Black [O] life Matter: Race, Crime, dan Fire to Kill di Amerika Serikat. Bagian 2

Di bagian pertama artikel, saya menjelaskan latar belakang studi, tujuan, asumsi, masukan, dan alatnya. Sekarang Anda dapat mengatakan Gagarin tanpa basa-basi ...

Pergilah!

Kami mengimpor perpustakaan dan menentukan jalur ke direktori dengan semua file:

import pandas as pd, numpy as np

#      
ROOT_FOLDER = r'c:\_PROG_\Projects\us_crimes'

Kematian di tangan hukum

Mari kita mulai dengan menganalisis data korban polisi. Mari unggah file dari CSV ke DataFrame:

#    Fatal Encounters (FENC)
FENC_FILE = ROOT_FOLDER + '\\fatal_enc_db.csv'

#   DataFrame
df_fenc = pd.read_csv(FENC_FILE, sep=';', header=0, usecols=["Date (Year)", "Subject's race with imputations", "Cause of death", "Intentional Use of Force (Developing)", "Location of death (state)"])

, , : , ( ), ( , ), , .

, " " . , , FENC , , . , ( ). Fatal Encounters Excel ( ).

:

df_fenc.columns = ['Race', 'State', 'Cause', 'UOF', 'Year']
df_fenc.dropna(inplace=True)

, . . FENC, , (Hispanic/Latino), (Asian/Pacific Islander) (Middle Eastern). . :

df_fenc = df_fenc.replace({'Race': {'European-American/White': 'White', 'African-American/Black': 'Black', 
                          'Hispanic/Latino': 'White', 'Native American/Alaskan': 'American Indian',
                          'Asian/Pacific Islander': 'Asian', 'Middle Eastern': 'Asian',
                          'NA': 'Unknown', 'Race unspecified': 'Unknown'}}, value=None)

( ) :

df_fenc = df_fenc.loc[df_fenc['Race'].isin(['White', 'Black'])]

"UOF" ( )? , ( ) . , (, ) , . : 1) - (: , ; : ); 2) ; , , ( ) , . , :

df_fenc = df_fenc.loc[df_fenc['UOF'].isin(['Deadly force', 'Intentional use of force'])]

. CSV, :

df_state_names = pd.read_csv(ROOT_FOLDER + '\\us_states.csv', sep=';', header=0)
df_fenc = df_fenc.merge(df_state_names, how='inner', left_on='State', right_on='state_abbr')

df_fenc.head(), :

, :

#     
ds_fenc_agg = df_fenc.groupby(['Year', 'Race']).count()['Cause']
df_fenc_agg = ds_fenc_agg.unstack(level=1)
#     UINT16  
df_fenc_agg = df_fenc_agg.astype('uint16')

2 : White ( ) Black ( ), ( 2000 2020). :

#        (- )
plt = df_fenc_agg.plot(xticks=df_fenc_agg.index, color=['olive', 'g'])
plt.set_xticklabels(df_fenc_agg.index, rotation='vertical')
plt.set_xlabel('')
plt.set_ylabel('-    ')
plt

:

() , .

2.4 . , . , .

( ):

#  CSV     (1991 - 2018)
POP_FILE = ROOT_FOLDER + '\\us_pop_1991-2018.csv'
df_pop = pd.read_csv(POP_FILE, index_col=0, dtype='int64')

:

#     -     2000 - 2018 .
df_pop = df_pop.loc[2000:2018, ['White_pop', 'Black_pop']]

#  ,    
df_fenc_agg = df_fenc_agg.join(df_pop)
df_fenc_agg.dropna(inplace=True)

#       
df_fenc_agg = df_fenc_agg.astype({'White_pop': 'uint32', 'Black_pop': 'uint32'})

. 2 , ( 1 . ):

df_fenc_agg['White_promln'] = df_fenc_agg['White'] * 1e6 / df_fenc_agg['White_pop']
df_fenc_agg['Black_promln'] = df_fenc_agg['Black'] * 1e6 / df_fenc_agg['Black_pop']

, :

2 - . :

plt = df_fenc_agg.loc[:, ['White_promln', 'Black_promln']].plot(xticks=df_fenc_agg.index, color=['g', 'olive'])
plt.set_xticklabels(df_fenc_agg.index, rotation='vertical')
plt.set_xlabel('')
plt.set_ylabel('-    \n 1   ')
plt

:

df_fenc_agg.loc[:, ['White_promln', 'Black_promln']].describe()

:

1. 5.9 1 . 2.3 1 . ( 2.6 ).

2. () 1.8 , . ( , , .)

3. - 2013 . (7.7 ); - 2018 . (3.3 ).

4. ( 0.1 - 0.2 ), 2009 . 2011 - 2013 .

, :

- , , ?

- , . 2.6 , .

, - , , .

CSV :

CRIMES_FILE = ROOT_FOLDER + '\\culprits_victims.csv'
df_crimes = pd.read_csv(CRIMES_FILE, sep=';', header=0, index_col=0, usecols=['Year', 'Offense', 'Offender/Victim', 'White', 'White pro capita', 'Black', 'Black pro capita'])

- : , , , ( - "White", "Black" - "White pro capita", "Black pro capita").

(`df_crimes.head()`):

. :

#    ( )
df_crimes1 = df_crimes.loc[df_crimes['Offender/Victim'] == 'Offender']
#    (2000-2018)    
df_crimes1 = df_crimes1.loc[2000:2018, ['Offense', 'White', 'White pro capita', 'Black', 'Black pro capita']]

(1295 * 5 ):

1 1 ( ). :

df_crimes1['White_promln'] = df_crimes1['White pro capita'] * 1e6
df_crimes1['Black_promln'] = df_crimes1['Black pro capita'] * 1e6

, ( ), :

df_crimes_agg = df_crimes1.groupby(['Offense']).sum().loc[:, ['White', 'Black']]

:

plt = df_crimes_agg.plot.barh(color=['g', 'olive'])
plt.set_ylabel(' ')
plt.set_xlabel('-   ( 2000 - 2018 )')

, , :

• , , " " , ,

• , ( 2 " ")

, "" . , :

df_crimes_agg1 = df_crimes1.groupby(['Offense']).sum().loc[:, ['White_promln', 'Black_promln']]

:

plt = df_crimes_agg1.plot.barh(color=['g', 'olive'])
plt.set_ylabel(' ')
plt.set_xlabel('-    1    ( 2000 - 2018 )')

. ( ) , . " " 3 .

" " (All Offenses) , ( ) ( - , ).

#   'All Offenses' =  
df_crimes1 = df_crimes1.loc[df_crimes1['Offense'] == 'All Offenses']
#    , , ,    :
#df_crimes1 = df_crimes1.loc[df_crimes1['Offense'].str.contains('Assault|Murder')]

#       
df_crimes1 = df_crimes1.groupby(level=0).sum().loc[:, ['White_promln', 'Black_promln']]

:

:

plt = df_crimes1.plot(xticks=df_crimes1.index, color=['g', 'olive'])
plt.set_xticklabels(df_fenc_agg.index, rotation='vertical')
plt.set_xlabel('')
plt.set_ylabel('-  \n 1   ')
plt

:

1. 2 , , , 3 ( ).

2. ( 2 18 ). , : 2001 2006 . , 2007 2016 , 2017 . 2 ( ).

3. 2007-2016 ., , .

, :

- ?

- 3 .

: , " , ?"

- - .

, :

#  
df_uof_crimes = df_fenc_agg.join(df_crimes1, lsuffix='_uof', rsuffix='_cr')
#    (.   )
df_uof_crimes = df_uof_crimes.loc[:, 'White_pop':'Black_promln_cr']

?

, :

1. White_pop -

2. Black_pop -

3. White promln_uof - ( 1 )

4. Black promln_uof - ( 1 )

5. White promln_cr - , ( 1 )

6. Black promln_cr - , ( 1 )

, ... , :)

, . - :)

plt = df_uof_crimes['White_promln_cr'].plot(xticks=df_uof_crimes.index, legend=True)
plt.set_ylabel('-     1  .')
plt2 = df_uof_crimes['White_promln_uof'].plot(xticks=df_uof_crimes.index, legend=True, secondary_y=True, style='g')
plt2.set_ylabel('-     1  .', rotation=90)
plt2.set_xlabel('')
plt.set_xlabel('')
plt.set_xticklabels(df_uof_crimes.index, rotation='vertical')
plt

:

, . , :

plt = df_uof_crimes['Black_promln_cr'].plot(xticks=df_uof_crimes.index, legend=True)
plt.set_ylabel('-     1  .')
plt2 = df_uof_crimes['Black_promln_uof'].plot(xticks=df_uof_crimes.index, legend=True, secondary_y=True, style='g')
plt2.set_ylabel('-     1  .', rotation=90)
plt2.set_xlabel('')
plt.set_xlabel('')
plt.set_xticklabels(df_uof_crimes.index, rotation='vertical')
plt

:

: "", : , .

, :

df_corr = df_uof_crimes.loc[:, ['White_promln_cr', 'White_promln_uof', 'Black_promln_cr', 'Black_promln_uof']].corr(method='pearson')
df_corr.style.background_gradient(cmap='PuBu')

:

: = 0.885, = 0.722. , , , ( ), . , , , .

, . ( , , ). : ( 100, %):

#   ( )
df_uof_crimes_agg = df_uof_crimes.loc[:, ['White_promln_cr', 'White_promln_uof', 'Black_promln_cr', 'Black_promln_uof']].agg(['mean', 'sum', 'min', 'max'])
# ""   
df_uof_crimes_agg['White_uof_cr'] = df_uof_crimes_agg['White_promln_uof'] * 100. / df_uof_crimes_agg['White_promln_cr']
df_uof_crimes_agg['Black_uof_cr'] = df_uof_crimes_agg['Black_promln_uof'] * 100. / df_uof_crimes_agg['Black_promln_cr']

:

:

plt = df_uof_crimes_agg.loc['mean', ['White_uof_cr', 'Black_uof_cr']].plot.bar(color=['g', 'olive'])
plt.set_ylabel(' -   - ')
plt.set_xticklabels(['', ''], rotation=0)

, , . , , - .

:

1. ( ). : , .

2. , " " , ( ). , "" ( -> -> -> ).

3. , . .

, :

- , ?

- Ya, korelasi seperti itu diamati, meskipun heterogen berdasarkan ras: untuk kulit putih hampir ideal, untuk kulit hitam hampir tidak sempurna.

Di bagian artikel selanjutnya, kita akan melihat distribusi geografis dari data yang dianalisis di seluruh negara bagian AS.

Tautan ke artikel versi bahasa Inggris (atas permintaan pekerja).