Web scraping to efficiently extract data from various online sources, including websites, APIs, and databases.
Joining, merging, and harmonizing information from disparate sources and formats and integrating it into unified, high-quality datasets.
Leveraging the power of predictive analytics to help clients anticipate and adapt to future trends. By combining historical data with real-time insights, I develop sophisticated forecasting models that provide a clear vision of what lies ahead.
Using natural language processing (NLP) capabilities and techniques like sentiment analysis, text classification, topic modeling, named entity recognition, and parts of speech tagging to extract deep insights from unstructured text data, uncover hidden patterns, classify content, and identify key entities and themes.
Solving complex business problems and empowering clients to make strategic, data-driven decisions, by using advanced data analysis techniques, and generating actionable insights and tailored recommendations.
Utilizing exploratory data analysis (EDA) to delve deeply into the data, uncovering hidden patterns, relationships, and trends that drive business decisions.
Generating visually appealing and insightful plots, charts, and graphs that effectively communicate complex data in a clear and concise manner.
Creating dynamic and interactive dashboards that enhance user experience, enable interactive exploration of data and facilitate deeper engagement.
Creating compelling data stories that communicate key findings and recommendations that empower informed decisions.
Python (Requests, Tweepy, Beautiful Soup), HTML, CSS.
Scikit Learn, Tensorflow, Keras, NLP(NLTK, Spacy, Gensim)
Python (Seaborn, Matplotlib), Tableau, ggplot, Spreadsheets.
Python (Pandas, Numpy, StatsModels, Scipy), Spreadsheets, SQL.
Analyzing the English Premier League matches; from most goals in a match to the full premier league table of 2009/2010 season.
A detailed analysis to determine whether more goals are scored in women’s soccer matches than in men's.
Exploring the video games dataset in detail.
Analysis of the HR dataset to identify reasons for employee attrition
Showing different ways of importing data from different from formats into python.
Utilizing Natural Language Processing for sentiment analysis of tweets.
Employing various methods for feature selection as a preprocessing step to decrease dataset dimensionality and enhance model efficacy.
Predicting bank customer churn through ensemble techniques with 0.87 accuracy.
Predicting the likelihood of floods occurring with an R2 score of 0.84
Using binary classification to predict kidney stone presence or absence.
Predicting concrete strength using XGBoost and ensemble techniques for regression.
Using Python tools to scrape and collect EASports FC 24 player traits, statistics, and features.
Gathering video games data from IMDb via web scraping using Python tools
Analysis to identify key factors influencing customer churn.
A summary of the key reasons for employee attrition.
A comprehensive analysis of games genre, release year, publisher etc.
A summarized analysis of the bike sharing dataset by gender, subscription and time.
Exploration of the movies dataset.
Article about common data files and how to import them into Python for analysis.
How do you handle a dataset with hundreds or thousands of features? Find out here...
There is a simple trick to plotting with GGPLOT2 in R. We break it down in this article.
Phone : +254728542793
Email : davis.anunda@gmail.com