Project 2 Data Mining Part 1

Project 2 Data Mining Part 1

• 1.
  Project II Data Mininga Mushroom Dataset Group 1 Raymond Borges Jarilyn Hernandez
• 2.
  The Mushroom Dataset DataSet Number of Multivariate 8124 Area: Life Characteristics: Instances: Attribute Number of Date Categorical 22 1987 Characteristics: Attributes: Donated: This data set includes descriptions of hypothetical samples corresponding to 23 species of gilled mushrooms in the Agaricus and Lepiota Family. Each species is identified as definitely edible, definitely poisonous, or of unknown edibility and not recommended. This latter class was combined with the poisonous one.
• 3.
  Mushroom Dataset  22Independent attributes  1 Class Attribute (Can you eat it?) Edible(4,208)51.8% Poisonous(3,916)48.2%
• 4.
  Mushroom Dataset 22 AttributesTotal 18 Intrinsically on Mushroom 4 Others 1 Habitat 1 Population 1 Bruises 1 Odor
• 5.
  Odor attribute, 1RLearner The Simplest Rule 98.52% Acc. A = almond N = none C = creosote P = pungent F = foul S = spicy L = anise Y = fishy M = musty a c f l m n p s y
• 6.
  J48 Tree 100% E = Edible Classification P = Poisonous E P P E P P P P almond creosote foul anise musty none pungent spicy fishy E E E E P E E E black brown buff chocolate green orange purple white yellow E P E narrow broad close crowded distant E P E E E E abundant clustered numerous scattered several solitary
• 7.
  Simplest rule-set (Benchmark) Theseare Poisonous 1. Odor = not almond or anise or none (120 poisonous cases missed, 98.52% accuracy) 2. Spore-print-color =green (48 cases missed, 99.41% accuracy) 3. Odor=none and stalk-surface-below-ring = scaly and stalk-color-above-ring= not brown (8 cases missed, 99.90% accuracy) 4. Habitat= leaves and cap-color=white 4. May also be population=clustered and cap-color=white (100% accuracy)
• 8.
  Habitat Insights Waste issafe but stay away from paths Woods Grasses Leaves Meadows Paths Urban Waste
• 9.
  Population Insights Mushrooms travel safer in groups Abundant Clustered Numerous Scattered Several Solitary
• 10.
  Information  Knowledge Population Data %Rates vs. Mushrooms 120.00% 100.00% 80.00% 60.00% 40.00% 20.00% Abundant Clustered Numerous Scattered Several Solitary 0.00% % Poisonous % Edible
• 11.
  Poisonous/Edible Ratio vs. MushroomPopulation Density 300.00% 250.00% several Poisonous/Edible Ratio 200.00% 150.00% 100.00% 50.00% solitary scattered clustered 0.00% numerous abundant 0 1 2 3 4 5 6 7 -50.00% Mushroom Density
• 12.
  Conclusions  If it stinks don’t eat it, 98.52% accuracy  Ifit doesn’t stink and it’s spore color is not green then you have a 99.41% chance of survival  Odor and spore color may be the best attributes statistically but not in the field
• 13.
  Future Work  Use more easily identified attributes to classify mushrooms to produce a method of easier visual classification  Eliminate nonvisual attributes Focus on visual-queue attributes, e.g. habitat, population, cap and stalk  Compare the two methods