Data Visionaries

A Simple Linear Regression

Smart Campus Data Analysis This project focuses on analyzing classroom utilization and electricity consumption in a smart campus environment using R programming. The objective is to improve resource efficiency and support data-driven decision-making. The dataset includes variables such as room capacity, number of students, department, and electricity usage. Data preprocessing steps such as handling missing values and removing duplicates were performed to ensure data quality. A new metric called Utilization was calculated as the ratio of students used to capacity, and further categorized into low, medium, and high levels for better analysis. Exploratory Data Analysis (EDA) was conducted using statistical measures like mean, median, standard deviation, quartiles, and skewness. Outliers were detected using both IQR and Z-score methods. Various visualizations were created using ggplot2, including histograms, density plots, boxplots, scatter plots, and bar charts to understand data distribution, relationships, and departmental comparisons. The analysis revealed that while most classrooms are efficiently utilized, some are underutilized, and there is variation in electricity consumption across departments. This project demonstrates how data analytics can be used to optimize campus resources and improve operational efficiency.

Projek Based Learning dan UTS Visualisasi Data Lanjut Nama : Dinda Dwi Anugrah Pertiwi NPM : ***010 Dosen Pengampu : Miftahus Sholihin, S.Si, M.Si

Analisis untuk uts ini menggunakan dua portofolio saham pertambangan yang terdaftar di Bursa Efek Indonesia (IDX) menggunakan data historis dari Yaho Finance periode Januari-Maret 2026. Modal awal diinvestasikan sebesar Rp 120.000.000 Saham yang dipilih: 1. ADRO.JK – Adaro Energy Indonesia Tbk 2. PTBA.JK – Bukit Asam Tbk 3. INCO.JK – Vale Indonesia Tbk 4. ANTM.JK – Aneka Tambang Tbk (hanya Portofolio 4 saham)

When you interpolate between complex time evolving features (say Teff), some form of non-linear warping is required. ProGeny uses Dynamic Time Warping (DTW) to achieve such interpolation. This vignette demonstrates the approach on a simple synthetic curve, then shows the full workflow for interpolating between two real MIST stellar isochrones.