python关联分析sklearn_关于sklearn算法学习的一部分总结

前言

关于一部分算法实践的代码整理

关于算法实践的几个步骤关键步骤

载入python相关的包

# 基础

import pandas as pd

import numpy as np

from collections import defaultdict

import matplotlib.pyplot as plt

import seaborn as sns

import gc

# import sklearn

from sklearn.preprocessing import LabelEncoder

from sklearn.preprocessing import StandardScaler

from sklearn.model_selection import train_test_split

# X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size = 0.25, random_state = 0)

from sklearn.model_selection import KFold

from sklearn.metrics import mean_squared_error as mse

from lightgbm.sklearn import LGBMRegressor

# import boosting algorithm

import lightgbm as lgb

import xgboost as xgb

import catboost as ctb

载入数据

df=pd.read_csv(filepath)

print(df.info())

数据清洗

0、数据描述

trainset.describe().apply(lambda x:round(x,2) if isinstance(x,'int') else x)

1、查看特征空值情况

df_nulldata='\n'.join(['{} feature have: {} null data'.format(col,df[col].isnull().sum()) for col in df.column