MISTAKE #4
— 👩💻 @DynamicWebPaige 🔜 #APICityConf 🌇 (@DynamicWebPaige) September 27, 2018
Failing to report a confidence interval as well as the p-value. You need both!
👉The p-value tells you if something is statistically significant.
👬The confidence interval tells you what the population value might be.
For example, if we look at gender and phone use: pic.twitter.com/smUbbV8st3
MISTAKE #3
— 👩💻 @DynamicWebPaige 🔜 #APICityConf 🌇 (@DynamicWebPaige) September 27, 2018
Implementing experiments that are poorly designed. 🔬
📊Study doesn't have enough power to call meaningful differences statistically significant.
👎Includes concluding that the null hypothesis is true - should be "not enough evidence to say that the null is false".
MISTAKE #1:
— 👩💻 @DynamicWebPaige 🔜 #APICityConf 🌇 (@DynamicWebPaige) September 27, 2018
Garbage in, garbage out.
🤦♀️Failing to investigate your input for data entry or recording errors.
📊Failing to graph data and calculate basic descriptive statistics (mean, median, mode, outliers, etc.) before analyzing it in-depth. pic.twitter.com/DuBSAw7qJT
📓 Am rereading my class notes from grad school, as well as from mentoring students for @Coursera and @EdX courses on statistics - and thought I'd share the most common mistakes when doing data analysis.
— 👩💻 @DynamicWebPaige 🔜 #APICityConf 🌇 (@DynamicWebPaige) September 27, 2018
✨Have counted 8 of 'em, with examples - please feel free to add your own!
Example of how crucial it is to talk with domain experts https://t.co/YYBRKOe2pk pic.twitter.com/Di5GRw9m7f
— Rachel Thomas (@math_rachel) September 25, 2018
One of my favorite things in Python. Testing if a string A contains a substring B is just "B in A", for example,
— Daily Python Tip (@python_tip) September 24, 2018
>>> x = 'hello'
>>> y = 'll'
>>> y in x
True#pythontip
training to overfit a new model on a small dataset (or existing model on new data) is prob the most important and useful rule in practical DL
— helena sarin (@glagolista) September 20, 2018
(just found a bug in my new code for synthetic data generator 😌)
Use "\N" escape sequence to print #unicode symbols by name.
— Daily Python Tip (@python_tip) September 19, 2018
>>> print('\N{smiling face with sunglasses}’)
😎#python
Overfitting is always a good first step. Overfitting on training data and making sure the results look reasonable and that there are no obvious bugs is what everyone should do first for a new task/model :)
— Denny Britz (@dennybritz) September 17, 2018
When using expand=True in pandas.Series.str.split(), the elements will expand out into separate columns. #python #pandas #python pic.twitter.com/jJVLH2kX4P
— Daily Python Tip (@python_tip) September 17, 2018
For R projects, you can use `devtools::spell_check` to detect any spelling errors. But what about checking writing style for grammatical (& stylistic) errors?
— Indrajeet Patil (@patilindrajeets) September 15, 2018
`gramr` by @jasdumas has you covered!https://t.co/PWpMoGTa2z
(Reminds me of my 5th-grade English teacher 🤣)#rstats pic.twitter.com/eOuMut0XV3
Google Cloud Platform now has preconfigured deep learning images with Tensorflow, PyTorch, Jupyter, Cuda and CuDNN already installed. It took me some time to figure out how to start Jupyter on such an instance. Turns out it's a one liner: pic.twitter.com/oTlSZkpCXE
— Martin Görner (@martin_gorner) September 13, 2018
