DATA 607 Week 1 - Basic Loading and Transformation
Kavya Beheraj
February 3, 2018
The Mushroom Dataset contains descriptions of hypothetical samples corresponding to 23 species of gilled mushrooms in the Agaricus and Lepiota Family. It includes 8,124 instances and 22 variables, and was published on April 27, 1987.
In this assignment, I studied the Mushrooms dataset, renamed the columns and variables to make it easier to understand, and created subsets of the data to answer a few questions about it.
1. Load in the Mushrooms dataset:
mushroom <- read.table("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data", sep=",")
print(head(mushroom))## V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20
## 1 p x s n t p f c n k e e s s w w p w o p
## 2 e x s y t a f c b k e c s s w w p w o p
## 3 e b s w t l f c b n e c s s w w p w o p
## 4 p x y w t p f c n n e e s s w w p w o p
## 5 e x s g f n f w b k t e s s w w p w o e
## 6 e x y y t a f c b n e c s s w w p w o p
## V21 V22 V23
## 1 k s u
## 2 n n g
## 3 n n m
## 4 k s u
## 5 n a g
## 6 k n g
2. Rename the columns:
names(mushroom) <- c("Class", "Cap-Shape", "Cap-Surface", "Cap-Color", "Bruises", "Odor", "Gill-Attachment", "Gill-Spacing", "Gill-Size", "Gill-Color", "Stalk-Shape", "Stalk-Root", "Stalk-Surface-Above-Ring", "Stalk-Surface-Below-Ring", "Stalk-Color-Above-Ring", "Stalk-Color-Below-Ring", "Veil-Type", "Veil-Color", "Ring-Number", "Ring-Type", "Spore-Print-Color", "Population", "Habitat")
print(head(mushroom))## Class Cap-Shape Cap-Surface Cap-Color Bruises Odor Gill-Attachment
## 1 p x s n t p f
## 2 e x s y t a f
## 3 e b s w t l f
## 4 p x y w t p f
## 5 e x s g f n f
## 6 e x y y t a f
## Gill-Spacing Gill-Size Gill-Color Stalk-Shape Stalk-Root
## 1 c n k e e
## 2 c b k e c
## 3 c b n e c
## 4 c n n e e
## 5 w b k t e
## 6 c b n e c
## Stalk-Surface-Above-Ring Stalk-Surface-Below-Ring Stalk-Color-Above-Ring
## 1 s s w
## 2 s s w
## 3 s s w
## 4 s s w
## 5 s s w
## 6 s s w
## Stalk-Color-Below-Ring Veil-Type Veil-Color Ring-Number Ring-Type
## 1 w p w o p
## 2 w p w o p
## 3 w p w o p
## 4 w p w o p
## 5 w p w o e
## 6 w p w o p
## Spore-Print-Color Population Habitat
## 1 k s u
## 2 n n g
## 3 n n m
## 4 k s u
## 5 n a g
## 6 k n g
3. Rename the variables in each column:
mushroom$Class <- recode(mushroom$Class, e = "edible", p = "poisonous")
mushroom$`Cap-Shape` <- recode(mushroom$`Cap-Shape`,
b = "bell", c = "conical", x = "convex", f = "flat", k = "knobbed", s = "sunken")
mushroom$`Cap-Surface` <- recode(mushroom$`Cap-Surface`, f="fibrous", g="grooves", y="scaly", s="smooth")
mushroom$`Cap-Color` <- recode(mushroom$`Cap-Color`, n = "brown", b = "buff", c = "cinnamon", g = "gray", r = "green", p = "pink", u = "purple", e = "red", w = "white", y = "yellow")
mushroom$Bruises <- recode(mushroom$Bruises, t = "bruises", f = "no-bruises")
mushroom$Odor <- recode(mushroom$Odor, a = 'almond', l = 'anise', c = 'creosote', y = 'fishy', f = 'foul', m = 'musty', n = 'none', p = 'pungent', s = 'spicy')
mushroom$`Gill-Attachment` <- recode(mushroom$`Gill-Attachment`, a = 'attached', d = 'descending', f = 'free', n = 'notched')
mushroom$`Gill-Spacing` <- recode(mushroom$`Gill-Spacing`, c = 'close', w = 'crowded', d = 'distant')
mushroom$`Gill-Size` <- recode(mushroom$`Gill-Size`, b = 'broad', n = 'narrow' )
mushroom$`Gill-Color` <- recode(mushroom$`Gill-Color`, k = 'black', n = 'brown', b = 'buff', h = 'chocolate', g = 'gray', r = 'green', o = 'orange', p = 'pink', u = 'purple', e = 'red', w = 'white', y = 'yellow')
mushroom$`Stalk-Shape` <- recode(mushroom$`Stalk-Shape`, e = 'enlarging', t = 'tapering')
mushroom$`Stalk-Root` <- recode(mushroom$`Stalk-Root`, b = 'bulbous', c = 'club', u = 'cup', e = 'equal', z = 'rhizomorphs', r = 'rooted')
mushroom$`Stalk-Surface-Above-Ring` <- recode(mushroom$`Stalk-Surface-Above-Ring`, f = 'fibrous', y = 'scaly', k = 'silky', s = 'smooth')
mushroom$`Stalk-Surface-Below-Ring` <- recode(mushroom$`Stalk-Surface-Below-Ring`, f = 'fibrous', y = 'scaly', k = 'silky', s = 'smooth')
mushroom$`Stalk-Color-Above-Ring` <- recode(mushroom$`Stalk-Color-Above-Ring`, n = 'brown', b = 'buff', c = 'cinnamon', g = 'gray', o = 'orange', p = 'pink', e = 'red', w = 'white', y = 'yellow')
mushroom$`Stalk-Color-Below-Ring` <- recode(mushroom$`Stalk-Color-Below-Ring`, n = 'brown', b = 'buff', c = 'cinnamon', g = 'gray', o = 'orange', p = 'pink', e = 'red', w = 'white', y = 'yellow')
mushroom$`Veil-Type` <- recode(mushroom$`Veil-Type`, p = 'partial', u = 'universal')
mushroom$`Veil-Color` <- recode(mushroom$`Veil-Color`, n = 'brown', o = 'orange', w = 'white', y = 'yellow')
mushroom$`Ring-Number` <- recode(mushroom$`Ring-Number`, n = 'none', o = 'one', t = 'two')
mushroom$`Ring-Type` <- recode(mushroom$`Ring-Type`, c = 'cobwebby', e = 'evanescent', f = 'flaring', l = 'large', n = 'none', p = 'pendant', s = 'sheathing', z = 'zone')
mushroom$`Spore-Print-Color` <- recode(mushroom$`Spore-Print-Color`, k = 'black', n = 'brown', b = 'buff', h = 'chocolate', r = 'green', o = 'orange', u = 'purple',
w = 'white', y = 'yellow')
mushroom$Population <- recode(mushroom$Population, a = 'abundant', c = 'clustered', n = 'numerous', s = 'scattered', v = 'several', y = 'solitary')
mushroom$Habitat <- recode(mushroom$Habitat, g = 'grasses', l = 'leaves', m = 'meadows', p = 'paths', u = 'urban', w = 'waste', d = 'woods')
summary(mushroom)## Class Cap-Shape Cap-Surface Cap-Color
## edible :4208 bell : 452 fibrous:2320 brown :2284
## poisonous:3916 conical: 4 grooves: 4 gray :1840
## flat :3152 smooth :2556 red :1500
## knobbed: 828 scaly :3244 yellow :1072
## sunken : 32 white :1040
## convex :3656 buff : 168
## (Other): 220
## Bruises Odor Gill-Attachment Gill-Spacing
## no-bruises:4748 none :3528 attached: 210 close :6812
## bruises :3376 foul :2160 free :7914 crowded:1312
## spicy : 576
## fishy : 576
## almond : 400
## anise : 400
## (Other): 484
## Gill-Size Gill-Color Stalk-Shape Stalk-Root
## broad :5612 buff :1728 enlarging:3516 ? :2480
## narrow:2512 pink :1492 tapering :4608 bulbous:3776
## white :1202 club : 556
## brown :1048 equal :1120
## gray : 752 rooted : 192
## chocolate: 732
## (Other) :1170
## Stalk-Surface-Above-Ring Stalk-Surface-Below-Ring Stalk-Color-Above-Ring
## fibrous: 552 fibrous: 600 white :4464
## silky :2372 silky :2304 pink :1872
## smooth :5176 smooth :4936 gray : 576
## scaly : 24 scaly : 284 brown : 448
## buff : 432
## orange : 192
## (Other): 140
## Stalk-Color-Below-Ring Veil-Type Veil-Color Ring-Number
## white :4384 partial:8124 brown : 96 none: 36
## pink :1872 orange: 96 one :7488
## gray : 576 white :7924 two : 600
## brown : 512 yellow: 8
## buff : 432
## orange : 192
## (Other): 156
## Ring-Type Spore-Print-Color Population Habitat
## evanescent:2776 white :2388 abundant : 384 woods :3148
## flaring : 48 brown :1968 clustered: 340 grasses:2148
## large :1296 black :1872 numerous : 400 leaves : 832
## none : 36 chocolate:1632 scattered:1248 meadows: 292
## pendant :3968 green : 72 several :4040 paths :1144
## buff : 48 solitary :1712 urban : 368
## (Other) : 144 waste : 192
4. Question: Where are poisonous mushrooms most commonly found compared to edible mushrooms?
subset1 <- subset(mushroom, Class == "poisonous", select = c(Class, Population, Habitat))
subset2 <- subset(mushroom, Class == "edible", select = c(Class, Population, Habitat))
summary(subset1)## Class Population Habitat
## edible : 0 abundant : 0 woods :1268
## poisonous:3916 clustered: 52 grasses: 740
## numerous : 0 leaves : 592
## scattered: 368 meadows: 36
## several :2848 paths :1008
## solitary : 648 urban : 272
## waste : 0summary(subset2)## Class Population Habitat
## edible :4208 abundant : 384 woods :1880
## poisonous: 0 clustered: 288 grasses:1408
## numerous : 400 leaves : 240
## scattered: 880 meadows: 256
## several :1192 paths : 136
## solitary :1064 urban : 96
## waste : 192The data shows that poisonous mushrooms are most often found in the woods and paths, while edible mushrooms are most found in woods and grasses. Few poisonous mushrooms are found in waste or meadows.
5. Question: What do poisonous mushrooms smell like compared to edible mushrooms?
subset3 <- subset(mushroom, Class == "poisonous", select = c(Class,Odor))
summary(subset3)## Class Odor
## edible : 0 foul :2160
## poisonous:3916 spicy : 576
## fishy : 576
## pungent : 256
## creosote: 192
## none : 120
## (Other) : 36subset4 <- subset(mushroom, Class == "edible", select = c(Class,Odor))
summary(subset4)## Class Odor
## edible :4208 none :3408
## poisonous: 0 almond : 400
## anise : 400
## creosote: 0
## foul : 0
## musty : 0
## (Other) : 0qplot(mushroom$Class, mushroom$Odor, xlab="Type of Mushroom", ylab="Odor", geom="jitter")
The majority of poisonous mushrooms smell foul, while the majority of edible mushrooms don’t smell at all.
6. Question: How does the look of the mushroom’s cap affect its edibility?
subset5 <- subset(mushroom, Class == "poisonous", select = c(Class, `Cap-Shape`, `Cap-Color`, `Cap-Surface`))
subset6 <- subset(mushroom, Class == "edible", select = c(Class, `Cap-Shape`, `Cap-Color`, `Cap-Surface`))
summary(subset5)## Class Cap-Shape Cap-Color Cap-Surface
## edible : 0 bell : 48 brown :1020 fibrous: 760
## poisonous:3916 conical: 4 red : 876 grooves: 4
## flat :1556 gray : 808 smooth :1412
## knobbed: 600 yellow : 672 scaly :1740
## sunken : 0 white : 320
## convex :1708 buff : 120
## (Other): 100summary(subset6)## Class Cap-Shape Cap-Color Cap-Surface
## edible :4208 bell : 404 brown :1264 fibrous:1560
## poisonous: 0 conical: 0 gray :1032 grooves: 0
## flat :1596 white : 720 smooth :1144
## knobbed: 228 red : 624 scaly :1504
## sunken : 32 yellow : 400
## convex :1948 pink : 56
## (Other): 112qplot(mushroom$Class, mushroom$`Cap-Color`, xlab="Type of Mushroom", ylab="Cap Color", geom="jitter")
qplot(mushroom$Class, mushroom$`Cap-Shape`, xlab="Type of Mushroom", ylab="Cap Shape", geom="jitter")
qplot(mushroom$Class, mushroom$`Cap-Surface`, xlab="Type of Mushroom", ylab="Cap Surface", geom="jitter")
It seems difficult to predict a mushroom’s edibility just by looking at its cap. On the whole, both poisonous and edible mushrooms have the same cap color, shape, and surface.
There are a few outliers – for example, only edible mushrooms have a purple or green cap, but those mushrooms are rare in this sample.
My takeaway from this data is that one reliable way to determine a mushroom’s edibility is to smell it. Foul mushrooms are always poisonous.