MLF Date-A-Scientist Grade Summary

[mackenzieyoung]

Rubric Score

Criteria 1: Valid Python Code

• Score Level: 4 (Exceeds expectations)
• Comment(s): Very good, your code runs without any errors. However, you're printing out too much information to the console, which makes it difficult to determine what is important information and what isn't.

Criteria 2: Exploration of Data

• Score Level: 2 (Approaches expectations)
• Comment(s): You did explore the data by making some histograms and getting different feature counts, but the experimental questions you chose are not based on the data exploration. For example, you did not explore the relationship between education level with essay text word counts in your initial data exploration, which you could have done by making a plot. If you did this, you might have reason to believe that some questions are more useful to ask than others.

Criteria 3: Machine Learning Techniques used correctly

• Score Level: 3 (Meets expectations)
• Comment(s): The algorithms are used correctly, it is not clear how your conclusions are drawn from the results.

Criteria 4: Report: Are conclusions clear and supported by data?

• Score Level: 1 (Does not meet expectations)
• Comment(s): You state your questions, but you do not explain any of the algorithms you used. What we want is for you to explain the algorithms, including why you chose to use the ones you used. You state some of your conclusions, but in many cases it is not how you got to them, and in particular what is meant by accuracy. For example, when you're comparing the parameter weights in KNN regression, the accuracies are all > 1, which shouldn't be the case if they are a proportion. Your final conclusions are not necessarily based on your model results, and seem to be based on your intuition instead.

Criteria 5: Code formatting

• Score Level: 4 (Exceeds expectations)
• Comment(s): Code is formatted clearly and readable, good use of comments to break it up into sections.

Overall Score: 14/20

Good job writing your code, but your presentation of your results and conclusions needs some work. You should have an explanation of the algorithms you used, why you chose to use those particular ones, and a clear discussion of how your conclusions were drawn based on the results of your models.

[DamianLukasik]

Hi, I have submitted my project. Will I receive feedback tomorrow or monday? Will I have to correct my project again? Will I receive certificate? 

Regards Enjoy weekend :)

 

Sent: Tuesday, November 06, 2018 at 8:51 PM From: "Mackenzie Young" notifications@github.com To: DamianLukasik/date-a-scientist date-a-scientist@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [DamianLukasik/date-a-scientist] MLF Date-A-Scientist Grade Summary (#6)

Rubric Score

Criteria 1: Valid Python Code

Score Level: 4 (Exceeds expectations)
Comment(s): Very good, your code runs without any errors. However, you're printing out too much information to the console, which makes it difficult to determine what is important information and what isn't.

Criteria 2: Exploration of Data

Score Level: 2 (Approaches expectations)
Comment(s): You did explore the data by making some histograms and getting different feature counts, but the experimental questions you chose are not based on the data exploration. For example, you did not explore the relationship between education level with essay text word counts in your initial data exploration, which you could have done by making a plot. If you did this, you might have reason to believe that some questions are more useful to ask than others.

Criteria 3: Machine Learning Techniques used correctly

Score Level: 3 (Meets expectations)
Comment(s): The algorithms are used correctly, it is not clear how your conclusions are drawn from the results.

Criteria 4: Report: Are conclusions clear and supported by data?

Score Level: 1 (Does not meet expectations)
Comment(s): You state your questions, but you do not explain any of the algorithms you used. What we want is for you to explain the algorithms, including why you chose to use the ones you used. You state some of your conclusions, but in many cases it is not how you got to them, and in particular what is meant by accuracy. For example, when you're comparing the parameter weights in KNN regression, the accuracies are all > 1, which shouldn't be the case if they are a proportion. Your final conclusions are not necessarily based on your model results, and seem to be based on your intuition instead.

Criteria 5: Code formatting

Score Level: 4 (Exceeds expectations)
Comment(s): Code is formatted clearly and readable, good use of comments to break it up into sections.

Overall Score: 14/20

Good job writing your code, but your presentation of your results and conclusions needs some work. You should have an explanation of the algorithms you used, why you chose to use those particular ones, and a clear discussion of how your conclusions were drawn based on the results of your models.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.

[mackenzieyoung]

Hi Damian! This is your grade and feedback, you do not need to submit again!