Skip to content
View dlhaar's full-sized avatar

Block or report dlhaar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dlhaar/README.md

Deborah Haar

I'm a junior data analyst with a background (PhD) in philosophy of science and am interested in :electron: energy and 🚲 transportation issues. I have experience in the Tech and Manufacturing sectors building data pipelines, conducting exploratory data analysis, statistical analysis, building machine learning models and visualizing with Tableau.

  • 🔭 I’m currently working on an exploratory data analysis of the Kaggle Superstore data set
  • 🌱 I’m currently learning forecasting for operations analytics and business German
  • 💬 I speak English, French, Portuguese and German (B1)
  • 📌 I am currently looking for new opportunities
  • 📫 How to reach me

Skills

Excel / Python / SQL / Tableau / Snowflake / git / ETL / Exploratory Data Analysis / Statistical Testing / Machine Learning

Examples of work

  • Tableau dashboard of German Energy Market from 2017-2022

    • Energy production data and energy prices gathered from SMARD and DeStatis and visualized with Tableau. Notable findings include solar energy production was 19% greater in 2022 than the prior year. Tableau Public
  • SpotiFind song recommendation app

    • Provides Spotify song recommendations based on user song input. App was built with song data gathered via web scraping (BeautifulSoup) and the Spotify API. Songs are modeled based on five musical features using KMeans clustering. App interface developed with Streamlit.
  • Citi Bikes rental predictor

    • Predicts the number of rides based the station, day of week and weather metrics. Dataset (45+M rows) was prepped using Polars. KNN regression, Random Forest and Gradient Boost models were tested. Random Forest yielded best results with R2 0.79 and RMSE 3.

github linkedin

Pinned Loading

  1. electricity-analysis electricity-analysis Public

    Jupyter Notebook

  2. song_recommender song_recommender Public

    Jupyter Notebook

  3. citi_bikes citi_bikes Public

    Jupyter Notebook