Wendy Minai's Projects
Data Visualization and Data Analytics with Tableau by solving real data analytics problems
I introduce the basic idea and implementation of 5 imputation approaches. In short, filling with a single value works well for a shorter period of missing values. MICE should be one of your first choices if the missing data is relatively long. It is explicitly designed for imputation tasks and can effectively learn data patterns.
LSTM (Long Short-Term Network) is a kind of Recurrent Neural Network which used in the field of deep learning. Traditional neural networks can't remember previous inputs. But Recurrent Neural Networks enable us to learn from previous sequence input datas. A LSTM unit is composed of a cell, an input gate, an output gate and a forget gate.
This project aims to predict people who will survive breast cancer using machine learning models with the help of clinical data and gene expression profiles of the patients.
Recurrent Neural Networks are standard methods in which chatbots are trained. These bots contain encoders that can update the states in line with the input phrases.Then the stated response is passed to the chatbot. The chatbot then uses the decoder to find acceptable and future responses based on inputs and in addition to the purpose.
A unique Data Science field that utilizes the power of data & statistics to understand the factors that influence customer attrition, identify customers that are most likely to churn, and offer them some discounts.
This project aims at creating a classifier. It detects whether or not the card transaction is valid. Diverse machine learning algorithms are applied in this project to distinguish between a non-fraudulent and fraudulent transactions.
Twitter report of Trump's tweets: 2009/2022. Tweet Binder analyzed all the tweets sent by the U.S.A President and there are surprises.
Building and training Speech Emotion Recognizer that predicts human emotions using Python, Sci-kit learn and Keras
In this data science project, I use Python as a model to assess if a news report is accurate or false. To carry out this, I created a TfidfVectorizer classifier and then used the PassiveAggressiveClassifier to identify the news into a ‘True’ and ‘False.’ There will be a 7796×4 shaped dataset, and all these will be executed in the JupyterLab.
The ultimate goal of the project is to build a prediction engine capable of predicting district's median housing price
This Image-Toonification was done using GANS - A generative model that is able to generate new content. I used 99 cartooon styles to generate different cartoon structures. I have the original picture and the different cartoon structures in the output of the code. Please check the google colab attached in my repository.
In this work, we present a novel approach of line detection through CNNs (convolutional neural networks) which can be used as a first stepping stone towards building an end-to-end neural network to detect lines. The CNN-based method would eliminate the limitations of standard hough transform including hyperparameter finetuning at test time.
Exploring items frequently bought together for an Online Retailer using Apriori Algorithm Resources
Market basket analysis is a versatile use case in the retail industry that helps cross-sell products in a physical outlet. It is all about analyzing the association among products bought together by customers. It helps recommend products to the customers based on the historical data & existing product associations.
This project is focused on a collaborative recommendation filtering system. This kind of recommendation system recommends films based on other people’s browsing history who could watch films of the same tastes.
Movie Recommendation System is an R project to enhance your Machine Learning knowledge. It is simply a recommendation system that provides consumers with various suggestions based on their history and interests.
The goal is to build a music recommendation system that can provide custom playlists for individual users based on collaborative and metadata filtering.
I will be uploading my Power BI here as I complete them. Go to my blog to read more about the individual projects
The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)
SQL data analysis & visualization projects using MySQL, PostgreSQL, SQLite, Tableau, Apache Spark and pySpark.
Project for detecting tennis ball using OpenCV library and Python. Prerequisites. Linux environment,; installed OpenCV tools.
Tesl Stock Price Data Analysis and Visualization using Tableau
The system will use R programming and the ggplot2 library to analyze different customer parameters like the number of trips made in a day, the daily trip hours of repeat customers, the number of trips during a particular month, etc.