수치를 통한 연속형 자료의 요약

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

synthetic data

drink = np.array([101.8, 101.5, 101.8, 102.6, 101, 96.8, 102.4, 100, 98.8, 98.1,
                  98.8, 98, 99.4, 95.5, 100.1, 100.5, 97.4, 100.2, 101.4, 98.7,
                  101.4, 99.4, 101.7, 99, 99.7, 98.9, 99.5, 100, 99.7, 100.9,
                  99.7, 99, 98.8, 99.7, 100.9, 99.9, 97.5, 101.5, 98.2, 99.2,
                  98.6, 101.4, 102.1, 102.9, 100.8, 99.4, 103.7, 100.3, 100.2, 101.1,
                  101.8, 100, 101.2, 100.5, 101.2, 101.6, 99.9, 100.5, 100.4, 98.1,
                  100.1, 101.6, 99.3, 96.1, 100, 99.7, 99.7, 99.4, 101.5, 100.9,
                  101.3, 99.9, 99.1, 100.7, 100.8, 100.8, 101.4, 100.3, 98.4, 97.2])

np.mean(drink) #평균

100.04125

np.median(drink) #중앙값

100.05

print(np.var(drink)) #분산값
print(np.var(drink, ddof=1)) #분산값 (n-1)

2.287173437500001
2.316125000000001

print(np.std(drink)) #표준편차
print(np.std(drink, ddof=1)) #표준편차 (n-1)

1.5123403841397614
1.521882058505192

np.max(drink)

103.7

np.min(drink)

95.5

np.percentile(drink, [25, 50, 75])

array([ 99.175, 100.05 , 101.2  ])

drink_df = pd.DataFrame(drink) #numpy인 drink 데이터를 데이터프레임으로 만들기
drink_df.columns = ['Value']

drink_df

drink_df.describe() #데이터프레임 요약

drink_df.info() #데이터프레임 정보

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 80 entries, 0 to 79
Data columns (total 1 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   Value   80 non-null     float64
dtypes: float64(1)
memory usage: 768.0 bytes

Box-plot (상자그림) 그리기

import seaborn as sns

sns.boxplot(data=drink)
plt.show()

타이타닉 데이터

df = sns.load_dataset("titanic")

df.head(5)

sns.boxplot(data=df)
plt.show()

sns.boxplot(data=df, x="age", y="class",)
plt.show()

sns.boxplot(data=df, x="age", y="class", hue = 'survived')
plt.show()