作業一：判斷資料趨勢（正偏/負偏/對稱）

# Pandas and numpy for data manipulation import pandas as pd import numpy as np

# matplotlib for plotting import matplotlib.pyplot as plt import matplotlib from scipy import stats from scipy.stats import norm # Set text size matplotlib.rcParams['font.size'] = 18 # Seaborn import seaborn as sns sns.set_context('talk', font_scale=1.2);

df = pd.read_csv('hw1常態分配資料集.csv') df.columns = ['Object','A1','A2','A3'] df

data = df.A1 sns.distplot(data, fit=norm, rug=True, hist=False) # sns.displot(data,kind="kde",rug=True) (mu, sigma) = norm.fit(data) print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma)) plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)],loc='best') #圖中的藍色線標題 plt.ylabel('Frequency') plt.title('Distribution') plt.show()

data = df.A2 sns.distplot(data, fit=norm, rug=True, hist=False) # sns.displot(data,kind="kde",rug=True) (mu, sigma) = norm.fit(data) print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma)) plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)],loc='best') plt.ylabel('Frequency') plt.title('Distribution') plt.show()

data = df.A3 sns.distplot(data, fit=norm, rug=True, hist=False) # sns.displot(data,kind="kde",rug=True) (mu, sigma) = norm.fit(data) print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma)) plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)],loc='best') plt.ylabel('Frequency') plt.title('Distribution') plt.show()

a1 = stats.kstest(df.A1,'norm',(mu,sigma)) a2 = stats.kstest(df.A2,'norm',(mu,sigma)) a3 = stats.kstest(df.A3,'norm',(mu,sigma)) print(a1) print(a2) print(a3)