| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | --- | 
					
						
							|  |  |  | id: 5e9a093a74c4063ca6f7c15d | 
					
						
							|  |  |  | title: Data Cleaning Introduction | 
					
						
							|  |  |  | challengeType: 11 | 
					
						
							| 
									
										
										
										
											2020-06-23 17:36:39 +05:30
										 |  |  | isHidden: false | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | videoId: ovYNhnltVxY | 
					
						
							|  |  |  | --- | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | ## Description
 | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | <section id='description'> | 
					
						
							| 
									
										
										
										
											2020-07-17 05:12:45 -04:00
										 |  |  | More resources: | 
					
						
							|  |  |  | - <a href="https://notebooks.ai/rmotr-curriculum/data-cleaning-rmotr-freecodecamp-fd76fa59" target='_blank'>Notebook</a> | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | </section> | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | ## Tests
 | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | <section id='tests'> | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  | ````yml | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | question: | 
					
						
							| 
									
										
										
										
											2020-05-28 22:40:36 +09:00
										 |  |  |   text: | | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  |     What will the following code print out? | 
					
						
							| 
									
										
										
										
											2020-05-28 22:40:36 +09:00
										 |  |  | 
 | 
					
						
							|  |  |  |     ```py | 
					
						
							|  |  |  |     import pandas as pd | 
					
						
							|  |  |  |     import numpy as np | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |     s = pd.Series(['a', 3, np.nan, 1, np.nan]) | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |     print(s.notnull().sum()) | 
					
						
							|  |  |  |     ``` | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  |   answers: | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  |     - | | 
					
						
							|  |  |  |       3 | 
					
						
							| 
									
										
										
										
											2020-05-28 22:40:36 +09:00
										 |  |  |     - | | 
					
						
							|  |  |  |       ``` | 
					
						
							|  |  |  |       0     True | 
					
						
							|  |  |  |       1     True | 
					
						
							|  |  |  |       2    False | 
					
						
							|  |  |  |       3     True | 
					
						
							|  |  |  |       4    False | 
					
						
							|  |  |  |       dtype: bool | 
					
						
							|  |  |  |       ``` | 
					
						
							|  |  |  |     - | | 
					
						
							|  |  |  |       ``` | 
					
						
							|  |  |  |       0    False | 
					
						
							|  |  |  |       1    False | 
					
						
							|  |  |  |       2     True | 
					
						
							|  |  |  |       3    False | 
					
						
							|  |  |  |       4     True | 
					
						
							|  |  |  |       dtype: bool | 
					
						
							|  |  |  |       ``` | 
					
						
							|  |  |  |   solution: 1 | 
					
						
							| 
									
										
										
										
											2020-08-04 20:56:41 +01:00
										 |  |  | ```` | 
					
						
							| 
									
										
										
										
											2020-04-21 12:42:19 -04:00
										 |  |  | 
 | 
					
						
							|  |  |  | </section> |