-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstatistics copy.py
215 lines (166 loc) · 7.61 KB
/
statistics copy.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
from typing import List
def mean(xs: List[float]) -> float:
return sum(xs) / len(xs)
# The underscores indicate that these are "private" functions, as they're
# intended to be called by our median function but not by other people
# using our statistics library.
def _median_odd(xs: List[float]) -> float:
"""If len(xs) is odd, the median is the middle element"""
return sorted(xs)[len(xs) // 2]
def _median_even(xs: List[float]) -> float:
"""If len(xs) is even, it's the average of the middle two elements"""
sorted_xs = sorted(xs)
hi_midpoint = len(xs) // 2 # e.g. length 4 => hi_midpoint 2
return (sorted_xs[hi_midpoint - 1] + sorted_xs[hi_midpoint]) / 2
def median(v: List[float]) -> float:
"""Finds the 'middle-most' value of v"""
return _median_even(v) if len(v) % 2 == 0 else _median_odd(v)
assert median([1, 10, 2, 9, 5]) == 5
assert median([1, 9, 2, 10]) == (2 + 9) / 2
def mode(x: List[float]) -> List[float]:
"""Returns a list, since there might be more than one mode"""
counts = Counter(x)
max_count = max(counts.values())
return [x_i for x_i, count in counts.items()
if count == max_count]
##new functions
from collections import Counter
import matplotlib.pyplot as plt
from typing import List
import math
import numpy as np
from linear_algebra import sum_of_squares, dot
# Data
num_friends = [100.0,49,41,40,25,21,21,19,19,18,18,16,
15,15,15,15,14,14,13,13,13,13,12,12,11,10,10,10,10,
10,10,10,10,10,10,10,10,10,10,10,9,9,9,9,9,9,9,9,9,
9,9,9,9,9,9,9,9,9,8,8,8,8,8,8,8,8,8,8,8,8,8,7,7,7,7,
7,7,7,7,7,7,7,7,7,7,7,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
6,6,6,6,6,6,6,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,4,4,
4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,3,3,3,3,3,3,3,3,
3,3,3,3,3,3,3,3,3,3,3,3,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
2,2,2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
daily_minutes = [1,68.77,51.25,52.08,38.36,44.54,57.13,51.4,41.42,31.22,
34.76,54.01,38.79,47.59,49.1,27.66,41.03,36.73,48.65,28.12,46.62,35.57,
32.98,35,26.07,23.77,39.73,40.57,31.65,31.21,36.32,20.45,21.93,26.02,
27.34,23.49,46.94,30.5,33.8,24.23,21.4,27.94,32.24,40.57,25.07,19.42,
22.39,18.42,46.96,23.72,26.41,26.97,36.76,40.32,35.02,29.47,30.2,31,
38.11,38.18,36.31,21.03,30.86,36.07,28.66,29.08,37.28,15.28,24.17,22.31,
30.17,25.53,19.85,35.37,44.6,17.23,13.47,26.33,35.02,32.09,24.81,19.33,
28.77,24.26,31.98,25.73,24.86,16.28,34.51,15.23,39.72,40.8,26.06,35.76,
34.76,16.13,44.04,18.03,19.65,32.62,35.59,39.43,14.18,35.24,40.13,41.82,
35.45,36.07,43.67,24.61,20.9,21.9,18.79,27.61,27.21,26.61,29.77,20.59,
27.53,13.82,33.2,25,33.1,36.65,18.63,14.87,22.2,36.81,25.53,24.62,26.25,
18.21,28.08,19.42,29.79,32.8,35.99,28.32,27.79,35.88,29.06,36.28,14.1,
36.63,37.49,26.9,18.58,38.48,24.48,18.95,33.55,14.24,29.04,32.51,25.63,
22.22,19,32.73,15.16,13.9,27.2,32.01,29.27,33,13.74,20.42,27.32,18.23,
35.35,28.48,9.08,24.62,20.12,35.26,19.92,31.02,16.49,12.16,30.7,31.22,
34.65,13.13,27.51,33.2,31.57,14.1,33.42,17.44,10.12,24.42,9.82,23.39,
30.93,15.03,21.67,31.09,33.29,22.61,26.89,23.48,8.38,27.81,32.35,23.84]
daily_hours = [dm / 60 for dm in daily_minutes]
friend_counts = Counter(num_friends)
xs = range(101) # largest value is 100
ys = [friend_counts[x] for x in xs] # height is just # of friends
plt.bar(xs, ys)
plt.axis([0, 101, 0, 25])
plt.title("Histogram of Friend Counts")
plt.xlabel("# of friends")
plt.ylabel("# of people")
plt.show()
# FUNCTIONS
# correlation(xs: List[float], ys: List[float]) -> float
# Measures how much xs and ys vary in tandem about their means
# def correlation(xs,ys):
def correlation(xs: List[float], ys: List[float]) -> float:
"""Measures how much xs and ys vary in tandem about their means"""
stdev_x = standard_deviation(xs)
stdev_y = standard_deviation(ys)
if stdev_x > 0 and stdev_y > 0:
return covariance(xs, ys) / stdev_x / stdev_y
else:
return 0 # if no variation, correlation is zero
# covariance(xs: List[float], ys: List[float]) -> float
def covariance(xs: List[float], ys: List[float]) -> float:
assert len(xs) == len(ys), "xs and ys must have same number of elements"
return dot(de_mean(xs), de_mean(ys)) / (len(xs) - 1)
#
# data_range(xs: List[float]) -> float
# # "range" already means something in Python, so we'll use a different name
# "range" already means something in Python, so we'll use a different name
def data_range(xs: List[float]) -> float:
return max(xs) - min(xs)
#
# de_mean(xs: List[float]) -> List[float]
# Translate xs by subtracting its mean (so the result has mean 0)
def de_mean(xs: List[float]) -> List[float]:
"""Translate xs by subtracting its mean (so the result has mean 0)"""
x_bar = mean(xs)
return [x - x_bar for x in xs]
#
# interquartile_range(xs: List[float]) -> float
# Returns the difference between the 75%-ile and the 25%-ile
def interquartile_range(xs: List[float]) -> float:
"""Returns the difference between the 75%-ile and the 25%-ile"""
return quantile(xs, 0.75) - quantile(xs, 0.25)
#
# mean(xs: List[float]) -> float
#
def mean(xs: List[float]) -> float:
return sum(xs) / len(xs)
# The underscores indicate that these are "private" functions, as they're
# intended to be called by our median function but not by other people
# using our statistics library.
def _median_odd(xs: List[float]) -> float:
"""If len(xs) is odd, the median is the middle element"""
return sorted(xs)[len(xs) // 2]
def _median_even(xs: List[float]) -> float:
"""If len(xs) is even, it's the average of the middle two elements"""
sorted_xs = sorted(xs)
hi_midpoint = len(xs) // 2 # e.g. length 4 => hi_midpoint 2
return (sorted_xs[hi_midpoint - 1] + sorted_xs[hi_midpoint]) / 2
# median(v: List[float]) -> float
# Finds the 'middle-most' value of v
def median(v: List[float]) -> float:
return np.median(v)
#
# mode(x: List[float]) -> List[float]
# Returns a list, since there might be more than one mode
def mode(x: List[float]) -> List[float]:
data = Counter(x)
mode = [k for k, v in data.items() if v == max(list(data.values()))]
return mode
# quantile(xs: List[float], p: float) -> float
# Returns the pth-percentile value in x
def quantile(xs: List[float], p: float) -> float:
"""Returns the pth-percentile value in x"""
p_index = int(p * len(xs))
return sorted(xs)[p_index]
#
# standard_deviation(xs: List[float]) -> float
# The standard deviation is the square root of the variance
def standard_deviation(xs: List[float]) -> float:
"""The standard deviation is the square root of the variance"""
return math.sqrt(variance(xs))
#
# variance(xs: List[float]) -> float
# Almost the average squared deviation from the mean
#
def variance(xs: List[float]) -> float:
"""Almost the average squared deviation from the mean"""
assert len(xs) >= 2, "variance requires at least two elements"
n = len(xs)
deviations = de_mean(xs)
return sum_of_squares(deviations) / (n - 1)
# start the tests
assert mean([1,2,3,4]) == 2.5
assert set(mode([1.0,2.0])) == {1.0, 2.0}
assert interquartile_range(num_friends) == 6
assert 9.02 < standard_deviation(num_friends) < 9.04
assert 81.54 < variance(num_friends) < 81.55
assert quantile(num_friends, 0.10) == 1
assert quantile(num_friends, 0.25) == 3
assert quantile(num_friends, 0.75) == 9
assert quantile(num_friends, 0.90) == 13
assert interquartile_range(num_friends) == 6
assert 22.42 < covariance(num_friends, daily_minutes) < 22.43
assert 22.42 / 60 < covariance(num_friends, daily_hours) < 22.43 / 60