数据分析案例

abb = pd.read_csv(‘./data/state-abbrevs.csv‘)
pop = pd.read_csv(‘./data/state-population.csv‘)
area = pd.read_csv(‘./data/state-areas.csv‘)

#将人口数据和各州简称数据进行合并
display(abb.head(1),pop.head(1))
abb_pop = pd.merge(abb,pop,left_on=‘abbreviation‘,right_on=‘state/region‘,how=‘outer‘)
abb_pop.head()

#将合并的数据中重复的abbreviation列进行删除
abb_pop.drop(labels=‘abbreviation‘,axis=1,inplace=True)
abb_pop.head()

state    state/region    ages    year    population
0    Alabama    AL    under18    2012    1117489.0
1    Alabama    AL    total    2012    4817528.0
2    Alabama    AL    under18    2010    1130966.0
3    Alabama    AL    total    2010    4785570.0
4    Alabama    AL    under18    2011    1125763.0

#查看存在缺失数据的列
abb_pop.isnull().any(axis=0)

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

#找到有哪些state/region使得state的值为NaN，进行去重操作
#1.检测state列中的空值
abb_pop[‘state‘].isnull()
#2.将1的返回值作用的state_region这一列中
abb_pop[‘state/region‘][abb_pop[‘state‘].isnull()]
#3.去重
abb_pop[‘state/region‘][abb_pop[‘state‘].isnull()].unique()

#为找到的这些state/region的state项补上正确的值，从而去除掉state这一列的所有NaN
abb_pop[‘state/region‘] == ‘USA‘
# 将控制覆盖成United State
abb_pop.loc[indexs,‘state‘] = ‘United State‘
pr_index = abb_pop[‘state‘][abb_pop[‘state/region‘] == ‘PR‘].index
abb_pop.loc[pr_index,‘state‘] = ‘PPPRRR‘

#合并各州面积数据areas 我们会发现area(sq.mi)这一列有缺失数据，找出是哪些行 去除含有缺失数据的行 找出2010年的全民人口数据 计算各州的人口密度 排序，并找出人口密度最高的五个州 df.sort_values()

#合并各州面积数据areas
abb_pop_area = pd.merge(abb_pop,area,how=‘outer‘)
abb_pop_area.head()

    state    state/region    ages    year    population    area (sq. mi)
0    Alabama    AL    under18    2012.0    1117489.0    52423.0
1    Alabama    AL    total    2012.0    4817528.0    52423.0
2    Alabama    AL    under18    2010.0    1130966.0    52423.0
3    Alabama    AL    total    2010.0    4785570.0    52423.0
4    Alabama    AL    under18    2011.0    1125763.0    52423.0

#我们会发现area(sq.mi)这一列有缺失数据，找出是哪些行
abb_pop_area[‘area (sq. mi)‘].isnull()
a_index = abb_pop_area.loc[abb_pop_area[‘area (sq. mi)‘].isnull()].index

#去除含有缺失数据的行
abb_pop_area.drop(labels=a_index,axis=0,inplace=True)

#找出2010年的全民人口数据
abb_pop_area.query(‘year == 2010 & ages == "total"‘)

    state    state/region    ages    year    population    area (sq. mi)
3    Alabama    AL    total    2010.0    4785570.0    52423.0
91    Alaska    AK    total    2010.0    713868.0    656425.0
101    Arizona    AZ    total    2010.0    6408790.0    114006.0
189    Arkansas    AR    total    2010.0    2922280.0    53182.0
197    California    CA    total    2010.0    37333601.0    163707.0
283    Colorado    CO    total    2010.0    5048196.0    104100.0
293    Connecticut    CT    total    2010.0    3579210.0    5544.0
379    Delaware    DE    total    2010.0    899711.0    1954.0
389    District of Columbia    DC    total    2010.0    605125.0    68.0
475    Florida    FL    total    2010.0    18846054.0    65758.0
485    Georgia    GA    total    2010.0    9713248.0    59441.0
570    Hawaii    HI    total    2010.0    1363731.0    10932.0


#计算各州的人口密度
abb_pop_area[‘midu‘] = abb_pop_area[‘population‘] / abb_pop_area[‘area (sq. mi)‘]
abb_pop_area.head()

state    state/region    ages    year    population    area (sq. mi)    midu
0    Alabama    AL    under18    2012.0    1117489.0    52423.0    21.316769
1    Alabama    AL    total    2012.0    4817528.0    52423.0    91.897221
2    Alabama    AL    under18    2010.0    1130966.0    52423.0    21.573851
3    Alabama    AL    total    2010.0    4785570.0    52423.0    91.287603
4    Alabama    AL    under18    2011.0    1125763.0    52423.0    21.474601

#排序，并找出人口密度最高的五个州 df.sort_values()
abb_pop_area.sort_values(by=‘midu‘,axis=0,ascending=False).head()

state    state/region    ages    year    population    area (sq. mi)    midu
391    District of Columbia    DC    total    2013.0    646449.0    68.0    9506.602941
385    District of Columbia    DC    total    2012.0    633427.0    68.0    9315.102941
387    District of Columbia    DC    total    2011.0    619624.0    68.0    9112.117647
431    District of Columbia    DC    total    1990.0    605321.0    68.0    8901.779412
389    District of Columbia    DC    total    2010.0    605125.0    68.0    8898.897059