14 Conditional probability and independence

%%html
<iframe width="700" height="400" src="https://www.youtube.com/embed/pIfpHdGVwLU/" frameborder="0" allowfullscreen></iframe>

import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import matplotlib.pyplot as plt
import seaborn as sns

khanacademy

df = DataFrame({
    'On time': [167, 115, 40, 8],
    'Delayed': [3, 5, 15, 12]
}, index=['Sunny', 'Cloudy', 'Rainy', 'Snowy'])

df['Total'] = df['On time'] + df['Delayed']

df = df.append(df.sum().rename('Total'))

/tmp/ipykernel_7685/333771010.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df = df.append(df.sum().rename('Total'))

df[-1:]

	On time	Delayed	Total
Total	330	35	365

#P(Delayed)
df[-1:]['Delayed'] / df[-1:]['Total']

Total    0.09589
dtype: float64

df[-2:-1]

	On time	Delayed	Total
Snowy	8	12	20

#P(Delayed | Snowy)
df[-2:-1]['Delayed'] / df[-2:-1]['Total']

Snowy    0.6
dtype: float64