EDA Workflow II

import seaborn as sns
import matplotlib.pyplot as plt

df = sns.load_dataset('tips')

# Scatter Plot
sns.scatterplot(x='total_bill', y='tip', data=df)
plt.title('Bill vs Tip')
plt.show()

# Correlation
correlation = df['total_bill'].corr(df['tip'])
print(f"Correlation: {correlation:.2f}")

# Box Plot (Distribution by category)
sns.boxplot(x='day', y='total_bill', data=df)
plt.title('Bill Distribution by Day')
plt.show()

# Bar Plot (Mean by category)
sns.barplot(x='sex', y='total_bill', data=df) # Shows mean with confidence interval
plt.show()

# Cross Tabulation
ct = pd.crosstab(df['day'], df['sex'])
print(ct)

# Heatmap of counts
sns.heatmap(ct, annot=True, fmt='d', cmap='Blues')
plt.show()

# Scatter plot with Color (Hue)
sns.scatterplot(x='total_bill', y='tip', hue='sex', data=df)
plt.title('Bill vs Tip by Sex')
plt.show()

# Scatter plot with Size
sns.scatterplot(x='total_bill', y='tip', size='size', data=df)
plt.show()

# Pair Plot (All numerical relationships)
sns.pairplot(df, hue='sex')
plt.show()

# Calculate correlation matrix
corr_matrix = df.corr(numeric_only=True)

# Plot heatmap
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
plt.title('Correlation Matrix')
plt.show()

import seaborn as sns

# Load diamonds dataset
diamonds = sns.load_dataset('diamonds')

# 1. Correlation between price and carat
print("Correlation:", diamonds['price'].corr(diamonds['carat']))

# 2. Price distribution by cut (Boxplot)
# (Visualization code would go here)

# 3. Price vs Carat colored by Clarity
# (Visualization code would go here)