔞

# 5折交叉验证
folds = KFold(n_splits=5,shuffle=True,random_state=10)
splits = folds.split(X, y) # 分割成5份，前4份是训练集索引，最后1份是验证集索引


best_auc = 0
best_model = None

for fold, (train_indices, val_indices) in enumerate(splits):
    print('fold ', fold + 1)
    X_train_data, X_val_data = X.iloc[train_indices], X.iloc[val_indices] # 训练集， 验证集
    y_train, y_val = y.iloc[train_indices], y.iloc[val_indices] # 训练标签，验证标签

    
    train_dataset = lgb.Dataset(X_train_data, label=y_train) # 训练集
    val_dataset = lgb.Dataset(X_val_data, label=y_val) # 验证集
    
    lgb_model = lgb.train(params=params, # 超参数设置
                          train_set=train_dataset, # 训练数据
                          num_boost_round=1000, # 循环的轮数
                          valid_sets=val_dataset, # 验证数据
                          valid_names='validation', # 验证集名称
                          early_stopping_rounds=200,# 如果200轮后没有提升，就停止循环
                          verbose_eval=False) 
    # 保存特征重要性
    feature_importances[f'fold_{fold+1}'] = lgb_model.feature_importance()
    
    # 对验证集进行预测
    y_val_pred = lgb_model.predict(X_val_data)
    
    # 计算roc_auc
    roc_auc = roc_auc_score(y_val, y_val_pred)
    print(f" Fold {fold + 1} | AUC_ROC ： { roc_auc * 100}%")
    print(f"{'-'*50}\n")
    
    # 判断是否是最优模型
    if roc_auc > best_auc:
        best_auc = roc_auc
        best_model = lgb_model

1️⃣可视化特征重要性

feature_importances['average'] = feature_importances[[f'fold_{fold+1}' for fold in range(folds.n_splits-1)]].mean(axis=1)


# 可视化显示特征
plt.figure(figsize=(10, 6))
sns.barplot(data=feature_importances.sort_values(by='average', ascending=False), 
            x='average', 
            y='features')
plt.title("top features importance over {} folds average.".format(folds.n_splits))

2️⃣模型预测

print("The best roc_auc : ", roc_auc)


# 对与test进行预测
pred = best_model.predict(test)


from collections import Counter
labels = np.round(pred) # np.round() 四舍五入
Counter(labels)