Provides quick access to a list of tasks solved during work and education path, results in various competitions and my own pet projects.
| Title | Description | Stack | Source |
|---|---|---|---|
| Hospital KPI Analysis Automation | Python scripts orchestrated in Airflow. Designed to export and analyze key hospital metrics from various sources (reports and information systems). Uses browser automation on Selenium, where there is no direct access to data warehouses, and MySQL queries. Additionally organizes simple dashboards in Google Sheets for quick access to aggregated data, Telegram notifications. The goal is to improve the quality of medical care to patients, based on the limited data sources, and to increase the KPI of the medical institution in the ratings of the Ministry of Health of the Moscow region. | Airflow, Python, pandas, Selenium, gspread, SQL, Telegram API | DragonSigh/pokb-airflow |
| Title | Description | Stack | Source |
|---|---|---|---|
| Mobile Game A/B Testing with Cookie Cats | Performing exploratory data analysis and A/B testing of in-game changes to the Cookie Cats mobile game. | Python, matplotlib, statsmodel | Kaggle/vladkovnerov |
| Final Work on Hipothesis Testing | Tasks: make hypothesis for landing page improvement, ARPPU experiment, A/B test for traffic sources, comparing CPA metrics, creating technical architecture for an online cinema A/B test. | Statistics, Python, SciPy | Final control work on the block of specialization (GeekBrains) |
| Analyzing the Effectiveness of Marketing Campaigns on the Internet | A Premium Auto dealer wants to analyze the effectiveness of its online marketing campaigns. We combined data from Google analytics and CRM system in order to see which campaigns lead not only to requests, but also to sales. Our current task is to take the data from the systems, combine them, deduce the missing data and based on it give the client a dashboard that answers his questions. | Excel (Power Query), Python, Microsoft Power BI | Intermediate control work on the specialization block (GeekBrains) |
| Investigating Netflix Movies | Aim to discover if Netflix's movies are getting shorter over time. | Python, pandas, matplotlib | Data Analyst with Python track (DataCamp) |
| Exploring NYC Public School Test Result Scores | Finding schools with the best math scores. Identifying the top 10 performing schools. Locating the NYC borough with the largest standard deviation in SAT performance. | Python, pandas | Data Analyst with Python track (DataCamp) |
| Visualizing the History of Nobel Prize Winners | This project analyzes Nobel Prize winner data to detect patterns, specifically the most common gender and birth country, the decade with the highest percentage of US-born laureates, the decade-category pair with the highest proportion of female winners, the first female laureate and category, and individuals or organizations with multiple Nobel Prizes. | Python, pandas, matplotlib, seaborn | Data Analyst with Python track (DataCamp) |
| Analyzing Students' Mental Health | Compare depression rates (and other indicators) between student groups. Explore trends between length of stay and mental health for international students. | PostgreSQL | Data Analyst with SQL track (DataCamp) |
| Title | Description | Stack | Source |
|---|---|---|---|
| Amazon Python Scrapy Scraper | A web scraper of products from the Amazon website based on Scrapy. Goes through the search by given keywords and collects information about the found products into a csv file. Used to collect a dataset for training a classification model. | Python, Scrapy | DragonSigh/amazon-python-scrapy-scraper |
| Ebay Python Scrapy Scraper | A web scraper of products from the Ebay website based on Scrapy. Goes through the search by given keywords and collects information about the found products into a csv file. Used to collect a dataset for training a classification model. | Python, Scrapy | DragonSigh/ebay-python-scrapy-scraper |