plydata,siuba,dplython
plydata
plydata是python之中很类似与R之中tidyverse的操作的包
用 tidyverse 的方式玩转 Python 数据处理 - 知乎 (zhihu.com)
import numpy as np
import pandas as pd
from plydata import define, query, if_else, ply
# NOTE: query is the equivalent of dplyr's filter but with
# slightly different python syntax for the expressions
df = pd.DataFrame({
'x': [0, 1, 2, 3],
'y': ['zero', 'one', 'two', 'three']})
df >> define(z='x')
"""
x y z
0 0 zero 0
1 1 one 1
2 2 two 2
3 3 three 3
"""
df >> define(z=if_else('x > 1', 1, 0))
"""
x y z
0 0 zero 0
1 1 one 0
2 2 two 1
3 3 three 1
"""
# You can pass the dataframe as the # first argument
query(df, 'x > 1') # same as `df >> query('x > 1')`
"""
x y
2 2 two
3 3 three
"""
# You can use the ply function instead of the >> operator
ply(df,
define(z=if_else('x > 1', 1, 0)),
query('z == 1')
)
"""
x y z
2 2 two 1
3 3 three 1
"""
from plotnine import ggplot, aes, geom_line
df = pd.DataFrame({'x': np.linspace(0, 2*np.pi, 500)})
(df
>> define(y='np.sin(x)')
>> define(sign=if_else('y >= 0', '"positive"', '"negative"'))
>> (ggplot(aes('x', 'y'))
+ geom_line(aes(color='sign'), size=1.5))
)
siuba
machow/siuba: Python library for using dplyr like syntax with pandas and SQL (github.com)
from siuba import group_by, summarize, _
from siuba.data import mtcars
(mtcars
>> group_by(_.cyl)
>> summarize(avg_hp = _.hp.mean())
)
dplython
python 学习之 python 里也能用 dplyr? (qq.com)
Python and Tidyverse (itsalocke.com)
import pandas
from dplython import (DplyFrame, X, diamonds, select, sift, sample_n,
sample_frac, head, arrange, mutate, group_by, summarize, DelayFunction)
print(diamondsSmall >> head(4))
## carat cut price color clarity depth table
## 0 0.23 Ideal 326 E SI2 61.5 55.0
## 1 0.21 Premium 326 E SI1 59.8 61.0
## 2 0.23 Good 327 E VS1 56.9 65.0
## 3 0.29 Premium 334 I VS2 62.4 58.0
