PyPyPy

Suppose a complete data frame df is given. Which of the following code converts df into missing data whose missing rate is 20% for each column? c=df.shape[1] (A) for i in range (c): df[i]=df[i].sample(frac=0.8) r=df.shape[0] B for i in range (r) : df[i]=df[i].sample(frac=0.8) c=df.shape[1] (C) for i in range (c): df[i]=df[i].sample(frac=0.2) c=df. shape [1] (D) for i in c : df[i]=df[i].sample(frac=0.2) Suppose imputation by row means is applied to the following data set. What is the imputed value for the shaded cell? 3.5 (B) 3 (C) 2.75 3.25 Given a data set with 500 rows and 15 columns, suppose the data set includes 2700 missing entries. Assume that the true values of the missing entries are known. Consider the following formula for the mean square error: What is the value of m in the formula? Question 12 2 Points Assume that the NumPy package was imported and renamed as np. For a given data frame df with 500 rows, 10 columns, and 400 missing entries, what is the output of the following code? na_ind = np.where (df.isnull()) print(len(na_ind)) Add your answer Given a data set with 100 rows and 10 columns, suppose the data set includes 170 missing entries. Assume that the true values of the missing entries are unknown. 10-fold cross validation is used to measure the performance of an imputation method. Consider the following formula for the individual mean absolute deviation: What is the value of m in the formula