88.py

# Importing libraries
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import warnings

# Ignore warnings
warnings.filterwarnings('ignore')

# Load dataset (Iris dataset is built into seaborn)
df = sns.load_dataset("iris")

# Basic EDA
print("First 5 rows:\n", df.head())
print("\nDataset shape:", df.shape)
print("\nData Types:\n", df.dtypes)
print("\nSummary Statistics:\n", df.describe())
print("\nMissing Values:\n", df.isnull().sum())
print("\nUnique values in each column:\n", df.nunique())

# Univariate Analysis

# Distribution of each numerical column
num_columns = df.select_dtypes(include=['float64', 'int64']).columns
for col in num_columns:
    plt.figure(figsize=(6, 4))
    sns.histplot(df[col], kde=True, color='skyblue')
    plt.title(f"Distribution of {col}")
    plt.xlabel(col)
    plt.ylabel("Frequency")
    plt.grid(True)
    plt.show()

# Univariate analysis for categorical column
plt.figure(figsize=(6, 4))
sns.countplot(x='species', data=df, palette='Set2')
plt.title("Count of each species")
plt.xlabel("Species")
plt.ylabel("Count")
plt.grid(True)
plt.show()