xuefliang

conda update -n base conda conda install -c pyviz holoviz geoviews

 library(rstatix)  library(ggpubr)  # For easy data-visualizatio library(gtsummary) library(tidyverse) iris %>%    group_by(Species) %>%    get_summary_stats(Sepal.Length, Sepal.Width, type = "common") iris %>% get_summary_stats(type = "common") iris %>%   group_by(Species) %>%    get_summary_stats(Sepal.Length, show=c('n'))    df <- ToothGrowth df$dose <- as.factor(df$dose) # 比较2个独立组别 df %>%    t_test(len ~ supp, paired = FALSE)  -> stat.test # 分组数据：在按照「dose」分组后比较 supp 水平： stat.test <- df %>%   group_by(dose) %>%   t_test(len ~ supp) %>%   adjust_pvalue() %>%   add_significance("p.adj") # 比较配对样本 stat.test <- df %>%    t_test(len ~ supp, paired = TRUE) stat.test <- df %>%  # 成对比较：如果分组变量包含多于2个分类，会自动执行成对比较 pairwise.test <- df %>% t_test(len ~ dose) # 基于参考组的成对比较 stat.test <- df %>% t_test(len ~ dose, ref.group = "0.5...

import pandas as pd data = pd.DataFrame({     "Student": ["A", "B", "C", "D"],      "Physics": [89,34,23,56],      "Chemistry": [34,56,98,56],      "Math": [34,94,50,59],     'Name':["LI","Zhang","Wang","Xiao"]     }) pd.eval("data.Physics+data.Chemistry+data.Math") data.eval("total=Physics+Chemistry+Math").query('Math>50') data.eval('total2=Student',engine='python') data.eval('total2=Student+Name',engine='python') # 'numexpr': This default engine evaluates pandas objects using # numexpr for large speed ups in complex expressions with large frames. # 'python': Performs operations as if you had eval’d in top # level python. This engine is generally not that useful. (data.eval('total=sqrt(Math)')  .query('Chemistry>34')) data=pd.read_excel(r"C:\Users\xuefe\Desk...

 from sklearn.preprocessing import LabelEncoder #Auto encodes any dataframe column of type category or object. def dummyEncode(df):         columnsToEncode = list(df.select_dtypes(include=['category','object']))         le = LabelEncoder()         for feature in columnsToEncode:             try:                 df[feature] = le.fit_transform(df[feature])             except:                 print('Error encoding '+feature)         return df      X=dummyEncode(X)

 import cx_Oracle import os import pandas as pd import numpy as np import geopandas as gpd yg=pd.read_excel(r"C:\Users\xuefe\Documents\乙肝项目.xlsx") yg.info() # duplicated 判断是否有重复项 mask=yg[['GRDA_CODE','YM_MC']].duplicated(keep=False) #选择重复 yg[mask] yg.duplicated() #去重 yg[~mask] yg['YM_MC'].drop_duplicates() yg.drop_duplicates(['YM_MC']) # 当keep=False时，就是去掉所有的重复行  # 当keep=‘first'时，就是保留第一次出现的重复行  # 当keep='last'时就是保留最后一次出现的重复行。

 sqltxt = '''   select t.grda_code,        t.grda_xm,        e.csrq,        t.ym_mc,        t.jz_sj,        t.jz_zc,        t.ym_yxq,        t.ym_ph,        t.ym_bm,        t.ymsccj_mc,        t.jzdd_mc,        t.jzdd_dm   from inoc_jzjl t, grda_cr e  where e.grda_cr_lsh = t.grda_et_lsh  and t.config_ymxx_lsh in ('2901','2902','2903','2904','2905','2906')  and  t.jz_sj>=to_date('2021-01-01','yyyy-mm-dd')  and jcqk='1'  '''   jzjl=pd.read_sql(sqltxt,con) jzjl.columns=[str(item).lower() for item in jzjl.columns] jzjl['jz_sj']=jzjl['jz_sj'].dt.date jzjl['csrq']=pd.to_datetime(jzjl['csrq'],format='%Y%m%d') jzjl=jzjl[jzjl['ym_ph'].isin(['20210411','20210310','20210205','20210206','20201212','20210102'])] test=jzjl test...

  conda install contextily --channel conda-forge