import pandas as pd
import numpy as np
from matplotlib.pyplot import subplots

data = pd.read_csv('united_summer2015.csv')
data

	Date	Flight Number	Destination	Delay
0	6/1/15	73	HNL	257
1	6/1/15	217	EWR	28
2	6/1/15	237	STL	-3
3	6/1/15	250	SAN	0
4	6/1/15	267	PHL	64
...	...	...	...	...
13820	8/31/15	1978	LAS	-4
13821	8/31/15	1993	IAD	8
13822	8/31/15	1994	ORD	3
13823	8/31/15	2000	PHX	-1
13824	8/31/15	2013	EWR	-2

13825 rows × 4 columns

data['Delay'].hist(bins = np.arange(-15, 600, 20), density = True)

<Axes: >

mean_delay = data['Delay'].mean()
sd_delay = data['Delay'].std()
mean_delay, sd_delay

(np.float64(16.658155515370705), np.float64(39.48162778440366))

num_repetitions = 10000

L_100 = []
for i in range(num_repetitions):
    sample = data.sample(100, replace = True)
    L_100.append(sample['Delay'].mean())

L_400 = []
for i in range(num_repetitions):
    sample = data.sample(400, replace = True)
    L_400.append(sample['Delay'].mean())

L_625 = []
for i in range(num_repetitions):
    sample = data.sample(625, replace = True)
    L_625.append(sample['Delay'].mean())

fig, ax = subplots(figsize = (8, 4))
ax.hist(L_100, bins = np.arange(0, 35, 0.5), density = True, alpha = 0.5, label='sample size 100');
ax.hist(L_400, bins = np.arange(0, 35, 0.5), density = True, alpha = 0.5, label='sample size 400');
ax.hist(L_625, bins = np.arange(0, 35, 0.5), density = True, alpha = 0.5, label='sample size 625');
ax.legend()

<matplotlib.legend.Legend at 0x10dee9970>

print('population mean: ', mean_delay)
print('population sd: ', sd_delay)
print('SD of 100 size sample: ', np.std(L_100), 'population sd/sqrt(n): ', sd_delay/np.sqrt(100))
print('SD of 400 size sample: ', np.std(L_400), 'population sd/sqrt(n): ', sd_delay/np.sqrt(400))
print('SD of 625 size sample: ', np.std(L_625), 'population sd/sqrt(n): ', sd_delay/np.sqrt(625))

population mean:  16.658155515370705
population sd:  39.48162778440366
SD of 100 size sample:  3.9409088987581278 population sd/sqrt(n):  3.9481627784403663
SD of 400 size sample:  1.96880221956649 population sd/sqrt(n):  1.9740813892201832
SD of 625 size sample:  1.5809695898057818 population sd/sqrt(n):  1.5792651113761464

data = pd.read_csv('hybrid.csv')
data

	vehicle	year	msrp	acceleration	mpg	class
0	Prius (1st Gen)	1997	24509.74	7.46	41.26	Compact
1	Tino	2000	35354.97	8.20	54.10	Compact
2	Prius (2nd Gen)	2000	26832.25	7.97	45.23	Compact
3	Insight	2000	18936.41	9.52	53.00	Two Seater
4	Civic (1st Gen)	2001	25833.38	7.04	47.04	Compact
...	...	...	...	...	...	...
148	S400	2013	92350.00	13.89	21.00	Large
149	Prius Plug-in	2013	32000.00	9.17	50.00	Midsize
150	C-Max Energi Plug-in	2013	32950.00	11.76	43.00	Midsize
151	Fusion Energi Plug-in	2013	38700.00	11.76	43.00	Midsize
152	Chevrolet Volt	2013	39145.00	11.11	37.00	Compact

153 rows × 6 columns

fig, ax = subplots(figsize = (4,4))
ax.scatter(data['msrp'], data['acceleration']);

fig, ax = subplots(figsize = (4,4))
ax.scatter(data['mpg'], data['acceleration'])

<matplotlib.collections.PathCollection at 0x10e167280>