hyb <- read.csv(file.choose()) # choose hybrid.csv}1 Data Types and Structures
1.1 Data in R
In R, you can work with many different types of data including but not limited to data frames, lists, vectors, and matrices. For the purposes of our course, we are going to be working mostly with data frames. A data frame is a tabular data structure with observations in the rows and variables in the columns. Each of these variables might be stored within the data frame as different levels of data. There are a few tricks in R to identify and change the level of data.
Follow each chunk to examine the a data set.
First, you can take a look at the data set using a few different functions. Follow the logic in the next chunk to inspect the data.
hyb # call the object you created to see the whole data set. id model year msrp msrp_dollars accel_rate
1 1 Prius (1st gen.) 1997 24509.74 $24,509.74 7.46
2 2 Tino Hybrid 2000 35354.97 $35,354.97 8.20
3 3 Prius (2nd gen.) 2000 26832.25 $26,832.25 7.97
4 4 Insight 2000 18936.41 $18,936.41 9.52
5 5 Civic Hybrid 1st gen. 2001 25833.38 $25,833.38 7.04
6 6 Insight 2001 19036.71 $19,036.71 9.52
7 7 Insight 2002 19137.01 $19,137.01 9.71
8 8 Alphard Hybrid 2003 38084.77 $38,084.77 8.33
9 9 Insight 2003 19137.01 $19,137.01 9.52
10 10 Civic Hybrid 2003 14071.92 $14,071.92 8.62
11 11 Escape Hybrid 2004 36676.10 $36,676.10 10.32
12 12 Insight 2004 19237.31 $19,237.31 9.35
13 13 Prius 2004 20355.64 $20,355.64 9.90
14 14 Silverado 15 Hybrid 2WD 2004 30089.64 $30,089.64 9.09
15 15 Lexus RX400h 2005 58521.14 $58,521.14 12.76
16 16 Civic Hybrid 2nd gen. 2005 26354.44 $26,354.44 7.63
17 17 Highlander Hybrid 2005 29186.21 $29,186.21 12.76
18 18 Insight 2005 19387.76 $19,387.76 9.71
19 19 Civic Hybrid 2005 18236.33 $18,236.33 8.26
20 20 Escape Hybrid 2WD 2005 19322.56 $19,322.56 9.52
21 21 Accord Hybrid 2005 16343.69 $16,343.69 14.93
22 22 Silverado 15 Hybrid 2WD 2005 32647.26 $32,647.26 11.11
23 23 Mercury Mariner Hybrid 2006 34772.40 $34,772.40 8.98
24 24 Camry Hybrid 2006 29853.25 $29,853.25 11.28
25 25 Lexus GS450h 2006 64547.56 $64,547.56 18.65
26 26 Estima Hybrid 2006 36012.70 $36,012.70 9.26
27 27 Altima Hybrid 2006 29524.75 $29,524.75 13.29
28 28 Chevrolet Tahoe Hybrid 2007 42924.35 $42,924.35 10.91
29 29 Kluger Hybrid 2007 46229.48 $46,229.48 12.76
30 30 Lexus LS600h/hL 2007 118543.60 $118,543.60 17.54
31 31 Tribute Hybrid 2007 24823.83 $24,823.83 11.28
32 32 GMC Yukon Hybrid 2007 57094.81 $57,094.81 12.28
33 33 Aura Hybrid 2007 22110.87 $22,110.87 10.87
34 34 Vue Hybrid 2007 22938.33 $22,938.33 10.75
35 35 Silverado 15 Hybrid 2WD 2007 34653.23 $34,653.23 11.49
36 36 Crown Hybrid 2008 62290.38 $62,290.38 8.70
37 37 Cadillac Escalade Hybrid 2008 78932.81 $78,932.81 9.09
38 38 F3DM 2008 23744.06 $23,744.06 9.52
39 39 Altima Hybrid 2008 18675.63 $18,675.63 13.70
40 40 A5 BSG 2009 11849.43 $11,849.43 7.87
41 41 Lexus RX450h 2009 46233.36 $46,233.36 13.47
42 42 ML450 Blue HV 2009 60519.83 $60,519.83 12.60
43 43 Prius (3rd gen.) 2009 24641.18 $24,641.18 9.60
44 44 S400 Hybrid/Hybrid Long 2009 96208.93 $96,208.93 13.89
45 45 Mercury Milan Hybrid 2009 30522.57 $30,522.57 11.55
46 46 Lexus HS250h 2009 38478.15 $38,478.15 11.55
47 47 Avante/Elantra LPI 2009 21872.71 $21,872.71 10.21
48 48 ActiveHybrid X6 2009 97237.90 $97,237.90 17.96
49 49 SAI 2009 39172.44 $39,172.44 11.55
50 50 Malibu Hybrid 2009 24768.79 $24,768.79 9.09
51 51 Vue Hybrid 2009 26408.67 $26,408.67 13.70
52 52 Aspen HEV 2009 44903.77 $44,903.77 13.51
53 53 Durango 2009 41033.24 $41,033.24 8.33
54 54 Auris HSD 2010 35787.29 $35,787.29 8.85
55 55 CR-Z 2010 21435.54 $21,435.54 9.24
56 56 F3DM PHEV 2010 23124.59 $23,124.59 9.24
57 57 Touareg HV 2010 64198.95 $64,198.95 15.38
58 58 Audi Q5 2010 37510.86 $37,510.86 14.08
59 59 Jeep Patriot EV 2010 17045.06 $17,045.06 12.05
60 60 Besturn B50 2010 14586.61 $14,586.61 7.14
61 61 ActiveHybrid 7 Series 2010 104300.43 $104,300.43 20.41
62 62 Lincoln MKZ Hybrid 2010 37036.64 $37,036.64 11.15
63 63 Fit/Jazz Hybrid 2010 16911.85 $16,911.85 8.26
64 64 Sonata HV 2010 28287.66 $28,287.66 14.70
65 65 Cayenne S HV 2010 73183.47 $73,183.47 14.71
66 66 Insight 2010 19859.16 $19,859.16 9.17
67 67 Fuga Hybrid/Infiniti M35h 2010 70157.02 $70,157.02 18.65
68 68 Chevrolet Volt 2010 42924.35 $42,924.35 10.78
69 69 Tribute Hybrid 4WD 2010 27968.32 $27,968.32 12.35
70 70 Fusion Hybrid FWD 2010 28033.51 $28,033.51 11.49
71 71 HS 250h 2010 34753.53 $34,753.53 11.76
72 72 Mariner Hybrid FWD 2010 30194.95 $30,194.95 11.63
73 73 RX 450h 2010 42812.54 $42,812.54 13.89
74 74 ML450 Hybrid 4natic 2010 55164.33 $55,164.33 12.99
75 75 Silverado 15 Hybrid 2WD 2010 38454.56 $38,454.56 11.76
76 76 S400 Hybrid 2010 88212.78 $88,212.78 12.99
77 77 Aqua 2011 22850.87 $22,850.87 9.35
78 78 Lexus CT200h 2011 30082.16 $30,082.16 9.71
79 79 Civic Hybrid 3rd gen 2011 24999.59 $24,999.59 9.60
80 80 Prius alpha (V) 2011 30588.35 $30,588.35 10.00
81 81 3008 Hybrid4 2011 45101.54 $45,101.54 11.36
82 82 Fit Shuttle Hybrid 2011 16394.36 $16,394.36 7.52
83 83 Buick Regal eAssist 2011 27948.93 $27,948.93 12.05
84 84 Prius V 2011 27272.28 $27,272.28 9.51
85 85 Freed/Freed Spike Hybrid 2011 27972.07 $27,972.07 6.29
86 86 Optima K5 HV 2011 26549.16 $26,549.16 10.54
87 87 Escape Hybrid FWD 2011 30661.34 $30,661.34 12.35
88 88 Insight 2011 18254.38 $18,254.38 9.52
89 89 MKZ Hybrid FWD 2011 34748.52 $34,748.52 11.49
90 90 CR-Z 2011 19402.80 $19,402.80 12.20
91 91 Sonata Hybrid 2011 25872.07 $25,872.07 11.90
92 92 Camry Hybrid 2011 27130.82 $27,130.82 13.89
93 93 Tribute Hybrid 2WD 2011 26213.09 $26,213.09 12.50
94 94 Cayenne S Hybrid 2011 67902.28 $67,902.28 18.52
95 95 Touareg Hybrid 2011 50149.39 $50,149.39 16.13
96 96 ActiveHybrid 7i 2011 102605.66 $102,605.66 18.18
97 97 Prius C 2012 19006.62 $19,006.62 9.35
98 98 Prius PHV 2012 32095.61 $32,095.61 8.82
99 99 Ampera 2012 31739.55 $31,739.55 11.11
100 100 ActiveHybrid 5 Series 2012 62180.23 $62,180.23 16.67
101 101 Lexus GS450h 2012 59126.14 $59,126.14 16.95
102 102 Insight 2012 18555.28 $18,555.28 9.42
103 103 Chevrolet Volt 2012 39261.96 $39,261.96 11.11
104 104 Camry Hybrid LE 2012 26067.66 $26,067.66 13.16
105 105 MKZ Hybrid FWD 2012 34858.84 $34,858.84 11.49
106 106 M35h 2012 53860.45 $53,860.45 19.23
107 107 LaCrosse eAssist 2012 30049.52 $30,049.52 11.36
108 108 ActiveHybrid 5 Series 2012 61132.11 $61,132.11 17.54
109 109 Panamera S Hybrid 2012 95283.85 $95,283.85 17.54
110 110 Yukon 1500 Hybrid 2WD 2012 52626.77 $52,626.77 13.50
111 111 Prius C 2013 19080.00 $19,080.00 8.70
112 112 Jetta Hybrid 2013 24995.00 $24,995.00 12.66
113 113 Civic Hybrid 2013 24360.00 $24,360.00 10.20
114 114 Prius 2013 24200.00 $24,200.00 10.20
115 115 Fusion Hybrid FWD 2013 27200.00 $27,200.00 11.72
116 116 C-Max Hybrid FWD 2013 25200.00 $25,200.00 12.35
117 117 Insight 2013 18600.00 $18,600.00 11.76
118 118 Camry Hybrid LE 2013 26140.00 $26,140.00 13.51
119 119 Camry Hybrid LXLE 2013 27670.00 $27,670.00 13.33
120 120 Sonata Hybrid 2013 25650.00 $25,650.00 11.76
121 121 Optima Hybrid 2013 25900.00 $25,900.00 11.63
122 122 Sonata Hybrid Limited 2013 30550.00 $30,550.00 11.76
123 123 Optima Hybrid EX 2013 31950.00 $31,950.00 11.36
124 124 Malibu eAssist 2013 24985.00 $24,985.00 11.49
125 125 LaCrosse eAssist 2013 31660.00 $31,660.00 11.36
126 126 Regal eAssist 2013 29015.00 $29,015.00 12.20
127 127 RX 450h 2013 46310.00 $46,310.00 12.99
128 128 Highlander Hybrid 4WD 2013 40170.00 $40,170.00 13.89
129 129 Q5 Hybrid 2013 50900.00 $50,900.00 14.71
130 130 Cayenne S Hybrid 2013 69850.00 $69,850.00 16.39
131 131 Touareg Hybrid 2013 62575.00 $62,575.00 16.13
132 132 Escalade Hybrid 2WD 2013 74425.00 $74,425.00 11.63
133 133 Tahoe Hybrid 2WD 2013 53620.00 $53,620.00 11.90
134 134 Yukon 1500 Hybrid 2WD 2013 54145.00 $54,145.00 11.88
135 135 Yukon 1500 Hybrid 4WD 2013 61960.00 $61,960.00 13.33
136 136 CR-Z 2013 19975.00 $19,975.00 11.11
137 137 MKZ Hybrid FWD 2013 35925.00 $35,925.00 14.03
138 138 CT 200h 2013 32050.00 $32,050.00 10.31
139 139 ES 300h 2013 39250.00 $39,250.00 12.35
140 140 ILX Hybrid 2013 28900.00 $28,900.00 9.26
141 141 ActiveHybrid 3 2013 49650.00 $49,650.00 14.93
142 142 Silverado 15 Hybrid 2WD 2013 41135.00 $41,135.00 12.35
143 143 Sierra 15 Hybrid 2WD 2013 41555.00 $41,555.00 10.00
144 144 GS 450h 2013 59450.00 $59,450.00 16.67
145 145 M35h 2013 54750.00 $54,750.00 19.61
146 146 E400 Hybrid 2013 55800.00 $55,800.00 14.93
147 147 ActiveHybrid 5 Series 2013 61400.00 $61,400.00 12.99
148 148 ActiveHybrid 7L 2013 84300.00 $84,300.00 18.18
149 149 Panamera S Hybrid 2013 96150.00 $96,150.00 18.52
150 150 S400 Hybrid 2013 92350.00 $92,350.00 13.89
151 151 Prius Plug-in Hybrid 2013 32000.00 $32,000.00 9.17
152 152 C-Max Energi Plug-in Hybrid 2013 32950.00 $32,950.00 11.76
153 153 Fusion Energi Plug-in Hybrid 2013 38700.00 $38,700.00 11.76
154 154 Chevrolet Volt 2013 39145.00 $39,145.00 11.11
mpg mpg_mpge class
1 41.26 41.26 C
2 54.10 54.10 C
3 45.23 45.23 C
4 53.00 53.00 TS
5 47.04 47.04 C
6 53.00 53.00 TS
7 53.00 53.00 TS
8 40.46 40.46 MV
9 53.00 53.00 TS
10 41.00 41.00 C
11 31.99 31.99 SUV
12 52.00 52.00 TS
13 46.00 46.00 M
14 17.00 17.00 PT
15 28.23 28.23 SUV
16 39.99 39.99 C
17 29.40 29.40 SUV
18 52.00 52.00 TS
19 41.00 41.00 C
20 29.00 29.00 SUV
21 28.00 28.00 M
22 17.00 17.00 PT
23 32.93 32.93 SUV
24 33.64 33.64 M
25 33.40 33.40 M
26 47.04 47.04 MV
27 32.93 32.93 M
28 22.35 22.35 SUV
29 25.87 25.87 SUV
30 21.00 21.00 M
31 31.75 31.75 SUV
32 21.78 21.78 SUV
33 27.00 27.00 M
34 26.00 26.00 SUV
35 17.00 17.00 PT
36 37.16 37.16 M
37 22.35 22.35 SUV
38 30.11 85.00 M
39 34.00 34.00 M
40 35.28 35.28 M
41 31.99 31.99 SUV
42 23.99 23.99 SUV
43 47.98 47.98 C
44 26.34 26.34 L
45 40.69 40.69 M
46 54.10 54.10 C
47 41.87 41.87 C
48 18.82 18.82 SUV
49 54.10 54.10 M
50 29.00 29.00 M
51 28.00 28.00 SUV
52 21.00 21.00 SUV
53 21.00 21.00 SUV
54 68.21 68.21 C
55 37.00 37.00 TS
56 30.15 85.00 M
57 28.70 28.70 SUV
58 33.64 33.64 SUV
59 29.40 38.00 SUV
60 31.28 31.28 M
61 22.11 22.11 L
62 37.63 37.63 M
63 30.00 30.00 C
64 37.00 37.00 M
65 26.11 26.11 SUV
66 41.00 41.00 C
67 33.64 33.64 M
68 35.00 93.00 C
69 29.00 29.00 SUV
70 39.00 39.00 M
71 35.00 35.00 C
72 32.00 32.00 SUV
73 30.00 30.00 SUV
74 22.00 22.00 SUV
75 22.00 22.00 PT
76 21.00 21.00 L
77 50.00 50.00 C
78 42.00 42.00 C
79 44.36 44.36 C
80 72.92 72.92 M
81 61.16 61.16 C
82 58.80 58.80 MV
83 25.99 25.99 M
84 32.93 32.93 M
85 50.81 50.81 MV
86 36.00 36.00 M
87 32.00 32.00 SUV
88 41.00 41.00 C
89 39.00 39.00 M
90 37.00 37.00 TS
91 36.00 36.00 M
92 33.00 33.00 M
93 32.00 32.00 SUV
94 21.00 21.00 SUV
95 21.00 21.00 SUV
96 20.00 20.00 M
97 50.00 50.00 C
98 50.00 95.00 M
99 37.00 98.00 C
100 26.00 26.00 M
101 31.00 31.00 M
102 42.00 42.00 C
103 37.00 94.00 C
104 41.00 41.00 M
105 39.00 39.00 M
106 29.00 29.00 M
107 29.00 29.00 M
108 26.00 26.00 M
109 25.00 25.00 L
110 21.00 21.00 SUV
111 50.00 50.00 C
112 45.00 45.00 C
113 44.00 44.00 C
114 50.00 50.00 M
115 47.00 47.00 M
116 43.00 43.00 L
117 42.00 42.00 C
118 41.00 41.00 M
119 40.00 40.00 M
120 38.00 38.00 M
121 38.00 38.00 M
122 37.00 37.00 M
123 37.00 37.00 M
124 29.00 29.00 M
125 29.00 29.00 M
126 29.00 29.00 M
127 30.00 30.00 SUV
128 28.00 28.00 SUV
129 26.00 26.00 SUV
130 21.00 21.00 SUV
131 21.00 21.00 SUV
132 21.00 21.00 SUV
133 21.00 21.00 SUV
134 21.00 21.00 SUV
135 21.00 21.00 SUV
136 37.00 37.00 TS
137 45.00 45.00 M
138 42.00 42.00 C
139 40.00 40.00 M
140 38.00 38.00 C
141 28.00 28.00 C
142 21.00 21.00 PT
143 21.00 21.00 PT
144 31.00 31.00 M
145 29.00 29.00 M
146 26.00 26.00 M
147 26.00 26.00 M
148 25.00 25.00 L
149 25.00 25.00 L
150 21.00 21.00 L
151 50.00 95.00 M
152 43.00 100.00 M
153 43.00 100.00 M
154 37.00 98.00 Chead(hyb, 5) # Take a look at the first 5 observations in the set (you can set the number) id model year msrp msrp_dollars accel_rate mpg mpg_mpge
1 1 Prius (1st gen.) 1997 24509.74 $24,509.74 7.46 41.26 41.26
2 2 Tino Hybrid 2000 35354.97 $35,354.97 8.20 54.10 54.10
3 3 Prius (2nd gen.) 2000 26832.25 $26,832.25 7.97 45.23 45.23
4 4 Insight 2000 18936.41 $18,936.41 9.52 53.00 53.00
5 5 Civic Hybrid 1st gen. 2001 25833.38 $25,833.38 7.04 47.04 47.04
class
1 C
2 C
3 C
4 TS
5 Ctail(hyb, 10) # Look at the last 10 observations (you can set the number) id model year msrp msrp_dollars accel_rate mpg
145 145 M35h 2013 54750 $54,750.00 19.61 29
146 146 E400 Hybrid 2013 55800 $55,800.00 14.93 26
147 147 ActiveHybrid 5 Series 2013 61400 $61,400.00 12.99 26
148 148 ActiveHybrid 7L 2013 84300 $84,300.00 18.18 25
149 149 Panamera S Hybrid 2013 96150 $96,150.00 18.52 25
150 150 S400 Hybrid 2013 92350 $92,350.00 13.89 21
151 151 Prius Plug-in Hybrid 2013 32000 $32,000.00 9.17 50
152 152 C-Max Energi Plug-in Hybrid 2013 32950 $32,950.00 11.76 43
153 153 Fusion Energi Plug-in Hybrid 2013 38700 $38,700.00 11.76 43
154 154 Chevrolet Volt 2013 39145 $39,145.00 11.11 37
mpg_mpge class
145 29 M
146 26 M
147 26 M
148 25 L
149 25 L
150 21 L
151 95 M
152 100 M
153 100 M
154 98 CSo, we have quite a few numeric and categorical variables here. We need to know how each of these variables are stored in this data set so we know how to work with them. The following chunk uses the str() function to take a look at how this data set is structured.
str(hyb)'data.frame': 154 obs. of 9 variables:
$ id : int 1 2 3 4 5 6 7 8 9 10 ...
$ model : chr "Prius (1st gen.)" "Tino Hybrid" "Prius (2nd gen.)" "Insight" ...
$ year : int 1997 2000 2000 2000 2001 2001 2002 2003 2003 2003 ...
$ msrp : num 24510 35355 26832 18936 25833 ...
$ msrp_dollars: chr "$24,509.74 " "$35,354.97 " "$26,832.25 " "$18,936.41 " ...
$ accel_rate : num 7.46 8.2 7.97 9.52 7.04 9.52 9.71 8.33 9.52 8.62 ...
$ mpg : num 41.3 54.1 45.2 53 47 ...
$ mpg_mpge : num 41.3 54.1 45.2 53 47 ...
$ class : chr "C" "C" "C" "TS" ...Starting from the top right, we have a data.frame (a type of data structure) that has 154 observations (the rows) with 9 variables (columns). under this line is an explanation of each of the 9 variables. From left to right, we have the name of the variable, the type, then a short example of the data stored therein. For example, we have an ‘id variable’ stored as an integer (int) which. The “model” variable is stored as a character (chr) variable which indicates that it is stored as text (also known as a string). There is one more variable class you should know which is factor. While characters are text, factors are categories with a set number of possible values.
Notice the $? The $ is an operator used in R to access different elements in an object. This comes in handy when we want to work with the data and transform it. For example, we may wish to view certain elements of this data frame. Follow the logic in the following chunk.
class(hyb$id) # identify the class of data using class()[1] "integer"hyb$id_chr <- as.character(hyb$id) # change a variable to a character create a new variable with that.
class(hyb$id_chr)[1] "character"One final thing to note when working with character data is that often you need to convert characters into factors so that R recognises the long list of text as being truly categorical. This actually encodes each unique character as a distinct category recognising all with the same text as sharing a category.
For example, the variable ‘class’ is actually categorical. What type of car it is. It is, however, stored as a character. In order to do anything with this variables (say visualising average cost by each category?), we need to convert this into a factor.
hyb$class <- as.factor(hyb$class)
class(hyb$class)[1] "factor"Keep this trick in your pocket! You are likely going to need this throughout the semester!
1.2 Levels of Data
Within a data set you will encounter different variables that are measures at various levels and using different units of measurement. Let’s say, for example, you have some survey data that asks questions about the respondent’s biological sex, income, and how satisfied they are are work. All of these questions are useful, and can be useful in visualisation. However, there are some visualisations that are more appropriate and useful for some of these more than others. In order to properly visualise data, we need to understand data.
There are two main ‘umbrella’ terms that you can use when talking about data. These are, categorical and numeric. Categorical data, as the name suggests, are measured in buckets or categories while numeric data use units and numbers. There are a few further distinctions you need to understand before these become useful to you.
| Categorical Data |
|---|
Nominal: These are data with distinct labels that have no quantitative difference between one another. E.g. Sex (Male, Female). Race (White, Black, Other). |
Ordinal: These are data with set differences between each response. These are categorical responses that are ranked in a specific order. E.g. Likert Scale (Agree, Neutral, Disagree). |
There are some other variations of categorical data that are sometimes referred to such as dummy variables (true or false, or 0/1). So, an honorable mention goes to dummy variables!!
Categorical data will almost always be stored as characters or factors. Alternatively, you might come across encoded versions of categorical data. For example, male and female may be given a numeric code but, we know this to be categorical. So, you must decide what to do. You may want to convert this to a categorical variable, or simply remember what 1 and 0 mean.
Since there are distinct buckets of information that are stored in categorical data, it is best presented using tables, bar charts or pie charts.
| Numeric Data |
|---|
Interval: Continuous data that do not have a zero point. E.g. Temperature (measured in Farenheit), Time (measured on a 12-hour clock, ACT scores). |
Ratio: Continuous data that have a true zero point. E.g. Earnings (dollar amount), Age (measured in years). |
Numeric data all have equal intervals (i.e. one decimal place, or one year, or one degree) which creates a continuous stream of data.
In R, numeric data is stored as integer (int) or numeric (num). You may come across data that should be numeric but is stored as categorical or perhaps a character.
1.2.1 Activity - Levels of Data
Look at the following examples of questions and, with a partner, decide whether the unit of measurement is nominal, ordinal, interval or ratio.
- Please indicate how much you earn a year from your current job: - $0 - $24,999
- $25,000 - $49,999
- $50,000 - $74,999
- $75,000 - $99,999
- $100,000+How much do you earn at your current job (in USD): _____________
How likely are you to recommend this product?:
- Likely
- Neutral
- Unlikely