import pandas as pd
df = pd.read_csv('data/gapminder.tsv',sep='t')
print(df.head())
country continent year lifeExp pop gdpPercap 0 Afghanistan Asia 1952 28.801 8425333 779.445314 1 Afghanistan Asia 1957 30.332 9240934 820.853030 2 Afghanistan Asia 1962 31.997 10267083 853.100710 3 Afghanistan Asia 1967 34.020 11537966 836.197138 4 Afghanistan Asia 1972 36.088 13079460 739.981106查看每一列的类型 df.dtypes或df.info()
- object – string – 字符串
- int64 – int – 整型
- float64 – float – 浮点型
- datetime64 – datetime – 时间
print(df.dtypes)
country object continent object year int64 lifeExp float64 pop int64 gdpPercap float64 dtype: object查看行列信息
# df.shape shape是属性,加上括号会报错 print(df.shape) #(行数，列数)
(1704, 6)获取列名和行索引
# df.columns (列名) print(df.columns) # df.index (行索引) print(df.index) print(list(df.index)[:10])
Index(['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap'], dtype='object') RangeIndex(start=0, stop=1704, step=1) [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]获取列子集
# 单列 continent = df.continent #只适合英文列名 continent = df['continent'] print(continent[:5]) # 多列 year_continent = df[['year','continent']] print(year_continent[:5])
0 Asia 1 Asia 2 Asia 3 Asia 4 Asia Name: continent, dtype: object year continent 0 1952 Asia 1 1957 Asia 2 1962 Asia 3 1967 Asia 4 1972 Asia获取行子集
- 通过行名(loc)
- 用过行号(iloc)
# 取一行 sample = df.loc[0] # 因为只取1行输出Series print(sample) # 取多行 samples = df.loc[[0,100,200]] print(samples) # df.loc[-1]会报错，因为没有-1这个标签的行 # 取一行 sample = df.iloc[0] # 因为只取1行输出Series # 取多行 samples = df.iloc[[0,100,200]] # iloc可以输入数值 sample = df.iloc[-1]
country Afghanistan
continent Asia
year 1952
lifeExp 28.801
pop 8425333
gdpPercap 779.445
Name: 0, dtype: object
country continent year lifeExp pop gdpPercap
0 Afghanistan Asia 1952 28.801 8425333 779.445314
100 Bangladesh Asia 1972 45.252 70759295 630.233627
200 Burkina Faso Africa 1992 50.260 8878303 931.752773
混合，抽取行列子集
iloc/loc[,] 逗号左边是行，右边是列
# 获取整列 subset = df.loc[:,['year','pop']] subset = df.iloc[:,[1,3,-1]] # 可以指定具体位置的列 subset = df.iloc[:,3:6] subset = df.iloc[:,:3] # 多行多列 subset = df.loc[[1,10,20],['year','pop']] subset = df.iloc[[1,10,20],[1,-1]] print(subset)
continent gdpPercap 1 Asia 820.853030 10 Asia 726.734055 20 Europe 2497.437901
