import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler, Normalizer, LabelEncoder
from sklearn.model_selection import train_test_split, KFold
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score
import matplotlib.pyplot as plt

# -------------------------------------------------------
# a. Đọc dữ liệu và chuẩn hóa
# -------------------------------------------------------
df = pd.read_csv("wine.csv")

# Giả sử cột class là cột cuối
class_col = df.columns[-1]

# Chuẩn hóa 4 cột đầu về [0,10]
scaler = MinMaxScaler(feature_range=(0, 10))
df.iloc[:, 0:4] = scaler.fit_transform(df.iloc[:, 0:4])

# Chuẩn hóa các cột còn lại trừ cột class
norm = Normalizer()
cols_to_norm = df.columns[4:-1]
df[cols_to_norm] = norm.fit_transform(df[cols_to_norm])

# Mã hóa cột class
le = LabelEncoder()
df[class_col] = le.fit_transform(df[class_col])

print("Dữ liệu sau chuẩn hóa:")
print(df.head())

# -------------------------------------------------------
# b. Biến đổi cosine cho 5 dòng đầu
# -------------------------------------------------------
print("\n--- Biến đổi cosine thuận (5 dòng đầu) ---")
cos_forward = np.cos(df.iloc[0:5, :-1])
print(cos_forward)

print("\n--- Biến đổi cosine nghịch (arccos) ---")
cos_inverse = np.arccos(np.clip(cos_forward, -1, 1))
print(cos_inverse)

# -------------------------------------------------------
# c. Chia dữ liệu 97% train, 3% test
# -------------------------------------------------------
X = df.drop(class_col, axis=1).values
y = df[class_col].values

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.03, random_state=42
)

# -------------------------------------------------------
# d. Tạo KFold 10
# -------------------------------------------------------
kf = KFold(n_splits=10, shuffle=True, random_state=42)

# -------------------------------------------------------
# e. SVM 10-fold
# -------------------------------------------------------
svm_acc = []
svm_pre = []
svm_rec = []

for train_idx, test_idx in kf.split(X_train):
    Xtr, Xte = X_train[train_idx], X_train[test_idx]
    ytr, yte = y_train[train_idx], y_train[test_idx]

    model_svm = SVC()
    model_svm.fit(Xtr, ytr)
    pred = model_svm.predict(Xte)

    svm_acc.append(accuracy_score(yte, pred))
    svm_pre.append(precision_score(yte, pred, average='macro'))
    svm_rec.append(recall_score(yte, pred, average='macro'))

# -------------------------------------------------------
# f. Logistic Regression 10-fold
# -------------------------------------------------------
log_acc = []
log_pre = []
log_rec = []

for train_idx, test_idx in kf.split(X_train):
    Xtr, Xte = X_train[train_idx], X_train[test_idx]
    ytr, yte = y_train[train_idx], y_train[test_idx]

    model_log = LogisticRegression(max_iter=1000)
    model_log.fit(Xtr, ytr)
    pred = model_log.predict(Xte)

    log_acc.append(accuracy_score(yte, pred))
    log_pre.append(precision_score(yte, pred, average='macro'))
    log_rec.append(recall_score(yte, pred, average='macro'))

# -------------------------------------------------------
# g. Vẽ đồ thị
# -------------------------------------------------------

plt.figure(figsize=(10,5))
plt.plot(svm_acc, label="SVM Accuracy")
plt.plot(log_acc, label="Logistic Accuracy")
plt.title("Accuracy qua 10-fold")
plt.legend()
plt.show()

plt.figure(figsize=(10,5))
plt.plot(svm_pre, label="SVM Precision")
plt.plot(log_pre, label="Logistic Precision")
plt.title("Precision qua 10-fold")
plt.legend()
plt.show()

plt.figure(figsize=(10,5))
plt.plot(svm_rec, label="SVM Recall")
plt.plot(log_rec, label="Logistic Recall")
plt.title("Recall qua 10-fold")
plt.legend()
plt.show()

print("\n===== KẾT QUẢ TRUNG BÌNH =====")
print("SVM:", np.mean(svm_acc), np.mean(svm_pre), np.mean(svm_rec))
print("Logistic:", np.mean(log_acc), np.mean(log_pre), np.mean(log_rec))