Coggle 30 Day——零基础入门推荐系统 - 新闻推荐任务一

本文链接：https://blog.csdn.net/shine_rise/article/details/128392947

本文介绍了如何使用Python进行比赛报名操作，包括数据读取和关键库的导入。涵盖了CSV文件处理、特征工程、模型选择（如LightGBM、XGBoost）以及数据预处理技术（如MinMaxScaler）。重点讲解了如何运用交叉验证和网格搜索优化模型参数。

摘要由CSDN通过智能技术生成

任务一比赛报名与数据读取

import pandas as pd
import numpy as np
import time
import lightgbm as lgb
import xgboost as xgb
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
pd.set_option('mode.chained_assignment', None)
import warnings
# import eli5
# from eli5.sklearn import PermutationImportance
warnings.filterwarnings("ignore")
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV, RepeatedKFold, cross_val_score,cross_val_predict,KFold
from sklearn.metrics import make_scorer,mean_squared_error
from sklearn.linear_model import LinearRegression, Lasso, Ridge, ElasticNet
from sklearn.svm import LinearSVR, SVR
from sklearn.neighbors import KNeighborsRegressor
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor,AdaBoostRegressor

from sklearn.preprocessing import PolynomialFeatures,MinMaxScaler,StandardScaler,Normalizer
# from xgboost import XGBRegressor
from sklearn.model_selection import TimeSeriesSplit
import joblib
plt.rcParams['font.sans-serif'] = ['SimHei']  # 中文字体设置-黑体
plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
sns.set(font='SimHei')  # 解决Seaborn中文显示问题

import pandas as pd
import numpy as np

articles = pd.read_csv('articles.csv')
articles_emb = pd.read_csv('articles_emb.csv')

train_clicks = pd.read_csv('train_click_log.csv')
test_clicks = pd.read_csv('testA_click_log.csv')