Covid-19-Impact-on-Student-Wellness/Texas vs New York 1600m Running Times at main · sarvagna9/Covid-19-Impact-on-Student-Wellness · GitHub

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
214
215
216
217
218
219
220
221
222
223
224
225
import csv
import requests
from bs4 import BeautifulSoup
import re
import matplotlib.pyplot as plt
import statistics

# New York - 1600m

# Gathering webpages with 1600m running times in New York

NY_urls_2023 = ["https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=136246&Event=52&type=4",
"https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=136247&Event=52&type=4",
"https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=136248&Event=52&type=4"]

NY_urls_2022 = []
for i in range(126898, 126901):
    NY_urls_2022.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

NY_urls_2021 = []
for i in range(117774, 117777):
    NY_urls_2021.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

#NY_urls_2020 = []
#for i in range(108687, 108690):
#    NY_urls_2020.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

NY_urls_2019 = []
for i in range(99650, 99653):
    NY_urls_2019.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

NY_urls_2018 = []
for i in range(90807, 90810):
    NY_urls_2018.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

NY_urls_2017 = []
for i in range(81549, 81552):
    NY_urls_2017.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")

NY_urls_2016 = []
for i in range(72361, 72364):
    NY_urls_2016.append("https://www.athletic.net/TrackAndField/Division/Event.aspx?DivID=" + str(i) + "&Event=52&type=4")


NY_2023 = []
NY_2022 = []
NY_2021 = []
NY_2020 = []
NY_2019 = []
NY_2018 = []
NY_2017 = []
NY_2016 = []

# Extracting the 1600m running times from each webpage and appending to lists.

for url in NY_urls_2023:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2023 += seconds

for url in NY_urls_2022:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2022 += seconds

# No running times in 2020 in NY

for url in NY_urls_2021:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2021 += seconds

for url in NY_urls_2019:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2019 += seconds

for url in NY_urls_2018:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2018 += seconds


for url in NY_urls_2017:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2017 += seconds


for url in NY_urls_2016:
    page = requests.get(url)
    soup = BeautifulSoup(page.content, 'html5lib')

    results = soup.find('tbody')

    for element in results:
        string_version = str(element)
        string_time = re.findall(r'\d\:\d\d\.\d\d+', string_version)
        seconds = [int(item[0])*60 + int(item[2:4]) + int(item[5:7])*10**-2 for item in string_time]
        NY_2016 += seconds


# Calculating mean and standard deviations for running times in NY
NY_mean_2023 = average(NY_2023)
NY_mean_2022 = average(NY_2022)
NY_mean_2021 = average(NY_2021)
#NY_mean_2020 = average(NY_2020)
NY_mean_2019 = average(NY_2019)
NY_mean_2018 = average(NY_2018)
NY_mean_2017 = average(NY_2017)
NY_mean_2016 = average(NY_2016)

NY_std_above_2023 = NY_mean_2023 + statistics.stdev(NY_2023)
NY_std_below_2023 = NY_mean_2023 - statistics.stdev(NY_2023)
NY_std_above_2022 = NY_mean_2022 + statistics.stdev(NY_2022)
NY_std_below_2022 = NY_mean_2022 - statistics.stdev(NY_2022)
NY_std_above_2021 = NY_mean_2021 + statistics.stdev(NY_2021)
NY_std_below_2021 = NY_mean_2021 - statistics.stdev(NY_2021)
#NY_std_above_2020 = NY_mean_2020 + statistics.stdev(NY_2020)
#NY_std_below_2020 = NY_mean_2020 - statistics.stdev(NY_2020)
NY_std_above_2019 = NY_mean_2019 + statistics.stdev(NY_2019)
NY_std_below_2019 = NY_mean_2019 - statistics.stdev(NY_2019)
NY_std_above_2018 = NY_mean_2018 + statistics.stdev(NY_2018)
NY_std_below_2018 = NY_mean_2018 - statistics.stdev(NY_2018)
NY_std_above_2017 = NY_mean_2017 + statistics.stdev(NY_2017)
NY_std_below_2017 = NY_mean_2017 - statistics.stdev(NY_2017)
NY_std_above_2016 = NY_mean_2016 + statistics.stdev(NY_2016)
NY_std_below_2016 = NY_mean_2016 - statistics.stdev(NY_2016)

NY_means = [NY_mean_2016, NY_mean_2017, NY_mean_2018, NY_mean_2019, NY_mean_2021, NY_mean_2022, NY_mean_2023]
NY_std_above = [NY_std_above_2016, NY_std_above_2017, NY_std_above_2018, NY_std_above_2019, NY_std_above_2021, NY_std_above_2022, NY_std_above_2023]
NY_std_below = [NY_std_below_2016, NY_std_below_2017, NY_std_below_2018, NY_std_below_2019, NY_std_below_2021, NY_std_below_2022, NY_std_below_2023]

years = [2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023]
NY_means.insert(4, np.nan)
NY_std_above.insert(4, np.nan)
NY_std_below.insert(4, np.nan)


# Code for Texas running times are in another file in this repository


# Plotting Texas vs New York running 1600m running times

plt.figure()
plt.plot(years, TX_means, label='Texas')
plt.plot(years, TX_std_above, '--',color=colormap(0))
plt.plot(years, TX_std_below, '--', color=colormap(0))
plt.plot(years, NY_means, label='New York')
plt.plot(years, NY_std_above, '--', color=colormap(1))
plt.plot(years, NY_std_below, '--', color=colormap(1))
ax=plt.gca()
ax.fill_between(years, TX_std_above, TX_std_below, alpha=0.3, color=colormap(0))
ax.fill_between(years, NY_std_above, NY_std_below, alpha=0.3, color=colormap(1))
plt.legend()
plt.xlabel('Year')
plt.ylabel('Seconds')
plt.title('Texas vs New York 1600m Times')

plt.savefig('Texas_vs_NewYork.png', dpi=300)


range6 = (230, 400)
bins = 15
tx_data = [TX_2016, TX_2017, TX_2018, TX_2019, TX_2020, TX_2021, TX_2022, TX_2023]
new_york_data = [NY_2016, NY_2017, NY_2018, NY_2019, NY_2020, NY_2021, NY_2022, NY_2023]

fig, ax = plt.subplots(sharey=True, sharex=True, nrows=2, ncols=4, figsize=(12,5))
for idx,axis in enumerate(ax.flat):
    axis.hist(tx_data[idx], bins=bins, alpha=0.5, label="Texas",range=range6)
    axis.hist(new_york_data[idx], bins=bins, alpha=0.5, label="New York",range=range6)
    if idx>3:
        axis.set_xlabel('Seconds')
    if idx in (0,4):
        axis.set_ylabel('Frequency')
    #
    #  axis.set_ylabel('Frequency')
    axis.set_title(str(2016+idx))
    axis.legend()

plt.suptitle("Texas vs New York 1600m Times")

plt.savefig('Texas_vs_NewYork_1600m.png', dpi=300)