ML1

1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')

df = pd.read_csv('housing.csv')

df['total_bedrooms'].fillna(df['total_bedrooms'].median(), inplace=True)

numerical_cols = df.select_dtypes(include=[np.number]).columns

for col in numerical_cols:
    plt.figure(figsize=(10,6))
    df[col].plot(kind='hist', title=col, bins=60, edgecolor='black')
    plt.ylabel('Frequency')
    plt.show()

for col in numerical_cols:
    plt.figure(figsize=(6, 6))
    sns.boxplot(df[col], color='blue')
    plt.title(col)
    plt.ylabel(col)
    plt.show()

outliers_summary = {}
for feature in numerical_cols:
    Q1 = df[feature].quantile(0.25)
    Q3 = df[feature].quantile(0.75)
    IQR = Q3 - Q1
    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR
    outliers = df[(df[feature] < lower_bound) | (df[feature] > upper_bound)]
    outliers_summary[feature] = len(outliers)
    print(f"{feature}: {len(outliers)} outliers")