와인 분류기

import pandas as pd
import matplotlib.pyplot as plt

red_url = "https://raw.githubusercontent.com/PinkWink/ML_tutorial/refs/heads/master/dataset/winequality-red.csv"
white_url = "https://raw.githubusercontent.com/PinkWink/ML_tutorial/refs/heads/master/dataset/winequality-white.csv"

red_wine = pd.read_csv(red_url, sep=";")
white_wine = pd.read_csv(white_url, sep=";")

red_wine.head()

white_wine.head()

white_wine.columns

red_wine['color'] = 1.
white_wine['color'] = 0.

wine = pd.concat([red_wine, white_wine])
wine.info()

wine["quality"].unique()

import plotly.express as px

fig = px.histogram(wine, x="quality")
fig.show()

fig = px.histogram(wine, x="quality", color="color")
fig.show()

from sklearn.model_selection import train_test_split
import numpy as np

# 특성(features)과 타겟(target) 분리
# X: 모델이 학습할 입력 데이터 (color 컬럼을 제외한 모든 특성)
# y: 모델이 예측해야 할 출력 데이터 (color: 레드와인=1, 화이트와인=0)
X = wine.drop(['color'], axis = 1) # axis = 1 (컬럼 삭제), axis = 0 (행 삭제)
y = wine['color']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)

# 학습 데이터의 클래스 분포 확인
# return_counts=True: 각 클래스(0=화이트와인, 1=레드와인)의 개수를 함께 반환
# 클래스 불균형을 확인하여 모델 학습에 영향을 주는지 체크
np.unique(y_train, return_counts = True)

import plotly.graph_objects as go

fig = go.Figure()
fig.add_trace(go.Histogram(x=X_train['quality'], name="Train"))
fig.add_trace(go.Histogram(x=X_test['quality'], name="Test"))
fig.update_layout(barmode='overlay')
fig.update_traces(opacity=0.75)
fig.show()

from sklearn.tree import DecisionTreeClassifier

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=42)
wine_tree.fit(X_train, y_train);

from sklearn.metrics import accuracy_score

y_pred_tr = wine_tree.predict(X_train)
y_pred_test = wine_tree.predict(X_test)

print("Train accuracy: ", accuracy_score(y_train, y_pred_tr))
print("Test accuracy: ", accuracy_score(y_test, y_pred_test))

fig = go.Figure()
fig.add_trace(go.Box(y=X['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X['quality'], name='quality'))
fig.show()

from sklearn.preprocessing import MinMaxScaler, StandardScaler

MMS = MinMaxScaler()
SS = StandardScaler()

MMS.fit(X)
SS.fit(X)

X_ss = SS.transform(X)
X_mms = MMS.transform(X)

X_ss_pd = pd.DataFrame(X_ss, columns=X.columns)
X_mms_pd = pd.DataFrame(X_mms, columns=X.columns)

fig = go.Figure()
fig.add_trace(go.Box(y=X_mms_pd['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X_mms_pd['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X_mms_pd['quality'], name='quality'))
fig.show()

fig = go.Figure()
fig.add_trace(go.Box(y=X_ss_pd['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X_ss_pd['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X_ss_pd['quality'], name='quality'))
fig.show()

X_train, X_test, y_train, y_test = train_test_split(X_mms_pd, y, test_size=0.2, random_state=42, stratify=y)
wine_tree = DecisionTreeClassifier(max_depth=2, random_state=42)
wine_tree.fit(X_train, y_train)

y_pred_tr = wine_tree.predict(X_train)
y_pred_test = wine_tree.predict(X_test)

print("Train accuracy: ", accuracy_score(y_train, y_pred_tr))
print("Test accuracy: ", accuracy_score(y_test, y_pred_test))

X_train, X_test, y_train, y_test = train_test_split(X_ss_pd, y, test_size=0.2, random_state=42, stratify=y)
wine_tree = DecisionTreeClassifier(max_depth=2, random_state=42)
wine_tree.fit(X_train, y_train)

y_pred_tr = wine_tree.predict(X_train)
y_pred_test = wine_tree.predict(X_test)

print("Train accuracy: ", accuracy_score(y_train, y_pred_tr))
print("Test accuracy: ", accuracy_score(y_test, y_pred_test))

import matplotlib.pyplot as plt
from sklearn import tree

fig = plt.figure(figsize=(15, 8))
_ = tree.plot_tree(wine_tree,
        feature_names=list(X_train.columns),
        class_names=['white', 'red'],
        rounded=True,
        filled=True)

dict(zip(X_train.columns, wine_tree.feature_importances_))

wine['taste'] = [1. if grade > 5 else 0. for grade in wine['quality']]
wine.head()

X = wine.drop(['taste', 'quality'], axis = 1)
y = wine['taste']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=42)
wine_tree.fit(X_train, y_train)

y_pred_tr = wine_tree.predict(X_train)
y_pred_test = wine_tree.predict(X_test)

print("Train accuracy: ", accuracy_score(y_train, y_pred_tr))
print("Test accuracy: ", accuracy_score(y_test, y_pred_test))

fig = plt.figure(figsize=(15, 8))
_ = tree.plot_tree(wine_tree,
        feature_names=list(X_train.columns),
        class_names=['Soso', 'Good'],
        rounded=True,
        filled=True)