Pandas Interviews Preparations (Questions and Answers)

Data cleaning is the process of identifying and correcting errors, inconsistencies, and inaccuracies in datasets to improve data quality.

2. Why is data cleaning important?

It ensures accurate analysis, better decision-making, and improved model performance in data science.

3. What are missing values?

Missing values are data points that are not recorded or are unavailable in a dataset.

4. How can missing values be handled?

They can be removed, filled with mean/median/mode, or predicted using algorithms.

5. What is data inconsistency?

It occurs when the same data is stored in different formats or values.

6. What are duplicate records?

Duplicate records are repeated entries in a dataset that can bias analysis.

7. How do you remove duplicates?

Using functions like drop_duplicates() in data tools.

8. What is data normalization?

It is the process of scaling data to a standard range.

9. What is data standardization?

It transforms data to have mean 0 and standard deviation 1.

10. What are outliers?

Outliers are extreme values that differ significantly from other observations.

26. What is data validation?

It ensures that data meets predefined rules and constraints.

27. What is data transformation?

It is converting data into a suitable format for analysis.

28. What is data wrangling?

Data wrangling is the process of cleaning and transforming raw data into usable format.

29. What is a null value?

A null value represents missing or undefined data.

30. What is imputation?

Imputation is the process of replacing missing data with substituted values.

51. What is data manipulation?

It involves modifying data to make it more organized and useful.

52. What is filtering?

Filtering is selecting specific rows based on conditions.

53. What is sorting?

Sorting arranges data in ascending or descending order.

54. What is grouping?

Grouping combines data based on similar values for aggregation.

55. What is aggregation?

Aggregation performs calculations like sum, average, count on grouped data.

76. What is pivoting?

Pivoting reshapes data from rows to columns.

77. What is melting?

Melting converts columns into rows.

78. What is joining datasets?

Joining combines two datasets based on a common column.

79. What is merging?

Merging integrates datasets similarly to SQL joins.

80. What is concatenation?

Concatenation combines datasets along rows or columns.

81. What is indexing?

Indexing allows quick access to data rows and columns.

82. What is slicing?

Slicing extracts subsets of data.

83. What is feature engineering?

Creating new features from existing data to improve models.

84. What is encoding?

Encoding converts categorical data into numerical form.

85. What is one-hot encoding?

It converts categories into binary columns.

86. What is label encoding?

Assigning unique numbers to categories.

87. What is scaling?

Scaling adjusts data range for consistency.

88. What is binning?

Binning groups continuous data into intervals.

89. What is reshaping?

Changing the structure of data.

90. What is time series manipulation?

Handling and analyzing time-based data.

91. What is window function?

Performs calculations across a set of rows.

92. What is rolling average?

Calculates average over a sliding window.

93. What is cumulative sum?

Running total of values.

94. What is rank function?

Assigns ranking to data values.

95. What is transformation pipeline?

Sequence of data processing steps.

96. What is ETL?

Extract, Transform, Load process for data integration.

97. What is data integrity?

Accuracy and consistency of data.

98. What is schema?

Structure of database or dataset.

99. What is data pipeline?

Automated data processing workflow.

100. What is data governance?

Management of data availability, usability, and security.