# Suppress warnings for a cleaner output
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)
 

# Data setup
import pandas as pd
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv'
df = pd.read_csv(url, sep=';')
print(df.shape)
print(df.head(3))

# Checking for missing data
df.isnull().sum()

# Basic data statistics
df.describe()

# Show all column names
print(df.columns.tolist())

# Bar plot of quality scores distribution
import matplotlib.pyplot as plt
df['quality'].value_counts().sort_index().plot(kind='bar', color='skyblue')
plt.xlabel('Wine Quality Score')
plt.ylabel('Count')
plt.title('Wine Quality Score Distribution')
plt.show()

# Visualizing the relationship between alcohol and quality
import seaborn as sns
sns.boxplot(x='quality', y='alcohol', data=df, palette='coolwarm')
plt.title('Alcohol Content vs Quality')
plt.show()

# Correlation heatmap of features
plt.figure(figsize=(10,7))
sns.heatmap(df.corr(), annot=True, fmt='.2f', cmap='YlGnBu')
plt.title('Feature Correlation Heatmap')
plt.show()

# Splitting features and target
X = df.drop('quality', axis=1)
y = df['quality']

# Split data into train and test sets
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print(X_train.shape, X_test.shape)

# Training the model
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# Making predictions on the test set
y_pred = model.predict(X_test)
print(y_pred[:10])

# Evaluating our model
from sklearn.metrics import accuracy_score, classification_report
acc = accuracy_score(y_test, y_pred)
print(f'Accuracy: {acc:.2f}')
print(classification_report(y_test, y_pred))

# Feature importance plot
import numpy as np
importances = model.feature_importances_
indices = np.argsort(importances)[::-1]
plt.figure(figsize=(8,5))
sns.barplot(x=importances[indices], y=X.columns[indices], palette='viridis')
plt.title('Feature Importance for Predicting Wine Quality')
plt.xlabel('Importance')
plt.ylabel('Feature')
plt.show()

# Interactive: Predict wine quality for your own sample
sample = []
for col in X.columns:
    val = float(input(f'Enter value for {col}: '))
    sample.append(val)
sample = np.array(sample).reshape(1, -1)
pred = model.predict(sample)
print(f'Predicted quality: {pred[0]}')