十分钟快速了解Pandas的常用操作！

#安装pandas
!pip install pandas

#安装numpy
!pip install numpy

#安装matplotlib
!pip install matoplotlib

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

s = pd.Series([1,3,5,np.nan,6,8])

s

0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

dates = pd.date_range('20130101', periods=6)

dates

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')

df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))

df

df2 = pd.DataFrame({ 'A' : 1.,
                     'B' : pd.Timestamp('20130102'),
                     'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
                     'D' : np.array([3] * 4,dtype='int32'),
                     'E' : pd.Categorical(["test","train","test","train"]),
                     'F' : 'foo' })

df2

df2.dtypes

A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object

dir(df2)

['A',
 'B',
 'C',
 'D',
 'E',
 'F',
 'T',
 '_AXIS_ALIASES',
 '_AXIS_IALIASES',
 '_AXIS_LEN',
 '_AXIS_NAMES',
 '_AXIS_NUMBERS',
 '_AXIS_ORDERS',
 '_AXIS_REVERSED',
······
 'unstack',
 'update',
 'values',
 'var',
 'where',
 'xs']

df.head()

df.tail(3)

df.index

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')

df.columns

Index(['A', 'B', 'C', 'D'], dtype='object')

df.values

array([[-0.46936354, -1.38929068,  0.84403157,  0.04286594],
       [ 0.98657633, -0.68954348, -0.38326456, -1.10493201],
       [-0.19242554,  1.74076522,  0.73047859, -1.32078058],
       [ 0.04734752, -1.95230265, -0.6915437 , -1.40388308],
       [ 0.23302102,  0.61911183,  0.628579  , -0.80258543],
       [ 0.49394583,  0.84824737,  1.633055  , -0.74056229]])

df.describe()

df.T

df.sort_index(axis=1, ascending=False)

df.sort_values(by='B')

df['A']

2013-01-01   -0.469364
2013-01-02    0.986576
2013-01-03   -0.192426
2013-01-04    0.047348
2013-01-05    0.233021
2013-01-06    0.493946
Freq: D, Name: A, dtype: float64

df[0:3]

df['20130102':'20130104']

df.loc[dates[0]]

A   -0.469364
B   -1.389291
C    0.844032
D    0.042866
Name: 2013-01-01 00:00:00, dtype: float64

df.loc[:,['A','B']]

df.loc['20130102':'20130104',['A','B']]

df.loc['20130102',['A','B']]

A    0.986576
B   -0.689543
Name: 2013-01-02 00:00:00, dtype: float64

df.loc[dates[0],'A']

-0.46936353804430075

df.at[dates[0],'A']

-0.46936353804430075

df.iloc[3]

A    0.047348
B   -1.952303
C   -0.691544
D   -1.403883
Name: 2013-01-04 00:00:00, dtype: float64

df.iloc[3:5, 0:2]

df.iloc[[1,2,4],[0,2]]

df.iloc[1:3]

df.iloc[:, 1:3]

df.iloc[1, 1]

-0.689543482094678

df.iat[1, 1]

-0.689543482094678

df[df.A>0]

df[df>0]

df2 = df.copy()

df2['E'] = ['one', 'one','two','three','four','three']

df2

df2[df2['E'].isin(['two','four'])]

s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))

s1

2013-01-02    1
2013-01-03    2
2013-01-04    3
2013-01-05    4
2013-01-06    5
2013-01-07    6
Freq: D, dtype: int64

df['F'] = s1

df.at[dates[0], 'A'] = 0

df.iat[0, 1] = 0

df.loc[:, 'D'] = np.array([5] * len(df)) 

df

df2 = df.copy()

df2[df2 > 0] = -df2

df2

df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])

df1.loc[dates[0]:dates[1],'E'] = 1

df1

df1.dropna(how='any')

df1.fillna(value=5)

pd.isnull(df1)

df.mean()

A    0.261411
B    0.094380
C    0.460223
D    5.000000
F    3.000000
dtype: float64

df.mean(1)

2013-01-01    1.461008
2013-01-02    1.182754
2013-01-03    1.855764
2013-01-04    1.080700
2013-01-05    2.096142
2013-01-06    2.595050
Freq: D, dtype: float64

s = pd.Series([1,3,5,np.nan,6,8], index=dates).shift(2)

s

2013-01-01    NaN
2013-01-02    NaN
2013-01-03    1.0
2013-01-04    3.0
2013-01-05    5.0
2013-01-06    NaN
Freq: D, dtype: float64

df.sub(s, axis='index')

df.apply(np.cumsum)

df.apply(lambda x: x.max() - x.min())

A    1.179002
B    3.693068
C    2.324599
D    0.000000
F    4.000000
dtype: float64

s = pd.Series(np.random.randint(0, 7, size=10))

s

0    6
1    1
2    4
3    6
4    3
5    2
6    3
7    5
8    2
9    2
dtype: int64

s.value_counts()

2    3
6    2
3    2
5    1
4    1
1    1
dtype: int64

s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])

s.str.lower()

0       a
1       b
2       c
3    aaba
4    baca
5     NaN
6    caba
7     dog
8     cat
dtype: object

df = pd.DataFrame(np.random.randn(10, 4))

df

pieces = [df[:3], df[3:6], df[7:]]

pd.concat(pieces)

left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})

right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})

left

right

pd.merge(left, right, on='key')

df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])

df

s = df.iloc[3]

df.append(s, ignore_index=True)

df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar',
                          'foo', 'bar', 'foo', 'foo'],
                   'B' : ['one', 'one', 'two', 'three',
                           'two', 'two', 'one', 'three'],
                   'C' : np.random.randn(8),
                   'D' : np.random.randn(8)})

df

df.groupby('A').sum()

df.groupby(['A', 'B']).sum()

tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
                     'foo', 'foo', 'qux', 'qux'],
                   ['one', 'two', 'one', 'two',
                    'one', 'two', 'one', 'two']]))

index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])

df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])

df2 = df[:4]

df2

stacked = df2.stack()

stacked

first  second
bar    one     A   -0.625492
               B    2.471493
       two     A    0.934708
               B    1.595349
baz    one     A    0.686079
               B    0.279957
       two     A    0.039190
               B   -0.534317
dtype: float64

stacked.unstack()

stacked.unstack(1)

stacked.unstack(0)

df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3,
                   'B' : ['A', 'B', 'C'] * 4,
                   'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
                   'D' : np.random.randn(12),
                   'E' : np.random.randn(12)})

df

df.pivot_table(values='D', index=['A', 'B'], columns='C')

rng = pd.date_range('1/1/2012', periods=100, freq='S')

ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng)

ts.resample('5Min').sum()

2012-01-01    27339
Freq: 5T, dtype: int64

rng = pd.date_range('3/6/2012 00:00', periods=5, freq='D')

ts = pd.Series(np.random.randn(len(rng)), rng)

ts

2012-03-06   -0.118691
2012-03-07   -1.424038
2012-03-08    0.377441
2012-03-09   -1.116195
2012-03-10    1.180595
Freq: D, dtype: float64

ts_utc = ts.tz_localize('UTC')

ts_utc

2012-03-06 00:00:00+00:00   -0.118691
2012-03-07 00:00:00+00:00   -1.424038
2012-03-08 00:00:00+00:00    0.377441
2012-03-09 00:00:00+00:00   -1.116195
2012-03-10 00:00:00+00:00    1.180595
Freq: D, dtype: float64

ts_utc.tz_convert('US/Eastern')

2012-03-05 19:00:00-05:00   -0.118691
2012-03-06 19:00:00-05:00   -1.424038
2012-03-07 19:00:00-05:00    0.377441
2012-03-08 19:00:00-05:00   -1.116195
2012-03-09 19:00:00-05:00    1.180595
Freq: D, dtype: float64

rng = pd.date_range('1/1/2012', periods=5, freq='M')

ts = pd.Series(np.random.randn(len(rng)), index=rng)

ts

2012-01-31    1.138201
2012-02-29    0.677539
2012-03-31    0.272933
2012-04-30   -0.238112
2012-05-31   -1.122162
Freq: M, dtype: float64

ps = ts.to_period()

ps

2012-01    1.138201
2012-02    0.677539
2012-03    0.272933
2012-04   -0.238112
2012-05   -1.122162
Freq: M, dtype: float64

ps.to_timestamp()

2012-01-01    1.138201
2012-02-01    0.677539
2012-03-01    0.272933
2012-04-01   -0.238112
2012-05-01   -1.122162
Freq: MS, dtype: float64

prng = pd.period_range('1990Q1', '2000Q4', freq='Q-NOV')

ts = pd.Series(np.random.randn(len(prng)), prng)

ts.index = (prng.asfreq('M', 'e') + 1).asfreq('H', 's') + 9

ts.head()

1990-03-01 09:00   -1.555191
1990-06-01 09:00    1.535344
1990-09-01 09:00   -0.092187
1990-12-01 09:00    1.285081
1991-03-01 09:00    1.130063
Freq: H, dtype: float64

df = pd.DataFrame({"id":[1,2,3,4,5,6], "raw_grade":['a', 'b', 'b', 'a', 'a', 'e']})

df['grade'] = df['raw_grade'].astype("category")

df['grade']

0    a
1    b
2    b
3    a
4    a
5    e
Name: grade, dtype: category
Categories (3, object): [a, b, e]

df["grade"].cat.categories = ["very good", "good", "very bad"]

df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium", "good", "very good"])

df["grade"]

0    very good
1         good
2         good
3    very good
4    very good
5     very bad
Name: grade, dtype: category
Categories (5, object): [very bad, bad, medium, good, very good]

df.sort_values(by='grade')

df.groupby("grade").size()

grade
very bad     1
bad          0
medium       0
good         2
very good    3
dtype: int64

ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))

ts.head()

2000-01-01   -1.946554
2000-01-02   -0.354670
2000-01-03    0.361473
2000-01-04   -0.109408
2000-01-05    0.877671
Freq: D, dtype: float64

ts = ts.cumsum() #累加

ts.plot()

df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
                  columns=['A', 'B', 'C', 'D']) 

df = df.cumsum()

plt.figure(); df.plot(); plt.legend(loc='best')

df.to_csv('foo.csv')

pd.read_csv('foo.csv').head()

df.to_hdf('foo.h5','df')

pd.read_hdf('foo.h5','df').head()

df.to_excel('foo.xlsx', sheet_name='Sheet1')

pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA']).head()

>>> if pd.Series([False, T`mrue, False]):
...     print("I was true")
Traceback
    ...
ValueError: The truth value of an array is ambiguous. Use a.empty, a.any() or a.all().