2sample

import pandas as pd
import numpy as np
from scipy.stats import ttest_ind

# Load dataset
df = pd.read_csv("weather.csv")

# Select two groups
group1 = df[df["Condition"] == "Sunny"]["Data.Temperature.Avg Temp"].dropna()
group2 = df[df["Condition"] == "Rain"]["Data.Temperature.Avg Temp"].dropna()

# Sample statistics
print("Group 1 Mean:", group1.mean())
print("Group 2 Mean:", group2.mean())

# Independent t-test
t_stat, p_value = ttest_ind(group1, group2)

print("\nt-statistic:", t_stat)
print("p-value:", p_value)

# Decision
alpha = 0.05
if p_value < alpha:
    print("Reject Null Hypothesis (Means are different)")
else:
    print("Fail to Reject Null Hypothesis (Means are same)")