6 Which of the following statements create a new feature d, storing the sum of columns a and b? df_1['b'] + df_1['c'] df_1['d'] = df_1['b'] + df_1['c'] + df_1['a'] + df_1['b'] df_1['d'] = df_1['a'] + df_1['b'] 7 Which of the following statements would create a one-hot-encoded copy of the df_1 data frame? pd.one_hot_encode(df_1, prefix_sep='_', drop_first=True) df_1_dumm = one_hot_encode (df_1, prefix_sep='_', drop_first=True) df_1_dumm = pd.get_dummies(df_1, prefix_sep='_', drop_first=True) pd.get_dummies(df_1, prefix_sep='_', drop_first=True) 8 Which of the following linear models are appropriate for binary classification problems? Logistic Regression Linear Regression 9 Which of the following two-line statements correctly initialize and train a logistic regression model with sklearn (assume we have already done a train test split)? logistic_model = LogisticRegression() logistic_model.fit(x_train, y_train) = logistic_model = LogisticRegression() logistic_model.fit(y_train, x_train) logistic_model = LogisticModel() logistic_model.fit(x_train, y_train) = logistic_model = LogisticModel() logistic_model.fit(y_train, x_train) 10 What is the precision of the model that generated the confusion matrix? 35000 30000 35801 676 25000 20000 True label 15000 1 9715 439 10000 -5000 1 Predicted label 0.21 0.39 0.78 0.04