This contains snippets of code working with a variety of data analysis tools including Python (pandas, scikit-learn), R, SPSS (Syntax), and Tableau.
Python/LifelineChat - My final project for the General Assembly Data Science course.
- I used data models to create chat metrics and attempt to identify patterns for at-risk users.
- Chat metrics were created using a Logistic Regression to determine an ideal chat time (comparing length of chat to survey question if users found chat helpful).
- Identifying patterns for at-risk users used a Multinomial Naive Bayes Classifier using TF-IDF Vectorizer to identify keywords to watch out for (unigram, bigram, trigrams) based on survey question if users responded they have thoughts of suicide.
R
- intro_class: My notes from a GILT sponsored introduction class on using R (loading data, data manipulation, plotting).
- va_concurrent_calls: Plotting of concurrent calls per hour from the VA
SPSS/h2h_satisfaction_survey - Results of the H2H Employee Satisfaction and Clinical Supervision Survey All H2H Staff were invited to participate in the survey through a SurveyMonkey survey. Survey assessed variables (largely through Likert responses on a continuous 5-point scale) including:
- Background (demographic variables: Age, Employment History: length of employment, perceived fairness of compensation, on-the-job learning, perceived opportunities for growth)
- Professional Quality of Life (compassion satisfaction, compassion fatigure: burnout + secondary traumatic stress)
- Supervision Rating (safe base, reflection education, structure)
Tableau - Report template that I created for our organization's reports (details in private repo)
- R_integration: Example of how to integrate a Tableau Report along with R