赛题背景
赛题以银行产品认购预测为背景，想让你来预测下客户是否会购买银行的产品。在和客户沟通的过程中，我们记录了和客户联系的次数，上一次联系的时长，上一次联系的时间间隔，同时在银行系统中我们保存了客户的基本信息，包括：年龄、职业、婚姻、之前是否有违约、是否有房贷等信息，此外我们还统计了当前市场的情况：就业、消费信息、银行同业拆解率等。
赛题任务
输出结果：
输出结果;
模型训练
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import AdaBoostClassifier
from xgboost import XGBRFClassifier
from lightgbm import LGBMClassifier
from sklearn.model_selection import cross_val_score
import time
clf_lr = LogisticRegression(random_state=0, solver='lbfgs', multi_class='multinomial')
clf_dt = DecisionTreeClassifier()
clf_rf = RandomForestClassifier()
clf_gb = GradientBoostingClassifier()
clf_adab = AdaBoostClassifier()
clf_xgbrf = XGBRFClassifier()
clf_lgb = LGBMClassifier()
from sklearn.model_selection import train_test_split
train_new = pd.read_csv('train_new.csv')
test_new = pd.read_csv('test_new.csv')
feature_columns = [col for col in train_new.columns if col not in ['subscribe']]
train_data = train_new[feature_columns]
target_data = train_new['subscribe']
# 模型调参
from lightgbm import LGBMClassifier
from sklearn.metrics import classification_report
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(train_data, target_data, test_size=0.2,shuffle=True, random_state=)
#X_test, X_valid, y_test, y_valid = train_test_split(X_test, y_test, test_size=0.5,shuffle=True,random_state=)
n_estimators = [300]
learning_rate = [0.02]#中0.2最优
subsample = [0.6]
colsample_bytree = [0.7] ##在[0.5, 0.6, 0.7]中0.6最优
max_depth = [9, 11, 13] ##在[7, 9, 11, 13]中11最优
is_unbalance = [False]
early_stopping_rounds = [300]
num_boost_round = [5000]
metric = ['binary_logloss']
feature_fraction = [0.6, 0.75, 0.9]
bagging_fraction = [0.6, 0.75, 0.9]
bagging_freq = [2, 4, 5, 8]
lambda_l1 = [0, 0.1, 0.4, 0.5]
lambda_l2 = [0, 10, 15, 35]
cat_smooth = [1, 10, 15, 20]
param = {'n_estimators':n_estimators,
'learning_rate':learning_rate,
'subsample':subsample,
'colsample_bytree':colsample_bytree,
'max_depth':max_depth,
'is_unbalance':is_unbalance,
'early_stopping_rounds':early_stopping_rounds,
'num_boost_round':num_boost_round,
'metric':metric,
'feature_fraction':feature_fraction,
'bagging_fraction':bagging_fraction,
'lambda_l1':lambda_l1,
'lambda_l2':lambda_l2,
'cat_smooth':cat_smooth}
model = LGBMClassifier()
clf = GridSearchCV(model, param, cv=3, scoring='accuracy', verbose=1, n_jobs=-1)
clf.fit(X_train, y_train, eval_set=[(X_train, y_train),(X_test, y_test)])
print(clf.best_params_, clf.best_score_)
提交结果
