{ "hash": "c2d0687da1235de32c5ae9a007c668a7", "result": { "engine": "knitr", "markdown": "---\ntitle: \"Quarto Assignment\"\nauthor: \"Aare Akintunde\"\ndata: \"2026-10-05\"\nformat: html\nexecute:\n echo: true\n---\n\n# Assignment\n\n# 1) Data Import & Initial Exploration\n\nThe Dataset: telco-customer-churn.csv was used for this assignment. It requires the loading of the dataset and initial exploration of the data. The dataset contains information about customers of a telecommunications company, including their demographics, services subscribed to, and whether they have churned (i.e., stopped using the service).\n\n# call library\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# if (!require(pacman)) { install.packages(\"pacman\") }\n\npacman::p_load(tidyverse, bulkreadr, janitor, readxl, writexl)\n```\n:::\n\n\n# importing dataset and labelled as telco_data\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_data <- read_csv(\"data/telco-customer-churn.csv\")\n```\n\n::: {.cell-output .cell-output-stderr}\n\n```\nRows: 7043 Columns: 21\n── Column specification ────────────────────────────────────────────────────────\nDelimiter: \",\"\nchr (17): customerID, gender, Partner, Dependents, PhoneService, MultipleLin...\ndbl (4): SeniorCitizen, tenure, MonthlyCharges, TotalCharges\n\nℹ Use `spec()` to retrieve the full column specification for this data.\nℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.\n```\n\n\n:::\n:::\n\n\n## Exploring the dataset\n\n\n::: {.cell}\n\n```{.r .cell-code}\nhead(telco_data)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 6 × 21\n customerID gender SeniorCitizen Partner Dependents tenure PhoneService\n \n1 7590-VHVEG Female 0 Yes No 1 No \n2 5575-GNVDE Male 0 No No 34 Yes \n3 3668-QPYBK Male 0 No No 2 Yes \n4 7795-CFOCW Male 0 No No 45 No \n5 9237-HQITU Female 0 No No 2 Yes \n6 9305-CDSKC Female 0 No No 8 Yes \n# ℹ 14 more variables: MultipleLines , InternetService ,\n# OnlineSecurity , OnlineBackup , DeviceProtection ,\n# TechSupport , StreamingTV , StreamingMovies ,\n# Contract , PaperlessBilling , PaymentMethod ,\n# MonthlyCharges , TotalCharges , Churn \n```\n\n\n:::\n\n```{.r .cell-code}\nglimpse(telco_data) \n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\nRows: 7,043\nColumns: 21\n$ customerID \"7590-VHVEG\", \"5575-GNVDE\", \"3668-QPYBK\", \"7795-CFOCW…\n$ gender \"Female\", \"Male\", \"Male\", \"Male\", \"Female\", \"Female\",…\n$ SeniorCitizen 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…\n$ Partner \"Yes\", \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes…\n$ Dependents \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes\", \"No\", \"No\"…\n$ tenure 1, 34, 2, 45, 2, 8, 22, 10, 28, 62, 13, 16, 58, 49, 2…\n$ PhoneService \"No\", \"Yes\", \"Yes\", \"No\", \"Yes\", \"Yes\", \"Yes\", \"No\", …\n$ MultipleLines \"No phone service\", \"No\", \"No\", \"No phone service\", \"…\n$ InternetService \"DSL\", \"DSL\", \"DSL\", \"DSL\", \"Fiber optic\", \"Fiber opt…\n$ OnlineSecurity \"No\", \"Yes\", \"Yes\", \"Yes\", \"No\", \"No\", \"No\", \"Yes\", \"…\n$ OnlineBackup \"Yes\", \"No\", \"Yes\", \"No\", \"No\", \"No\", \"Yes\", \"No\", \"N…\n$ DeviceProtection \"No\", \"Yes\", \"No\", \"Yes\", \"No\", \"Yes\", \"No\", \"No\", \"Y…\n$ TechSupport \"No\", \"No\", \"No\", \"Yes\", \"No\", \"No\", \"No\", \"No\", \"Yes…\n$ StreamingTV \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes\", \"Yes\", \"No\", \"Ye…\n$ StreamingMovies \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes\", \"No\", \"No\", \"Yes…\n$ Contract \"Month-to-month\", \"One year\", \"Month-to-month\", \"One …\n$ PaperlessBilling \"Yes\", \"No\", \"Yes\", \"No\", \"Yes\", \"Yes\", \"Yes\", \"No\", …\n$ PaymentMethod \"Electronic check\", \"Mailed check\", \"Mailed check\", \"…\n$ MonthlyCharges 29.85, 56.95, 53.85, 42.30, 70.70, 99.65, 89.10, 29.7…\n$ TotalCharges 29.85, 1889.50, 108.15, 1840.75, 151.65, 820.50, 1949…\n$ Churn \"No\", \"No\", \"Yes\", \"No\", \"Yes\", \"Yes\", \"No\", \"No\", \"Y…\n```\n\n\n:::\n\n```{.r .cell-code}\nsummary(telco_data)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n customerID gender SeniorCitizen Partner \n Length :7043 Length :7043 Min. :0.0000 Length :7043 \n N.unique :7043 N.unique : 2 1st Qu.:0.0000 N.unique : 2 \n N.blank : 0 N.blank : 0 Median :0.0000 N.blank : 0 \n Min.nchar: 10 Min.nchar: 4 Mean :0.1621 Min.nchar: 2 \n Max.nchar: 10 Max.nchar: 6 3rd Qu.:0.0000 Max.nchar: 3 \n Max. :1.0000 \n \n Dependents tenure PhoneService MultipleLines \n Length :7043 Min. : 0.00 Length :7043 Length :7043 \n N.unique : 2 1st Qu.: 9.00 N.unique : 2 N.unique : 3 \n N.blank : 0 Median :29.00 N.blank : 0 N.blank : 0 \n Min.nchar: 2 Mean :32.37 Min.nchar: 2 Min.nchar: 2 \n Max.nchar: 3 3rd Qu.:55.00 Max.nchar: 3 Max.nchar: 16 \n Max. :72.00 \n \n InternetService OnlineSecurity OnlineBackup DeviceProtection\n Length :7043 Length :7043 Length :7043 Length :7043 \n N.unique : 3 N.unique : 3 N.unique : 3 N.unique : 3 \n N.blank : 0 N.blank : 0 N.blank : 0 N.blank : 0 \n Min.nchar: 2 Min.nchar: 2 Min.nchar: 2 Min.nchar: 2 \n Max.nchar: 11 Max.nchar: 19 Max.nchar: 19 Max.nchar: 19 \n \n \n TechSupport StreamingTV StreamingMovies Contract \n Length :7043 Length :7043 Length :7043 Length :7043 \n N.unique : 3 N.unique : 3 N.unique : 3 N.unique : 3 \n N.blank : 0 N.blank : 0 N.blank : 0 N.blank : 0 \n Min.nchar: 2 Min.nchar: 2 Min.nchar: 2 Min.nchar: 8 \n Max.nchar: 19 Max.nchar: 19 Max.nchar: 19 Max.nchar: 14 \n \n \n PaperlessBilling PaymentMethod MonthlyCharges TotalCharges \n Length :7043 Length :7043 Min. : 18.25 Min. : 18.8 \n N.unique : 2 N.unique : 4 1st Qu.: 35.50 1st Qu.: 401.4 \n N.blank : 0 N.blank : 0 Median : 70.35 Median :1397.5 \n Min.nchar: 2 Min.nchar: 12 Mean : 64.76 Mean :2283.3 \n Max.nchar: 3 Max.nchar: 25 3rd Qu.: 89.85 3rd Qu.:3794.7 \n Max. :118.75 Max. :8684.8 \n NAs :11 \n Churn \n Length :7043 \n N.unique : 2 \n N.blank : 0 \n Min.nchar: 2 \n Max.nchar: 3 \n \n \n```\n\n\n:::\n\n```{.r .cell-code}\ninspect_na(telco_data)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 21 × 3\n col_name cnt pcnt\n \n 1 TotalCharges 11 0.156\n 2 customerID 0 0 \n 3 gender 0 0 \n 4 SeniorCitizen 0 0 \n 5 Partner 0 0 \n 6 Dependents 0 0 \n 7 tenure 0 0 \n 8 PhoneService 0 0 \n 9 MultipleLines 0 0 \n10 InternetService 0 0 \n# ℹ 11 more rows\n```\n\n\n:::\n:::\n\n\n# 2) Data Transformation\n\nRecode the churn column into a binary variable where \"Yes\" = 1, and \"No\" = 0\n\nRecode the SeniorCitizen variable into a more descriptive format (e.g. \"Yes\" → \"Senior\", \"No\" → \"non-Senior\")\n\nCreate a new column ServiceCount that sums the indicators (1/0) for multiple services (e.g. PhoneService, OnlineSecurity, etc.)\n\nthese are the multiple services; PhoneService, MultipleLines, OnlineSecurity, OnlineBackup, DeviceProtection, TechSupport, StreamingTV, StreamingMovies\n\nrecode churn (\"Yes\" = 1, and \"No\" = 0) & recode SeniorCitizen (1 = \"Senior\", 0 = \"non-senior\")\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# telco_data |> mutate(Churn= if_else(Churn==\"Yes\", 1, 0))\n# telco_data |> mutate(SeniorCitizen = if_else(SeniorCitizen == 1, \"Senior\", \"non-senior\")) |> View()\n```\n:::\n\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_data_1 <- telco_data |>\n mutate(\n Churn = if_else(Churn == \"Yes\", 1, 0),\n SeniorCitizen = if_else(SeniorCitizen == 1, \"Senior\", \"non-senior\")\n )\nnames(telco_data_1)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n [1] \"customerID\" \"gender\" \"SeniorCitizen\" \"Partner\" \n [5] \"Dependents\" \"tenure\" \"PhoneService\" \"MultipleLines\" \n [9] \"InternetService\" \"OnlineSecurity\" \"OnlineBackup\" \"DeviceProtection\"\n[13] \"TechSupport\" \"StreamingTV\" \"StreamingMovies\" \"Contract\" \n[17] \"PaperlessBilling\" \"PaymentMethod\" \"MonthlyCharges\" \"TotalCharges\" \n[21] \"Churn\" \n```\n\n\n:::\n:::\n\n\nconverting Yes/No to 1/0 for the multiple services\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_data_2 <- telco_data_1 |> \n mutate(\n PhoneService = if_else(PhoneService==\"Yes\", 1, 0), \n OnlineSecurity = if_else(OnlineSecurity==\"Yes\", 1, 0), \n OnlineBackup = if_else(OnlineBackup == \"Yes\", 1, 0), \n DeviceProtection = if_else(DeviceProtection== \"Yes\", 1, 0), \n TechSupport = if_else(TechSupport== \"Yes\", 1, 0), \n StreamingTV = if_else(StreamingTV== \"Yes\", 1, 0), \n StreamingMovies = if_else(StreamingMovies== \"Yes\", 1, 0)\n )\n```\n:::\n\n\ncreate a new column ServiceCount\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_data_clean <- telco_data_2 |> \n mutate(ServiceCount = PhoneService + OnlineSecurity + OnlineBackup + DeviceProtection + TechSupport + StreamingTV + StreamingMovies) \n\nglimpse(telco_data_clean)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\nRows: 7,043\nColumns: 22\n$ customerID \"7590-VHVEG\", \"5575-GNVDE\", \"3668-QPYBK\", \"7795-CFOCW…\n$ gender \"Female\", \"Male\", \"Male\", \"Male\", \"Female\", \"Female\",…\n$ SeniorCitizen \"non-senior\", \"non-senior\", \"non-senior\", \"non-senior…\n$ Partner \"Yes\", \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes…\n$ Dependents \"No\", \"No\", \"No\", \"No\", \"No\", \"No\", \"Yes\", \"No\", \"No\"…\n$ tenure 1, 34, 2, 45, 2, 8, 22, 10, 28, 62, 13, 16, 58, 49, 2…\n$ PhoneService 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…\n$ MultipleLines \"No phone service\", \"No\", \"No\", \"No phone service\", \"…\n$ InternetService \"DSL\", \"DSL\", \"DSL\", \"DSL\", \"Fiber optic\", \"Fiber opt…\n$ OnlineSecurity 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 1, 0, 1,…\n$ OnlineBackup 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0,…\n$ DeviceProtection 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1,…\n$ TechSupport 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0,…\n$ StreamingTV 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1,…\n$ StreamingMovies 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1,…\n$ Contract \"Month-to-month\", \"One year\", \"Month-to-month\", \"One …\n$ PaperlessBilling \"Yes\", \"No\", \"Yes\", \"No\", \"Yes\", \"Yes\", \"Yes\", \"No\", …\n$ PaymentMethod \"Electronic check\", \"Mailed check\", \"Mailed check\", \"…\n$ MonthlyCharges 29.85, 56.95, 53.85, 42.30, 70.70, 99.65, 89.10, 29.7…\n$ TotalCharges 29.85, 1889.50, 108.15, 1840.75, 151.65, 820.50, 1949…\n$ Churn 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0,…\n$ ServiceCount 1, 3, 3, 3, 1, 4, 3, 1, 5, 3, 2, 1, 4, 5, 6, 7, 1, 5,…\n```\n\n\n:::\n\n```{.r .cell-code}\nsummary(telco_data_clean)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n customerID gender SeniorCitizen Partner \n Length :7043 Length :7043 Length :7043 Length :7043 \n N.unique :7043 N.unique : 2 N.unique : 2 N.unique : 2 \n N.blank : 0 N.blank : 0 N.blank : 0 N.blank : 0 \n Min.nchar: 10 Min.nchar: 4 Min.nchar: 6 Min.nchar: 2 \n Max.nchar: 10 Max.nchar: 6 Max.nchar: 10 Max.nchar: 3 \n \n \n Dependents tenure PhoneService MultipleLines \n Length :7043 Min. : 0.00 Min. :0.0000 Length :7043 \n N.unique : 2 1st Qu.: 9.00 1st Qu.:1.0000 N.unique : 3 \n N.blank : 0 Median :29.00 Median :1.0000 N.blank : 0 \n Min.nchar: 2 Mean :32.37 Mean :0.9032 Min.nchar: 2 \n Max.nchar: 3 3rd Qu.:55.00 3rd Qu.:1.0000 Max.nchar: 16 \n Max. :72.00 Max. :1.0000 \n \n InternetService OnlineSecurity OnlineBackup DeviceProtection\n Length :7043 Min. :0.0000 Min. :0.0000 Min. :0.0000 \n N.unique : 3 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 \n N.blank : 0 Median :0.0000 Median :0.0000 Median :0.0000 \n Min.nchar: 2 Mean :0.2867 Mean :0.3449 Mean :0.3439 \n Max.nchar: 11 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 \n Max. :1.0000 Max. :1.0000 Max. :1.0000 \n \n TechSupport StreamingTV StreamingMovies Contract \n Min. :0.0000 Min. :0.0000 Min. :0.0000 Length :7043 \n 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 N.unique : 3 \n Median :0.0000 Median :0.0000 Median :0.0000 N.blank : 0 \n Mean :0.2902 Mean :0.3844 Mean :0.3879 Min.nchar: 8 \n 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 Max.nchar: 14 \n Max. :1.0000 Max. :1.0000 Max. :1.0000 \n \n PaperlessBilling PaymentMethod MonthlyCharges TotalCharges \n Length :7043 Length :7043 Min. : 18.25 Min. : 18.8 \n N.unique : 2 N.unique : 4 1st Qu.: 35.50 1st Qu.: 401.4 \n N.blank : 0 N.blank : 0 Median : 70.35 Median :1397.5 \n Min.nchar: 2 Min.nchar: 12 Mean : 64.76 Mean :2283.3 \n Max.nchar: 3 Max.nchar: 25 3rd Qu.: 89.85 3rd Qu.:3794.7 \n Max. :118.75 Max. :8684.8 \n NAs :11 \n Churn ServiceCount \n Min. :0.0000 Min. :0.000 \n 1st Qu.:0.0000 1st Qu.:1.000 \n Median :0.0000 Median :3.000 \n Mean :0.2654 Mean :2.941 \n 3rd Qu.:1.0000 3rd Qu.:4.000 \n Max. :1.0000 Max. :7.000 \n \n```\n\n\n:::\n:::\n\n\n# GBG Version\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_data_2. <- \n telco_data_1 |> \n mutate(\n ServiceCount = \n (PhoneService == \"Yes\") +\n (OnlineSecurity == \"Yes\") +\n (OnlineBackup == \"Yes\") +\n (DeviceProtection == \"Yes\") +\n (TechSupport == \"Yes\") +\n (StreamingTV == \"Yes\") +\n (StreamingMovies == \"Yes\"\n )\n )\ntelco_data_2.\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 7,043 × 22\n customerID gender SeniorCitizen Partner Dependents tenure PhoneService\n \n 1 7590-VHVEG Female non-senior Yes No 1 No \n 2 5575-GNVDE Male non-senior No No 34 Yes \n 3 3668-QPYBK Male non-senior No No 2 Yes \n 4 7795-CFOCW Male non-senior No No 45 No \n 5 9237-HQITU Female non-senior No No 2 Yes \n 6 9305-CDSKC Female non-senior No No 8 Yes \n 7 1452-KIOVK Male non-senior No Yes 22 Yes \n 8 6713-OKOMC Female non-senior No No 10 No \n 9 7892-POOKP Female non-senior Yes No 28 Yes \n10 6388-TABGU Male non-senior No Yes 62 Yes \n# ℹ 7,033 more rows\n# ℹ 15 more variables: MultipleLines , InternetService ,\n# OnlineSecurity , OnlineBackup , DeviceProtection ,\n# TechSupport , StreamingTV , StreamingMovies ,\n# Contract , PaperlessBilling , PaymentMethod ,\n# MonthlyCharges , TotalCharges , Churn , ServiceCount \n```\n\n\n:::\n:::\n\n\n# 3) Grouping & Summarisation\n\nUse group_by() and summarise() to calculate the churn rate for key segments (e.g. by Contract, InternetService)\n\nchurn rate by contract\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_by_contract <- telco_data_clean |>\n group_by(Contract) |>\n summarise(\n churn = sum(Churn, na.rm = TRUE),\n churn_rate = mean(Churn) * 100\n )\ntelco_by_contract\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 3 × 3\n Contract churn churn_rate\n \n1 Month-to-month 1655 42.7 \n2 One year 166 11.3 \n3 Two year 48 2.83\n```\n\n\n:::\n:::\n\n\nchurn rate by Internet Service\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_by_inter <- telco_data_clean |>\n group_by(InternetService) |>\n summarise(\n churn = sum(Churn),\n churn_rate = mean(Churn) * 100\n )\n```\n:::\n\n\nchurn rate by both contract and Internet Service\n\n\n::: {.cell}\n\n```{.r .cell-code}\ntelco_by_contract_internet <- telco_data_clean |> group_by(Contract, InternetService) |> \n summarise(churn = sum(Churn, na.rm = TRUE), \n churn_rate = mean(Churn)*100)\n```\n\n::: {.cell-output .cell-output-stderr}\n\n```\n`summarise()` has regrouped the output.\nℹ Summaries were computed grouped by Contract and InternetService.\nℹ Output is grouped by Contract.\nℹ Use `summarise(.groups = \"drop_last\")` to silence this message.\nℹ Use `summarise(.by = c(Contract, InternetService))` for per-operation\n grouping (`?dplyr::dplyr_by`) instead.\n```\n\n\n:::\n\n```{.r .cell-code}\ntelco_by_contract_internet\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 9 × 4\n# Groups: Contract [3]\n Contract InternetService churn churn_rate\n \n1 Month-to-month DSL 394 32.2 \n2 Month-to-month Fiber optic 1162 54.6 \n3 Month-to-month No 99 18.9 \n4 One year DSL 53 9.30 \n5 One year Fiber optic 104 19.3 \n6 One year No 9 2.47 \n7 Two year DSL 12 1.91 \n8 Two year Fiber optic 31 7.23 \n9 Two year No 5 0.784\n```\n\n\n:::\n:::\n\n\nCalculate the overall churn rate\n\n\n::: {.cell}\n\n```{.r .cell-code}\noverall_churn <- telco_data_clean |> \n summarise(total_churn = sum(Churn), \n churn_rate = mean(Churn)*100)\noverall_churn\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 1 × 2\n total_churn churn_rate\n \n1 1869 26.5\n```\n\n\n:::\n:::\n\n\nchurn rate for each Contract type\n\n\n::: {.cell}\n\n```{.r .cell-code}\ncontract_churn <- telco_data_clean |> \n group_by(Contract) |> \n summarise(count = n(), \n churn = sum(Churn), \n churn_rate = mean(Churn)*100)\ncontract_churn\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 3 × 4\n Contract count churn churn_rate\n \n1 Month-to-month 3875 1655 42.7 \n2 One year 1473 166 11.3 \n3 Two year 1695 48 2.83\n```\n\n\n:::\n:::\n\n\nSummary statistics for internetservices (count, Average monthly charges, Average tenure)\n\n\n::: {.cell}\n\n```{.r .cell-code}\nsummary_internet <- telco_data_clean |> group_by(InternetService) |> \n summarise( ave_monthly_charges = mean(MonthlyCharges, \n na.rm = TRUE),\n ave_tenure = mean(tenure, na.rm = TRUE))\nsummary_internet\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 3 × 3\n InternetService ave_monthly_charges ave_tenure\n \n1 DSL 58.1 32.8\n2 Fiber optic 91.5 32.9\n3 No 21.1 30.5\n```\n\n\n:::\n:::\n\n\nUse across() to summarise monthly charges for both genders in one concise step\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# by use of summarise(.by)\ngender_summary <- telco_data_clean |>\n summarise(\n across(\n MonthlyCharges,\n list(\n Mean = ~ mean(.x, na.rm = TRUE),\n Median = ~ median(.x, na.rm = TRUE),\n Minimum = ~ min(.x, na.rm = TRUE),\n Maximum = ~ max(.x, na.rm = TRUE)\n )\n ),\n .by = gender\n )\ngender_summary\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 2 × 5\n gender MonthlyCharges_Mean MonthlyCharges_Median MonthlyCharges_Minimum\n \n1 Female 65.2 70.6 18.4\n2 Male 64.3 70.1 18.2\n# ℹ 1 more variable: MonthlyCharges_Maximum \n```\n\n\n:::\n\n```{.r .cell-code}\n# by use of group_by() and summarise() combo\ntelco_data_clean |>\n group_by(gender) |>\n summarise(\n mean_charges = mean(MonthlyCharges, na.rm = TRUE),\n median_charges = median(MonthlyCharges, na.rm = TRUE),\n min_charges = min(MonthlyCharges, na.rm = TRUE),\n max_charges = max(MonthlyCharges, na.rm = TRUE)\n )\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 2 × 5\n gender mean_charges median_charges min_charges max_charges\n \n1 Female 65.2 70.6 18.4 119.\n2 Male 64.3 70.1 18.2 118.\n```\n\n\n:::\n\n```{.r .cell-code}\ntelco_data_clean\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n# A tibble: 7,043 × 22\n customerID gender SeniorCitizen Partner Dependents tenure PhoneService\n \n 1 7590-VHVEG Female non-senior Yes No 1 0\n 2 5575-GNVDE Male non-senior No No 34 1\n 3 3668-QPYBK Male non-senior No No 2 1\n 4 7795-CFOCW Male non-senior No No 45 0\n 5 9237-HQITU Female non-senior No No 2 1\n 6 9305-CDSKC Female non-senior No No 8 1\n 7 1452-KIOVK Male non-senior No Yes 22 1\n 8 6713-OKOMC Female non-senior No No 10 0\n 9 7892-POOKP Female non-senior Yes No 28 1\n10 6388-TABGU Male non-senior No Yes 62 1\n# ℹ 7,033 more rows\n# ℹ 15 more variables: MultipleLines , InternetService ,\n# OnlineSecurity , OnlineBackup , DeviceProtection ,\n# TechSupport , StreamingTV , StreamingMovies ,\n# Contract , PaperlessBilling , PaymentMethod ,\n# MonthlyCharges , TotalCharges , Churn , ServiceCount \n```\n\n\n:::\n:::\n\n\n# 4. Data Visualization\n\nExploratory visualizations\n\nDistribution of customer tenure\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# tenure-histogram\n\n\nggplot(telco_data_clean, aes(x = tenure)) +\n geom_histogram(binwidth = 5, boundary = 0, color = \"white\") +\n labs(x = \"Tenure (months)\", y = \"Number of customers\") +\n theme_minimal()\n```\n\n::: {.cell-output-display}\n![](index_files/figure-html/unnamed-chunk-16-1.png){width=672}\n:::\n:::\n\n\nThe histogram reveals how customers are distributed across the customer lifecycle and helps identify concentrations of very new and long-standing customers.\n\nChurned versus non-churned customers\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# churn-bar\n\n\nggplot(telco_data_clean, aes(x = Churn, fill = Churn)) +\n geom_bar(show.legend = FALSE) +\n labs(x = \"Churn status\", y = \"Number of customers\") +\n theme_minimal()\n```\n\n::: {.cell-output .cell-output-stderr}\n\n```\nWarning: The following aesthetics were dropped during statistical transformation: fill.\nℹ This can happen when ggplot fails to infer the correct grouping structure in\n the data.\nℹ Did you forget to specify a `group` aesthetic or to convert a numerical\n variable into a factor?\n```\n\n\n:::\n\n::: {.cell-output-display}\n![](index_files/figure-html/unnamed-chunk-17-1.png){width=672}\n:::\n:::\n\n\nThe bar chart makes the class balance visible and provides context for interpreting the overall churn rate.\n\n# Discussion Points\n\nData transformation with `dplyr` converts raw records into analysis-ready variables and summaries. In this report, `mutate()` creates the binary churn indicator, descriptive senior-citizen label, average charge metric, and service count. `group_by()` and `summarise()` produce churn rates and segment-level statistics, while `across()` applies the same statistical functions efficiently to multiple variables. The result is shorter, more readable, reproducible code and a dataset that can move naturally from exploratory analysis into predictive modelling.", "supporting": [ "index_files" ], "filters": [ "rmarkdown/pagebreak.lua" ], "includes": {}, "engineDependencies": {}, "preserve": {}, "postProcess": true } }