{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "ir", "display_name": "R" }, "language_info": { "name": "R" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "aEWm3-obvxbV", "outputId": "aec96e82-1a86-4a0b-83ab-b74f483749b6" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "First 10 rows of production_data:\n", " Sol Station Team Output\n", "1 1 1 1 52\n", "2 1 1 2 54\n", "3 1 1 3 63\n", "4 1 1 4 57\n", "5 1 2 1 58\n", "6 1 2 2 65\n", "7 1 2 3 61\n", "8 1 2 4 62\n", "9 1 3 1 61\n", "10 1 3 2 66\n", "\n", "Total Production per Station:\n", " Station TotalOutput\n", "1 1 7001\n", "2 2 7355\n", "3 3 7723\n", "4 4 8049\n", "5 5 8419\n", "6 6 8800\n", "\n", "First 10 TRUE anomalies:\n", " Sol Station Team Output Anomaly\n", "3 1 1 3 63 TRUE\n", " Sol Station Team Output Anomaly\n", "28 2 1 4 66 TRUE\n", " Sol Station Team Output Anomaly\n", "73 4 1 1 53 TRUE\n", " Sol Station Team Output Anomaly\n", "121 6 1 1 52 TRUE\n", " Sol Station Team Output Anomaly\n", "148 7 1 4 65 TRUE\n", " Sol Station Team Output Anomaly\n", "165 7 6 1 65 TRUE\n", " Sol Station Team Output Anomaly\n", "232 10 4 4 74 TRUE\n", " Sol Station Team Output Anomaly\n", "233 10 5 1 62 TRUE\n", " Sol Station Team Output Anomaly\n", "236 10 5 4 76 TRUE\n", " Sol Station Team Output Anomaly\n", "241 11 1 1 51 TRUE\n", "\n", "Peak Productivity Days:\n", " Station Sol TotalOutput\n", "1 1 16 244\n", "2 2 7 255\n", "3 3 1 268\n", "4 4 20 283\n", "5 5 27 294\n", "6 6 1 304\n", "\n", "First 10 rows with Efficiency Score:\n", " Sol Station Team Output EfficiencyScore\n", "1 1 1 1 52 26.00000\n", "2 1 1 2 54 18.00000\n", "3 1 1 3 63 15.75000\n", "4 1 1 4 57 11.40000\n", "5 1 2 1 58 19.33333\n", "6 1 2 2 65 16.25000\n", "7 1 2 3 61 12.20000\n", "8 1 2 4 62 10.33333\n", "9 1 3 1 61 15.25000\n", "10 1 3 2 66 13.20000\n" ] } ], "source": [ "############################################################\n", "# Name: [PARTH KAMLESHKUMAR SUTHAR]\n", "# Student ID: [2434584]\n", "# Module: ACCA7022 – Advanced Statistical Programming\n", "# Assignment: Coursework 1 – Data Manipulation\n", "# Date: February 2026\n", "# Purpose: Alien Colony Resource Management Simulation\n", "############################################################\n", "\n", "\n", "###############################\n", "# SET CONSTANTS\n", "###############################\n", "\n", "BaseOutput <- 50\n", "set.seed(123) # Ensures reproducible results\n", "\n", "\n", "############################################################\n", "# PART A – GENERATE PRODUCTION DATA (PREALLOCATED)\n", "############################################################\n", "\n", "total_rows <- 30 * 6 * 4 # 720 rows\n", "\n", "Sol_vec <- numeric(total_rows)\n", "Station_vec <- numeric(total_rows)\n", "Team_vec <- numeric(total_rows)\n", "Output_vec <- numeric(total_rows)\n", "\n", "index <- 1\n", "\n", "for (sol in 1:30) {\n", " for (station in 1:6) {\n", " for (team in 1:4) {\n", "\n", " RandomNoise <- sample(-5:5, 1)\n", "\n", " Output <- BaseOutput + (station * 3) + (team * 2) + RandomNoise\n", "\n", " Sol_vec[index] <- sol\n", " Station_vec[index] <- station\n", " Team_vec[index] <- team\n", " Output_vec[index] <- Output\n", "\n", " index <- index + 1\n", " }\n", " }\n", "}\n", "\n", "production_data <- data.frame(\n", " Sol = Sol_vec,\n", " Station = Station_vec,\n", " Team = Team_vec,\n", " Output = Output_vec\n", ")\n", "\n", "cat(\"First 10 rows of production_data:\\n\")\n", "print(head(production_data, 10))\n", "\n", "\n", "############################################################\n", "# PART B – TOTAL PRODUCTION PER STATION\n", "############################################################\n", "\n", "Station_total_vec <- numeric(6)\n", "Total_output_vec <- numeric(6)\n", "\n", "for (station in 1:6) {\n", "\n", " total <- 0\n", "\n", " for (i in 1:nrow(production_data)) {\n", " if (production_data$Station[i] == station) {\n", " total <- total + production_data$Output[i]\n", " }\n", " }\n", "\n", " Station_total_vec[station] <- station\n", " Total_output_vec[station] <- total\n", "}\n", "\n", "station_totals <- data.frame(\n", " Station = Station_total_vec,\n", " TotalOutput = Total_output_vec\n", ")\n", "\n", "cat(\"\\nTotal Production per Station:\\n\")\n", "print(station_totals)\n", "\n", "\n", "############################################################\n", "# PART C – DETECT PRODUCTION ANOMALIES\n", "############################################################\n", "\n", "Anomaly_Sol <- numeric(total_rows)\n", "Anomaly_Station <- numeric(total_rows)\n", "Anomaly_Team <- numeric(total_rows)\n", "Anomaly_Output <- numeric(total_rows)\n", "Anomaly_Flag <- logical(total_rows)\n", "\n", "index <- 1\n", "\n", "for (sol in 1:30) {\n", " for (station in 1:6) {\n", "\n", " daily_total <- 0\n", "\n", " for (i in 1:nrow(production_data)) {\n", " if (production_data$Sol[i] == sol &&\n", " production_data$Station[i] == station) {\n", " daily_total <- daily_total + production_data$Output[i]\n", " }\n", " }\n", "\n", " daily_average <- daily_total / 4\n", "\n", " for (i in 1:nrow(production_data)) {\n", " if (production_data$Sol[i] == sol &&\n", " production_data$Station[i] == station) {\n", "\n", " deviation <- abs(production_data$Output[i] - daily_average)\n", "\n", " if (deviation > (0.10 * daily_average)) {\n", " flag <- TRUE\n", " } else {\n", " flag <- FALSE\n", " }\n", "\n", " Anomaly_Sol[index] <- sol\n", " Anomaly_Station[index] <- station\n", " Anomaly_Team[index] <- production_data$Team[i]\n", " Anomaly_Output[index] <- production_data$Output[i]\n", " Anomaly_Flag[index] <- flag\n", "\n", " index <- index + 1\n", " }\n", " }\n", " }\n", "}\n", "\n", "anomalies <- data.frame(\n", " Sol = Anomaly_Sol,\n", " Station = Anomaly_Station,\n", " Team = Anomaly_Team,\n", " Output = Anomaly_Output,\n", " Anomaly = Anomaly_Flag\n", ")\n", "\n", "cat(\"\\nFirst 10 TRUE anomalies:\\n\")\n", "\n", "count <- 0\n", "for (i in 1:nrow(anomalies)) {\n", " if (anomalies$Anomaly[i] == TRUE) {\n", " print(anomalies[i, ])\n", " count <- count + 1\n", " }\n", " if (count == 10) break\n", "}\n", "\n", "\n", "############################################################\n", "# PART D – IDENTIFY PEAK PRODUCTIVITY DAYS\n", "############################################################\n", "\n", "Peak_Station <- numeric(6)\n", "Peak_Sol <- numeric(6)\n", "Peak_Output <- numeric(6)\n", "\n", "for (station in 1:6) {\n", "\n", " max_output <- -Inf\n", " best_sol <- 0\n", "\n", " for (sol in 1:30) {\n", "\n", " sol_total <- 0\n", "\n", " for (i in 1:nrow(production_data)) {\n", " if (production_data$Station[i] == station &&\n", " production_data$Sol[i] == sol) {\n", " sol_total <- sol_total + production_data$Output[i]\n", " }\n", " }\n", "\n", " if (sol_total > max_output) {\n", " max_output <- sol_total\n", " best_sol <- sol\n", " }\n", " }\n", "\n", " Peak_Station[station] <- station\n", " Peak_Sol[station] <- best_sol\n", " Peak_Output[station] <- max_output\n", "}\n", "\n", "peak_days <- data.frame(\n", " Station = Peak_Station,\n", " Sol = Peak_Sol,\n", " TotalOutput = Peak_Output\n", ")\n", "\n", "cat(\"\\nPeak Productivity Days:\\n\")\n", "print(peak_days)\n", "\n", "\n", "############################################################\n", "# PART E – CALCULATE EFFICIENCY SCORE\n", "############################################################\n", "\n", "production_data$EfficiencyScore <- numeric(nrow(production_data))\n", "\n", "for (i in 1:nrow(production_data)) {\n", " production_data$EfficiencyScore[i] <-\n", " production_data$Output[i] /\n", " (production_data$Station[i] + production_data$Team[i])\n", "}\n", "\n", "cat(\"\\nFirst 10 rows with Efficiency Score:\\n\")\n", "print(head(production_data, 10))\n", "\n", "\n", "############################################################\n", "# END OF SCRIPT\n", "############################################################" ] } ] }