import os
import numpy as np
import pandas as pd
import warnings
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' 
warnings.filterwarnings('ignore')

df = pd.read_csv('data/winequalityN.csv')
df.sample(5)

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler


# Prepare the data
df = df.dropna()
df['is_white_wine'] = [1 if typ == 'white' else 0 for typ in df['type']]
df['is_good_wine'] = [1 if quality >= 6 else 0 for quality in df['quality']]
df.drop(['type', 'quality'], axis=1, inplace=True)

# Train/test split
X = df.drop('is_good_wine', axis=1)
y = df['is_good_wine']
X_train, X_test, y_train, y_test = train_test_split(
    X, y, 
    test_size=0.2, random_state=42
)

# Scaling
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

import tensorflow as tf
tf.random.set_seed(42)

cb_checkpoint = tf.keras.callbacks.ModelCheckpoint(
    filepath='checkpoints/model-{epoch:02d}-{val_accuracy:.2f}.hdf5',
    monitor='val_accuracy',
    mode='max',
    save_best_only=True,
    verbose=1
)

cb_reducelr = tf.keras.callbacks.ReduceLROnPlateau(
    monitor='val_loss',
    mode='min',
    factor=0.1,
    patience=10,
    verbose=1,
    min_lr=0.00001
)

cb_earlystop = tf.keras.callbacks.EarlyStopping(
    monitor='val_accuracy',
    mode='max',
    min_delta=0.001,
    patience=10,
    verbose=1
)

cb_csvlogger = tf.keras.callbacks.CSVLogger(
    filename='training_log.csv',
    separator=',',
    append=False
)

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(
    loss=tf.keras.losses.binary_crossentropy,
    optimizer=tf.keras.optimizers.Adam(),
    metrics=[tf.keras.metrics.BinaryAccuracy(name='accuracy')]
)

history = model.fit(
    X_train_scaled, 
    y_train, 
    epochs=1000,
    validation_data=(X_test_scaled, y_test),
    callbacks=[cb_checkpoint, cb_reducelr, cb_earlystop, cb_csvlogger]
)

best_model = tf.keras.models.load_model('checkpoints/model-25-0.80.hdf5')

best_model_preds = np.ravel(best_model.predict_classes(X_test_scaled))
best_model_preds

from sklearn.metrics import accuracy_score

print(accuracy_score(y_test, best_model_preds))