vcpreneur Goto Github PK

data-investigation-with-pandas-titanic-data

As part of Udacity's Data Analysis Nano Degree (DAND), and using Python, basically Pandas and Numpy, I had to investigate a data set including: cleaning the data programmatically, adding new features, imputing missing data points, and creating some basic visualizations to communicate the findings.

data-visualization-with-tableau-titanic-data

As part of Udacity's Data Analysis Nano Degree (DAND). Using Tableau, I had to create a Tableau story to deliver specific findings and provide the reasoning behind all design decisions I made for those visualizations.

data-wrangling-with-python-openstreetmap-data

As part of Udacity's Data Analysis Nano Degree (DAND), and using Python and SQL, I had to parse the data from xml files, audit and clean the data, then store, query, and aggregate data in SQL.

deep-learning-image-classifier

As part of Udacity's Data Scientist Nano Degree (DSND), and using PyTorch, I had to build a deep learning model to classify flowers based on 102 provided categories.

exploratory-data-analysis-with-r-nasdaq-data

As part of Udacity's Data Analysis Nano Degree (DAND). Using R, I had to apply exploratory data analysis techniques to explore relationships in one variable to multiple variables, and to explore the dataset for distributions, outliers, and anomalies.

fintech_bootcamp_challenges

Includes all the code from my UC Berkeley FinTech Bootcamp 2023

machine-learning-with-python-enron-data

As part of Udacity's Data Analysis Nano Degree (DAND), and using Python, basically scikit-learn, I had to build a classification algorithm to identify Enron employees who may have committed fraud based on the public Enron financial and email dataset. I experimented with several preprocessing, feature selection, and classification algorithms and implemented a pipeline with grid search to reach the final best result.

personal_financial_advisor

supervised-learning-finding-donors-for-charityml

As part of Udacity's Data Scientist Nano Degree (DSND), and using scikit-learn in Python, I had to build a classification algorithm to find doner for CharityML (a fictional charity organization). The task was to employ several supervised algorithms to accurately model individuals' income using data collected from the 1994 U.S. Census.

unsupervised-learning-identify-customer-segments

As part of Udacity's Data Scientist Nano Degree (DSND), and using PCA and KMeans, I had to build a model to classify a population and a sample into clusters and compare the distributions of both for over represented and under represented clusters in the sample.