Univariate Data Analysis: concrete strength, 20 data

We have a dataset of 20 data, concrete strength.

We want to develop simple data analysis, including:

• statistics of the samples

• histograms

• empirical cdf

----------------------------------

import numpy as np import matplotlib.pyplot as plt import OpenStat as sta

#===================

DATA SUMMARY

#===================

data=np.loadtxt('concrete20.dat') d=sta.data1(data)

#d is the object collecting the dataset

data=d.data d.disp_summary()

#===================

#HISTOGRAMS

#===================

#Binning

edges=[23, 26, 29, 32, 35, 38, 41] edges=np.array(edges)

#Number of observations d.plot_hist(bins=edges,stat='count')

#bins=edges: limits of the bins #stat='count': number of observations at each bin #color='blue': color of the bars d.ax.set_xlim(23,41) d.ax.set_xticks(edges) d.ax.set_xlabel('$f_c \ MPa$') d.ax.set_title('Concrete strength n=20')

#Relative frequency d.plot_hist(bins=edges, stat='probability')

#bins=edges: limits of the bins #stat='count': number of observations at each bin d.ax.set_xlim(23,41) d.ax.set_xticks(edges) d.ax.set_xlabel('$f_c \ MPa$') d.ax.set_title('Concrete strength n=20')

==================

#EMPIRICAL CDF

#===================

d.plot_cdf_emp()

#plot the empirical cdf d.ax.set_xlim(23,41) d.ax.set_ylim(0,1) d.ax.set_xlabel('$f_c \ MPa$') d.ax.set_ylabel('ecdf') d.ax.set_title('Concrete strength n=20')

d.plot_quantile_emp() #plot the empirical quantile function d.ax.set_xlabel('$probability$') d.ax.set_ylabel('f_c \ MPa') d.ax.set_xlim(0,1) d.ax.set_ylim(23,41) d.ax.set_xlabel('$probability$') d.ax.set_ylabel('$f_c \ MPa$')

concrete20

.txt

Download TXT • 360B