• About
  • tutorials and posts
  • Talks and workshops
  • Papers
Menu

Summer K. Rankin

  • About
  • tutorials and posts
  • Talks and workshops
  • Papers

My dog and pony show

dcft19.jpg

DCFem Tech Awards 2019 and Written Feedback

June 12, 2019

Moral of the story is this: give good and ‘bad’ feedback to your mentees often and in writing. It will make it easier for you and them to do things like nominate themselves or write a recommendation. Also, when you write for a women, read it and ask yourself if you would say those same things about a man. It will help you adjust any biased language that got in there.

Read More
In Issues Tags data science, women
2 Comments

Want more women in technology? Stop throwing out their resumes.

October 31, 2017

Opinion: we are inadvertently weeding women out in the name of 'rigor'.

Read More
In Issues Tags women, technology, jobs, diversity, sexism
1 Comment

Category

  • Classification 2
  • Exploratory Data Analysis 2
  • Issues 2
  • NLP 4
  • Python - general 1
  • Regression 3

Latest Posts

Featured
Bloatectomy: a method for the identification and removal of duplicate text in the bloated notes of electronic health records and other documents.
python, natural language processing, NLP, anaconda, cleaning, data science, exploratory data analysis
Bloatectomy: a method for the identification and removal of duplicate text in the bloated notes of electronic health records and other documents.
python, natural language processing, NLP, anaconda, cleaning, data science, exploratory data analysis

Bloatectomy: a method for the identification and removal of duplicate text in the bloated notes of electronic health records and other documents. Takes in a list of notes or a single file (.docx, .txt, .rtf, etc) or single string to be marked for duplicates which can then be highlighted, bolded, or removed. Marked output and tokens are output.

Read more →
python, natural language processing, NLP, anaconda, cleaning, data science, exploratory data analysis
Where to find conda (anaconda) packages and libraries
python, anaconda
Where to find conda (anaconda) packages and libraries
python, anaconda

where to find anaconda packages on osX

Read more →
python, anaconda
TED Talk Recommender (Part3): flask app
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED
TED Talk Recommender (Part3): flask app
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED

Topic modeling of TED talks using Latent Dirichlet Allocation and visualization with tSNE. 

Read more →
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED
DCFem Tech Awards 2019 and Written Feedback
data science, women
DCFem Tech Awards 2019 and Written Feedback
data science, women

Moral of the story is this: give good and ‘bad’ feedback to your mentees often and in writing. It will make it easier for you and them to do things like nominate themselves or write a recommendation. Also, when you write for a women, read it and ask yourself if you would say those same things about a man. It will help you adjust any biased language that got in there.

Read more →
data science, women
YMCA VS. Obesity Part 3: Linear Regression Results
Linear regression, public health, obesity, ymca, data science, modeling
YMCA VS. Obesity Part 3: Linear Regression Results
Linear regression, public health, obesity, ymca, data science, modeling

Linear regression of multiple county-level statistics on the obesity rate in the United States.

Read more →
Linear regression, public health, obesity, ymca, data science, modeling
TED Talk Recommender (Part2): Topic Modeling and tSNE
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED
TED Talk Recommender (Part2): Topic Modeling and tSNE
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED

Topic modeling of TED talks using Latent Dirichlet Allocation and visualization with tSNE. 

Read more →
NLP, NLTK, natural language processing, tSNE, Latent Dirichlet Allocation, Topic modeling, python, TED
Ted Talk Recommender (Part1): Cleaning text with NLTK
NLTK, natural language processing, NLP
Ted Talk Recommender (Part1): Cleaning text with NLTK
NLTK, natural language processing, NLP
Read more →
NLTK, natural language processing, NLP
Classification of  Meows and Woofs: Part 2
audio analysis, signal processing, cat, dogs, PCA, supervised learning, dimensionality reduction, FFT, librosa, sklearn
Classification of Meows and Woofs: Part 2
audio analysis, signal processing, cat, dogs, PCA, supervised learning, dimensionality reduction, FFT, librosa, sklearn

Dog and Cat sounds. I reduced the dimensionality of the 1D FFTs of the sounds and then used several models to see which one is able to classify them. Gaussian Naive Bayes won. 

Read more →
audio analysis, signal processing, cat, dogs, PCA, supervised learning, dimensionality reduction, FFT, librosa, sklearn
Classification of  Meows and Woofs: Part 1 Spectrograms!
signal processing, spectrograms, cats, dogs, fft, audio analysis, DSP, classifier, supervised learning
Classification of Meows and Woofs: Part 1 Spectrograms!
signal processing, spectrograms, cats, dogs, fft, audio analysis, DSP, classifier, supervised learning

Dog and Cat sounds. This post is mostly spectrograms. 

Read more →
signal processing, spectrograms, cats, dogs, fft, audio analysis, DSP, classifier, supervised learning
YMCA ExpLoratory Data Analysis: what the village people have to do with obesity (part 2)
ymca, python, metis, obesity, public health, data science, zip code, merging, exploratory data analysis, basemap
YMCA ExpLoratory Data Analysis: what the village people have to do with obesity (part 2)
ymca, python, metis, obesity, public health, data science, zip code, merging, exploratory data analysis, basemap

Merging of YMCA location data from zip code format to county, for data exploration and comparison to health data per county. 

Read more →
ymca, python, metis, obesity, public health, data science, zip code, merging, exploratory data analysis, basemap

Powered by Squarespace