wldcmzy的博客

用jupyter lab 做的 太多了懒得排版%matplotlib inlineimport numpy as npimport pandas as pdfrom sklearn.model_selection import GridSearchCVfrom sklearn.ensemble import RandomForestClassifierdf_t = pd.read_excel(r'D:\EdgeDownloadPlace\复赛数据集\train.xlsx',header=Non

sklearn.preprocessing.MinMaxScaler数据归一化（数据-最小值）/极差 把数据限制在0-1之间 范围可以改 feature_rangefrom sklearn.preprocessing import MinMaxScalerdata = [[-10,16],[-5,32],[0,48],[5,64]]scaler = MinMaxScaler(feature_range = [0,2])scaler = scaler.fit(data)#scaler = s

%matplotlib inlineimport numpy as npimport pandas as pdimport matplotlib.pyplot as pltfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import GridSearchCVfrom sklearn

import numpy as npimport pandas as pdfrom sklearn.ensemble import RandomForestClassifier# 从excel表导入数据df_t = pd.read_excel(r'D:\EdgeDownloadPlace\3dd40612152202ee8440f82a3d277008\train.xlsx')# 删除uid列df_t = df_t.drop(columns='uid')# 把数据中的'?'换成每一列的众

从excel中导入训练集+交叉验证随机森林import numpy as npimport pandas as pdfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import cross_val_scoreimport matplotlib.pyplot as plt# 从excel表导入数据df_t = pd.read_excel(r'D:\EdgeDownloadPlace\

import pandas as pdimport numpy as npfrom sklearn import treefrom sklearn.model_selection import train_test_splitdf_t=pd.read_excel(r'D:\EdgeDownloadPlace\3dd40612152202ee8440f82a3d277008\train.xlsx')df_t=df_t.drop(columns='uid')df_tfor col in df

发现随机森林的正确率在0.76-0.86左右，多次用随机森林找一个正确率大于0.84的模型输出答案import numpy as npimport pandas as pdfrom sklearn.ensemble import RandomForestClassifier#随机森林分类器from sklearn.model_selection import train_test_split#功能：将数据集分为训练集测试集 Xtrain,Xtest,Ytrain,Ytestdf_t=pd.r