Assignment 8

# Import libraries to be used for the project import matplotlib.pyplot as plt import seaborn as sns import pandas as pd

#Import the crime data from FBI website and create a new data frame and rename the columns crime_df= pd.read_csv('crime.csv', header=None) crime_df.columns = ["Year","Population","Violent Crime","Violent Crime Rate","Murder and nonnegligent manslaughter","Murder and nonnegligent manslaughter Rate","Rape Revised def","Rape Revised def rate","Rape Legacy def","Rape Legacy def rate", "Robbery","Robbery rate","Aggrevated Assult","Aggrevated Assult rate","Property Crime","Property crime rate","Burglary", "Burglary rate", "Larceny-theft","Larceny-theft rate", "Motor vehicle theft", "Motor vehicle theft rate"]

# drop row one and rename data frame to df1 for ease in future manipulation df1= crime_df[1:] df1

	Yearobject 19975% 19985% 18 others90%	Populationobject 267,783,6075% 270,248,0035% 18 others90%	Violent Crimeobject 1,636,0965% 1,533,8875% 18 others90%	Violent Crime Rateobject 611.05% 567.65% 18 others90%	Murder and nonnegligent manslaughterobject 18,2085% 16,9745% 18 others90%	Murder and nonnegligent manslaughter Rateobject 5.715% 5.615% 12 others70%	Rape Revised defobject 5% 4 others20% Missing75%	Rape Revised def rateobject 35.95% 3 others15% Missing80%	Rape Legacy defobject 96,1535% 93,1445% 18 others90%	Rape Legacy def rateobject 31.810% 35.95% 17 others85%	Robberyobject 498,5345% 447,1865% 18 others90%	Robbery rateobject 186.25% 165.55% 18 others90%	Aggrevated Assultobject 1,023,2015% 976,5835% 18 others90%	Aggrevated Assult rateobject 382.15% 361.45% 18 others90%	Property Crimeobject 11,558,4755% 10,951,8275% 18 others90%	Property crime rateobject 4,316.35% 4,052.55% 18 others90%	Burglaryobject 2,460,5265% 2,332,7355% 18 others90%	Burglary rateobject 918.85% 863.25% 18 others90%	Larceny-theftobject 7,743,7605% 7,376,3115% 18 others90%	Larceny-theft rateobject 2,891.85% 2,729.55% 18 others90%	Motor vehicle theftobject 1,354,1895% 1,242,7815% 18 others90%	Motor vehicle theft rateobject 505.75% 459.95% 18 others90%
1	1997	267,783,607	1,636,096	611.0	18,208	6.8	nan	nan	96,153	35.9	498,534	186.2	1,023,201	382.1	11,558,475	4,316.3	2,460,526	918.8	7,743,760	2,891.8	1,354,189	505.7
2	1998	270,248,003	1,533,887	567.6	16,974	6.3	nan	nan	93,144	34.5	447,186	165.5	976,583	361.4	10,951,827	4,052.5	2,332,735	863.2	7,376,311	2,729.5	1,242,781	459.9
3	1999	272,690,813	1,426,044	523.0	15,522	5.7	nan	nan	89,411	32.8	409,371	150.1	911,740	334.3	10,208,334	3,743.6	2,100,739	770.4	6,955,520	2,550.7	1,152,075	422.5
4	2000	281,421,906	1,425,486	506.5	15,586	5.5	nan	nan	90,178	32.0	408,016	145.0	911,706	324.0	10,182,584	3,618.3	2,050,992	728.8	6,971,590	2,477.3	1,160,002	412.2
5	2001	285,317,559	1,439,480	504.5	16,037	5.6	nan	nan	90,863	31.8	423,557	148.5	909,023	318.6	10,437,189	3,658.1	2,116,531	741.8	7,092,267	2,485.7	1,228,391	430.5
Expand rows 5 - 14
16	2012	313,873,685	1,217,057	387.8	14,856	4.7	nan	nan	85,141	27.1	355,051	113.1	762,009	242.8	9,001,992	2,868.0	2,109,932	672.2	6,168,874	1,965.4	723,186	230.4
17	2013	316,497,531	1,168,298	369.1	14,319	4.5	113,695	35.9	82,109	25.9	345,093	109.0	726,777	229.6	8,651,892	2,733.6	1,932,139	610.5	6,019,465	1,901.9	700,288	221.3
18	2014	318,907,401	1,153,022	361.6	14,164	4.4	118,027	37.0	84,864	26.6	322,905	101.3	731,089	229.2	8,209,010	2,574.1	1,713,153	537.2	5,809,054	1,821.5	686,803	215.4
19	2015	320,896,618	1,199,310	373.7	15,883	4.9	126,134	39.3	91,261	28.4	328,109	102.2	764,057	238.1	8,024,115	2,500.5	1,587,564	494.7	5,723,488	1,783.6	713,063	222.2
20	2016	323,127,513	1,248,185	386.3	17,250	5.3	130,603	40.4	95,730	29.6	332,198	102.8	803,007	248.5	7,919,035	2,450.7	1,515,096	468.9	5,638,455	1,745.0	765,484	236.9
20 rows × 22 columns

# replace all commas df1 = df1.replace(',','', regex=True)

# convert each columnn to an integer column df1["Population"]= df1["Population"].astype (int)

df1["Violent Crime"]= df1["Violent Crime"].astype (int)

df1["Murder and nonnegligent manslaughter"]= df1["Murder and nonnegligent manslaughter"].astype (int)

df1["Rape Legacy def"]= df1["Rape Legacy def"].astype (int)

df1["Robbery"]= df1["Robbery"].astype (int)

df1["Aggrevated Assult"]= df1["Aggrevated Assult"].astype (int)

df1["Property Crime"]= df1["Property Crime"].astype (int)

df1["Burglary"]= df1["Burglary"].astype (int)

df1["Larceny-theft"]= df1["Larceny-theft"].astype (int)

df1["Motor vehicle theft"]= df1["Motor vehicle theft"].astype (int)

# preview to ensure everything looks good df1

	Yearobject 19975% 19985% 18 others90%	Populationint64267783607 – 323127513	Violent Crimeint641153022 – 1636096	Violent Crime Rateobject 611.05% 567.65% 18 others90%	Murder and nonnegligent manslaughterint6414164 – 18208	Murder and nonnegligent manslaughter Rateobject 5.715% 5.615% 12 others70%	Rape Revised defobject 5% 4 others20% Missing75%	Rape Revised def rateobject 35.95% 3 others15% Missing80%	Rape Legacy defint6482109 – 96153	Rape Legacy def rateobject 31.810% 35.95% 17 others85%	Robberyint64322905 – 498534	Robbery rateobject 186.25% 165.55% 18 others90%	Aggrevated Assultint64726777 – 1023201	Aggrevated Assult rateobject 382.15% 361.45% 18 others90%	Property Crimeint647919035 – 11558475	Property crime rateobject 4316.35% 4052.55% 18 others90%	Burglaryint641515096 – 2460526	Burglary rateobject 918.85% 863.25% 18 others90%	Larceny-theftint645638455 – 7743760	Larceny-theft rateobject 2891.85% 2729.55% 18 others90%	Motor vehicle theftint64686803 – 1354189	Motor vehicle theft rateobject 505.75% 459.95% 18 others90%
1	1997	267783607	1636096	611.0	18208	6.8	nan	nan	96153	35.9	498534	186.2	1023201	382.1	11558475	4316.3	2460526	918.8	7743760	2891.8	1354189	505.7
2	1998	270248003	1533887	567.6	16974	6.3	nan	nan	93144	34.5	447186	165.5	976583	361.4	10951827	4052.5	2332735	863.2	7376311	2729.5	1242781	459.9
3	1999	272690813	1426044	523.0	15522	5.7	nan	nan	89411	32.8	409371	150.1	911740	334.3	10208334	3743.6	2100739	770.4	6955520	2550.7	1152075	422.5
4	2000	281421906	1425486	506.5	15586	5.5	nan	nan	90178	32.0	408016	145.0	911706	324.0	10182584	3618.3	2050992	728.8	6971590	2477.3	1160002	412.2
5	2001	285317559	1439480	504.5	16037	5.6	nan	nan	90863	31.8	423557	148.5	909023	318.6	10437189	3658.1	2116531	741.8	7092267	2485.7	1228391	430.5
Expand rows 5 - 14
16	2012	313873685	1217057	387.8	14856	4.7	nan	nan	85141	27.1	355051	113.1	762009	242.8	9001992	2868.0	2109932	672.2	6168874	1965.4	723186	230.4
17	2013	316497531	1168298	369.1	14319	4.5	113695	35.9	82109	25.9	345093	109.0	726777	229.6	8651892	2733.6	1932139	610.5	6019465	1901.9	700288	221.3
18	2014	318907401	1153022	361.6	14164	4.4	118027	37.0	84864	26.6	322905	101.3	731089	229.2	8209010	2574.1	1713153	537.2	5809054	1821.5	686803	215.4
19	2015	320896618	1199310	373.7	15883	4.9	126134	39.3	91261	28.4	328109	102.2	764057	238.1	8024115	2500.5	1587564	494.7	5723488	1783.6	713063	222.2
20	2016	323127513	1248185	386.3	17250	5.3	130603	40.4	95730	29.6	332198	102.8	803007	248.5	7919035	2450.7	1515096	468.9	5638455	1745.0	765484	236.9
20 rows × 22 columns

# create a plot of crime over time to see which types of crime are commited most often df1.plot(kind='line',x="Year",y=["Violent Crime","Murder and nonnegligent manslaughter","Rape Legacy def", "Robbery","Aggrevated Assult","Property Crime","Burglary", "Larceny-theft", "Motor vehicle theft"]) plt.xlabel("Year") plt.ylabel("Crime") plt.suptitle('Crime rate from 1997 to 2016') plt.legend( ncol=1, loc='best');

/opt/venv/lib/python3.7/site-packages/pandas/plotting/_matplotlib/core.py:1192: UserWarning: FixedFormatter should only be used together with FixedLocator
  ax.set_xticklabels(xticklabels)

# create a chart of summary statistics for each column in the data frame df1.describe()

	Populationfloat64	Violent Crimefloat64	Murder and nonnegligent manslaughterfloat64	Rape Legacy deffloat64	Robberyfloat64	Aggrevated Assultfloat64	Property Crimefloat64	Burglaryfloat64	Larceny-theftfloat64	Motor vehicle theftfloat64
count	20	20	20	20	20	20	20	20	20	20
mean	298634769.45	1352037.7	16006.4	90689.95	399833.95	845507.4	9685756.25	2084818.85	6590070.15	1010867.25
std	17103091.16542078	128056.83481670819	1104.9214499349334	4307.024011945335	48106.378214246244	80063.83053171092	989650.207388336	233046.6906413199	572301.2933793818	247842.96380781013
min	267783607	1153022	14164	82109	322905	726777	7919035	1515096	5638455	686803
25%	287309832.75	1240403	15263.25	88329	354974.75	777397.25	9040055.25	2088302.25	6164429.25	735470.25
50%	300509820.5	1387210.5	16092.5	91062	409056.5	853205.5	9950906.5	2153043	6608952.5	1126273.5
75%	312159283.25	1425625.5	16798.5	94378.25	428558.5	895811	10348836.75	2191396.75	6985393	1236357
max	323127513	1636096	18208	96153	498534	1023201	11558475	2460526	7743760	1354189
8 rows × 10 columns

# set the x value to be years and the y value to be property crime df1['x'] = df1["Year"] df1['y'] = df1["Property Crime"]

# using seaborn scatter plot X vs. Y. sns.lmplot('x', 'y', data=df1, fit_reg=False)

/opt/venv/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

# create a density plot using seaborn sns.kdeplot(df1.y)

# this shows another version of the density plot with the histogram in the background sns.distplot(df1.y)

/opt/venv/lib/python3.7/site-packages/seaborn/distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

# rename the variables x being larceny theft and y being property crime df1['x'] = df1["Larceny-theft"] df1['y'] = df1["Property Crime"]

# using seaborn scatter plot X vs. Y. sns.lmplot('x', 'y', data=df1, fit_reg=False)

/opt/venv/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning