How can you prevent data leakage when using the `train_test_split` function from scikit-learn?By shuffling the data using the `shuffle` parameterBy setting a random stateBy increasing the test sizeBy using the `stratify` parameter with categorical target variables

Which function in scikit-learn is used to split data into training and testing sets?Answer areatrain_test_split()split_data()data_split()train_test()

What is the main characteristic of Shuffle Split Cross-Validation?Review LaterIt preserves the class distribution within each foldIt uses historical data for training and recent data for validationIt creates random train/validation splits with controlled proportionsIt ensures that samples belonging to the same group are kept together

Why do you think it is important to shuffle the dataset?

The default value of test_size parameter in train_test_split() is _____.1 point0.250.20.80.32. The confusion_matrix() function comes under _____ module.1 pointsklearn.utilssklearn.metricssklearn.model_selectionsklearn.calibration3. Pandas ______ is used to view some basic statistical details like percentile, mean, std etc. of a data frame.1 pointdescribe()desc()details()info()4. Consider a dataframe df containg two tuples. Then df.head() will return1 pointFive tuples where bottom 3 containing NoneFive tuples where bottom 3 containing garbage valuesTwo tuplesError5. To select a specific column (say ‘col3’) from a dataframe (say ‘df’), we have to write1 pointdf(‘col3’)df[['col3']]df.col3df[3]6. To implement linear regression, we can use _____.1 pointsklearn.model_selection.LinearRegression()sklearn.multiclass.LinearRegression()sklearn.preprocessing.LinearRegression()sklearn.linear_model.LinearRegression()7. What is the effect of following line:                                                 df = df.dropna(axis=0)1 pointDrops all rowsDrops all columnsDrop rows with null valuesDrop columns with null values8. Following data points represents ___________.1 pointPositive CorrelationNegative CorrelationNegative CovarianceZero Covariance9. Regression is one of the types of supervised learning models, where data is classified according to labels and output data need not be continuous. (True/False)1 pointTrueFalse10. Which of the following is defined as the measure of balance between precision and recall?1 pointAccuracyF1-scoreReliabilityPunctuality11. _____ helps to find the best model that represents our data and how well the chosen model will work in future.1 pointEvaluationPerformance MeasureLearningValidation12. While evaluating a model's performance, recall parameter considers _____.1 pointFalse PositiveFalse NegativeTrue PositiveTrue Negative13. Two conditions when prediction matches with the reality are true positive and __________.1 pointFalse PositiveFalse NegativeTrue PositiveTrue Negative14. Odd man out:Regression, Classification, Clustering1 pointRegressionClassificationClustering15. Which of the following talks about how true the predictions are by any model?1 pointAccuracyReliablityRecallF1-score16. Which of the following tasks can be best solved using reinforcement learning?1 pointPredicting the amount of rainfall based on various cuesDetecting fraudulent credit card transactionsTraining a robot to solve a maze17. During linear regression, with regard to residuals, which among the following is true?1 pointLower is betterHigher is betterDepends upon the dataNone of the above18. We can handle missing values in Machine Learning by1 pointDeleting rows with missing valuesReplacing with the mean, median, or mode of remaining values in the columnReplacing with the most frequent categoryAll of the mentioned19. Which of the following is NOT supervised learning?1 pointPCADecision TreeLinear RegressionNaive Bayesian20. A computer program is said to learn if1 pointIt improves with experienceIt learns from experienceIt learns from mistakesIt learns from supervisor21. A well-defined learning problem must include1 pointTaskPerformance measureTraining experienceAll of the mentioned22. Inductive bias is the assumption made by the learner.1 pointTrueFalse23. If X represents a matrix of feature, then1 pointA row in the X represents one data point or one instanceA column in the X represents one feature or one attributeAll of the mentionedNone of the mentioned24. Semi-supervised Learning combines a __________ with a __________ during training.1 pointsmall amount of labelled data, large amount of unlabelled datasmall amount of labelled data, small amount of unlabelled datalarge amount of labelled data, large amount of unlabelled datalarge amount of labelled data, small amount of unlabelled data25. In multiple regression, we have ____ independent variable and _____ dependent variable.1 pointsingle, singlemore than one, singlemore than one, more than onesingle, more than one26.  Entropy([9+,5-]) = ?1 point0.2460.2830.940.6527.  Entropy([5+,0-]) = ?1 point0.50.25010.7528. To measure the overall strength of the model in regression analysis, we use _______.1 pointFactor analysisCoefficient of partial correlationCoefficient of partial regressionCoefficient of determination29.  What is the purpose of performing cross-validation?1 pointTo assess the predictive performance of the modelsTo judge how the trained model performs outside the sample on test dataAll of the mentionedNone of the above30. What does p indicate in the following figure?1 pointProportionProbabilityPrecisionPercentage

10. import pandas as pdfrom sklearn.preprocessing import train_test_splitdf = pd.read_csv('insurance_claims.csv')xtrain, xtest, ytrain, ytest = train_test_split(df.drop("is_claim", axis=1), df.is_claim, test_size=0.3, random_state=42)Which of the following is true about the code above?The code reads a csv file named insurance_claims. It splits the data into train and test sets. The test split contains 30% of the data. The random state makes sure that the data is split at random to remove inherent order which may be in the data. When the code is run multiple times it produces the diffent splits since `train_test_split` with the parameter `random_state` splits data at random.None of the given answersThe code reads a csv file names insurance claims. The `train_test_split` function will give an error since the second position argument `df.is_claim` is referencing a column that has been drop on the first position argument `df.drop("is_claim", axis=1)The code reads a csv file named insurance_claims. It splits the data into train and test sets. The train split contains 70% of the data. The random state makes sure that when the code is run multiple times it produces the same identical splits since `train_test_split` splits data at random.