信息检索与数据挖掘 2019/5/510 朴素贝叶斯分类求解 El:outlook E2:temperature E3:humidity E4:windy C:play yes no yes no yes no yes no yes no sunny 2 3 hot 2 2 high 3 4 false 6 2 9 5 overcast 4 0 mild 4 2 normal 6 1 true 3 3 rainy 3 2 cool 3 1 测试集 outlook sunny Bayes公式：P(cle)→P(c)P(elc) temperature cool e ={el=sunny,e2=cool,e3-high,e4-false) humidity high windy FALSE P(c=yesle)P(c=yes)P(E1lc-yes)P(E2|c-yes)P(E3c-yes)P(E4c-yes) P(c=nole)P(c=no)P(E1c=no)P(E2c=no)P(E3c=no)P(E4c=no) P(c-yesle)*P(E)=9/14×2/9×3/9×3/9×3/9=0.0053 c=no P(c=nole)*P(E)=5/14×3/5×1/5×4/5×3/5=0.0206信息检索与数据挖掘 2019/5/5 10 E1:outlook E2: temperature E3:humidity E4:windy C:play yes no yes no yes no yes no yes no sunny 2 3 hot 2 2 high 3 4 false 6 2 9 5 overcast 4 0 mild 4 2 normal 6 1 true 3 3 rainy 3 2 cool 3 1 P(c=yes|e)*P(E)=9/14×2/9×3/9×3/9×3/9=0.0053 P(c=no|e)*P(E)=5/14×3/5×1/5×4/5×3/5=0.0206 outlook sunny temperature cool humidity high windy FALSE 测试集 Bayes公式：P(c|e)  P(c)P(e|c) e = {e1=sunny, e2=cool, e3=high, e4=false} c=no P(c=yes|e) ∝ P(c=yes)P(E1|c=yes)P(E2|c=yes) P(E3|c=yes) P(E4|c=yes) P(c=no|e) ∝ P(c=no)P(E1|c=no)P(E2|c=no) P(E3|c=no) P(E4|c=no) 朴素贝叶斯分类求解