-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathapp.py
205 lines (171 loc) · 7.8 KB
/
app.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
import streamlit as st
import numpy as np
import pandas as pd
import preprocessor, helper
import plotly.express as px
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.figure_factory as ff
# Load datasets
df = pd.read_csv('athlete_events.csv')
region_df = pd.read_csv('noc_regions.csv')
# Preprocess the data using the preprocessor module
df = preprocessor.preprocess(df, region_df)
# Streamlit sidebar configuration
st.sidebar.title("Olympics Analysis")
st.sidebar.image('https://e7.pngegg.com/pngimages/1020/402/png-clipart-2024-summer-olympics-brand-circle-area-olympic-rings-olympics-logo-text-sport.png')
# Sidebar option selection
user_menu = st.sidebar.radio(
'Select an Option',
('Medal Tally', 'Overall Analysis', 'Country-wise Analysis', 'Athlete wise Analysis')
)
# Medal Tally Analysis
if user_menu == 'Medal Tally':
st.sidebar.header("Medal Tally")
years, country = helper.country_year_list(df)
# Year and country selection from the sidebar
selected_year = st.sidebar.selectbox("Select Year", years)
selected_country = st.sidebar.selectbox("Select Country", country)
# Fetch and display the medal tally
medal_tally = helper.fetch_medal_tally(df, selected_year, selected_country)
if selected_year == 'Overall' and selected_country == 'Overall':
st.title("Overall Tally")
if selected_year != 'Overall' and selected_country == 'Overall':
st.title("Medal Tally in " + str(selected_year) + " Olympics")
if selected_year == 'Overall' and selected_country != 'Overall':
st.title(selected_country + " overall performance")
if selected_year != 'Overall' and selected_country != 'Overall':
st.title(selected_country + " performance in " + str(selected_year) + " Olympics")
st.table(medal_tally)
# Overall Analysis
if user_menu == 'Overall Analysis':
# Calculate various statistics about the Olympics dataset
editions = df['Year'].unique().shape[0] - 1
cities = df['City'].unique().shape[0]
sports = df['Sport'].unique().shape[0]
events = df['Event'].unique().shape[0]
athletes = df['Name'].unique().shape[0]
nations = df['region'].unique().shape[0]
# Display top statistics in columns
st.title("Top Statistics")
col1, col2, col3 = st.columns(3)
with col1:
st.header("Editions")
st.title(editions)
with col2:
st.header("Hosts")
st.title(cities)
with col3:
st.header("Sports")
st.title(sports)
col1, col2, col3 = st.columns(3)
with col1:
st.header("Events")
st.title(events)
with col2:
st.header("Nations")
st.title(nations)
with col3:
st.header("Athletes")
st.title(athletes)
# Visualizations for nations, events, and athletes over time
nations_over_time = helper.data_over_time(df, 'region')
fig = px.line(nations_over_time, x="Edition", y="count")
st.title("Participating Nations over the years")
st.plotly_chart(fig)
events_over_time = helper.data_over_time(df, 'Event')
fig = px.line(events_over_time, x="Edition", y="count")
st.title("Events over the years")
st.plotly_chart(fig)
athlete_over_time = helper.data_over_time(df, 'Name')
fig = px.line(athlete_over_time, x="Edition", y="count")
st.title("Athletes over the years")
st.plotly_chart(fig)
# Heatmap for number of events over time for every sport
st.title("No. of Events over time (Every Sport)")
fig, ax = plt.subplots(figsize=(20, 20))
x = df.drop_duplicates(['Year', 'Sport', 'Event'])
ax = sns.heatmap(x.pivot_table(index='Sport', columns='Year', values='Event', aggfunc='count').fillna(0).astype('int'),
annot=True)
st.pyplot(fig)
# Most successful athletes
st.title("Most successful Athletes")
sport_list = df['Sport'].unique().tolist()
sport_list.sort()
sport_list.insert(0, 'Overall')
selected_sport = st.selectbox('Select a Sport', sport_list)
x = helper.most_successful(df, selected_sport)
st.table(x)
# Country-wise Analysis
if user_menu == 'Country-wise Analysis':
st.sidebar.title('Country-wise Analysis')
country_list = df['region'].dropna().unique().tolist()
country_list.sort()
selected_country = st.sidebar.selectbox('Select a Country', country_list)
# Year-wise medal tally for the selected country
country_df = helper.yearwise_medal_tally(df, selected_country)
fig = px.line(country_df, x="Year", y="Medal")
st.title(selected_country + " Medal Tally over the years")
st.plotly_chart(fig)
st.title(selected_country + " excels in the following sports")
pt = helper.country_event_heatmap(df, selected_country)
fig, ax = plt.subplots(figsize=(20, 20))
ax = sns.heatmap(pt, annot=True)
st.pyplot(fig)
st.title("Top 10 athletes of " + selected_country)
top10_df = helper.most_successful_countrywise(df, selected_country)
st.table(top10_df)
# Athlete-wise Analysis
if user_menu == 'Athlete wise Analysis':
athlete_df = df.drop_duplicates(subset=['Name', 'region'])
# Distribution of age for athletes
x1 = athlete_df['Age'].dropna()
x2 = athlete_df[athlete_df['Medal'] == 'Gold']['Age'].dropna()
x3 = athlete_df[athlete_df['Medal'] == 'Silver']['Age'].dropna()
x4 = athlete_df[athlete_df['Medal'] == 'Bronze']['Age'].dropna()
fig = ff.create_distplot([x1, x2, x3, x4],
['Overall Age', 'Gold Medalist', 'Silver Medalist', 'Bronze Medalist'],
show_hist=False, show_rug=False)
fig.update_layout(autosize=False, width=1000, height=600)
st.title("Distribution of Age")
st.plotly_chart(fig)
# Distribution of age wrt sports for Gold Medalists
x = []
name = []
famous_sports = ['Basketball', 'Judo', 'Football', 'Tug-Of-War', 'Athletics',
'Swimming', 'Badminton', 'Sailing', 'Gymnastics',
'Art Competitions', 'Handball', 'Weightlifting', 'Wrestling',
'Water Polo', 'Hockey', 'Rowing', 'Fencing',
'Shooting', 'Boxing', 'Taekwondo', 'Cycling', 'Diving', 'Canoeing',
'Tennis', 'Golf', 'Softball', 'Archery',
'Volleyball', 'Synchronized Swimming', 'Table Tennis', 'Baseball',
'Rhythmic Gymnastics', 'Rugby Sevens',
'Beach Volleyball', 'Triathlon', 'Rugby', 'Polo', 'Ice Hockey']
for sport in famous_sports:
temp_df = athlete_df[athlete_df['Sport'] == sport]
x.append(temp_df[temp_df['Medal'] == 'Gold']['Age'].dropna())
name.append(sport)
fig = ff.create_distplot(x, name, show_hist=False, show_rug=False)
fig.update_layout(autosize=False, width=1000, height=600)
st.title("Distribution of Age wrt Sports (Gold Medalist)")
st.plotly_chart(fig)
# Height vs Weight Analysis
sport_list = df['Sport'].unique().tolist()
sport_list.sort()
sport_list.insert(0, 'Overall')
st.title('Height Vs Weight')
selected_sport = st.selectbox('Select a Sport', sport_list)
temp_df = helper.weight_v_height(df, selected_sport)
fig, ax = plt.subplots()
ax = sns.scatterplot(x=temp_df['Weight'], y=temp_df['Height'], hue=temp_df['Medal'], style=temp_df['Sex'], s=60)
st.pyplot(fig)
# Men vs Women participation over the years
st.title("Men Vs Women Participation Over the Years")
final = helper.men_vs_women(df)
fig = px.line(final, x="Year", y=["Male", "Female"])
fig.update_layout(autosize=False, width=1000, height=600)
st.plotly_chart(fig)
st.sidebar.markdown(
"[](https://www.linkedin.com/in/abhay-singh-050a5b293/)")
st.sidebar.markdown(
"[](https://x.com/@abhaysingh71711)")