Python 데이터 분석
NaiveBayes 분류모델 - GaussanNB 예제
코딩탕탕
2022. 11. 24. 18:14
<작성자 코드>
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
from sklearn import metrics
from sklearn.preprocessing import LabelEncoder
from xgboost import plot_importance
import matplotlib.pyplot as plt
import xgboost as xgb
df = pd.read_csv('../testdata/mushrooms.csv')
print(df.head(3))
print(df.info())
le = LabelEncoder() # for 문으로 각 칼럼들을 넣어 인코딩하였다.
for col in df.columns:
df[col] = le.fit_transform(df[col])
print(df.head(3))
x = df.drop(columns = ['class'])
y = df['class']
print(x[:3])
print(y[:3])
# 8 : 2 split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 1)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape) # (6499, 22) (1625, 22) (6499,) (1625,)
# 주요 변수 모델링 및 시각화
model = xgb.XGBClassifier(booster = 'gbtree', max_depth = 6, n_estimators=500 ).fit(x_train, y_train)
pred = model.predict(x_test)
fig, ax = plt.subplots(figsize=(10, 12))
plot_importance(model, ax = ax)
plt.show()
features = df[['spore-print-color', 'odor', 'gill-size', 'cap-color', 'population']]
labels = df['class']
# 8 : 2 split
x_train, x_test, y_train, y_test = train_test_split(features, labels, test_size = 0.2, random_state = 1)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape) # (6499, 22) (1625, 22) (6499,) (1625,)
# model
gmodel = GaussianNB()
gmodel.fit(x_train, y_train)
pred = gmodel.predict(x_test)
print('예측값 :', pred[:10])
print('실제값 :', y_test[:10].values)
acc = sum(y_test == pred) / len(pred)
print('acc :', acc)
print('acc :', accuracy_score(y_test, pred))
# kfold
from sklearn import model_selection
cross_val = model_selection.cross_val_score(gmodel, x, y, cv = 5)
print('교차 검증 :', cross_val)
print('교차 검증 평균값 :', cross_val.mean())
<console>
class cap-shape cap-surface ... spore-print-color population habitat
0 p x s ... k s u
1 e x s ... n n g
2 e b s ... n n m
[3 rows x 23 columns]
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8124 entries, 0 to 8123
Data columns (total 23 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 class 8124 non-null object
1 cap-shape 8124 non-null object
2 cap-surface 8124 non-null object
3 cap-color 8124 non-null object
4 bruises 8124 non-null object
5 odor 8124 non-null object
6 gill-attachment 8124 non-null object
7 gill-spacing 8124 non-null object
8 gill-size 8124 non-null object
9 gill-color 8124 non-null object
10 stalk-shape 8124 non-null object
11 stalk-root 8124 non-null object
12 stalk-surface-above-ring 8124 non-null object
13 stalk-surface-below-ring 8124 non-null object
14 stalk-color-above-ring 8124 non-null object
15 stalk-color-below-ring 8124 non-null object
16 veil-type 8124 non-null object
17 veil-color 8124 non-null object
18 ring-number 8124 non-null object
19 ring-type 8124 non-null object
20 spore-print-color 8124 non-null object
21 population 8124 non-null object
22 habitat 8124 non-null object
dtypes: object(23)
memory usage: 1.4+ MB
None
class cap-shape cap-surface ... spore-print-color population habitat
0 1 5 2 ... 2 3 5
1 0 5 2 ... 3 2 1
2 0 0 2 ... 3 2 3
[3 rows x 23 columns]
cap-shape cap-surface cap-color ... spore-print-color population habitat
0 5 2 4 ... 2 3 5
1 5 2 9 ... 3 2 1
2 0 2 8 ... 3 2 3
[3 rows x 22 columns]
0 1
1 0
2 0
Name: class, dtype: int32
(6499, 22) (1625, 22) (6499,) (1625,)
(6499, 5) (1625, 5) (6499,) (1625,)
예측값 : [0 1 1 1 1 1 1 0 0 0]
실제값 : [0 1 1 1 0 1 1 0 1 1]
acc : 0.7341538461538462
acc : 0.7341538461538462
교차 검증 : [0.72923077 0.96123077 0.79261538 0.65230769 0.49445813]
교차 검증 평균값 : 0.7259685486926866
