filtr 筛选,只对行，不对列，subset(),可以对行和列操作

> head(tips,3)
  total_bill  tip    sex smoker day   time size
1      16.99 1.01 Female     No Sun Dinner    2
2      10.34 1.66   Male     No Sun Dinner    3
3      21.01 3.50   Male     No Sun Dinner    3
> fil1 = filter(tips,tips$smoker =='No',tips$day == 'Sun');head(fil1)
  total_bill  tip    sex smoker day   time size
1      16.99 1.01 Female     No Sun Dinner    2
2      10.34 1.66   Male     No Sun Dinner    3
3      21.01 3.50   Male     No Sun Dinner    3
4      23.68 3.31   Male     No Sun Dinner    2
5      24.59 3.61 Female     No Sun Dinner    4
6      25.29 4.71   Male     No Sun Dinner    4

slice 切片,行

> s1 = slice(tips,1:5);s1
  total_bill  tip    sex smoker day   time size
1      16.99 1.01 Female     No Sun Dinner    2
2      10.34 1.66   Male     No Sun Dinner    3
3      21.01 3.50   Male     No Sun Dinner    3
4      23.68 3.31   Male     No Sun Dinner    2
5      24.59 3.61 Female     No Sun Dinner    4

select ,选择列

> s2 = select(tips,tip,sex,day);head(s2,3)
   tip    sex day
1 1.01 Female Sun
2 1.66   Male Sun
3 3.50   Male Sun
> s3 = select(tips,tip:time);head(s3,3)
   tip    sex smoker day   time
1 1.01 Female     No Sun Dinner
2 1.66   Male     No Sun Dinner
3 3.50   Male     No Sun Dinner
> s4 = select(tips,2:5);head(s4,3)
   tip    sex smoker day
1 1.01 Female     No Sun
2 1.66   Male     No Sun
3 3.50   Male     No Sun

arrange()

> new_tips = arrange(tips,total_bill,tip);head(new_tips)  #默认升序
    total_bill  tip    sex smoker  day   time size
68        3.07 1.00 Female    Yes  Sat Dinner    1
93        5.75 1.00 Female    Yes  Fri Dinner    2
112       7.25 1.00 Female     No  Sat Dinner    1
173       7.25 5.15   Male    Yes  Sun Dinner    2
150       7.51 2.00   Male     No Thur  Lunch    2
196       7.56 1.44   Male     No Thur  Lunch    2
> new_tips = arrange(tips,desc(total_bill),tip);head(new_tips) #降序的操作
    total_bill   tip    sex smoker day   time size
171      50.81 10.00   Male    Yes Sat Dinner    3
213      48.33  9.00   Male     No Sat Dinner    4
60       48.27  6.73   Male     No Sat Dinner    4
157      48.17  5.00   Male     No Sun Dinner    6
183      45.35  3.50   Male    Yes Sun Dinner    3
103      44.30  2.50 Female    Yes Sat Dinner    3

rename 重新命名 列

> new_tips = rename(tips,bill = total_bill);head(new_tips)
   bill  tip    sex smoker day   time size
1 16.99 1.01 Female     No Sun Dinner    2
2 10.34 1.66   Male     No Sun Dinner    3
3 21.01 3.50   Male     No Sun Dinner    3
4 23.68 3.31   Male     No Sun Dinner    2
5 24.59 3.61 Female     No Sun Dinner    4
6 25.29 4.71   Male     No Sun Dinner    4

distinct(data,variable) 将数据集里的列生成因子

> distinct(tips,day)
    day
1   Sun
20  Sat
78 Thur
91  Fri
> distinct(tips,sex)
     sex
1 Female
2   Male

mutate add new column

> m1 = mutate(tips,rate = tip/total_bill);head(m1)
  total_bill  tip    sex smoker day   time size       rate
1      16.99 1.01 Female     No Sun Dinner    2 0.05944673
2      10.34 1.66   Male     No Sun Dinner    3 0.16054159
3      21.01 3.50   Male     No Sun Dinner    3 0.16658734
4      23.68 3.31   Male     No Sun Dinner    2 0.13978041
5      24.59 3.61 Female     No Sun Dinner    4 0.14680765
6      25.29 4.71   Male     No Sun Dinner    4 0.18623962
> 
> m1 = mutate(tips,rate = tip/total_bill,new_rate = rate*100);head(m1)#可以同时生成rate和new_rate
  total_bill  tip    sex smoker day   time size       rate
1      16.99 1.01 Female     No Sun Dinner    2 0.05944673
2      10.34 1.66   Male     No Sun Dinner    3 0.16054159
3      21.01 3.50   Male     No Sun Dinner    3 0.16658734
4      23.68 3.31   Male     No Sun Dinner    2 0.13978041
5      24.59 3.61 Female     No Sun Dinner    4 0.14680765
6      25.29 4.71   Male     No Sun Dinner    4 0.18623962
   new_rate
1  5.944673
2 16.054159
3 16.658734
4 13.978041
5 14.680765
6 18.623962

transform cannot creat new variable like mutate for example

> transform(tips,rate = tip/total_bill,new_rate = rate*100) # error cannot find rate
Error in eval(substitute(list(...)), `_data`, parent.frame()) : 
  找不到对象'rate'

summarise 可以

head(summarize(tips,rate = tip/total_bill) ,3)# 
head(summarize(tips,rate = tip/total_bill,new_rate = rate*100) ,3)

sample random choose num

> sample_n(iris,size = 3)  #随机抽出行
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          6.5         2.8          4.6         1.5 versicolor
2          5.1         3.8          1.6         0.2     setosa
3          6.0         2.9          4.5         1.5 versicolor
> sample_frac(iris,size = 0.01)  #按百分比随机抽出行
  Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1          6.2         2.9          4.3         1.3 versicolor
2          6.8         3.2          5.9         2.3  virginica

%>% pip

> result = tips %>% group_by(smoker,sex) %>% summarise(count = n(),mean_tips = mean(tip),
+                                                      sd_bill = sd(total_bill));result
`summarise()` regrouping output by 'smoker' (override with `.groups` argument)
# A tibble: 4 x 5
# Groups:   smoker [2]
  smoker sex    count mean_tips sd_bill
  <fct>  <fct>  <int>     <dbl>   <dbl>
1 No     Female    54      2.77    7.29
2 No     Male      97      3.11    8.73
3 Yes    Female    33      2.93    9.19
4 Yes    Male      60      3.05    9.91

join join two data.frame

inner_join

semi_join

anit_join

left_join

right_join

> df1 = data.frame(x = letters[1:8],y = 1:8);df1
  x y
1 a 1
2 b 2
3 c 3
4 d 4
5 e 5
6 f 6
7 g 7
8 h 8
> df2 = data.frame(x = c("a","b","c"),z = 10:12);df2
  x  z
1 a 10
2 b 11
3 c 12
> inner_join(df1,df2,by = 'x')  #jiao ji 
  x y  z
1 a 1 10
2 b 2 11
3 c 3 12
> semi_join(df1,df2,by = "x")  #只取df1中在df2中出现的
  x y
1 a 1
2 b 2
3 c 3
> anti_join(df1,df2,by = "x") #只取df1不在df2出现的
  x y
1 d 4
2 e 5
3 f 6
4 g 7
5 h 8
> left_join(df1,df2,by = "x") #按照左侧数据库结合，没有的就自动填充NA
  x y  z
1 a 1 10
2 b 2 11
3 c 3 12
4 d 4 NA
5 e 5 NA
6 f 6 NA
7 g 7 NA
8 h 8 NA
> right_join(df1,df2,by = "x")
  x y  z
1 a 1 10
2 b 2 11
3 c 3 12