Machine Learning

Data Cleaning and Preparation

#Handle missing/inconsistent values in TotalCharges # Convert TotalCharges to numeric Telco_data\(TotalCharges <- as.numeric(as.character(Telco_data\)TotalCharges))

Replace NA values with mean

mean_total <- mean(Telco_data\(TotalCharges, na.rm = TRUE) Telco_data\)TotalCharges[is.na(Telco_data\(TotalCharges)] <- mean_total summary(Telco_data\)TotalCharges) View(Telco_data) # Convert categorical variables into numerical form (encoding) # Identify categorical variables to encode cat_vars <- c(“gender”,“partner”,“Dependents”, “PhoneService”, “MultipleLines”, “InternetService”, “OnlineSecurity”, “OnlineBackup”, “DeviceProtection”, “TechSupport”, “StreamingTV”, “StreamingMovies”, “Contract”, “PaperlessBilling”, “PaymentMethod”, “Churn”)