datasciencespecialization/courses

Course materials for the Data Science Specialization: https://www.coursera.org/specialization/jhudatascience/1

courses's Issues

Link to the EPS data in the case study video is broken

A quick-test question asks us to download data from

http://www.epa.gov/ttn/airs/airsaqs/detaildata/downloadaqsdata.htm

but we only get:

The Air Quality System (AQS) and AQS Data Mart websites have been updated and moved.

The new AQS website is at www2.epa.gov/aqs

The new AQS Data Mart is at https://aqs.epa.gov/aqsweb/documents/data_mart_welcome.html

The link should be changed to

http://aqsdr1.epa.gov/aqsweb/aqstmp/airdata/download_files.html

(Courtesy of Charles Wylie)

Rename folders by week and lecture numbers?

I like the way that Jeff has named the folders in his courses, like 01_02_topic for lecture 2 in week 1. It would be cool if the folders in Rogers' courses were renamed in the same way. It'd be a little easier to find things.

If you want, I'll do the work and submit a pull request, but I don't want to go to the effort if you wouldn't like it.

Download

How can i download the files so that i can view them locally? there is not download option.

Probability Lecture 01_02_Probability Figures aren't showing up

Title says it all... Images within the pdf/slides don't show up.

serve the pages

since it's mostly web pages

with github you just have to push it on gh-pages branch

git co -b gh-pages
git push gh-pages origin/gh-pages

then it will be visible on
http://DataScienceSpecialization.github.io/courses

Necrobot download page not found?

Necrobot download page not found?

Practical Machine Learning/ 016preProcessingPCA - Lecture example code change

This lecture needs to be updated, there is a change in how the "train" function has to be used.

With new version of caret (version 6.0-71), The lecture code:
modelFit <- train(training$type ~ .,method="glm",data=trainPC)`
gives an error.

I raised the issue with the caret package people.
https://github.com/topepo/caret/issues/480
They say this code is incorrect, we should use instead:
modelFit <- train(x = trainPC, y = training$type,method="glm")

You shouldn't use the data set name on the LHS of the formula. The formula interface should be used when the variables are in columns of the object that the data argument refers to.

If type is not in training and there are only numeric variables in trainPC, then you should use the non-formula method:
modelFit <- train(x = trainPC, y = training$type,method="glm")

Getting and Cleaning Data:Reading from Web example now fully out of date

For lecture 02_03_readingFromTheWeb in Getting and Cleaning Data, google are now loading the Google Scholar page via javascript rather than delivering static text, so all anyone who tries out the lecture code will get is an error message in the content in R (which is what you get if you visit the page with javascript off and a clear web browser cache).

Missing slides in ReproducibleResearchConcepts

"ReproducibleResearchConcepts" of "05_ReproducibleResearch" only contains 2 slides.

move a couple Swirl lessons to better match the EDA lectures

[I couldn't find in this repo where this would be specified, so perhaps it pertains more to do with setup in Coursera. Whatever the case, please pass these requests on to the applicable inbox.]

Course: 04_ExploratoryAnalysis

Request 1: Move the Swirl lesson "Working with Colors" from week 2 to week 3.
Request 2: Move the Swirl lesson "Clustering Example" from week 3 to week 4.

Thanks,
Steve

025combiningPredictors: Accuracy typo

025combiningPredictors/index.Rmd line 70:

- * $10\times(0.7)^3(0.3)^2 + 5\times(0.7)^4(0.3)^2 + (0.7)^5$
+ * $10\times(0.7)^3(0.3)^2 + 5\times(0.7)^4(0.3) + (0.7)^5$

Peer to peer evaluation

Hi, Jeff.
What shall I do when I find that two Course Project submissions are 99% identical? What is the preferable way of handling it?

Clean up and rewrite Git repository (or break it up)

This Git repository alone weighs in at 1073 MB (!!!) presently, which is infeasible to clone over anything but a decent broadband connection. A local clone (including work tree) is > 2GB.

It seems over time a lot of unnecessary and large binary files have accumulated (e.g. zip files with another copy of files already in the repository). Some have been removed again, but they're still present in the history.

It would be great to clean up this repository, remove unnecessary files and rewrite the history to get the repository size down using e.g. BFG Repo Cleaner.

Alternatively it might be better to split it up into repositories for each of the courses.

R-Enthusiasts is dead

In Hierarchical Clustering (part 3) (Exploratory Data Analysis, week 3) you link to r-enthusiasts.com.

This website does not seem to exist anymore.

DataScientistToolbox: Error in Announcements

There are two error that I noticed in the file "courses / 01_DataScientistToolbox / announcements.md"

In first sentence of the week 3 announcement and the week 4 announcement, the course is referred to as "Obtaining Data" rather than "Data Scientist's Toolbox." I am unsure if the entire announcement is from the wrong class or if it is just the name of the class that's wrong.

Typo hw2 slide 8: change vs chance

typo in 07_RegressionModels/02_01_multivariate slide 10

the last plus of the equation should be an minus

In ExploratoryAnalysis/clusteringExample no legend for the colors in slide 7

In the Exploratory Analysis classes, the slide 7 of the clustering example don't have legend. This is then hard to understand about what we are talking about. It's possible to refer to slide 5 to have the legend but it should be easy to add it on this slide.

Thank you for these nice classes!

swirl Lesson T Confidence Intervals encountered an error

When finish the step t.test(difference)$conf.int and come to the next step, it always comes out this error message, "Error in editor(file = file, title = title) : argument "name" is missing, with no default", and leaving swirl, "Leaving swirl now. Type swirl() to resume."

Dropbox links broken

I can't download either of the dropbox files for the lecture. Here is what happens:

fileUrl1 = "https://dl.dropboxusercontent.com/u/7710864/data/reviews-apr29.csv"
fileUrl2 = "https://dl.dropboxusercontent.com/u/7710864/data/solutions-apr29.csv"
download.file(fileUrl1,destfile="./data/reviews.csv",method="curl")
Error in download.file(fileUrl1, destfile = "./data/reviews.csv", method = "curl") :
'curl' call had nonzero exit status
In addition: Warning message:
running command 'curl "https://dl.dropboxusercontent.com/u/7710864/data/reviews-apr29.csv" -o "./data/reviews.csv"' had status 127
download.file(fileUrl2,destfile="./data/solutions.csv",method="curl")
Error in download.file(fileUrl2, destfile = "./data/solutions.csv", method = "curl") :
'curl' call had nonzero exit status
In addition: Warning message:
running command 'curl "https://dl.dropboxusercontent.com/u/7710864/data/solutions-apr29.csv" -o "./data/solutions.csv"' had status 127

So I got rid of "curl" and tried again, with these results:

download.file(fileUrl1,destfile="./data/reviews.csv")
trying URL 'https://dl.dropboxusercontent.com/u/7710864/data/reviews-apr29.csv'
Error in download.file(fileUrl1, destfile = "./data/reviews.csv") :
cannot open URL 'https://dl.dropboxusercontent.com/u/7710864/data/reviews-apr29.csv'
In addition: Warning message:
In download.file(fileUrl1, destfile = "./data/reviews.csv") :
cannot open URL 'https://dl.dropboxusercontent.com/u/7710864/data/reviews-apr29.csv': HTTP status was '404 Not Found'
download.file(fileUrl2,destfile="./data/solutions.csv")
trying URL 'https://dl.dropboxusercontent.com/u/7710864/data/solutions-apr29.csv'
Error in download.file(fileUrl2, destfile = "./data/solutions.csv") :
cannot open URL 'https://dl.dropboxusercontent.com/u/7710864/data/solutions-apr29.csv'
In addition: Warning message:
In download.file(fileUrl2, destfile = "./data/solutions.csv") :
cannot open URL 'https://dl.dropboxusercontent.com/u/7710864/data/solutions-apr29.csv': HTTP status was '404 Not Found'

Please help. Thanks!

Unable to find residual related zip files.

"swirl" package mentioned : Residuals. (Slides for this and other Data Science courses may be found at github https://github.com/DataScienceSpecialization/courses. If you care to use them,
| they must be downloaded as a zip file and viewed locally. This lesson corresponds to Regression_Models/01_03_ols.

But I don't see any zip file here. Pleas help

Wrong graphic in 04_Exploratory Analysis / kmeansClustering / slide 13 Heatmaps

In the course 04 Exploratory Analysis, Week 3, lecture kmeansClustering, slide 13, a couple of heatmaps are compared side by side to show the benefits of combining heatmaps with hierarchical clustering, unfortunately because of a typo the second heatmap picks the wrong order and looks as random as the first one.

I see the typo has already been fixed in the "index.*" files of the repository!

But all the images and pdf files are still wrong:

• fig/unnamed-chunk-7.png
• figure/unnamed-chunk-7.png
• slides_169/kmeans_16913.png
• slides_169/kmeans_16913.png
• slides_letter/kmeans_letter13.png
• K-meansClustering_169.pdf
• K-meansClustering_letter.pdf

are you missing a "make all"?

Statistical Inference Homework 1 Slide 10

At "Show Hint" incorrect expression to a Variance.
Should be a "The variance is E[X^2]−E[X]^2". Isnt "The variance is E[X^2]−E[X^2]".

Minor spelling error - Exploratory Data Analysis - K-Means Clustering

In Exploratory Data Analysis, Week 3, K-Means Clustering (part 1)

slide

- Continous - correlation similarity
+ Continuous - correlation similarity

Warning message being showing for the Statistical Inference exercises

When completing the Statistical Inference exercise, the following warning message shows up:

warning messages from top-level task callback 'mini'
Warning messages:
1: Use of `dat$y` is discouraged. Use `y` instead. 
2: Use of `dat$y` is discouraged. Use `y` instead. 
3: Use of `dat$y` is discouraged. Use `y` instead.

link to Gottardo's notes on data.table does not exist

https://github.com/DataScienceSpecialization/courses/blob/master/03_GettingData/01_09_dataTable/index.md
last link on the page

https://github.com/OpenClassrooms-Student-Center/Billed-app-FR-Front/blob/main/src/app/Store.js

https://github.com/OpenClassrooms-Student-Center/Billed-app-FR-Front/blob/main/src/app/Store.js

Incorrect values for information in predictingWithTrees lecture.

In 08_PracticalMachineLearning/019predictingWithTrees/index.Rmd line 127:

-* __Information:__$-[1/16 \times log2(1/16) + 15/16 \times log2(15/16)] = 1$
+* __Information:__$-[8/16 \times log2(8/16) + 8/16 \times log2(8/16)] = 1$

Wrong graph with the ggplot2 “Hello, world!” example

In Exploratory Data Analysis - Week 2 - ggplot2 (part 2) a wrong graph is shown in the ggplot2_p1.md file
the wrong image file is located here: 04_ExploratoryAnalysis/ggplot2/fig/unnamed-chunk-2.png

Stat Inference: In Quiz 2, Questions 6,7 and 10 don't have a way to enter a response