6 回归集成：xgb、lgb、cat
这个代码是从kaggle上拷贝过来的：
- 如何使用三个树模型模块化训练；
- 文本特征如何做，如何挖掘；
- 时间特征的处理；
- 模型权重集成；
import pandas as pd
import math
import numpy as np
import joblib
import optunafrom lightgbm import LGBMRegressor
from catboost import CatBoostRegressor
from xgboost import XGBRegressor
from sklearn.preprocessing import *
from sklearn.metrics import *
from sklearn.model_selection import *from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizerimport datetime
import gc
from sklearn.base import clonepd.set_option('display.max_columns', None)import warnings
warnings.filterwarnings("ignore")d_s = pd.read_csv('/kaggle/input/rohlik-orders-forecasting-challenge/solution_example.csv')te_d = pd.read_csv('/kaggle/input/rohlik-orders-forecasting-challenge/test.csv')tr_d = pd.read_csv('/kaggle/input/rohlik-orders-forecasting-challenge/train.csv')tr_d.drop('id',axis=1,inplace=True)
te_d.drop('id',axis=1,inplace=True)tr_d['holiday_name'].fillna('None', inplace=True)
te_d['holiday_name'].fillna('None', inplace=True)def Process_Date(Df):Df['date'] = pd.to_datetime(Df['date'])Df['year'] = Df['date'].dt.yearDf['day'] = Df['date'].dt.dayDf['month'] = Df['date'].dt.monthDf['month_name'] = Df['date'].dt.month_name()Df['day_of_week'] = Df['date'].dt.day_name()Df['week'] = Df['date'].dt.isocalendar().weekDf['year_sin'] = np.sin(2 * np.pi * Df['year'])Df['year_cos'] = np.cos(2 * np.pi * Df['year'])Df['month_sin'] = np.sin(2 * np.pi * Df['month'] / 12) Df['month_cos'] = np.cos(2 * np.pi * Df['month'] / 12)Df['day_sin'] = np.sin(2 * np.pi * Df['day'] / 31) Df['day_cos'] = np.cos(2 * np.pi * Df['day'] / 31)Df['group']=(Df['year']-2020)*48+Df['month']*4+Df['day']//7Df['total_holidays_month'] = Df.groupby(['year', 'month'])['holiday'].transform('sum')Df['total_shops_closed_week'] = Df.groupby(['year', 'week'])['shops_closed'].transform('sum')Df['group_sin'] = np.sin(2 * np.pi * Df['group'] / Df['group'].max())Df['group_cos'] = np.cos(2 * np.pi * Df['group'] / Df['group'].max())return Dftr_d = Process_Date(tr_d)
te_d = Process_Date(te_d)tr_d = tr_d[['warehouse', 'date', 'holiday_name', 'holiday', 'shops_closed','winter_school_holidays', 'school_holidays', 'year', 'day', 'month','month_name', 'day_of_week', 'week', 'year_sin', 'year_cos','month_sin', 'month_cos', 'day_sin', 'day_cos', 'group','total_holidays_month', 'total_shops_closed_week','group_sin', 'group_cos','orders']]le_month = LabelEncoder()
le_week = LabelEncoder()
le_war = LabelEncoder()tr_d['month_name'] = le_month.fit_transform(tr_d['month_name'])
tr_d['day_of_week'] = le_week.fit_transform(tr_d['day_of_week'])
tr_d['warehouse'] = le_war.fit_transform(tr_d['warehouse'])te_d['month_name'] = le_month.transform(te_d['month_name'])
te_d['day_of_week'] = le_week.transform(te_d['day_of_week'])
te_d['warehouse'] = le_war.transform(te_d['warehouse'])def apply_tfidf_svd(df, text_column, max_features=1000, n_components=10):vectorizer = TfidfVectorizer(max_features=max_features, stop_words='english')vectors = vectorizer.fit_transform(df[text_column])svd = TruncatedSVD(n_components)x_sv = svd.fit_transform(vectors)tfidf_df = pd.DataFrame(x_sv)cols = [(text_column + "_tfidf_" + str(f)) for f in tfidf_df.columns.to_list()]tfidf_df.columns = colsdf = df.reset_index(drop=True)df = pd.concat([df, tfidf_df], axis="columns")return dftr_d = apply_tfidf_svd(tr_d,'holiday_name')
te_d = apply_tfidf_svd(te_d,'holiday_name')tr_d.drop(['date','holiday_name'],axis=1,inplace=True)
te_d.drop(['date','holiday_name'],axis=1,inplace=True)print(f"Shape Of Train Data is {tr_d.shape}")
print(f"Shape Of Test Data is {te_d.shape}")%%time X = tr_d.drop('orders',axis=1)
y =tr_d['orders']def cross_validate(model, n_splits=15):scores = []test_preds = np.zeros(len(te_d))groups = X['group']kfold = GroupKFold(n_splits=n_splits)for fold, (train_index, valid_index) in enumerate(kfold.split(X, y, groups=groups)):X_train = X.iloc[train_index]y_train = y.iloc[train_index]X_val = X.iloc[valid_index]y_val = y.iloc[valid_index]m = clone(model)m.fit(X_train, y_train, eval_set=[(X_val, y_val)])y_pred = m.predict(X_val)score = mean_absolute_percentage_error(y_val, y_pred)scores.append(score)test_preds += m.predict(te_d) / n_splitsgc.collect()print(f" MAPE mean: {np.array(scores).mean():.7f} (+- {np.array(scores).std():.7f})")return test_preds%%timeSEED = 2375cat = CatBoostRegressor(verbose=0,learning_rate=0.01,iterations=2000,random_state = SEED)
cat_test_preds = cross_validate(cat)SEED = 1023
xgb = XGBRegressor(n_estimators=1000,learning_rate=0.05,verbosity=0,random_state=SEED)
xgb_test_preds = cross_validate(xgb)%%timelgb = LGBMRegressor(verbose=-1,random_state = SEED)
lgb_test_preds = cross_validate(lgb)%%time weights = {'cat_test_preds': 0.45, 'lgb_test_preds': 0.45,'xgb_test_preds': 0.1,}cat_test_preds_weighted = cat_test_preds * weights['cat_test_preds']
lgb_test_preds_weighted = lgb_test_preds * weights['lgb_test_preds']
xgb_test_preds_weighted = xgb_test_preds * weights['xgb_test_preds']ensemble_preds = cat_test_preds_weighted + lgb_test_preds_weighted + xgb_test_preds_weightedd_s['orders'] = ensemble_preds
d_s['id'] = d_s['id']d_s.to_csv('Submission.csv', index=False)print(d_s.head())