1/18/2019 Udacity Reviews

Back to Data Analyst Nanodegree

Investigate a Dataset
REVIEW

HISTORY

Requires Changes
3 S PE CI FI CA TION S REQU IRE C H A N G ES

Dear Student, Very good submission !!! You are just one step closer to the project completion !!! There are few
speci cations to be included in the project. Carefully go through all the speci cations and do the changes
wherever required in your next submission.

Keep up your good work !!!

This is starting point of your Data Science Career. And I would say you landed in the right place. If interested,
download more real time dataset from kaggle.com and do analysis on those datasets.

Here are few references you could use :

https://chrisalbon.com/
https://machinelearningmastery.com/
https://machinelearningmastery.com/data-cleaning-turn-messy-data-into-tidy-data/
www.kaggle.com
www.analyticsvidhya.com

As you know math algebra is the basis of all our data analysis. Again to refresh those topics there are many links
and you might have come across them in the course itself.

khanacademy
mathisfun
https://www.youtube.com/watch?v=Dft1cqjwlXE

Code Functionality

https://review.udacity.com/#!/reviews/1666952 1/5
1/18/2019 Udacity Reviews

All code is functional and produces no errors when run. The code given is su cient to reproduce the
results described.

The project uses NumPy arrays and Pandas Series and DataFrames where appropriate rather than
Python lists and dictionaries. Where possible, vectorized operations and built-in functions are used
instead of loops.

The code makes use of functions to avoid repetitive code. The code contains good comments and
variable names, making it easy to read.

This is still missing in the project. To meet this speci cation, you need to add a new function or move a piece
of code into a function and execute that function.

Some examples on how to use function : ( pls ignore this if you already have an idea about function and how
to implement it in the code. This is meant for the students who need help on function implementation. )

def multiply(x,y=0):
print("value of x=",x)
print("value of y=",y)
return x*y

print(multiply(y=2,x=4))

Basically we use function to reuse the same piece of code to execute the same function. Instead of writing
the same functionality again and again, put that piece of code inside function and call that function
wherever required. Say for example in a project we make same kind of plots many times. We can have the
plot implementation in a function.

Quality of Analysis

The project clearly states one or more questions, then addresses those questions in the rest of the
analysis.

You have stated questions in the exploratory phase but previous reviewer has given feedback to de ne
them in the beginning of the project.

For any Data Science Project, rst thing to do is to state the questions given by the client. Here for our
project, its data analyst rst work to de ne the questions to be analysed. All the other phases will be done
based on those initially stated questions.

Data Wrangling Phase

https://review.udacity.com/#!/reviews/1666952 2/5
1/18/2019 Udacity Reviews

The project documents any changes that were made to clean the data, such as merging multiple les,
handling missing values, etc.

You have done some cleaning required for the analysis. Meet the speci cation. In any code, its always a
good practice to give comments and elaborate explanation. That way anyone can understand the code
structure and understand the code ow correctly.

Exploration Phase

The project investigates the stated question(s) from multiple angles. At least three variables are
investigated using both single-variable (1d) and multiple-variable (2d) explorations.

The project's visualizations are varied and show multiple comparisons and trends. Relevant statistics are
computed throughout the analysis when an inference is made about the data.

At least two kinds of plots should be created as part of the explorations.

Conclusions Phase

The results of the analysis are presented such that any limitations are clear. The analysis does not state
or imply that one change causes another based solely on a correlation.

This is also missing in the conclusion phase.

Here are few suggestions about limitations :

Limitations are something you come across while doing the analysis part in the dataset itself which may or
may not a ect the nal predictions. What hinders your analysis with the current data? And be elaborate in
your analysis why you say there are hindrances?

Say for example, there are more than 5 to 10% of data is having null values or highly correlated having
erroneous or missing values or imbalanced data. Sample doesn't represent the population.All these will lead
either to wrong analysis which will lead to wrong predictions or biased analysis. Such ones only should be
mentioned as your limitations.

In such cases, its always good to list down and give elaborate explanation about the limitations and what
way it may a ect the output. Be very speci c while mention about limitations.

After completing the analysis if you feel there are no limitations in the input dataset, you can as well
mention that there are no limitations in this project.

Communication

https://review.udacity.com/#!/reviews/1666952 3/5
1/18/2019 Udacity Reviews

Reasoning is provided for each analysis decision, plot, and statistical summary.

For any Data Science Project, you need to give an elaborate explanation for every part of your analysis. The
reason because you need to convince client about your analysis. This analysis doesn't stop here. Client will
be using this analysis outcome for further analysis or some predictions to take any important business
decisions. That's the value this analysis carries. Have more write up will ease the part of conveying your
analysis inference.

As previous reviewer mentioned, add few lines about what do you infer from the analysis after visual part of
each question to meet this speci cation.

Visualizations made in the project depict the data in an appropriate manner that allows plots to be
readily interpreted.

Every visual must have axes and data labels, title and legend ( if any). All the visuals in the project are neatly
labelled with title.

 RESUBMIT

DOWNLOAD PROJECT

https://review.udacity.com/#!/reviews/1666952 4/5
1/18/2019 Udacity Reviews

Best practices for your project resubmission

Ben shares 5 helpful tips to get you through revising and resubmitting your project.

 Watch Video (3:01)

RETURN TO PATH

https://review.udacity.com/#!/reviews/1666952 5/5