fun.py

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

np.random.seed(42)
data = {
    "Age": np.random.randint(18, 70, 100),
    "Salary": np.random.randint(20000, 120000, 100),
    "Experience": np.random.randint(1, 40, 100),
    "Department": np.random.choice(["HR", "Finance", "Engineering", "Marketing"], 100)
}

df = pd.DataFrame(data)

print("### Summary Statistics ###")
print(df.describe())

print("\n### Frequency Counts ###")
print(df["Department"].value_counts())

print("\n### Missing Values ###")
print(df.isnull().sum())

plt.figure(figsize=(10, 5))

plt.subplot(1, 2, 1)
sns.histplot(df["Age"], kde=True, bins=15, color="blue")
plt.title("Age Distribution")
plt.xlabel("Age")
plt.ylabel("Frequency")

plt.subplot(1, 2, 2)
sns.boxplot(data=df, y="Salary", color="orange")
plt.title("Salary Boxplot")
plt.ylabel("Salary")

plt.tight_layout()
plt.show()

correlation = df.corr()
print("\n### Correlation Matrix ###")
print(correlation)

plt.figure(figsize=(8, 6))
sns.heatmap(correlation, annot=True, cmap="coolwarm", fmt=".2f")
plt.title("Correlation Heatmap")
plt.show()