利用Python进行数据分析-----pandas

利用Python进行数据分析-----pandas

pandas基础

pandas的数据结构介绍

obj2 = pd.Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])
obj2
obj2.index

sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}
obj3 = pd.Series(sdata)
obj3

data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002, 2003],
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
frame = pd.DataFrame(data)

pd.DataFrame(data, columns=['year', 'state', 'pop'])

pop = {'Nevada': {2001: 2.4, 2002: 2.9},
       'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}

frame3.index.name = 'year'; frame3.columns.name = 'state'
frame3

obj = pd.Series(range(3), index=['a', 'b', 'c'])
index = obj.index
index
index[1:]

基本功能

obj2 = obj.reindex(['a', 'b', 'c', 'd', 'e'])
obj2

obj3 = pd.Series(['blue', 'purple', 'yellow'], index=[0, 2, 4])
obj3
obj3.reindex(range(6), method='ffill')

0 blue
1 blue
2 purple
3 purple
4 yellow
5 yellow
dtype: object

frame = pd.DataFrame(np.arange(9).reshape((3, 3)),
                     index=['a', 'c', 'd'],
                     columns=['Ohio', 'Texas', 'California'])
frame
frame2 = frame.reindex(['a', 'b', 'c', 'd'])
frame2

obj = pd.Series(np.arange(5.), index=['a', 'b', 'c', 'd', 'e'])
obj
new_obj = obj.drop('c')
new_obj
obj.drop(['d', 'c'])

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                    index=['Ohio', 'Colorado', 'Utah', 'New York'],
                    columns=['one', 'two', 'three', 'four'])
data

df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)),
                   columns=list('abcd'))
df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)),
                   columns=list('abcde'))
df2.loc[1, 'b'] = np.nan
df1
df2

frame = pd.DataFrame(np.arange(12.).reshape((4, 3)),
                     columns=list('bde'),
                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])
series = frame.iloc[0]
frame
series

series2 = pd.Series(range(3), index=['b', 'e', 'f'])
frame + series2

series3 = frame['d']
frame
series3
frame.sub(series3, axis='index')

frame = pd.DataFrame(np.random.randn(4, 3), columns=list('bde'),
                     index=['Utah', 'Ohio', 'Texas', 'Oregon'])
frame
np.abs(frame)

obj = pd.Series(range(4), index=['d', 'a', 'b', 'c'])
obj.sort_index()

frame = pd.DataFrame(np.arange(8).reshape((2, 4)),
                     index=['three', 'one'],
                     columns=['d', 'a', 'b', 'c'])
frame.sort_index()
frame.sort_index(axis=1)

obj = pd.Series([4, np.nan, 7, np.nan, -3, 2])
obj.sort_values()

frame = pd.DataFrame({'b': [4, 7, -3, 2], 'a': [0, 1, 0, 1]})
frame
frame.sort_values(by='b')

frame = pd.DataFrame({'b': [4.3, 7, -3, 2], 'a': [0, 1, 0, 1],
                      'c': [-2, 5, 8, -2.5]})
frame
frame.rank(axis='columns')

汇总和计算描述统计

df = pd.DataFrame([[1.4, np.nan], [7.1, -4.5],
                   [np.nan, np.nan], [0.75, -1.3]],
                  index=['a', 'b', 'c', 'd'],
                  columns=['one', 'two'])
df

import pandas_datareader.data as web all_data = {ticker: web.get_data_yahoo(ticker) for ticker in ['AAPL', 'IBM', 'MSFT', 'GOOG']}

price = pd.DataFrame({ticker: data['Adj Close'] for ticker, data in all_data.items()}) volume = pd.DataFrame({ticker: data['Volume'] for ticker, data in all_data.items()})

price = pd.read_pickle('examples/yahoo_price.pkl')
volume = pd.read_pickle('examples/yahoo_volume.pkl')

pandas进阶

分类数据

GroupBy高级应用

链式编程技术