python与r

import numpy as np
import pandas as pd

df = pd.DataFrame({'col_a': np.arange(10), 
                   'col_b': np.random.randn(10), 
                   'col_c': np.random.choice(['A', 'B', 'C'], 10), 
                   'col_d': np.random.choice([0, 1], 10)})
df.head(5)

# R code:
# df <- data.frame(col_a = 0:9,
#                  col_b = rnorm(10),
#                  col_c = sample(c('A', 'B', 'C'), size = 10, replace = TRUE),
#                  col_d = sample(c(0, 1), size = 10, replace = TRUE), 
#                  stringsAsFactors = FALSE)
# head(df, 5)

	col_a	col_b	col_c	col_d
0	0	-1.030159	B	0
1	1	1.447636	B	1
2	2	1.572227	C	0
3	3	0.031504	A	1
4	4	0.071705	C	0

print(df.shape, df.shape[0], df.shape[1])

# R code:
# dim(df), rnow(df), ncol(df)

(10, 4) 10 4

df.columns

# R code:
# names(df)

Index(['col_a', 'col_b', 'col_c', 'col_d'], dtype='object')

# 选取前5行数据
df.iloc[:5]

# R code:
# df[1:5, ]

	col_a	col_b	col_c	col_d
0	0	-1.030159	B	0
1	1	1.447636	B	1
2	2	1.572227	C	0
3	3	0.031504	A	1
4	4	0.071705	C	0

# 选取col_a和col_b列
df[['col_a', 'col_b']]

# R code:
# df[, c('col_a', 'col_b')]

	col_a	col_b
0	0	-1.030159
1	1	1.447636
2	2	1.572227
3	3	0.031504
4	4	0.071705
5	5	-0.284231
6	6	0.403412
7	7	1.271582
8	8	0.693771
9	9	1.510458

# 选取前5行和前2列
df.iloc[:5, :2]

# R code:
# df[1:5, 1:2]

	col_a	col_b
0	0	-1.030159
1	1	1.447636
2	2	1.572227
3	3	0.031504
4	4	0.071705

# 选取单个值(scalar)
df.iat[0, 1]

# R code:
# df[1, 2]

-1.0301593908948492

df[(df['col_a'] > 3) & (df['col_b'] < 0)]
# or 
# df.query('col_a > 3 & col_b < 0')

# R code:
# df[df$col_a > 3 & df$col_b < 0, ]

	col_a	col_b	col_c	col_d
5	5	-0.284231	A	0

df[df['col_c'].isin(['A', 'B'])]

# R code:
# df[df$col_c %in% c('A', 'B'), ]

	col_a	col_b	col_c	col_d
0	0	-1.030159	B	0
1	1	1.447636	B	1
3	3	0.031504	A	1
5	5	-0.284231	A	0
7	7	1.271582	A	0
8	8	0.693771	B	1
9	9	1.510458	A	1

df['col_e'] = df['col_a'] + df['col_b']
df

# df$col_e <- df$col_a + df$col_b

	col_a	col_b	col_c	col_d	col_e
0	0	-1.030159	B	0	-1.030159
1	1	1.447636	B	1	2.447636
2	2	1.572227	C	0	3.572227
3	3	0.031504	A	1	3.031504
4	4	0.071705	C	0	4.071705
5	5	-0.284231	A	0	4.715769
6	6	0.403412	C	1	6.403412
7	7	1.271582	A	0	8.271582
8	8	0.693771	B	1	8.693771
9	9	1.510458	A	1	10.510458

# 删除col_e列
df = df.drop(columns='col_e')
df

# R code:
# df <- df[, !names(df) == 'col_e']

	col_a	col_b	col_c	col_d
0	0	-1.030159	B	0
1	1	1.447636	B	1
2	2	1.572227	C	0
3	3	0.031504	A	1
4	4	0.071705	C	0
5	5	-0.284231	A	0
6	6	0.403412	C	1
7	7	1.271582	A	0
8	8	0.693771	B	1
9	9	1.510458	A	1

# 删除第一列
df.drop(columns=df.columns[0])

# R code:
# df[, -1]

	col_b	col_c	col_d
0	-1.030159	B	0
1	1.447636	B	1
2	1.572227	C	0
3	0.031504	A	1
4	0.071705	C	0
5	-0.284231	A	0
6	0.403412	C	1
7	1.271582	A	0
8	0.693771	B	1
9	1.510458	A	1

df.T

# R code:
# t(df)

	0	1	2	3	4	5	6	7	8	9
col_a	0	1	2	3	4	5	6	7	8	9
col_b	-1.03016	1.44764	1.57223	0.0315043	0.0717051	-0.284231	0.403412	1.27158	0.693771	1.51046
col_c	B	B	C	A	C	A	C	A	B	A
col_d	0	1	0	1	0	0	1	0	1	1

df['col_a'].astype(str)

# as.character(df$col_a)

0    0
1    1
2    2
3    3
4    4
5    5
6    6
7    7
8    8
9    9
Name: col_a, dtype: object

pd.Categorical(df['col_c'])

# factor(df$col_d)

[B, B, C, A, C, A, C, A, B, A]
Categories (3, object): [A, B, C]

#按行统计
df[['col_a', 'col_b']].sum(axis=1)

# R code:
# apply(df[, c('col_a', 'col_b')], 1, sum)

0    -1.030159
1     2.447636
2     3.572227
3     3.031504
4     4.071705
5     4.715769
6     6.403412
7     8.271582
8     8.693771
9    10.510458
dtype: float64

#按列统计
df[['col_a', 'col_b']].mean(axis=0)

# R code:
# apply(df[, c('col_a', 'col_b')], 2, mean)

col_a    4.50000
col_b    0.56879
dtype: float64

df[['col_a', 'col_b']].apply(lambda x: x.mean() + 10)

# R code:
# apply(df[, c('col_a', 'col_b')], 2, function(x) mean(x) + 10)

col_a    14.50000
col_b    10.56879
dtype: float64

df2 = pd.DataFrame({'col_x': np.arange(10), 
                    'col_y': np.arange(10)[::-1]})
df2

	col_x	col_y
0	0	9
1	1	8
2	2	7
3	3	6
4	4	5
5	5	4
6	6	3
7	7	2
8	8	1
9	9	0

#数据合并
#合并列
pd.concat([df, df2], axis=1)


# R code:
# cbind(df, df2)

	col_a	col_b	col_c	col_d	col_x	col_y
0	0	-1.030159	B	0	0	9
1	1	1.447636	B	1	1	8
2	2	1.572227	C	0	2	7
3	3	0.031504	A	1	3	6
4	4	0.071705	C	0	4	5
5	5	-0.284231	A	0	5	4
6	6	0.403412	C	1	6	3
7	7	1.271582	A	0	7	2
8	8	0.693771	B	1	8	1
9	9	1.510458	A	1	9	0

df3 = pd.DataFrame({'col_a': [-1, -2], 
                    'col_b' : [0, 1], 
                    'col_c': ['B', 'C'], 
                    'col_d': [1, 0]})
df3

	col_a	col_b	col_c	col_d
0	-1	0	B	1
1	-2	1	C	0

pd.concat([df, df3], axis=0, ignore_index=True)

# R code:
# rbind(df, df3)

	col_a	col_b	col_c	col_d
0	0	-1.030159	B	0
1	1	1.447636	B	1
2	2	1.572227	C	0
3	3	0.031504	A	1
4	4	0.071705	C	0
5	5	-0.284231	A	0
6	6	0.403412	C	1
7	7	1.271582	A	0
8	8	0.693771	B	1
9	9	1.510458	A	1
10	-1	0.000000	B	1
11	-2	1.000000	C	0