# System import warnings # Data manipulation import pandas as pd import numpy as np # Data visualization import matplotlib.pyplot as plt import seaborn as sns

# Suppress warnings warnings.filterwarnings('ignore') # Set the default Seaborn style sns.set_theme(style='whitegrid', font='serif')

data = pd.read_csv('../datasets/raw/white_wine.csv', delimiter=';') # Display the first 5 rows of the dataset data.head()

data.describe().T

data.info()

data.isnull().sum()

data.duplicated().sum()

# Drop duplicates data = data.drop_duplicates() # Check for duplicates data.duplicated().sum()

# Set the figure size plt.figure(figsize=(10, 6)) # Plot the distribution of the target variable ax = sns.countplot(data=data, x='quality', color='lightblue') # Find the bar with the highest value max_height = max([p.get_height() for p in ax.patches]) for p in ax.patches: if p.get_height() == max_height: p.set_color('salmon') # Set the title and labels plt.title('Distribution of the Quality Variable') plt.xlabel('Quality') plt.ylabel('Count') # Add text annotations for p in ax.patches: ax.annotate(f'{int(p.get_height())}', (p.get_x() + p.get_width() / 2., p.get_height()), ha='center', va='center', xytext=(0, 5), textcoords='offset points') # Add grid lines plt.grid(linestyle='--', alpha=0.6) # Display the plot plt.tight_layout() plt.show()

# Set the figure size plt.figure(figsize=(10, 6)) # Plot the distribution of the target variable sns.scatterplot(data=data, x='alcohol', y='quality', color='salmon') # Set the title and labels plt.title('Quality vs Alcohol Content') plt.xlabel('Alcohol Content') plt.ylabel('Quality') # Add grid lines plt.grid(linestyle='--', alpha=0.6) # Display the plot plt.tight_layout() plt.show()

# Get unique quality values qualities = data['quality'].unique() # Set the figure size fig, axes = plt.subplots(3, 3, figsize=(15, 15)) axes = axes.flatten() # Plot the distribution of alcohol content for each quality for i, quality in enumerate(qualities): ax = axes[i] sns.histplot(data[data['quality'] == quality], x='alcohol', kde=True, bins=30, ax=ax, color='lightblue') ax.set_title(f'Quality: {quality}') ax.set_xlabel('Alcohol Content') ax.set_ylabel('Count') ax.grid(linestyle='--', alpha=0.6) # Remove any empty subplots for j in range(i + 1, len(axes)): fig.delaxes(axes[j]) # Adjust layout plt.tight_layout() plt.show()

# Set the figure size plt.figure(figsize=(10, 10)) # Plot the heatmap sns.heatmap(data.corr(), annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5) # Set the title plt.title('Correlation Heatmap') # Display the plot plt.tight_layout() plt.show()