import numpy as np
import pandas as pd 

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

df.shape

df.isnull().sum()

df = df.dropna()
df.isnull().sum()

df['type'].value_counts()

df['is_white_wine'] = [1 if typ == 'white' else 0 for typ in df['type']]
df.drop('type', axis=1, inplace=True)

df.head()

df.dtypes

df['quality'].value_counts()

len(df[df['quality'] >= 6]) / len(df)

df['is_good_wine'] = [1 if quality >= 6 else 0 for quality in df['quality']]
df.drop('quality', axis=1, inplace=True)

df.head()

df['is_good_wine'].value_counts()

df.head()

from sklearn.model_selection import 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
)

X_train.shape, X_test.shape

X_train.head()

from sklearn.preprocessing import StandardScaler

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

X_train_scaled[:3]

import tensorflow as tf

tf.random.set_seed(42)

model = tf.keras.Sequential([
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(
    loss=tf.keras.losses.binary_crossentropy,
    optimizer=tf.keras.optimizers.Adam(lr=0.03),
    metrics=[
        tf.keras.metrics.BinaryAccuracy(name='accuracy'),
        tf.keras.metrics.Precision(name='precision'),
        tf.keras.metrics.Recall(name='recall')
    ]
)

history = model.fit(X_train_scaled, y_train, epochs=100)

import matplotlib.pyplot as plt
from matplotlib import rcParams

rcParams['figure.figsize'] = (18, 8)
rcParams['axes.spines.top'] = False
rcParams['axes.spines.right'] = False

plt.plot(np.arange(1, 101), history.history['loss'], label='Loss')
plt.plot(np.arange(1, 101), history.history['accuracy'], label='Accuracy')
plt.plot(np.arange(1, 101), history.history['precision'], label='Precision')
plt.plot(np.arange(1, 101), history.history['recall'], label='Recall')
plt.title('Evaluation metrics', size=20)
plt.xlabel('Epoch', size=14)
plt.legend();

predictions = model.predict(X_test_scaled)
predictions

prediction_classes = [1 if prob > 0.5 else 0 for prob in np.ravel(predictions)]
print(prediction_classes[:20])

loss, accuracy, precision, recall = model.evaluate(X_test_scaled, y_test)
loss, accuracy, precision, recall

from sklearn.metrics import confusion_matrix

print(confusion_matrix(y_test, prediction_classes))

from sklearn.metrics import accuracy_score, precision_score, recall_score

print(f'Accuracy:  {accuracy_score(y_test, prediction_classes):.2f}')
print(f'Precision: {precision_score(y_test, prediction_classes):.2f}')
print(f'Recall:    {recall_score(y_test, prediction_classes):.2f}')