240926

240926

In [6]:

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

In [10]:

path = 'https://raw.githubusercontent.com/DA4BAM/dataset/master/titanic_simple.csv'
titanic = pd.read_csv(path)
titanic.head()

Out[10]:

PassengerIdSurvivedPclassNameSexAgeFareEmbarked01234

1	0	3	Braund, Mr. Owen Harris	male	22.0	7.2500	Southampton
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	71.2833	Cherbourg
3	1	3	Heikkinen, Miss. Laina	female	26.0	7.9250	Southampton
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	53.1000	Southampton
5	0	3	Allen, Mr. William Henry	male	35.0	8.0500	Southampton

In [13]:

path = 'https://raw.githubusercontent.com/DA4BAM/dataset/master/air2.csv'
air = pd.read_csv(path)
air.head()

Out[13]:

OzoneSolar.RWindTempDate01234

41	190.0	7.4	67	1973-05-01
36	118.0	8.0	72	1973-05-02
12	149.0	12.6	74	1973-05-03
18	313.0	11.5	62	1973-05-04
19	NaN	14.3	56	1973-05-05

단변량 범주형 변수

1. 수치화: 기초통계량

• value_counts()
• value_counts(normalize = True) #비율

In [18]:

titanic['Pclass'].value_counts()

Out[18]:

Pclass
3    491
1    216
2    184
Name: count, dtype: int64

In [20]:

titanic['Pclass'].value_counts(normalize = True)

Out[20]:

Pclass
3    0.551066
1    0.242424
2    0.206510
Name: proportion, dtype: float64

2. 시각화

• bar chart
• pie chart

In [33]:

# sns.countplot()

# 가로로 그리기
sns.countplot(y = 'Pclass', data = titanic)
plt.show()

In [35]:

# 세로로 그리기
sns.countplot(x = 'Pclass', data = titanic)
plt.show()

In [45]:

# plt.pie()

temp = titanic['Pclass'].value_counts()
plt.pie(temp.values, labels = temp.index, autopct = '%.2f%%')
plt.show()

 

In [ ]:

이변량 숫자 vs 숫자

In [52]:

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

In [61]:

titanic = pd.read_csv('https://raw.githubusercontent.com/DA4BAM/dataset/master/titanic.0.csv')
titanic.head()

Out[61]:

PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked01234

1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

In [75]:

air = pd.read_csv('https://raw.githubusercontent.com/DA4BAM/dataset/master/air2.csv')
air['Date'] = pd.to_datetime(air['Date'])
air['Year'] = air['Date'].dt.year
air['Month'] = air['Date'].dt.month
air['Day'] = air['Date'].dt.day

In [91]:

air2 = air[['Ozone', 'Solar.R', 'Wind', 'Temp']]
air2.head()

Out[91]:

OzoneSolar.RWindTemp01234

41	190.0	7.4	67
36	118.0	8.0	72
12	149.0	12.6	74
18	313.0	11.5	62
19	NaN	14.3	56

1. 시각화: 산점도

• plt.scatter(x = x축값, y= y축값)
• sns.pairplot(df, kind = 'reg') : 한 번에 그리기

In [99]:

# plt.scatter(x = , y = )
plt.scatter(x = air['Temp'], y = air['Ozone'])
plt.show()

In [105]:

# Temp, Wind, Solar.R과 Ozone과의 관계 시각화
plt.figure(figsize = (14,5))
plt.subplot(1,3,1)
plt.scatter(x = air['Temp'], y = air['Ozone'])

plt.subplot(1,3,2)
plt.scatter(x = air['Wind'], y = air['Ozone'])

plt.subplot(1,3,3)
plt.scatter(x = 'Wind', y = 'Ozone', data=  air)

plt.show()

In [109]:

# sns.pairplot()으로 한 번에 시각화
sns.pairplot(air2)
plt.show()

In [111]:

# kind = 'reg'로 회귀선 추가 가능
sns.pairplot(air2)
plt.show()

2. 수치화: 상관분석

• 상관계수
• p-value

In [115]:

import scipy.stats as spst

In [119]:

# spst.pearsonr() : 상관계수와 p value 구하기
# Nan 값 제거하고 사용해야함: .notnull()
# 상관계수와 p-value
spst.pearsonr(air['Temp'], air['Ozone'])

Out[119]:

PearsonRResult(statistic=0.6833717861490114, pvalue=2.197769800200284e-22)

In [124]:

# 데이터프레임 수치형 데이터에 대한 상관계수 구하기
air2.corr()

Out[124]:

OzoneSolar.RWindTempOzoneSolar.RWindTemp

1.000000	0.280068	-0.605478	0.683372
0.280068	1.000000	-0.056792	0.275840
-0.605478	-0.056792	1.000000	-0.457988
0.683372	0.275840	-0.457988	1.000000

In [133]:

## 상관계수 heatmap 시각화
sns.heatmap(air2.corr(),
            annot = True,            # 숫자(상관계수) 표기 여부
            fmt = '.3f',             # 숫자 포멧 : 소수점 3자리까지 표기
            cmap = 'RdYlBu_r',       # 칼라맵
            vmin = -1, vmax = 1)
plt.show()