pandas基础复习

# 导入相关包
import pandas as pd 
import numpy as np

字典创建为DataFrame

data = {"grammer":["Python","C++","Java","Go",np.nan,"SQL","PHP","Python"],
        "score":[1,2,np.nan,4,5,6,7,10]}

df = pd.DataFrame(data)
df

	grammer	score
0	Python	1.0
1	C++	2.0
2	Java	NaN
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0

取得含有"Python"的行

df[df['grammer'] == 'Python']

	grammer	score
0	Python	1.0
7	Python	10.0

输出所有列名

print(df.columns)

Index(['grammer', 'score'], dtype='object')

修改第二列列名为 fraction

df.rename(columns={'score':'fraction'},inplace= True)

统计 grammer 列中每种编程语言出现的次数

df['grammer'].value_counts()

Python    2
C++       1
Java      1
Go        1
SQL       1
PHP       1
Name: grammer, dtype: int64

将 fraction列的空值，用平均值填充

df['fraction'] = df['fraction'].fillna(df['fraction'].mean())

df

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0

提取 fraction 列中值大于3的行

df['fraction'] > 3

0    False
1    False
2     True
3     True
4     True
5     True
6     True
7     True
Name: fraction, dtype: bool

df[df['fraction'] > 3]

	grammer	fraction
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0

按照 fraction 列进行去重复值操作

df.drop_duplicates(['fraction'])  # 自上而下

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0

计算 fraction 列的平均值

df['fraction'].mean()

5.0

将 grammer 列转换为list

df['grammer'].to_list()

['Python', 'C++', 'Java', 'Go', nan, 'SQL', 'PHP', 'Python']

将 DataFrame 保存为csv

df.to_csv('data.csv')

查看数据行列数

df.shape

(8, 2)

提取 fraction 列 值大于 2 且 小于 7 的行

df[(df['fraction'] > 2) & (df['fraction'] < 7)]

	grammer	fraction
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0

提取 fraction 列最大值所在的行

df['fraction'].max()

10.0

df[df['fraction'] == df['fraction'].max()]

	grammer	fraction
7	Python	10.0

查看最后5行

df.tail()   # tail(x)   后 x 行

	grammer	fraction
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0

查看前五行

df.head()  # head(x)   前 x 行   

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0

删除最后一行

# method 1
df.drop([len(df)-1])

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0

# method 2
df.drop(df.shape[0]-1)

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0

# method 3
df.drop(df.index[-1])

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0

添加一行数据 [‘ASP’,8.28]

s = pd.Series({'grammer':'ASP','fraction':8.28})

# DateFrame.append()方法已经被弃用了，所以用 pandas.concat方法
df = pd.concat([df, s.to_frame().T], ignore_index=True)
df

	grammer	fraction
0	Python	1.0
1	C++	2.0
2	Java	5.0
3	Go	4.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
7	Python	10.0
8	ASP	8.28

对数据进行排序，按照"fraction"列值的大小

df.sort_values("fraction")  
# 相关参数
# ascending(默认True)  升序：True 降序: False
# ignore_index(默认False) True: 重新索引

	grammer	fraction
0	Python	1.0
1	C++	2.0
3	Go	4.0
2	Java	5.0
4	NaN	5.0
5	SQL	6.0
6	PHP	7.0
8	ASP	8.28
7	Python	10.0

统计 grammer 列每个字符串的长度

df['grammer'] = df['grammer'].fillna('Lisp')

df['len_str'] = df['grammer'].apply(lambda x: len(x))
df

	grammer	fraction	len_str
0	Python	1.0	6
1	C++	2.0	3
2	Java	5.0	4
3	Go	4.0	2
4	Lisp	5.0	4
5	SQL	6.0	3
6	PHP	7.0	3
7	Python	10.0	6
8	ASP	8.28	3