What does a typical exploratory data analysis (EDA) workflow look like in Python?

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# 1. Load and inspect
df = pd.read_csv('housing.csv')
print(df.shape)          # (rows, cols)
print(df.dtypes)         # types per column
print(df.head())         # first 5 rows
print(df.info())         # dtypes + non-null counts
print(df.describe())     # summary stats for numeric cols

# 2. Missing value audit
missing = df.isnull().sum().sort_values(ascending=False)
print(missing[missing > 0])

# 3. Duplicate rows
print(df.duplicated().sum())
df = df.drop_duplicates()

# 4. Distribution of each numeric column
df.select_dtypes('number').hist(bins=30, figsize=(16, 10))
plt.tight_layout(); plt.show()

# 5. Correlation heatmap
corr = df.select_dtypes('number').corr()
sns.heatmap(corr, annot=True, fmt='.2f', cmap='coolwarm')
plt.title('Correlation Matrix'); plt.show()

# 6. Target variable distribution
target = 'price'
sns.histplot(df[target], kde=True)
print(f'Skewness: {df[target].skew():.2f}')

# 7. Categorical breakdown
for col in df.select_dtypes('object').columns:
    print(df[col].value_counts())

# 8. Outlier detection
for col in df.select_dtypes('number').columns:
    Q1, Q3 = df[col].quantile([0.25, 0.75])
    IQR = Q3 - Q1
    n_out = ((df[col] < Q1-1.5*IQR)|(df[col] > Q3+1.5*IQR)).sum()
    if n_out > 0: print(f'{col}: {n_out} outliers')