[pandas] DO IT 데이터분석을 위한 판다스 입문 (기초)

데이터 : https://github.com/easysIT/doit_pandas

import pandas as pd

df = pd.read_csv('./data/gapminder.tsv', sep='\t')

print(df.head())

# 데이터 추출
subset = df.loc[:, ['year', 'pop']]
print(subset.head())

subset = df.iloc[:, [2,4,-1]]
print(subset.head())

# 평균
print(df.groupby('year')['lifeExp'].mean())

# group by 
grouped_year_df = df.groupby('year')
grouped_year_df_lifeExp = grouped_year_df['lifeExp']
mean_lifeExp_by_year = grouped_year_df_lifeExp.mean()

multi_group_var = df.groupby(['year', 'continent'])[['lifeExp','gdpPercap']].mean()
print(multi_group_var)

# 빈도수
print(df.groupby('continent')['country'].nunique())

# 그래프
import matplotlib.pyplot as plt

global_yearly_life_expectancy = df.groupby('year')['lifeExp'].mean()
print(global_yearly_life_expectancy)

global_yearly_life_expectancy.plot()