Decision Tree _ Example ) abalone

import pandas as pd
import numpy as np
import seaborn as sns

from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split

from sklearn.tree import DecisionTreeCalssifier, plot_tree
#from sklearn.native_bayes import GaussianNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier

from sklearn.metrics import r2_score, mean_sqaured_error

#from sklearn.model_selection import KFold

#from sklearn.neighbors import KNeighborsClassifier

data = pd.read_csv('C:/Users/ddi05/Class_05/abalone/abalone.data', header=None)
data.head()

< column 1 ~ 7 을 이용하여, 성별 (M, F, I) 를 예측 >

1. column 별 결측치 확인

for i in data :
    #print(i)
    print(i, data[i].isnull().sum())
 
# 0 0
# 1 0
# 2 0
# 3 0
# 4 0
# 5 0
# 6 0
# 7 0
# 8 0

2. LabelEncoding

encoder = LabelEncoder()

data[0] = encoder.fit_transform(data[0])
data

3. MinMaxScaling

print(data[8].unique())
# [15  7  9 10  8 20 16 19 14 11 12 18 13  5  4  6 21 17 22  1  3 26 23 29
#   2 27 25 24]

scaler = MinMaxScaler()

labels = [[1,2,3,4,5,6,7]]
for i in labels :
	data[i] = scaler.fit_transform(data[i])
 
data

4. X, y split / DecisionTree model fit

y = data[0]
X = data[[1,2,3,4,5,6,7,8]]

X_train, y_train, X_test, y_test = train_test_split(X, y, stratify = y, random_state = 10)

dt = DecisionTreeClassifier(max_depth=10)
dt.fit(X_train, y_train)
pred_dt = dt.predict(X_test)

print('train score', dt.score(X_train, y_train))
print('test score', dt.score(X_test, y_test))

5. 여러 분류모델 적합 : DecisionTree, Logistic Reg

models = [DecisionTreeClassifier(max_depth=5), LogisticRegression(solver='liblinear')]
model_names = ['DecisionTree', 'Logistic Reg']

for model, model_name in zip(models, model_names) :
	m = model
    m.fit(X_train, y_train)
    pred = m.predict(X_test)
    
    print('-------', model_name, '--------')
    print('train score', m.score(X_train, y_train))
    print('test score', m.score(X_test, y_test))