Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')
df=pd.read_csv("athlete_events.csv")
df.head()
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 271116 entries, 0 to 271115
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 271116 non-null int64
1 Name 271116 non-null object
2 Sex 271116 non-null object
3 Age 261642 non-null float64
4 Height 210945 non-null float64
5 Weight 208241 non-null float64
6 Team 271116 non-null object
7 NOC 271116 non-null object
8 Games 271116 non-null object
9 Year 271116 non-null int64
10 Season 271116 non-null object
11 City 271116 non-null object
12 Sport 271116 non-null object
13 Event 271116 non-null object
14 Medal 39783 non-null object
dtypes: float64(3), int64(2), object(10)
memory usage: 31.0+ MB
df.shape
(271116, 15)