sons dataStory

The following graphs are the codes for the figures included in Chapters 6 and 7 of the e-book Statistics with Python . import numpy as np import pandas as pd from scipy import stats from sklearn.preprocessing import StandardScaler import FinanceDataReader as fdr import yfinance as yf import statsmodels.api as sm from statsmodels.formula.api import ols from sklearn.linear_model import LinearRegression import matplotlib.pyplot as plt import seaborn as sns sns.set_style("darkgrid") #fig 611 st=pd.Timestamp(2024,1, 1) et=pd.Timestamp(2024, 5, 30) code=["^KS11", "^KQ11", "^DJI", "KRW=X"] nme=['kos','kq','dj','WonDol'] da=pd.DataFrame() for i in code: x=yf.download(i,st, et)['Close'] x1=x.pct_change() da=pd.concat([da, x1], axis=1) da.columns=nme da1=da.dropna() da1.index=range(len(da1)) da2=pd.melt(da1, value_vars=['kos', 'kq', 'dj', 'WonDol'], var_name=...

The following graphs are the codes for the figures included in Chapter 5 of the e-book Statistics with Python . import numpy as np import pandas as pd from scipy import stats from sklearn.preprocessing import StandardScaler import yfinance as yf import matplotlib.pyplot as plt import seaborn as sns sns.set_style("darkgrid") #fig511 st=pd.Timestamp(2024, 4,20) et=pd.Timestamp(2024, 5, 30) da1=yf.download('GOOGL', st, et)["Close"] da2=yf.download('MSFT', st, et)["Close"] da1=da1.iloc[:,0].pct_change()[1:]*100 da2=da2.iloc[:,0].pct_change()[1:]*100 da=pd.DataFrame([da1, da2], index=['data1', 'data2']).T da.index=range(len(da1)) mu1, sd1, n1=np.mean(da1), np.std(da1, ddof=1), len(da1) mu2, sd2, n2=np.mean(da2), np.std(da2, ddof=1), len(da2) s_p=np.sqrt(((n1-1)*sd1**2+(n2-1)*sd2**2)/(n1+n2-2)) se=s_p*np.sqrt((1/n1+1/n2)) df=n1+n2-2 mu=mu1-mu2 testStatic=((mu1-mu2)-0)/se x=np.linspace(-3, 3, 500) p=stats.t.pdf(x, df) l=stats.t...

다음 그래프들은 전자책 파이썬과 함께하는 통계이야기 6 장과 7장에 수록된 그림들의 코드들입니다. import numpy as np import pandas as pd from scipy import stats from sklearn.preprocessing import StandardScaler import FinanceDataReader as fdr import yfinance as yf import statsmodels.api as sm from statsmodels.formula.api import ols from sklearn.linear_model import LinearRegression import matplotlib.pyplot as plt import seaborn as sns sns.set_style("darkgrid") #fig 611 st=pd.Timestamp(2024,1, 1) et=pd.Timestamp(2024, 5, 30) code=["^KS11", "^KQ11", "^DJI", "KRW=X"] nme=['kos','kq','dj','WonDol'] da=pd.DataFrame() for i in code: x=yf.download(i,st, et)['Close'] x1=x.pct_change() da=pd.concat([da, x1], axis=1) da.columns=nme da1=da.dropna() da1.index=range(len(da1)) da2=pd.melt(da1, value_vars=['kos', 'kq', 'dj', 'WonDol'], var_name="idx", value_name="val") model=ols("val~...

다음 그래프들은 전자책 파이썬과 함께하는 통계이야기 5 장에 수록된 그림들의 코드들입니다. import numpy as np import pandas as pd from scipy import stats from sklearn.preprocessing import StandardScaler import FinanceDataReader as fdr import yfinance as yf import matplotlib.pyplot as plt import seaborn as sns sns.set_style("darkgrid") #fig 511 st=pd.Timestamp(2024, 4,20) et=pd.Timestamp(2024, 5, 30) da1=fdr.DataReader('091160', st, et)["Close"] da2=fdr.DataReader('005930', st, et)["Close"] da1=da1.pct_change()[1:]*100 da2=da2.pct_change()[1:]*100 da=pd.DataFrame([da1, da2], index=['data1', 'data2']).T da.index=range(len(da1)) mu1, sd1, n1=np.mean(da1), np.std(da1, ddof=1), len(da1) mu2, sd2, n2=np.mean(da2), np.std(da2, ddof=1), len(da2) s_p=np.sqrt(((n1-1)*sd1**2+(n2-1)*sd2**2)/(n1+n2-2)) se=s_p*np.sqrt((1/n1+1/n2)) se=s_p*np.sqrt((1/n1+1/n2)) df=n1+n2-2 mu=mu1-mu2 ci=stats.t.interval(0.95, df, mu, se) testStatic=((mu1-mu2)-0)/se x=np.linspace(-3, 3, 500) ...

Q-Q plot 관련된 내용 Q-Q plot shapiro-Wilk test Kolmogorov-Smirnov Test Anderson-Darling 검정 Jarque-Bera test Q-Q(사분위수) plot은 두 자료들을 분위수로 구분한 후 동일한 분위수 값들에 대해 작성한 도표로서 두 그룹의 분포를 비교하는 방법으로 역누적분포에 의해 설명됩니다. 역누적분포 (Inverse cumulative distribution) 는 누적분포의 역함수입니다. 예를 들어 표준정규분포의 누적분포와 역누적분포는 그림 1과 같이 나타낼 수 있습니다. 그림 1. 표준정규분포의 (a) pdf, cdf와 (b)역누적확률분포. x=np.linspace(-3, 3,1000) pdf=stats.norm.pdf(x) cdf=stats.norm.cdf(x) q=np.linspace(0, 1, 1000) ppf=stats.norm.ppf(q) plt.figure(figsize=(8, 5)) plt.subplots_adjust(wspace=0.3) plt.subplot(1,2,1) plt.plot(x, pdf, color="blue", label="PDF") plt.plot(x, cdf, color="red", label="CDF") plt.xlabel("x") plt.ylabel("probability") plt.legend(loc="best") plt.title("(a)", loc="left") plt.subplot(1,2,2) plt.plot(q, ppf, color="green", label="Inverse CDF") plt.xlabel("probaility(q)") plt.ylabel("I(q)") plt.leg...