Machine_Learning_Classification-Clustering

Machine Learning Programming Homework 1~2, Department of Software, Gachon Univ, South Korea. (2021 fall semester)

Preprocessing

Preprocessing(dataset, encode_list, scale_list)

: Apply data preprocessing(scaling & encoding) to dataset

parameters:
dataset : dataframe.
encode_list : list to encode feature
scale_list : list to scale feature

return:
dictionary to dataframe

Examples

//classification
train = Preprocessing(train, ["Sex"], ["Pclass", "Age", "SibSp", "Parch", "Fare"])

//clustering
pre_feature = Preprocessing(dataset, ["ocean_proximity"], ["longitude", "latitude", "housing_median_age", "total_rooms", "population", "households", "median_income"])

reference : https://github.com/catsaveearth/scale_encode_combination

Classification

Data load -> data preprocessing -> model training -> check result

model:

1. DecisionTreeClassifier (entropy)
   
2. Support vector machine (SVC)
   
3. GaussianNB
   
   

Clustering

Data load -> data preprocessing -> model training -> check result

model:

1. k-mean
   
2. EM (GaussianMixture)
   
3. Clarans
   
4. DBSCAN
   
5. Meanshift