Prac 4:-
Data Preprocessing 
Code:-
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from scipy.stats import chi2_contingency
df=pd.read_csv("Match.csv")
num_df=df.select_dtypes(include=["int64","float64"])
correlation_matrix=num_df.corr()
print("correlation matrix:\n",correlation_matrix)
plt.figure(figsize=(10,8))
sns.heatmap(correlation_matrix,annot=True,cmap="coolwarm",fmt=".2f")
plt.title("correlation matrix")
plt.show()
if 'Toss_Decision' in df.columns:
  contingency_table=pd.crosstab(df['Toss_Decision'],df['Match_Winner_Id'])
  print("Contigency Table:\n",contingency_table)
  chi2,p,dof,expected=chi2_contingency(contingency_table)
  print(f"\nChi-square Statistic: {chi2}")
  print(f"P-value: {p}")
  print(f"Degrees of Freedom: {dof}")
  print("Expected Frequencies:\n",expected)
  if p< 0.05:
    print("\n Variables are dependent (reject H0)")
  else:
    print("\nVariables are independent (fail to reject H0) ")
Output:-