Today, through Starford machine learning courseware, the next Naive Bayes algorithm is reviewed, and several key points of knowledge are recorded as follows:
The derivation process of 1.Naive Bayes formula
2. Calculation of classification accuracy rate
(1) Harmonic average (harmonic mean)
The harmonic mean is calculated by calculating the average velocity at the same distance but not at the same speed, for example, a distance of 60 km/h and a second half speed of 30 km (two distances equal), the average speed is 40 km/h of the harmonic average speed. Or calculate the average resistance of two shunt resistors.
(2) Laplace Smoothing for Naive Bayes
(3) The classification accuracy rate is f-measure. Its essence is the harmonic average.
Relive naive Bayes