pandas1:pandas基础

一时失言乱红尘 2023-02-26 11:28 25阅读 0赞

# DataFrame的基本元素 #

pandas是一个可以处理文本，二维表的独立第三方库

官网：[https://pandas.pydata.org/][https_pandas.pydata.org]

import pandas
    
    df = pandas.read_csv('./data/gapminder.tsv',sep='\t')

## 获取前n行 ##

print(df.head()) #默认显示5行
    print(df.head(6))

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
           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
    5  Afghanistan      Asia  1977   38.438  14880372  786.113360

# head类型也是DataFrame

## 获取二维表维度 ##

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

(1704, 6)
    1704
    6

## 获取列名 ##

print(df.columns)
    for col in df.columns:
        print(col)

Index(['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap'], dtype='object')
    country
    continent
    year
    lifeExp
    pop
    gdpPercap

## 每个列的类型 ##

print(df.dtypes)
    for type in df.dtypes:
        print(type)

country       object
    continent     object
    year           int64
    lifeExp      float64
    pop            int64
    gdpPercap    float64
    dtype: object
    object
    object
    int64
    float64
    int64
    float64

for item in zip(df.columns,df.dtypes):
        print(item)

('country', dtype('O'))
    ('continent', dtype('O'))
    ('year', dtype('int64'))
    ('lifeExp', dtype('float64'))
    ('pop', dtype('int64'))
    ('gdpPercap', dtype('float64'))

columnTypes = dict(zip(df.columns,df.dtypes))
    print(columnTypes.get('country'))
    print(columnTypes.get('pop'))

object
    int64

## data frame结构描述 ##

print(df.info)

## pandas与python数据类型对应关系 ##

‘’’

object string

int64 int

float64 float

datetim364 datetime  
‘’’

# 2.获取DataFrame数据 #

import pandas
    df = pandas.read_csv('./data/gapminder.tsv',sep='\t')
    print(df.columns)

Index(['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap'], dtype='object')

## 2.1获取列 ##

country_df = df['country']
    print(type(country_df))
    print(country_df)

<class 'pandas.core.series.Series'>
    0       Afghanistan
    1       Afghanistan
    2       Afghanistan
    3       Afghanistan
    4       Afghanistan
               ...     
    1699       Zimbabwe
    1700       Zimbabwe
    1701       Zimbabwe
    1702       Zimbabwe
    1703       Zimbabwe
    Name: country, Length: 1704, dtype: object

print(country_df.head())
    print(country_df.tail(6))

0    Afghanistan
    1    Afghanistan
    2    Afghanistan
    3    Afghanistan
    4    Afghanistan
    Name: country, dtype: object
    1698    Zimbabwe
    1699    Zimbabwe
    1700    Zimbabwe
    1701    Zimbabwe
    1702    Zimbabwe
    1703    Zimbabwe
    Name: country, dtype: object

## 获取多个列数据 ##

subset = df[['country','continent']]
    print(subset.head(6))

country continent
    0  Afghanistan      Asia
    1  Afghanistan      Asia
    2  Afghanistan      Asia
    3  Afghanistan      Asia
    4  Afghanistan      Asia
    5  Afghanistan      Asia

## 2.2获取行数据 ##

### loc iloc ###

print(df.loc[0])
    print(type(df.loc[15])) 
    #print(type(df.loc[-1])) #error 不能为负数

country      Afghanistan
    continent           Asia
    year                1952
    lifeExp           28.801
    pop              8425333
    gdpPercap        779.445
    Name: 0, dtype: object
    <class 'pandas.core.series.Series'>

numer_of_rows = df.shape[0]
    print(df.loc[numer_of_rows-1])

country      Zimbabwe
    continent      Africa
    year             2007
    lifeExp        43.487
    pop          12311143
    gdpPercap     469.709
    Name: 1703, dtype: object

print(type(df.loc[0]))
    print(type(df.head()))

print(df.loc[[1,2]])
    print(type(df.loc[[1,2]]))

country continent  year  lifeExp       pop  gdpPercap
    1  Afghanistan      Asia  1957   30.332   9240934  820.85303
    2  Afghanistan      Asia  1962   31.997  10267083  853.10071
    <class 'pandas.core.frame.DataFrame'>

### iloc可以用负数 ###

print(df.iloc[-1])

country      Zimbabwe
    continent      Africa
    year             2007
    lifeExp        43.487
    pop          12311143
    gdpPercap     469.709
    Name: 1703, dtype: object

## 2.3获取单元格数据 ##

subset = df.loc[:,['year','pop']]
    print(type(subset))
    print(subset.head())

<class 'pandas.core.frame.DataFrame'>
       year       pop
    0  1952   8425333
    1  1957   9240934
    2  1962  10267083
    3  1967  11537966
    4  1972  13079460

subset = df.iloc[:,[2,4,-1]]
    print(type(subset))
    print(subset.head())

<class 'pandas.core.frame.DataFrame'>
       year       pop   gdpPercap
    0  1952   8425333  779.445314
    1  1957   9240934  820.853030
    2  1962  10267083  853.100710
    3  1967  11537966  836.197138
    4  1972  13079460  739.981106

## 2.4分片 ##

subset = df.iloc[:,3:6]
    print(subset.head())

lifeExp       pop   gdpPercap
    0   28.801   8425333  779.445314
    1   30.332   9240934  820.853030
    2   31.997  10267083  853.100710
    3   34.020  11537966  836.197138
    4   36.088  13079460  739.981106

subset = df.iloc[0:3,:]
    print(subset.head())

subset = df.loc[1,'lifeExp']
    print(subset)

30.331999999999997

## 2.5分组统计 ##

import pandas
    df = pandas.read_csv('./data/gapminder.tsv',sep='\t')
    print(df.columns)

Index(['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap'], dtype='object')

print(df.groupby('year')['lifeExp'].mean())

year
    1952    49.057620
    1957    51.507401
    1962    53.609249
    1967    55.678290
    1972    57.647386
    1977    59.570157
    1982    61.533197
    1987    63.212613
    1992    64.160338
    1997    65.014676
    2002    65.694923
    2007    67.007423
    Name: lifeExp, dtype: float64

print(df.groupby('year'))
    print(df.groupby('year')['lifeExp'])

<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7ff46dbd5890>
    <pandas.core.groupby.generic.SeriesGroupBy object at 0x7ff46dbd58d0>

## 2.6多组统计 ##

multi_group_var = df.groupby(['year','continent'])[['lifeExp','gdpPercap']].mean()

print(type(multi_group_var))
    print(multi_group_var)

<class 'pandas.core.frame.DataFrame'>
                      lifeExp     gdpPercap
    year continent                         
    1952 Africa     39.135500   1252.572466
         Americas   53.279840   4079.062552
         Asia       46.314394   5195.484004
         Europe     64.408500   5661.057435
         Oceania    69.255000  10298.085650
    1957 Africa     41.266346   1385.236062
         Americas   55.960280   4616.043733
         Asia       49.318544   5787.732940
         Europe     66.703067   6963.012816
         Oceania    70.295000  11598.522455
    1962 Africa     43.319442   1598.078825
         Americas   58.398760   4901.541870
         Asia       51.563223   5729.369625
         Europe     68.539233   8365.486814
         Oceania    71.085000  12696.452430
    1967 Africa     45.334538   2050.363801
         Americas   60.410920   5668.253496
         Asia       54.663640   5971.173374
         Europe     69.737600  10143.823757
         Oceania    71.310000  14495.021790
    1972 Africa     47.450942   2339.615674
         Americas   62.394920   6491.334139
         Asia       57.319269   8187.468699
         Europe     70.775033  12479.575246
         Oceania    71.910000  16417.333380
    1977 Africa     49.580423   2585.938508
         Americas   64.391560   7352.007126
         Asia       59.610556   7791.314020
         Europe     71.937767  14283.979110
         Oceania    72.855000  17283.957605
    1982 Africa     51.592865   2481.592960
         Americas   66.228840   7506.737088
         Asia       62.617939   7434.135157
         Europe     72.806400  15617.896551
         Oceania    74.290000  18554.709840
    1987 Africa     53.344788   2282.668991
         Americas   68.090720   7793.400261
         Asia       64.851182   7608.226508
         Europe     73.642167  17214.310727
         Oceania    75.320000  20448.040160
    1992 Africa     53.629577   2281.810333
         Americas   69.568360   8044.934406
         Asia       66.537212   8639.690248
         Europe     74.440100  17061.568084
         Oceania    76.945000  20894.045885
    1997 Africa     53.598269   2378.759555
         Americas   71.150480   8889.300863
         Asia       68.020515   9834.093295
         Europe     75.505167  19076.781802
         Oceania    78.190000  24024.175170
    2002 Africa     53.325231   2599.385159
         Americas   72.422040   9287.677107
         Asia       69.233879  10174.090397
         Europe     76.700600  21711.732422
         Oceania    79.740000  26938.778040
    2007 Africa     54.806038   3089.032605
         Americas   73.608120  11003.031625
         Asia       70.728485  12473.026870
         Europe     77.648600  25054.481636
         Oceania    80.719500  29810.188275

print(multi_group_var.reset_index())

year continent    lifeExp     gdpPercap
    0   1952    Africa  39.135500   1252.572466
    1   1952  Americas  53.279840   4079.062552
    2   1952      Asia  46.314394   5195.484004
    3   1952    Europe  64.408500   5661.057435
    4   1952   Oceania  69.255000  10298.085650
    5   1957    Africa  41.266346   1385.236062
    6   1957  Americas  55.960280   4616.043733
    7   1957      Asia  49.318544   5787.732940
    8   1957    Europe  66.703067   6963.012816
    9   1957   Oceania  70.295000  11598.522455
    10  1962    Africa  43.319442   1598.078825
    11  1962  Americas  58.398760   4901.541870
    12  1962      Asia  51.563223   5729.369625
    13  1962    Europe  68.539233   8365.486814
    14  1962   Oceania  71.085000  12696.452430
    15  1967    Africa  45.334538   2050.363801
    16  1967  Americas  60.410920   5668.253496
    17  1967      Asia  54.663640   5971.173374
    18  1967    Europe  69.737600  10143.823757
    19  1967   Oceania  71.310000  14495.021790
    20  1972    Africa  47.450942   2339.615674
    21  1972  Americas  62.394920   6491.334139
    22  1972      Asia  57.319269   8187.468699
    23  1972    Europe  70.775033  12479.575246
    24  1972   Oceania  71.910000  16417.333380
    25  1977    Africa  49.580423   2585.938508
    26  1977  Americas  64.391560   7352.007126
    27  1977      Asia  59.610556   7791.314020
    28  1977    Europe  71.937767  14283.979110
    29  1977   Oceania  72.855000  17283.957605
    30  1982    Africa  51.592865   2481.592960
    31  1982  Americas  66.228840   7506.737088
    32  1982      Asia  62.617939   7434.135157
    33  1982    Europe  72.806400  15617.896551
    34  1982   Oceania  74.290000  18554.709840
    35  1987    Africa  53.344788   2282.668991
    36  1987  Americas  68.090720   7793.400261
    37  1987      Asia  64.851182   7608.226508
    38  1987    Europe  73.642167  17214.310727
    39  1987   Oceania  75.320000  20448.040160
    40  1992    Africa  53.629577   2281.810333
    41  1992  Americas  69.568360   8044.934406
    42  1992      Asia  66.537212   8639.690248
    43  1992    Europe  74.440100  17061.568084
    44  1992   Oceania  76.945000  20894.045885
    45  1997    Africa  53.598269   2378.759555
    46  1997  Americas  71.150480   8889.300863
    47  1997      Asia  68.020515   9834.093295
    48  1997    Europe  75.505167  19076.781802
    49  1997   Oceania  78.190000  24024.175170
    50  2002    Africa  53.325231   2599.385159
    51  2002  Americas  72.422040   9287.677107
    52  2002      Asia  69.233879  10174.090397
    53  2002    Europe  76.700600  21711.732422
    54  2002   Oceania  79.740000  26938.778040
    55  2007    Africa  54.806038   3089.032605
    56  2007  Americas  73.608120  11003.031625
    57  2007      Asia  70.728485  12473.026870
    58  2007    Europe  77.648600  25054.481636
    59  2007   Oceania  80.719500  29810.188275

## 2.7统计数量 ##

print(df.groupby('continent')['country'].nunique())

continent
    Africa      52
    Americas    25
    Asia        33
    Europe      30
    Oceania      2
    Name: country, dtype: int64

print(df.groupby('continent')['year'].nunique())

continent
    Africa      12
    Americas    12
    Asia        12
    Europe      12
    Oceania     12
    Name: year, dtype: int64

## 2.8可视化统计数据 ##

import pandas
    import matplotlib.pyplot as plt
    df = pandas.read_csv('./data/gapminder.tsv',sep='\t')
    print(df.columns)

Index(['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap'], dtype='object')

global_yearly_life_expectancy = df.groupby('year')['lifeExp'].mean()

print(global_yearly_life_expectancy)

global_yearly_life_expectancy.plot()
    plt.show()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70]

multi_group_var = df.groupby('year')['gdpPercap'].mean()
    multi_group_var.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7ff46de9fed0>

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70 1]

#NumPy、Pandas、Matplot
    
    fig,(ax1,ax2) = plt.subplots(1,2,figsize=(8,4))
    ax1.plot(global_yearly_life_expectancy)
    ax2.plot(multi_group_var)
    plt.show()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70 2]

[https_pandas.pydata.org]: https://pandas.pydata.org/
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70]: /images/20230209/ffc0de6dacc142b0b66d0d2355ea7bf4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70 1]: /images/20230209/40a0fc359dd143a2b1ace46f3bec8583.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x1dGVyZXNh_size_16_color_FFFFFF_t_70 2]: /images/20230209/dc9d9e6c7d5b443e82d05b58ac95614b.png