Pandas 合并数据集merge 和 join的使用

import pandas as pd
import numpy as np

class display(object):
    """Display HTML representation of multiple objects"""
    template = """<div style="float: left; padding: 10px;">
    <p style='font-family:"Courier New", Courier, monospace'>{0}</p>{1}
    </div>"""
    def __init__(self, *args):
        self.args = args
        
    def _repr_html_(self):
        return '\n'.join(self.template.format(a, eval(a)._repr_html_())
                         for a in self.args)
    
    def __repr__(self):
        return '\n\n'.join(a + '\n' + repr(eval(a))
                           for a in self.args)

df1 = pd.DataFrame({'employee': ['Bob', 'Jake', 'Lisa', 'Sue'],
                    'group': ['Accounting', 'Engineering',
                              'Engineering', 'HR']})
df2 = pd.DataFrame({'employee': ['Lisa', 'Bob', 'Jake', 'Sue'],
                    'hire_date': [2004, 2008, 2012, 2014]})
display('df1', 'df2')

df3 = pd.merge(df1, df2)
df3

df4 = pd.DataFrame({'group': ['Accounting', 'Engineering', 'HR'],
                    'supervisor': ['Carly', 'Guido', 'Steve']})
display('df3', 'df4', 'pd.merge(df3, df4)')

df5 = pd.DataFrame({'group': ['Accounting', 'Accounting',
                              'Engineering', 'Engineering', 'HR', 'HR'],
                    'skills': ['math', 'spreadsheets', 'software', 'math',
                               'spreadsheets', 'organization']})
display('df1', 'df5', "pd.merge(df1, df5)")

display('df1', 'df2', "pd.merge(df1, df2, on='employee')")

df3 = pd.DataFrame({'name': ['Bob', 'Jake', 'Lisa', 'Sue'],
                    'salary': [70000, 80000, 120000, 90000]})
display('df1', 'df3', 'pd.merge(df1, df3, left_on="employee", right_on="name")')

pd.merge(df1, df3, left_on="employee", right_on="name").drop('name', axis=1)

df1a = df1.set_index('employee')
df2a = df2.set_index('employee')
display('df1a', 'df2a')

display('df1a', 'df2a',
        "pd.merge(df1a, df2a, left_index=True, right_index=True)")

df1a.join(df2a)

display('df1a', 'df3', "pd.merge(df1a, df3, left_index=True, right_on='name')")

df6 = pd.DataFrame({'name': ['Peter', 'Paul', 'Mary'],
                    'food': ['fish', 'beans', 'bread']},
                   columns=['name', 'food'])
df7 = pd.DataFrame({'name': ['Mary', 'Joseph'],
                    'drink': ['wine', 'beer']},
                   columns=['name', 'drink'])
display('df6', 'df7', 'pd.merge(df6, df7)')

pd.merge(df6, df7, how='inner')

display('df6', 'df7', "pd.merge(df6, df7, how='outer')")

display('df6', 'df7', "pd.merge(df6, df7, how='left')")

pd.merge(df8, df9, on="name", suffixes=["_L", "_R"])

# Following are commands to download the data
# repo = "https://raw.githubusercontent.com/jakevdp/data-USstates/master"
# !cd data && curl -O {repo}/state-population.csv
# !cd data && curl -O {repo}/state-areas.csv
# !cd data && curl -O {repo}/state-abbrevs.csv

pop = pd.read_csv('data/state-population.csv')
areas = pd.read_csv('data/state-areas.csv')
abbrevs = pd.read_csv('data/state-abbrevs.csv')

display('pop.head()', 'areas.head()', 'abbrevs.head()')

merged = pd.merge(pop, abbrevs, how='outer',
                  left_on='state/region', right_on='abbreviation')
merged = merged.drop('abbreviation', axis=1) # drop duplicate info
merged.head()

merged.isnull().any()

state/region    False
ages            False
year            False
population       True
state            True
dtype: bool

merged[merged['population'].isnull()].head()

merged.loc[merged['state'].isnull(), 'state/region'].unique()

array(['PR', 'USA'], dtype=object)

merged.loc[merged['state/region'] == 'PR', 'state'] = 'Puerto Rico'
merged.loc[merged['state/region'] == 'USA', 'state'] = 'United States'
merged.isnull().any()

state/region    False
ages            False
year            False
population       True
state           False
dtype: bool

final = pd.merge(merged, areas, on='state', how='left')
final.head()

final['state'][final['area (sq. mi)'].isnull()].unique()

array(['United States'], dtype=object)

final.dropna(inplace=True)
final.head()

data2010 = final.query("year == 2010 & ages == 'total'")
data2010.head()

data2010.set_index('state', inplace=True)
density = data2010['population'] / data2010['area (sq. mi)']

density.sort_values(ascending=False, inplace=True)
density.head()

state
District of Columbia    8898.897059
Puerto Rico             1058.665149
New Jersey              1009.253268
Rhode Island             681.339159
Connecticut              645.600649
dtype: float64

density.tail()

state
South Dakota    10.583512
North Dakota     9.537565
Montana          6.736171
Wyoming          5.768079
Alaska           1.087509
dtype: float64