In [1]:
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
In [2]:
#2007 Data
xls_file = pd.ExcelFile('FBI By State/state/07tbl69.xls')
df = xls_file.parse('TABLE69k')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations', 'Runaways',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2007 = df[:-8]
count = 2
state = ""
for each in df2007.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2007.set_value(count, 'State', state)
df2007 = df2007.iloc[1::2]
#df2007.to_csv('2007FBI', sep='\t', encoding='utf-8')
In [3]:
#2008 data
xls_file = pd.ExcelFile('FBI By State/state/08tbl69.xls')
df = xls_file.parse('08tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations', 'Runaways',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2008 = df[:-14]
count = 2
state = ""
for each in df2008.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2008.set_value(count, 'State', state)
df2008 = df2008.iloc[1::2]
#df2008.to_csv('2008FBI', sep='\t', encoding='utf-8')
In [4]:
#2009 Data
xls_file = pd.ExcelFile('FBI By State/state/09tbl69.xls')
df = xls_file.parse('09tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations', 'Runaways',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2009 = df[:-8]
count = 2
state = ""
for each in df2009.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2009.set_value(count, 'State', state)
df2009 = df2009.iloc[1::2]
In [5]:
#2010 Data
xls_file = pd.ExcelFile('FBI By State/state/10tbl69.xls')
df = xls_file.parse('10tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2010 = df[:-8]
count = 2
state = ""
for each in df2010.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2010.set_value(count, 'State', state)
df2010 = df2010.iloc[1::2]
In [6]:
#2011 Data
xls_file = pd.ExcelFile('FBI By State/state/table_69_arrest_by_state_2011.xls')
df = xls_file.parse('11tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2011 = df[:-8]
count = 2
state = ""
for each in df2011.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2011.set_value(count, 'State', state)
df2011 = df2011.iloc[1::2]
In [7]:
#2012 Data
xls_file = pd.ExcelFile('FBI By State/state/table_69_arrest_by_state_2012.xls')
df = xls_file.parse('12tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2012 = df[:-9]
count = 2
state = ""
for each in df2012.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2012.set_value(count, 'State', state)
df2012 = df2012.iloc[1::2]
In [8]:
#2013 Data
xls_file = pd.ExcelFile('FBI By State/state/table_69_arrest_by_state_2013.xls')
df = xls_file.parse('13tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2013 = df[:-9]
count = 2
state = ""
for each in df2013.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2013.set_value(count, 'State', state)
df2013 = df2013.iloc[1::2]
In [9]:
#2014 Data
xls_file = pd.ExcelFile('FBI By State/state/table_69_arrest_by_state_2014.xls')
df = xls_file.parse('14tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2014 = df[:-16]
count = 2
state = ""
for each in df2014.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2014.set_value(count, 'State', state)
df2014 = df2014.iloc[1::2]
In [10]:
#2015 Data
xls_file = pd.ExcelFile('FBI By State/state/table_69_arrest_by_state_2015.xls')
df = xls_file.parse('15tbl69')
df.columns =['State', 'Age', 'Total all classes', 'Violent crime', 'Property crime','Murder', 'Forcible rape',
'Robbery', 'Aggravated assault', 'Burglary', 'Larceny-theft', 'Motor vehicle theft', 'Arson',
'Other assaults', 'Forgery and counterfeiting', 'Fraud', 'Embezzlement', 'Stolen property; buying, receiving, possessing',
'Vandalism', 'Weapons; carring, possessing', 'Prostitution and commercialized vice', 'Sex offences',
'Drug abuse violations',
'Gambling', 'Offenses against the family and children', 'Driving under the influence', 'Liquor laws', 'Drunkenness',
'Disorderly conduct', 'Vagrancy', 'All other offenses', 'Suspicion', 'Curfew and loitering law violations',
'Number of agencies', 'Estimated population']
df = df[3:]
df = df[['State', 'Age', 'Forgery and counterfeiting', 'Fraud', 'Stolen property; buying, receiving, possessing',
'Weapons; carring, possessing','Drug abuse violations','Gambling']]
df2015 = df[:-9]
count = 2
state = ""
for each in df2015.State:
count = count + 1
if(count % 2 == 1):
state = each
if(count % 2 == 0):
df2015.set_value(count, 'State', state)
df2015 = df2015.iloc[1::2]
In [11]:
# Forgery Data
dataForgery = {'State': df2007['State'],
'2007': df2007['Forgery and counterfeiting'],
'2008': df2008['Forgery and counterfeiting'],
'2009': df2009['Forgery and counterfeiting'],
'2010': df2010['Forgery and counterfeiting'],
'2011': df2011['Forgery and counterfeiting'],
'2012': df2012['Forgery and counterfeiting'],
'2013': df2013['Forgery and counterfeiting'],
'2014': df2014['Forgery and counterfeiting'],
'2015': df2015['Forgery and counterfeiting']}
dfForgery = pd.DataFrame(dataForgery)
dfForgery = dfForgery.set_index('State')
dfForgery['mean'] = dfForgery[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfForgerySort = dfForgery.sort_values(by='mean', ascending=False)
In [12]:
dataFraud = {'State': df2007['State'],
'2007': df2007['Fraud'],
'2008': df2008['Fraud'],
'2009': df2009['Fraud'],
'2010': df2010['Fraud'],
'2011': df2011['Fraud'],
'2012': df2012['Fraud'],
'2013': df2013['Fraud'],
'2014': df2014['Fraud'],
'2015': df2015['Fraud']}
dfFraud = pd.DataFrame(dataFraud)
dfFraud = dfFraud.set_index('State')
dfFraud['mean'] = dfFraud[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfFraudSort = dfFraud.sort_values(by='mean', ascending=False)
In [13]:
dataStolen = {'State': df2007['State'],
'2007': df2007['Stolen property; buying, receiving, possessing'],
'2008': df2008['Stolen property; buying, receiving, possessing'],
'2009': df2009['Stolen property; buying, receiving, possessing'],
'2010': df2010['Stolen property; buying, receiving, possessing'],
'2011': df2011['Stolen property; buying, receiving, possessing'],
'2012': df2012['Stolen property; buying, receiving, possessing'],
'2013': df2013['Stolen property; buying, receiving, possessing'],
'2014': df2014['Stolen property; buying, receiving, possessing'],
'2015': df2015['Stolen property; buying, receiving, possessing']}
dfStolen = pd.DataFrame(dataStolen)
dfStolen = dfStolen.set_index('State')
dfStolen['mean'] = dfStolen[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfStolenSort = dfStolen.sort_values(by='mean', ascending=False)
In [14]:
dataWeapons = {'State': df2007['State'],
'2007': df2007['Weapons; carring, possessing'],
'2008': df2008['Weapons; carring, possessing'],
'2009': df2009['Weapons; carring, possessing'],
'2010': df2010['Weapons; carring, possessing'],
'2011': df2011['Weapons; carring, possessing'],
'2012': df2012['Weapons; carring, possessing'],
'2013': df2013['Weapons; carring, possessing'],
'2014': df2014['Weapons; carring, possessing'],
'2015': df2015['Weapons; carring, possessing']}
dfWeapons = pd.DataFrame(dataWeapons)
dfWeapons = dfWeapons.set_index('State')
dfWeapons['mean'] = dfWeapons[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfWeaponsSort = dfWeapons.sort_values(by='mean', ascending=False)
In [30]:
dataDrug = {'State': df2007['State'],
'2007': df2007['Drug abuse violations'],
'2008': df2008['Drug abuse violations'],
'2009': df2009['Drug abuse violations'],
'2010': df2010['Drug abuse violations'],
'2011': df2011['Drug abuse violations'],
'2012': df2012['Drug abuse violations'],
'2013': df2013['Drug abuse violations'],
'2014': df2014['Drug abuse violations'],
'2015': df2015['Drug abuse violations']}
dfDrug = pd.DataFrame(dataDrug)
dfDrug = dfDrug.set_index('State')
dfDrug['mean'] = dfDrug[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfDrugSort = dfDrug.sort_values(by='mean', ascending=False)
dfDrug
Out[30]:
In [32]:
dataGamble = {'State': df2007['State'],
'2007': df2007['Gambling'],
'2008': df2008['Gambling'],
'2009': df2009['Gambling'],
'2010': df2010['Gambling'],
'2011': df2011['Gambling'],
'2012': df2012['Gambling'],
'2013': df2013['Gambling'],
'2014': df2014['Gambling'],
'2015': df2015['Gambling']}
dfGamble = pd.DataFrame(dataGamble)
dfGamble = dfGamble.set_index('State')
dfGamble['mean'] = dfGamble[['2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014', '2015']].mean(axis=1)
dfGambleSort = dfGamble.sort_values(by='mean', ascending=False)
dfGamble
Out[32]:
In [17]:
a2007 = df2007.drop('Age',1)
a2007 = a2007.set_index('State')
da2007 = {'ALABAMA': a2007.loc['ALABAMA '],
'ALASKA' : a2007.loc['ALASKA'],
'ARIZONA': a2007.loc['ARIZONA'],
'ARKANSAS': a2007.loc['ARKANSAS'],
'CALIFORNIA': a2007.loc['CALIFORNIA '],
'COLORADO': a2007.loc['COLORADO4'],
'CONNECTICUT': a2007.loc['CONNECTICUT'],
'DELAWARE': a2007.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2007.loc['DISTRICT OF COLUMBIA4, 5'],
'FLORIDA' : a2007.loc['FLORIDA4, 6'],
'GEORGIA': a2007.loc['GEORGIA'],
'HAWAII': a2007.loc['HAWAII'],
'IDAHO': a2007.loc['IDAHO'],
'ILLINOIS': a2007.loc['ILLINOIS'],
'INDIANA': a2007.loc['INDIANA'],
'IOWA': a2007.loc['IOWA'],
'KANSAS': a2007.loc['KANSAS'],
'KENTUCKY' : a2007.loc['KENTUCKY'],
'LOUISIANA': a2007.loc['LOUISIANA'],
'MAINE': a2007.loc['MAINE'],
'MARYLAND': a2007.loc['MARYLAND'],
'MASSACHUSETTS': a2007.loc['MASSACHUSETTS'],
'MICHIGAN': a2007.loc['MICHIGAN'],
'MINNESOTA': a2007.loc['MINNESOTA7'],
'MISSISSIPPI': a2007.loc['MISSISSIPPI'],
'MISSOURI' : a2007.loc['MISSOURI'],
'MONTANA': a2007.loc['MONTANA'],
'NEBRASKA': a2007.loc['NEBRASKA'],
'NEVADA': a2007.loc['NEVADA'],
'NEW HAMPSHIRE': a2007.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2007.loc['NEW JERSEY'],
'NEW MEXICO': a2007.loc['NEW MEXICO'],
'NEW YORK': a2007.loc['NEW YORK4'],
'NORTH CAROLINA' : a2007.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2007.loc['NORTH DAKOTA'],
'OHIO': a2007.loc['OHIO'],
'OKLAHOMA': a2007.loc['OKLAHOMA'],
'OREGON': a2007.loc['OREGON'],
'PENNSYLVANIA': a2007.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2007.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2007.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2007.loc['SOUTH DAKOTA'],
'TENNESSEE': a2007.loc['TENNESSEE'],
'TEXAS': a2007.loc['TEXAS'],
'UTAH': a2007.loc['UTAH'],
'VERMONT': a2007.loc['VERMONT'],
'VIRGINIA': a2007.loc['VIRGINIA'],
'WASHINGTON': a2007.loc['WASHINGTON'],
'WEST VIRGINIA': a2007.loc['WEST VIRGINIA'],
'WISCONSIN' : a2007.loc['WISCONSIN'],
'WYOMING': a2007.loc['WYOMING']}
d2007 = pd.DataFrame(da2007)
d2007
Out[17]:
In [29]:
a2008 = df2008.drop('Age',1)
a2008 = a2008.set_index('State')
da2008 = {'ALABAMA': a2008.loc['ALABAMA '],
'ALASKA' : a2008.loc['ALASKA'],
'ARIZONA': a2008.loc['ARIZONA'],
'ARKANSAS': a2008.loc['ARKANSAS'],
'CALIFORNIA': a2008.loc['CALIFORNIA '],
'COLORADO': a2008.loc['COLORADO4'],
'CONNECTICUT': a2008.loc['CONNECTICUT'],
'DELAWARE': a2008.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2008.loc['DISTRICT OF COLUMBIA4, 5'],
'FLORIDA' : a2008.loc['FLORIDA4, 6'],
'GEORGIA': a2008.loc['GEORGIA'],
'HAWAII': a2008.loc['HAWAII'],
'IDAHO': a2008.loc['IDAHO'],
'ILLINOIS': a2008.loc['ILLINOIS7'],
'INDIANA': a2008.loc['INDIANA'],
'IOWA': a2008.loc['IOWA'],
'KANSAS': a2008.loc['KANSAS'],
'KENTUCKY' : a2008.loc['KENTUCKY'],
'LOUISIANA': a2008.loc['LOUISIANA'],
'MAINE': a2008.loc['MAINE'],
'MARYLAND': a2008.loc['MARYLAND'],
'MASSACHUSETTS': a2008.loc['MASSACHUSETTS'],
'MICHIGAN': a2008.loc['MICHIGAN'],
'MINNESOTA': a2008.loc['MINNESOTA7'],
'MISSISSIPPI': a2008.loc['MISSISSIPPI'],
'MISSOURI' : a2008.loc['MISSOURI'],
'MONTANA': a2008.loc['MONTANA'],
'NEBRASKA': a2008.loc['NEBRASKA'],
'NEVADA': a2008.loc['NEVADA'],
'NEW HAMPSHIRE': a2008.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2008.loc['NEW JERSEY'],
'NEW MEXICO': a2008.loc['NEW MEXICO'],
'NEW YORK': a2008.loc['NEW YORK4'],
'NORTH CAROLINA' : a2008.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2008.loc['NORTH DAKOTA'],
'OHIO': a2008.loc['OHIO'],
'OKLAHOMA': a2008.loc['OKLAHOMA'],
'OREGON': a2008.loc['OREGON'],
'PENNSYLVANIA': a2008.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2008.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2008.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2008.loc['SOUTH DAKOTA'],
'TENNESSEE': a2008.loc['TENNESSEE'],
'TEXAS': a2008.loc['TEXAS'],
'UTAH': a2008.loc['UTAH'],
'VERMONT': a2008.loc['VERMONT'],
'VIRGINIA': a2008.loc['VIRGINIA'],
'WASHINGTON': a2008.loc['WASHINGTON'],
'WEST VIRGINIA': a2008.loc['WEST VIRGINIA'],
'WISCONSIN' : a2008.loc['WISCONSIN'],
'WYOMING': a2008.loc['WYOMING']}
d2008 = pd.DataFrame(da2008)
d2008
Out[29]:
In [19]:
a2009 = df2009.drop('Age',1)
a2009 = a2009.set_index('State')
da2009 = {'ALABAMA': a2009.loc['ALABAMA '],
'ALASKA' : a2009.loc['ALASKA'],
'ARIZONA': a2009.loc['ARIZONA'],
'ARKANSAS': a2009.loc['ARKANSAS'],
'CALIFORNIA': a2009.loc['CALIFORNIA '],
'COLORADO': a2009.loc['COLORADO'],
'CONNECTICUT': a2009.loc['CONNECTICUT'],
'DELAWARE': a2009.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2009.loc['DISTRICT OF COLUMBIA4, 5'],
'FLORIDA' : a2009.loc['FLORIDA4, 6'],
'GEORGIA': a2009.loc['GEORGIA'],
'HAWAII': a2009.loc['HAWAII'],
'IDAHO': a2009.loc['IDAHO'],
'ILLINOIS': a2009.loc['ILLINOIS7'],
'INDIANA': a2009.loc['INDIANA'],
'IOWA': a2009.loc['IOWA'],
'KANSAS': a2009.loc['KANSAS'],
'KENTUCKY' : a2009.loc['KENTUCKY'],
'LOUISIANA': a2009.loc['LOUISIANA'],
'MAINE': a2009.loc['MAINE'],
'MARYLAND': a2009.loc['MARYLAND'],
'MASSACHUSETTS': a2009.loc['MASSACHUSETTS'],
'MICHIGAN': a2009.loc['MICHIGAN'],
'MINNESOTA': a2009.loc['MINNESOTA7'],
'MISSISSIPPI': a2009.loc['MISSISSIPPI'],
'MISSOURI' : a2009.loc['MISSOURI'],
'MONTANA': a2009.loc['MONTANA'],
'NEBRASKA': a2009.loc['NEBRASKA'],
'NEVADA': a2009.loc['NEVADA'],
'NEW HAMPSHIRE': a2009.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2009.loc['NEW JERSEY'],
'NEW MEXICO': a2009.loc['NEW MEXICO'],
'NEW YORK': a2009.loc['NEW YORK4'],
'NORTH CAROLINA' : a2009.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2009.loc['NORTH DAKOTA'],
'OHIO': a2009.loc['OHIO'],
'OKLAHOMA': a2009.loc['OKLAHOMA'],
'OREGON': a2009.loc['OREGON'],
'PENNSYLVANIA': a2009.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2009.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2009.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2009.loc['SOUTH DAKOTA'],
'TENNESSEE': a2009.loc['TENNESSEE'],
'TEXAS': a2009.loc['TEXAS'],
'UTAH': a2009.loc['UTAH'],
'VERMONT': a2009.loc['VERMONT'],
'VIRGINIA': a2009.loc['VIRGINIA'],
'WASHINGTON': a2009.loc['WASHINGTON'],
'WEST VIRGINIA': a2009.loc['WEST VIRGINIA'],
'WISCONSIN' : a2009.loc['WISCONSIN'],
'WYOMING': a2009.loc['WYOMING']}
d2009 = pd.DataFrame(da2009)
In [20]:
a2010 = df2010.drop('Age',1)
a2010 = a2010.set_index('State')
da2010 = {'ALABAMA': a2010.loc['ALABAMA '],
'ALASKA' : a2010.loc['ALASKA'],
'ARIZONA': a2010.loc['ARIZONA'],
'ARKANSAS': a2010.loc['ARKANSAS'],
'CALIFORNIA': a2010.loc['CALIFORNIA '],
'COLORADO': a2010.loc['COLORADO'],
'CONNECTICUT': a2010.loc['CONNECTICUT'],
'DELAWARE': a2010.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2010.loc['DISTRICT OF COLUMBIA4, 5'],
'FLORIDA' : a2010.loc['FLORIDA4, 6'],
'GEORGIA': a2010.loc['GEORGIA'],
'HAWAII': a2010.loc['HAWAII'],
'IDAHO': a2010.loc['IDAHO'],
'ILLINOIS': a2010.loc['ILLINOIS7'],
'INDIANA': a2010.loc['INDIANA'],
'IOWA': a2010.loc['IOWA'],
'KANSAS': a2010.loc['KANSAS'],
'KENTUCKY' : a2010.loc['KENTUCKY'],
'LOUISIANA': a2010.loc['LOUISIANA'],
'MAINE': a2010.loc['MAINE'],
'MARYLAND': a2010.loc['MARYLAND'],
'MASSACHUSETTS': a2010.loc['MASSACHUSETTS'],
'MICHIGAN': a2010.loc['MICHIGAN'],
'MINNESOTA': a2010.loc['MINNESOTA7'],
'MISSISSIPPI': a2010.loc['MISSISSIPPI'],
'MISSOURI' : a2010.loc['MISSOURI'],
'MONTANA': a2010.loc['MONTANA'],
'NEBRASKA': a2010.loc['NEBRASKA'],
'NEVADA': a2010.loc['NEVADA'],
'NEW HAMPSHIRE': a2010.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2010.loc['NEW JERSEY'],
'NEW MEXICO': a2010.loc['NEW MEXICO'],
'NEW YORK': a2010.loc['NEW YORK4'],
'NORTH CAROLINA' : a2010.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2010.loc['NORTH DAKOTA'],
'OHIO': a2010.loc['OHIO'],
'OKLAHOMA': a2010.loc['OKLAHOMA'],
'OREGON': a2010.loc['OREGON'],
'PENNSYLVANIA': a2010.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2010.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2010.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2010.loc['SOUTH DAKOTA'],
'TENNESSEE': a2010.loc['TENNESSEE'],
'TEXAS': a2010.loc['TEXAS'],
'UTAH': a2010.loc['UTAH'],
'VERMONT': a2010.loc['VERMONT'],
'VIRGINIA': a2010.loc['VIRGINIA'],
'WASHINGTON': a2010.loc['WASHINGTON'],
'WEST VIRGINIA': a2010.loc['WEST VIRGINIA'],
'WISCONSIN' : a2010.loc['WISCONSIN'],
'WYOMING': a2010.loc['WYOMING']}
d2010 = pd.DataFrame(da2010)
In [21]:
a2011 = df2011.drop('Age',1)
a2011 = a2011.set_index('State')
da2011 = {'ALABAMA': a2011.loc['ALABAMA4 '],
'ALASKA' : a2011.loc['ALASKA'],
'ARIZONA': a2011.loc['ARIZONA'],
'ARKANSAS': a2011.loc['ARKANSAS'],
'CALIFORNIA': a2011.loc['CALIFORNIA '],
'COLORADO': a2011.loc['COLORADO'],
'CONNECTICUT': a2011.loc['CONNECTICUT'],
'DELAWARE': a2011.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2011.loc['DISTRICT OF COLUMBIA5'],
'FLORIDA' : a2011.loc['FLORIDA4, 6'],
'GEORGIA': a2011.loc['GEORGIA'],
'HAWAII': a2011.loc['HAWAII'],
'IDAHO': a2011.loc['IDAHO'],
'ILLINOIS': a2011.loc['ILLINOIS7'],
'INDIANA': a2011.loc['INDIANA'],
'IOWA': a2011.loc['IOWA'],
'KANSAS': a2011.loc['KANSAS'],
'KENTUCKY' : a2011.loc['KENTUCKY'],
'LOUISIANA': a2011.loc['LOUISIANA'],
'MAINE': a2011.loc['MAINE'],
'MARYLAND': a2011.loc['MARYLAND'],
'MASSACHUSETTS': a2011.loc['MASSACHUSETTS'],
'MICHIGAN': a2011.loc['MICHIGAN'],
'MINNESOTA': a2011.loc['MINNESOTA7'],
'MISSISSIPPI': a2011.loc['MISSISSIPPI'],
'MISSOURI' : a2011.loc['MISSOURI'],
'MONTANA': a2011.loc['MONTANA'],
'NEBRASKA': a2011.loc['NEBRASKA'],
'NEVADA': a2011.loc['NEVADA'],
'NEW HAMPSHIRE': a2011.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2011.loc['NEW JERSEY'],
'NEW MEXICO': a2011.loc['NEW MEXICO'],
'NEW YORK': a2011.loc['NEW YORK4'],
'NORTH CAROLINA' : a2011.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2011.loc['NORTH DAKOTA'],
'OHIO': a2011.loc['OHIO'],
'OKLAHOMA': a2011.loc['OKLAHOMA'],
'OREGON': a2011.loc['OREGON'],
'PENNSYLVANIA': a2011.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2011.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2011.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2011.loc['SOUTH DAKOTA'],
'TENNESSEE': a2011.loc['TENNESSEE'],
'TEXAS': a2011.loc['TEXAS'],
'UTAH': a2011.loc['UTAH'],
'VERMONT': a2011.loc['VERMONT'],
'VIRGINIA': a2011.loc['VIRGINIA'],
'WASHINGTON': a2011.loc['WASHINGTON'],
'WEST VIRGINIA': a2011.loc['WEST VIRGINIA'],
'WISCONSIN' : a2011.loc['WISCONSIN'],
'WYOMING': a2011.loc['WYOMING']}
d2011 = pd.DataFrame(da2011)
In [22]:
a2012 = df2012.drop('Age',1)
a2012 = a2012.set_index('State')
da2012 = {'ALABAMA': a2012.loc['ALABAMA4 '],
'ALASKA' : a2012.loc['ALASKA'],
'ARIZONA': a2012.loc['ARIZONA'],
'ARKANSAS': a2012.loc['ARKANSAS'],
'CALIFORNIA': a2012.loc['CALIFORNIA '],
'COLORADO': a2012.loc['COLORADO'],
'CONNECTICUT': a2012.loc['CONNECTICUT'],
'DELAWARE': a2012.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2012.loc['DISTRICT OF COLUMBIA4, 5'],
'FLORIDA' : a2012.loc['FLORIDA4, 6'],
'GEORGIA': a2012.loc['GEORGIA'],
'HAWAII': a2012.loc['HAWAII'],
'IDAHO': a2012.loc['IDAHO'],
'ILLINOIS': a2012.loc['ILLINOIS7'],
'INDIANA': a2012.loc['INDIANA'],
'IOWA': a2012.loc['IOWA'],
'KANSAS': a2012.loc['KANSAS'],
'KENTUCKY' : a2012.loc['KENTUCKY'],
'LOUISIANA': a2012.loc['LOUISIANA'],
'MAINE': a2012.loc['MAINE'],
'MARYLAND': a2012.loc['MARYLAND'],
'MASSACHUSETTS': a2012.loc['MASSACHUSETTS'],
'MICHIGAN': a2012.loc['MICHIGAN'],
'MINNESOTA': a2012.loc['MINNESOTA8'],
'MISSISSIPPI': a2012.loc['MISSISSIPPI'],
'MISSOURI' : a2012.loc['MISSOURI'],
'MONTANA': a2012.loc['MONTANA'],
'NEBRASKA': a2012.loc['NEBRASKA'],
'NEVADA': a2012.loc['NEVADA'],
'NEW HAMPSHIRE': a2012.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2012.loc['NEW JERSEY'],
'NEW MEXICO': a2012.loc['NEW MEXICO'],
'NEW YORK': a2012.loc['NEW YORK4'],
'NORTH CAROLINA' : a2012.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2012.loc['NORTH DAKOTA'],
'OHIO': a2012.loc['OHIO'],
'OKLAHOMA': a2012.loc['OKLAHOMA'],
'OREGON': a2012.loc['OREGON'],
'PENNSYLVANIA': a2012.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2012.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2012.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2012.loc['SOUTH DAKOTA'],
'TENNESSEE': a2012.loc['TENNESSEE'],
'TEXAS': a2012.loc['TEXAS'],
'UTAH': a2012.loc['UTAH'],
'VERMONT': a2012.loc['VERMONT'],
'VIRGINIA': a2012.loc['VIRGINIA'],
'WASHINGTON': a2012.loc['WASHINGTON'],
'WEST VIRGINIA': a2012.loc['WEST VIRGINIA'],
'WISCONSIN' : a2012.loc['WISCONSIN'],
'WYOMING': a2012.loc['WYOMING']}
d2012 = pd.DataFrame(da2012)
In [23]:
a2013 = df2013.drop('Age',1)
a2013 = a2013.set_index('State')
da2013 = {'ALABAMA': a2013.loc['ALABAMA5 '],
'ALASKA' : a2013.loc['ALASKA'],
'ARIZONA': a2013.loc['ARIZONA'],
'ARKANSAS': a2013.loc['ARKANSAS'],
'CALIFORNIA': a2013.loc['CALIFORNIA '],
'COLORADO': a2013.loc['COLORADO'],
'CONNECTICUT': a2013.loc['CONNECTICUT'],
'DELAWARE': a2013.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2013.loc['DISTRICT OF COLUMBIA6'],
'FLORIDA' : a2013.loc['FLORIDA5, 7'],
'GEORGIA': a2013.loc['GEORGIA'],
'HAWAII': a2013.loc['HAWAII'],
'IDAHO': a2013.loc['IDAHO'],
'ILLINOIS': a2013.loc['ILLINOIS8'],
'INDIANA': a2013.loc['INDIANA'],
'IOWA': a2013.loc['IOWA'],
'KANSAS': a2013.loc['KANSAS'],
'KENTUCKY' : a2013.loc['KENTUCKY'],
'LOUISIANA': a2013.loc['LOUISIANA'],
'MAINE': a2013.loc['MAINE'],
'MARYLAND': a2013.loc['MARYLAND'],
'MASSACHUSETTS': a2013.loc['MASSACHUSETTS'],
'MICHIGAN': a2013.loc['MICHIGAN'],
'MINNESOTA': a2013.loc['MINNESOTA'],
'MISSISSIPPI': a2013.loc['MISSISSIPPI'],
'MISSOURI' : a2013.loc['MISSOURI'],
'MONTANA': a2013.loc['MONTANA'],
'NEBRASKA': a2013.loc['NEBRASKA'],
'NEVADA': a2013.loc['NEVADA'],
'NEW HAMPSHIRE': a2013.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2013.loc['NEW JERSEY'],
'NEW MEXICO': a2013.loc['NEW MEXICO'],
'NEW YORK': a2013.loc['NEW YORK5'],
'NORTH CAROLINA' : a2013.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2013.loc['NORTH DAKOTA'],
'OHIO': a2013.loc['OHIO'],
'OKLAHOMA': a2013.loc['OKLAHOMA'],
'OREGON': a2013.loc['OREGON'],
'PENNSYLVANIA': a2013.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2013.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2013.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2013.loc['SOUTH DAKOTA'],
'TENNESSEE': a2013.loc['TENNESSEE'],
'TEXAS': a2013.loc['TEXAS'],
'UTAH': a2013.loc['UTAH'],
'VERMONT': a2013.loc['VERMONT'],
'VIRGINIA': a2013.loc['VIRGINIA'],
'WASHINGTON': a2013.loc['WASHINGTON'],
'WEST VIRGINIA': a2013.loc['WEST VIRGINIA'],
'WISCONSIN' : a2013.loc['WISCONSIN'],
'WYOMING': a2013.loc['WYOMING']}
d2013 = pd.DataFrame(da2013)
In [24]:
a2014 = df2014.drop('Age',1)
a2014 = a2014.set_index('State')
da2014 = {'ALABAMA': a2014.loc['ALABAMA5 '],
'ALASKA' : a2014.loc['ALASKA'],
'ARIZONA': a2014.loc['ARIZONA'],
'ARKANSAS': a2014.loc['ARKANSAS'],
'CALIFORNIA': a2014.loc['CALIFORNIA '],
'COLORADO': a2014.loc['COLORADO'],
'CONNECTICUT': a2014.loc['CONNECTICUT'],
'DELAWARE': a2014.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2014.loc['DISTRICT OF COLUMBIA6'],
'FLORIDA' : a2014.loc['FLORIDA5,7'],
'GEORGIA': a2014.loc['GEORGIA8'],
'HAWAII': a2014.loc['HAWAII'],
'IDAHO': a2014.loc['IDAHO'],
'ILLINOIS': a2014.loc['ILLINOIS5'],
'INDIANA': a2014.loc['INDIANA'],
'IOWA': a2014.loc['IOWA'],
'KANSAS': a2014.loc['KANSAS'],
'KENTUCKY' : a2014.loc['KENTUCKY'],
'LOUISIANA': a2014.loc['LOUISIANA'],
'MAINE': a2014.loc['MAINE'],
'MARYLAND': a2014.loc['MARYLAND'],
'MASSACHUSETTS': a2014.loc['MASSACHUSETTS'],
'MICHIGAN': a2014.loc['MICHIGAN'],
'MINNESOTA': a2014.loc['MINNESOTA'],
'MISSISSIPPI': a2014.loc['MISSISSIPPI'],
'MISSOURI' : a2014.loc['MISSOURI'],
'MONTANA': a2014.loc['MONTANA'],
'NEBRASKA': a2014.loc['NEBRASKA'],
'NEVADA': a2014.loc['NEVADA'],
'NEW HAMPSHIRE': a2014.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2014.loc['NEW JERSEY'],
'NEW MEXICO': a2014.loc['NEW MEXICO'],
'NEW YORK': a2014.loc['NEW YORK5'],
'NORTH CAROLINA' : a2014.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2014.loc['NORTH DAKOTA'],
'OHIO': a2014.loc['OHIO'],
'OKLAHOMA': a2014.loc['OKLAHOMA'],
'OREGON': a2014.loc['OREGON'],
'PENNSYLVANIA': a2014.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2014.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2014.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2014.loc['SOUTH DAKOTA'],
'TENNESSEE': a2014.loc['TENNESSEE'],
'TEXAS': a2014.loc['TEXAS'],
'UTAH': a2014.loc['UTAH'],
'VERMONT': a2014.loc['VERMONT'],
'VIRGINIA': a2014.loc['VIRGINIA'],
'WASHINGTON': a2014.loc['WASHINGTON'],
'WEST VIRGINIA': a2014.loc['WEST VIRGINIA'],
'WISCONSIN' : a2014.loc['WISCONSIN'],
'WYOMING': a2014.loc['WYOMING']}
d2014 = pd.DataFrame(da2014)
In [25]:
a2015 = df2015.drop('Age',1)
a2015 = a2015.set_index('State')
da2015 = {'ALABAMA': a2015.loc['ALABAMA '],
'ALASKA' : a2015.loc['ALASKA'],
'ARIZONA': a2015.loc['ARIZONA'],
'ARKANSAS': a2015.loc['ARKANSAS'],
'CALIFORNIA': a2015.loc['CALIFORNIA '],
'COLORADO': a2015.loc['COLORADO'],
'CONNECTICUT': a2015.loc['CONNECTICUT'],
'DELAWARE': a2015.loc['DELAWARE'],
'DISTRICT OF COLUMBIA': a2015.loc['DISTRICT OF COLUMBIA5'],
'FLORIDA' : a2015.loc['FLORIDA6,7'],
'GEORGIA': a2015.loc['GEORGIA'],
'HAWAII': a2015.loc['HAWAII'],
'IDAHO': a2015.loc['IDAHO'],
'ILLINOIS': a2015.loc['ILLINOIS6'],
'INDIANA': a2015.loc['INDIANA'],
'IOWA': a2015.loc['IOWA'],
'KANSAS': a2015.loc['KANSAS'],
'KENTUCKY' : a2015.loc['KENTUCKY'],
'LOUISIANA': a2015.loc['LOUISIANA'],
'MAINE': a2015.loc['MAINE'],
'MARYLAND': a2015.loc['MARYLAND'],
'MASSACHUSETTS': a2015.loc['MASSACHUSETTS'],
'MICHIGAN': a2015.loc['MICHIGAN'],
'MINNESOTA': a2015.loc['MINNESOTA'],
'MISSISSIPPI': a2015.loc['MISSISSIPPI'],
'MISSOURI' : a2015.loc['MISSOURI'],
'MONTANA': a2015.loc['MONTANA'],
'NEBRASKA': a2015.loc['NEBRASKA'],
'NEVADA': a2015.loc['NEVADA'],
'NEW HAMPSHIRE': a2015.loc['NEW HAMPSHIRE'],
'NEW JERSEY': a2015.loc['NEW JERSEY'],
'NEW MEXICO': a2015.loc['NEW MEXICO'],
'NEW YORK': a2015.loc['NEW YORK6'],
'NORTH CAROLINA' : a2015.loc['NORTH CAROLINA'],
'NORTH DAKOTA': a2015.loc['NORTH DAKOTA'],
'OHIO': a2015.loc['OHIO'],
'OKLAHOMA': a2015.loc['OKLAHOMA'],
'OREGON': a2015.loc['OREGON'],
'PENNSYLVANIA': a2015.loc['PENNSYLVANIA'],
'RHODE ISLAND': a2015.loc['RHODE ISLAND'],
'SOUTH CAROLINA': a2015.loc['SOUTH CAROLINA'],
'SOUTH DAKOTA' : a2015.loc['SOUTH DAKOTA'],
'TENNESSEE': a2015.loc['TENNESSEE'],
'TEXAS': a2015.loc['TEXAS8'],
'UTAH': a2015.loc['UTAH'],
'VERMONT': a2015.loc['VERMONT'],
'VIRGINIA': a2015.loc['VIRGINIA'],
'WASHINGTON': a2015.loc['WASHINGTON'],
'WEST VIRGINIA': a2015.loc['WEST VIRGINIA'],
'WISCONSIN' : a2015.loc['WISCONSIN'],
'WYOMING': a2015.loc['WYOMING']}
d2015 = pd.DataFrame(da2015)
In [26]:
# Pie chart of percentage of each crime based on year
colors = ["#E13F29", "#D69A80", "#D63B59", "#AE5552", "#CB5C3B", "#EB8076", "#96624E"]
for each in d2007.columns.values:
# Create a pie chart
plt.title(each + ' in 2007', y = 1.1)
plt.pie(
# using data total)arrests
d2007[each],
# with the labels being officer names
labels=d2007.index.values,
# with no shadows
shadow=False,
# with colors
colors=colors,
# with one slide exploded out
# with the start angle at 90%
startangle=90,
# with the percent listed as a fraction
autopct='%1.1f%%',
)
# View the plot drop above
plt.axis('equal')
# View the plot
plt.tight_layout()
plt.show()
In [27]:
# Pie chart of percentage of specific crimes at different location at different years
colors = ["#E13F29", "#D69A80", "#D63B59", "#AE5552", "#CB5C3B", "#EB8076", "#96624E"]
for each in dfDrug.columns.values:
# Create a pie chart
plt.title(each, y = 1.1)
plt.pie(
# using data total)arrests
dfDrug[each],
# with the labels being officer names
labels=dfDrug.index.values,
# with no shadows
shadow=False,
# with colors
colors=colors,
# with one slide exploded out
# with the start angle at 90%
startangle=90,
# with the percent listed as a fraction
autopct='%1.1f%%',
)
# View the plot drop above
plt.axis('equal')
# View the plot
plt.tight_layout()
plt.show()
In [28]:
plt.title('ALABAMA in 2012', y = 1.1)
plt.pie(
# using data total)arrests
d2012['ALABAMA'],
# with the labels being officer names
labels=d2012.index.values,
# with no shadows
shadow=False,
# with colors
colors=colors,
# with one slide exploded out
# with the start angle at 90%
startangle=90,
# with the percent listed as a fraction
autopct='%1.1f%%',
)
# View the plot drop above
plt.axis('equal')
# View the plot
plt.tight_layout()
plt.show()
In [33]:
dfDrug['2007'].sum(axis=0)
Out[33]:
In [62]:
daDrug = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfDrug['2007'].sum(axis=0), dfDrug['2008'].sum(axis=0),
dfDrug['2009'].sum(axis=0), dfDrug['2010'].sum(axis=0),
dfDrug['2011'].sum(axis=0), dfDrug['2012'].sum(axis=0),
dfDrug['2013'].sum(axis=0),dfDrug['2014'].sum(axis=0),dfDrug['2015'].sum(axis=0)]}
dDrug = pd.DataFrame(daDrug)
dDrug = dDrug.set_index('year')
dDrug.plot(kind='bar', title='Total Arrests related to Drugs Across the US')
In [78]:
Out[78]:
In [67]:
daGamble = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfGamble['2007'].sum(axis=0), dfGamble['2008'].sum(axis=0),
dfGamble['2009'].sum(axis=0), dfGamble['2010'].sum(axis=0),
dfGamble['2011'].sum(axis=0), dfGamble['2012'].sum(axis=0),
dfGamble['2013'].sum(axis=0),dfGamble['2014'].sum(axis=0),dfGamble['2015'].sum(axis=0)]}
dGamble = pd.DataFrame(daGamble)
dGamble = dGamble.set_index('year')
dGamble.plot(kind='bar', title='Total Arrests related to Gambling Across the US')
Out[67]:
In [79]:
daFraud = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfFraud['2007'].sum(axis=0), dfFraud['2008'].sum(axis=0),
dfFraud['2009'].sum(axis=0), dfFraud['2010'].sum(axis=0),
dfFraud['2011'].sum(axis=0), dfFraud['2012'].sum(axis=0),
dfFraud['2013'].sum(axis=0),dfFraud['2014'].sum(axis=0),dfFraud['2015'].sum(axis=0)]}
dFraud = pd.DataFrame(daFraud)
dFraud = dFraud.set_index('year')
dFraud.plot(kind='bar', title='Total Arrests related to Fraud Across the US')
Out[79]:
In [80]:
daForgery = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfForgery['2007'].sum(axis=0), dfForgery['2008'].sum(axis=0),
dfForgery['2009'].sum(axis=0), dfForgery['2010'].sum(axis=0),
dfForgery['2011'].sum(axis=0), dfForgery['2012'].sum(axis=0),
dfForgery['2013'].sum(axis=0),dfForgery['2014'].sum(axis=0),dfForgery['2015'].sum(axis=0)]}
dForgery = pd.DataFrame(daForgery)
dForgery = dForgery.set_index('year')
dForgery.plot(kind='bar', title='Total Arrests related to Forgery Across the US')
Out[80]:
In [76]:
daWeapons = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfWeapons['2007'].sum(axis=0), dfWeapons['2008'].sum(axis=0),
dfWeapons['2009'].sum(axis=0), dfWeapons['2010'].sum(axis=0),
dfWeapons['2011'].sum(axis=0), dfWeapons['2012'].sum(axis=0),
dfWeapons['2013'].sum(axis=0),dfWeapons['2014'].sum(axis=0),dfWeapons['2015'].sum(axis=0)]}
dWeapons = pd.DataFrame(daWeapons)
dWeapons = dWeapons.set_index('year')
dWeapons.plot(kind='bar', title='Total Arrests related to Weapons Across the US')
Out[76]:
In [75]:
daStolen = {'year': ['2007', '2008', '2009', '2010', '2011', '2012,', '2013', '2014', '2015'],
'sum': [dfStolen['2007'].sum(axis=0), dfStolen['2008'].sum(axis=0),
dfStolen['2009'].sum(axis=0), dfStolen['2010'].sum(axis=0),
dfStolen['2011'].sum(axis=0), dfStolen['2012'].sum(axis=0),
dfStolen['2013'].sum(axis=0),dfStolen['2014'].sum(axis=0),dfStolen['2015'].sum(axis=0)]}
dStolen = pd.DataFrame(daStolen)
dStolen = dStolen.set_index('year')
dStolen.plot(kind='bar', title='Total Arrests related to Stolen Across the US')
Out[75]:
In [ ]: