Naim Iskandar Zahari

This python project explores the Disneyland reviews dataset from Kaggle. The goal of the project is to identify individual visitor ratings with relations to the country of origin, park location, date of visit and median rating.

Python project of an analysis on Disneyland reviews using NLTK, Sentiment Analysis and WordCloud. The dataset was taken from Kaggle.

The project explores importing huge dataset and an image file into a python project using Google Colab. Using the Sentiment Intensity Analyzer from the NLTK library, the analyzer is able to identify the sentiment of the reviews from the park visitors and then, it is sorted from the most positive review to the most negative review.

As an added bonus, the projects also explores the extensive parameters of the WordCloud library for added customizability as demonstrated in the image above.

Data dashboard on employee retention analysis using Google Data Studio.

The project explores an arbitrary dataset of employee retention in an organization and identify the likelihood of employees to stay with the organization based on key features, such as duration of employment, satisfaction level, project scope or level of responsibility and et cetera.

The process of preparing the dashboard in Google Data Studio was rewarding, to say the least. Google Data Studio provides a wide selection of charts and graphs to form the dashboard, however other details were taken into consideration to provide an insightful finding such as hybrid title, annotations or compliance to the rule of thirds that adds to the dashboard quality.

The project explores the process of data cleaning and processing before fitting it into the Decision Tree Classifier. Preprocessing the data remain a crucial step that includes exploring relationship between variables, handling missing values and determining which variables are important in answering the problem statement.

Using the Decision Tree Classifier from the SciKit Learn library, the decision tree is able to predict if the customer will continue to use the service based on the current lifestyle and consumer habits.

This project is made using Python and the BeautifulSoup package to scrape the living costs data from the Numbeo website.

From the terminal, the project gives the option to choose between getting the living cost data of specific cities or countries. The data on living cost includes median expenditure at different types of restaurants, groceries, transportation, accomodation and miscellaneous consumption.

Once the data is gathered, it is saved into xlsx files in a specified directory.

Python project of forecasting sales performance based on social media advertisement activites using Linear Regression.

The project explores relationship between variables and using Linear Regression from SciKit Learn to predict the expected sales performance based on the budget distribution across 3 different social media platforms(Facebook, Instagram and Google) and evaluate the performance of the machine learning model itself.