def xgb_offline(train_data, cv_data):
train_data = build_train_dataset(train_data, rate)
train_data.reset_index(inplace=True, drop=True)
train_Y = train_data['is_trade'].values
cv_Y = cv_data['is_trade'].values
drop_cols = ['is_trade']
train_data.drop(drop_cols, axis=1, inplace=True)
cv_data.drop(drop_cols, axis=1, inplace=True)
print('train shap:', train_data.shape)
print('cv shape', cv_data.shape)
kf = KFold(len(train_data), n_folds=5, shuffle=True, random_state=520)
train_preds = np.zeros(train_data.shape[0])
cv_preds = np.zeros(train_data.shape[0])
test_preds = np.zeros((cv_data.shape[0], 5))
for i, (train_index, cv_index) in enumerate(kf):
print('第{}次训练...'.format(i))
train_feat = train_data.iloc[train_index]
cv_feat = train_data.iloc[cv_index]
train_feat = xgb.DMatrix(train_feat.values, label=train_Y[train_index])
cv_feat = xgb.DMatrix(cv_feat.values, label=train_Y[cv_index])
test_feat = xgb.DMatrix(cv_data.values)
watchlist = [(train_feat, 'train'), (cv_feat, 'val')]
clf = xgb.train(params=params, dtrain=train_feat,num_boost_round=n_round,\
evals=watchlist,early_stopping_rounds=7,verbose_eval=False)
predict_train = clf.predict(train_feat)
predict_cv = clf.predict(cv_feat)
predict_test = clf.predict(test_feat)
train_preds[train_index] += predict_train
cv_preds[cv_index] += predict_cv
test_preds[:, i] = predict_test
print(clf.best_iteration)
print(clf.best_score)
print(' 训练损失:', cal_log_loss(predict_train, train_Y[train_index]))
print(' 测试损失:', cal_log_loss(predict_cv, train_Y[cv_index]))
#特征重要度
features = train_data.columns
ceate_feature_map(features)
importance = clf.get_fscore(fmap='xgb.fmap')
importance = sorted(importance.items(), key=operator.itemgetter(1))
df = pd.DataFrame(importance, columns=['feature', 'fscore'])
df['fscore'] = df['fscore'] / df['fscore'].sum()
predict_test = np.median(test_preds, axis=1)
predict_test = predict_test / (predict_test + (1 - predict_test) / rate)
print('训练损失:', cal_log_loss(train_preds / 4, train_Y))
print('测试损失:', cal_log_loss(cv_preds, train_Y))
print('验证损失:', cal_log_loss(predict_test, cv_Y))
return df, clf
def lgb_offline(train_data, cv_data):
train_data = build_train_dataset(train_data, rate)
train_data.reset_index(inplace=True, drop=True)
train_Y = train_data['is_trade']
cv_Y = cv_data['is_trade']
drop_cols = ['is_trade']
train_data.drop(drop_cols, axis=1, inplace=True)
cv_data.drop(drop_cols, axis=1, inplace=True)
kf = KFold(len(train_data), n_folds=5, shuffle=True, random_state=520)
train_preds = np.zeros(train_data.shape[0])
cv_preds = np.zeros(train_data.shape[0])
test_preds = np.zeros((cv_data.shape[0], 5))
for i, (train_index, cv_index) in enumerate(kf):
train_feat = train_data.loc[train_index]
cv_feat = train_data.loc[cv_index]
print('第{}次训练...'.format(i))
lgb_train = lgb.Dataset(train_feat.values, train_Y.loc[train_index])
lgb_cv = lgb.Dataset(cv_feat.values, train_Y.loc[cv_index])
gbm = lgb.train(params=params,
train_set=lgb_train,
num_boost_round=6000,
valid_sets=lgb_cv,
verbose_eval=False,
early_stopping_rounds=100)
#评价特征的重要性
feat_imp = pd.Series(
gbm.feature_importance(),
index=train_data.columns).sort_values(ascending=False)
predict_train = gbm.predict(train_feat.values)
predict_cv = gbm.predict(cv_feat.values)
test_preds[:, i] = gbm.predict(cv_data.values)
train_preds[train_index] += predict_train
cv_preds[cv_index] += predict_cv
feat_imp = pd.Series(
gbm.feature_importance(),
index=train_data.columns).sort_values(ascending=False)
print(gbm.best_iteration)
print(gbm.best_score)
print(' 训练损失:', cal_log_loss(predict_train,
train_Y.loc[train_index]))
print(' 测试损失:', cal_log_loss(predict_cv, train_Y.loc[cv_index]))
predict_test = np.median(test_preds, axis=1)
predict_test = predict_test / (predict_test + (1 - predict_test) / rate)
print(params)
print('训练损失:', cal_log_loss(train_preds / 4, train_Y))
print('测试损失:', cal_log_loss(cv_preds, train_Y))
print('验证损失:', cal_log_loss(predict_test, cv_Y))
return gbm, feat_imp
def LR_online(train_data, cv_data, test_data):
train_data = pd.concat([train_data, cv_data],axis=0)
train_data = build_train_dataset(train_data, rate)
train_data.reset_index(inplace=True,drop=True)
train_Y = train_data['is_trade']
drop_cols = ['is_trade']
train_data.drop(drop_cols,axis=1,inplace=True)
test_data.drop(drop_cols,axis=1,inplace=True)
fold = 5
kf = KFold(len(train_data), n_folds = fold, shuffle=True, random_state=520)
train_preds = np.zeros(train_data.shape[0])
cv_preds = np.zeros(train_data.shape[0])
test_preds = np.zeros((test_data.shape[0], fold))
for i, (train_index, cv_index) in enumerate(kf):
train_feat = train_data.loc[train_index]
cv_feat = train_data.loc[cv_index]
clf = LogisticRegression(C=1.2, fit_intercept=True, max_iter=3000,class_weight={0:0.5, 1:0.5})
clf.fit(X=train_feat.values, y=train_Y[train_index])
predict_train = clf.predict_proba(train_feat.values)[:,1]
predict_cv = clf.predict_proba(cv_feat.values)[:,1]
predict_test = clf.predict_proba(test_data.values)[:,1]
train_preds[train_index] += predict_train
cv_preds[cv_index] += predict_cv
test_preds[:,i] = predict_test
print(' 训练损失:',cal_log_loss(predict_train, train_Y[train_index]))
print(' 测试损失:',cal_log_loss(predict_cv, train_Y[cv_index]))
predict_test = np.median(test_preds,axis=1)
predict_test = predict_test/(predict_test+(1-predict_test)/rate)
print('训练损失:',cal_log_loss(train_preds/4, train_Y))
print('测试损失:',cal_log_loss(cv_preds, train_Y))
submmit_result(predict_test, 'LR')