it-ebooks - Computational and Inferential Thinking (UCB Data8)

def permutation_test_means ( table , variable , classes , repetitions ): """Test whether two numerical samples come from the same underlying distribution, using the absolute difference between the means. table: name of table containing the sample variable: label of column containing the numerical variable classes: label of column containing names of the two samples repetitions: number of random permutations""" t = table . select ( variable , classes ) # Find the observed test statistic means_table = t . group ( classes , np . mean ) obs_stat = abs ( means_table . column ( ) . item ( ) - means_table . column ( ) . item ( )) # Assuming the null is true, randomly permute the variable # and collect all the generated test statistics stats = make_array () for i in np . arange ( repetitions ): shuffled_var = t . select ( variable ) . sample ( with_replacement = False ) . column ( ) shuffled = t . select ( classes ) . with_column ( 'Shuffled Variable' , shuffled_var ) m_tbl = shuffled . group ( classes , np . mean ) new_stat = abs ( m_tbl . column ( ) . item ( ) - m_tbl . column ( ) . item ( )) stats = np . append ( stats , new_stat ) # Find the empirical P-value: emp_p = np . count_nonzero ( stats >= obs_stat ) / repetitions # Draw the empirical histogram of the tvd's generated under the null, # and compare with the value observed in the original sample Table () . with_column ( 'Test Statistic' , stats ) . hist ( bins = ) plots . title ( 'Empirical Distribution Under the Null' ) print ( 'Observed statistic:' , obs_stat ) print ( 'Empirical P-value:' , emp_p )