### Install survminer from GitHub

Source: https://github.com/kassambara/survminer/blob/master/README.md

Install the latest development version of survminer from GitHub. Ensure the devtools package is installed first.

```r
if(!require(devtools)) install.packages("devtools")
devtools::install_github("kassambara/survminer", build_vignettes = FALSE)
```

--------------------------------

### Install Required Packages

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/quick-reference.md

Installs essential packages for survival analysis visualization and optional packages for advanced models like flexible parametric models and competing risks.

```r
install.packages(c(
  "ggplot2", "ggpubr", "survival", "gridExtra",
  "broom", "dplyr", "tidyr", "purrr", "maxstat"
))
```

```r
install.packages(c(
  "flexsurv",  # For flexible parametric models
  "cmprsk"     # For competing risks
))
```

--------------------------------

### Install and Load survminer

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/index.md

Install the survminer package from CRAN or GitHub and load it into your R session.

```r
# From CRAN
install.packages("survminer")

# From GitHub (latest development version)
devtools::install_github("kassambara/survminer")

# Load package
library("survminer")
```

--------------------------------

### surv_fit with Matching Formulas and Datasets

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Example of using surv_fit with multiple formulas and datasets, enabling matching between formulas and datasets using `match.fd = TRUE`. Requires setting a seed for reproducibility.

```r
formulas <- list(
  Surv(time, status) ~ sex,
  Surv(time, status) ~ rx
)
set.seed(123)
sample1 <- dplyr::sample_frac(colon, 0.5)
sample2 <- dplyr::sample_frac(colon, 0.5)
datasets <- list(sample1 = sample1, sample2 = sample2)
fit6 <- surv_fit(formulas, data = datasets, match.fd = TRUE)
surv_pvalue(fit6)
```

--------------------------------

### Inspecting Detailed Survival Estimates

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

This example shows how to use surv_summary to obtain detailed survival estimates and then inspect the first 10 rows of the resulting data frame. It also demonstrates how to extract the median survival statistics.

```r
fit <- survfit(Surv(time, status) ~ sex, data = lung)
res <- surv_summary(fit)

# View detailed survival estimates
head(res, 10)

# View median survival
attr(res, "table")
```

--------------------------------

### Package Not Installed Solution

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/errors.md

To resolve the 'package not installed' error, install the 'survminer' package from CRAN or GitHub, then verify the installation.

```r
# Install from CRAN
install.packages("survminer")
```

```r
# Or from GitHub
devtools::install_github("kassambara/survminer")
```

```r
# Verify installation
library("survminer")
packageVersion("survminer")
```

--------------------------------

### Missing Dependencies Solution

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/errors.md

If a 'Namespace error' occurs due to missing dependencies, install all required packages, including 'ggplot2', 'ggpubr', 'survival', and others.

```r
# Install missing dependencies
install.packages(c("ggplot2", "ggpubr", "survival", "gridExtra", 
                   "broom", "dplyr", "tidyr", "purrr", "maxstat"))
```

--------------------------------

### Install survminer from CRAN

Source: https://github.com/kassambara/survminer/blob/master/README.md

Use this command to install the survminer package from the Comprehensive R Archive Network (CRAN).

```r
install.packages("survminer")
```

--------------------------------

### Stratified Survival Analysis with surv_summary

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

This example demonstrates how to perform stratified survival analysis using surv_summary with multiple stratification variables. It shows how to subset the results to analyze survival for specific strata, such as males or individuals with a performance status of 0.

```r
fit <- survfit(Surv(time, status) ~ sex + ph.ecog, data = lung)
res <- surv_summary(fit)

# Survival for males only
males <- res[res$sex == "Male", ]

# Survival for performance status 0
perf0 <- res[res$ph.ecog == 0, ]
```

--------------------------------

### Fit Cox Model and Plot Deviance Residuals

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/cox-diagnostics.md

This example demonstrates how to fit a Cox proportional hazards model using the `coxph` function and then visualize the deviance residuals using `ggcoxdiagnostics`. Ensure the `survival` and `survminer` libraries are loaded.

```r
library("survival")
library("survminer")

fit <- coxph(Surv(time, status) ~ sex + log(inst) + log(nodes), 
             data = cancer)

# Deviance residuals
ggcoxdiagnostics(fit, type = "deviance")
```

--------------------------------

### Test Survival Models with Minimal Data

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/errors.md

Verify your survival analysis setup by testing with built-in datasets like 'lung' and gradually adding complexity to the `ggsurvplot` function.

```r
library("survival")

# Test with simple case
fit <- survfit(Surv(time, status) ~ sex, data = lung)
ggsurvplot(fit, data = lung)  # Should work
```

```r
# Add complexity gradually
ggsurvplot(fit, data = lung, risk.table = TRUE)
ggsurvplot(fit, data = lung, conf.int = TRUE)
```

--------------------------------

### Get R Session Information

Source: https://github.com/kassambara/survminer/blob/master/ISSUE_TEMPLATE.md

Use this command to retrieve detailed information about your R session, including package versions. This is crucial for debugging.

```R
# please paste here the result of
devtools::session_info()
```

--------------------------------

### Calculate Combined P-values for Multiple Survival Curve Comparisons

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_pvalue.md

This example shows how to compute and combine p-values for multiple, independent survival curve comparisons. It takes a list of survfit objects and calculates p-values for each, displaying them together with an option to combine results.

```r
fit1 <- survfit(Surv(time, status) ~ sex, data = lung)
fit2 <- survfit(Surv(time, status) ~ ph.ecog, data = lung)
fits <- list(sex = fit1, ecog = fit2)
surv_pvalue(fits, combine = TRUE)

#        pval    method        pval.txt variable
#1 0.001083102 survdiff p = 0.0011          sex
#2 0.000000010 survdiff p < 0.0001        ph.ecog
```

--------------------------------

### Custom Plotting with ggsurvplot_df

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

This example shows how to use the output of surv_summary with the ggsurvplot_df function to create custom survival plots, including confidence intervals and risk tables.

```r
fit <- survfit(Surv(time, status) ~ sex, data = lung)
res <- surv_summary(fit)

# Use with ggsurvplot_df for custom plotting
ggsubvplot_df(res, conf.int = TRUE, risk.table = TRUE)
```

--------------------------------

### Check Functional Form with Partial Residuals

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/cox-diagnostics.md

This example shows how to plot partial residuals against linear predictions to check the functional form of covariates in a Cox proportional hazards model using `ggcoxdiagnostics`. Ensure `survival` and `survminer` are loaded.

```r
library("survival")
library("survminer")

fit <- coxph(Surv(time, status) ~ sex + log(inst) + log(nodes), 
             data = cancer)

# Check functional form
ggcoxdiagnostics(fit, type = "partial", linear.predictions = TRUE)
```

--------------------------------

### Basic surv_fit Usage

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Demonstrates the basic usage of surv_fit, equivalent to survival::survfit, for a single formula and dataset. Requires the survival and survminer libraries.

```r
library("survival")
library("survminer")

# Case 1: Basic usage - equivalent to survival::survfit
fit1 <- surv_fit(Surv(time, status) ~ sex, data = colon)
ggsurvplot(fit1, data = colon)
```

--------------------------------

### Get survminer Citation

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/index.md

Use this R command to retrieve the citation details for the survminer package, which should be included in any published work that utilizes the package.

```r
citation("survminer")
```

--------------------------------

### Configure General Table Parameters

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/configuration.md

Set global parameters for all tables, such as height, color, font size, and font family. Options exist to color tables by strata or hide/color Y-axis labels.

```r
# Height of all tables
tables.height = 0.25

# Color all tables
tables.col = "black"

# Color tables by strata
tables.col = "strata"

# Font size for tables
fontsize = 4

# Font family for tables
font.family = "Courier New"

# Hide table Y-axis labels
tables.y.text = FALSE

# Color table Y-axis labels
tables.y.text.col = TRUE
```

--------------------------------

### Create Cox Proportional Hazards Model Object

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/types.md

Use this to create a coxph object, which is an input for Cox diagnostic and forest plot functions. Ensure the survival package is installed.

```r
fit <- coxph(Surv(time, status) ~ sex + age, data = lung)
class(fit)
summary(fit)
```

--------------------------------

### List of Formulas and List of Datasets (Cartesian Product)

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Apply all formulas to all datasets, creating a Cartesian product. Returns a named list of survfit objects, named by formula and data set.

```r
formulas <- list(
  sex = Surv(time, status) ~ sex,
  rx = Surv(time, status) ~ rx
)
datasets <- list(
  colon = colon,
  lung = lung
)
fit <- surv_fit(formulas, data = datasets)
# Returns 4 survfit objects: sex_colon, sex_lung, rx_colon, rx_lung
```

--------------------------------

### Enable Verbose Output with traceback and debug

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/errors.md

Use `traceback()` within `tryCatch` to inspect function call stacks on error. Employ `debug()` to step through function execution for detailed analysis.

```r
tryCatch(
  ggsurvplot(fit, data = data),
  error = function(e) traceback()
)
```

```r
debug(surv_summary)
surv_summary(fit)
# Step through function
```

--------------------------------

### Customizing Adjusted Survival Curves

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/cox-forest-adjusted.md

Provides an example of customizing the appearance of adjusted survival curves, including changing the color palette, applying a different theme, and modifying legend labels.

```r
ggadjustedcurves(fit, variable = "sex", data = cancer,
                palette = c("#E7B800", "#2E9FDF"),
                ggtheme = theme_bw(),
                legend.labs = c("Male", "Female"))
```

--------------------------------

### Fit and Visualize Survival Curves

Source: https://github.com/kassambara/survminer/blob/master/NEWS.md

Demonstrates how to fit survival curves using the survival package and visualize them with ggsurvplot, including p-value and confidence intervals.

```R
require("survival")
fit<- survfit(Surv(time, status) ~ sex, data = lung)

# visualize
require(survminer)
ggsurvplot(fit, pval = TRUE, conf.int = TRUE,
          risk.table = TRUE)
```

--------------------------------

### surv_fit with Multiple Formulas and Datasets

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Demonstrates fitting survival curves using multiple formulas across multiple datasets. The output is a named list of survfit objects.

```r
formulas <- list(
  by_sex = Surv(time, status) ~ sex,
  by_rx = Surv(time, status) ~ rx
)
datasets <- list(
  colon = colon,
  lung = lung
)
fit4 <- surv_fit(formulas, data = datasets)
surv_pvalue(fit4)
```

--------------------------------

### File Organization Structure

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/README.md

Illustrates the directory structure of the survminer R package documentation, showing the organization of various markdown files for different aspects of the package.

```markdown
/workspace/home/output/
├── README.md                       # This file
├── index.md                        # Full overview and index
├── quick-reference.md              # Task-oriented quick lookup
├── types.md                        # Type definitions
├── configuration.md                # Theming and styling
├── errors.md                       # Errors and troubleshooting
└── api-reference/
    ├── ggsurvplot.md             # Main plotting
    ├── surv_fit.md               # Fit functions
    ├── surv_summary.md           # Summary functions
    ├── surv_pvalue.md            # Statistical tests
    ├── surv_cutpoint.md          # Cutpoint analysis
    ├── cox-diagnostics.md        # Cox diagnostics
    ├── cox-forest-adjusted.md    # Cox visualization
    ├── utility-functions.md      # Utilities
    └── plotting-variants.md      # Specialized plots
```

--------------------------------

### Access survminer Function Help

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/index.md

These R commands allow you to access help documentation for specific survminer functions like ggsurvplot and surv_fit, or to browse all available functions and vignettes for the package.

```r
# Function help
?ggsurvplot
?surv_fit

# Browse all functions
help(package = "survminer")

# Vignettes
vignette("survminer")
browseVignettes("survminer")
```

--------------------------------

### Customize Survival Plot Labels and Fonts

Source: https://github.com/kassambara/survminer/blob/master/README.md

Applies custom labels and font styles to survival curves, risk tables, and censor plots. This example demonstrates changing titles, subtitles, captions, and axis label fonts using the `labs` function and the `customize_labels` helper.

```r
# Changing Labels
# %%%%%%%%%%%%%%%%%%%%%%%%%%
# Labels for Survival Curves (plot)
ggsubr$plot <- ggsubr$plot + labs(
  title    = "Survival curves",                     
  subtitle = "Based on Kaplan-Meier estimates",  
  caption  = "created with survminer"             
  )

# Labels for Risk Table 
ggsubr$table <- ggsubr$table + labs(
  title    = "Note the risk set sizes",          
  subtitle = "and remember about censoring.", 
  caption  = "source code: website.com"        
  )

# Labels for ncensor plot 
ggsubr$ncensor.plot <- ggsubr$ncensor.plot + labs( 
  title    = "Number of censorings", 
  subtitle = "over the time.",
  caption  = "source code: website.com"
  )

# Changing the font size, style and color
# %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
# Applying the same font style to all the components of ggsubr:
# survival curves, risk table and censor part

ggsubr <- customize_labels(
  gggsubr,
  font.title    = c(16, "bold", "darkblue"),         
  font.subtitle = c(15, "bold.italic", "purple"), 
  font.caption  = c(14, "plain", "orange"),        
  font.x        = c(14, "bold.italic", "red"),          
  font.y        = c(14, "bold.italic", "darkred"),      
  font.xtickslab = c(12, "plain", "darkgreen")
)

ggsubr
```

--------------------------------

### Basic surv_summary Usage

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

Demonstrates fitting a survival curve and then summarizing it using surv_summary. The output can be viewed with head() or printed entirely. Accessing attributes like 'table' provides median survival and other statistics.

```r
library("survival")
library("survminer")

# Fit survival curves
fit <- survfit(Surv(time, status) ~ rx + adhere, data = colon)

# Summarize
res <- surv_summary(fit, data = colon)

# View the summary
head(res)

# Access summary information
print(res)

# Extract median survival and other statistics
attr(res, "table")

# Subset by strata
res[res$strata == "rx=Lev", ]

# Plot from summary (surv_summary output can be passed to ggsurvplot)
ggsubvplot_df(res)

# Simple stratification
fit2 <- survfit(Surv(time, status) ~ sex, data = lung)
res2 <- surv_summary(fit2)
head(res2)

# Multi-level stratification
fit3 <- survfit(Surv(time, status) ~ sex + ph.ecog, data = lung)
res3 <- surv_summary(fit3)
head(res3)
```

--------------------------------

### Configure Break and Limit Parameters for Axes

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/configuration.md

Control axis breaks and limits for survival plots. You can break the time axis by a specific value or a vector of exact break points, break the y-axis, set x and y axis limits, and control whether axes start at the origin.

```r
# Break time axis by value
break.time.by = 100

# Or specify exact breaks
break.time.by = c(0, 100, 200, 300)

# Break Y-axis
break.y.by = 0.1
break.y.by = c(0, 0.25, 0.5, 0.75, 1)

# X-axis limits
xlim = c(0, 500)

# Y-axis limits
ylim = c(0, 1)

# Don't start axes at origin
axes.offset = FALSE
```

--------------------------------

### Comprehensive survminer Plot Customization

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/configuration.md

An example demonstrating extensive customization of a survival plot using ggsurvplot. This includes setting titles, labels, colors, line types, confidence intervals, legend appearance, median survival lines, censoring marks, p-values, risk tables, axis scaling and breaks, themes, and font styles.

```r
library("survival")
library("survminer")

fit <- survfit(Surv(time, status) ~ sex, data = lung)

# Comprehensive customization
ggsurvplot(
  fit,
  data = lung,
  # Title and labels
  title = "Lung Cancer Survival",
  xlab = "Time (months)",
  ylab = "Overall Survival",
  # Appearance
  palette = c("#E7B800", "#2E9FDF"),
  linetype = 1,
  size = 1,
  # Confidence intervals
  conf.int = TRUE,
  conf.int.fill = "lightblue",
  conf.int.alpha = 0.2,
  # Legend
  legend = c(0.8, 0.2),
  legend.title = "Gender",
  legend.labs = c("Male", "Female"),
  # Median survival
  surv.median.line = "hv",
  # Censoring marks
  censor = TRUE,
  censor.shape = "|",
  censor.size = 5,
  # P-value
  pval = TRUE,
  pval.size = 5,
  pval.coord = c(300, 0.9),
  # Risk table
  risk.table = TRUE,
  risk.table.title = "Subjects at Risk",
  risk.table.pos = "out",
  risk.table.col = "strata",
  risk.table.height = 0.2,
  tables.theme = theme_cleantable(),
  # Axes
  xlim = c(0, 600),
  ylim = c(0, 1),
  break.time.by = 100,
  xscale = "d_m",  # Convert days to months
  # Theme
  ggtheme = theme_bw(),
  # Font customization
  font.title = c(14, "bold", "darkblue"),
  font.x = c(12, "bold", "black"),
  font.y = c(12, "bold", "black"),
  font.tickslab = c(10, "plain", "black")
)
```

--------------------------------

### Project Directory Structure

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/MANIFEST.md

This is the hierarchical structure of the survminer project, showing the organization of markdown files for documentation.

```bash
/workspace/home/output/
├── README.md                    # Entry point
├── index.md                     # Full reference
├── quick-reference.md           # Task lookup
├── types.md                     # Type documentation
├── configuration.md             # Styling reference
├── errors.md                    # Troubleshooting
├── MANIFEST.md                  # This file
└── api-reference/               # Function documentation
    ├── ggsurvplot.md
    ├── surv_fit.md
    ├── surv_summary.md
    ├── surv_pvalue.md
    ├── surv_cutpoint.md
    ├── cox-diagnostics.md
    ├── cox-forest-adjusted.md
    ├── utility-functions.md
    └── plotting-variants.md
```

--------------------------------

### Filtering Cutpoints by Statistical Significance

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_cutpoint.md

This example shows how to filter cutpoints based on statistical significance. It first calculates cutpoints for multiple variables and then uses the `statistic` column from the summary to identify variables with a statistic greater than a specified threshold (e.g., 3.84 for a chi-square test with 1 degree of freedom), before categorizing the data using only these significant variables.

```r
res.cut <- surv_cutpoint(
  myeloma,
  time = "time",
  event = "event",
  variables = c("DEPDC1", "WHSC1", "CRIM1")
)

cutpoints <- summary(res.cut)

# Use only significant cutpoints (e.g., p < 0.05)
# Note: Significance is measured by the statistic, lower is better
sig_vars <- rownames(cutpoints)[cutpoints$statistic > 3.84]  # Chi-square threshold

res.cat <- surv_categorize(res.cut, variables = sig_vars)
```

--------------------------------

### Fit Cox Model and Create Forest Plot

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/cox-forest-adjusted.md

Demonstrates fitting a Cox proportional hazards model using the 'survival' package and then generating a basic forest plot with 'survminer'.

```r
library("survival")
library("survminer")

# Fit Cox model
fit <- coxph(Surv(time, status) ~ sex + log(inst) + log(nodes) +
             extent + xray, data = cancer)

# Create forest plot
ggforest(fit, data = cancer)
```

--------------------------------

### Multiple Test Methods for P-value Computation

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_pvalue.md

Demonstrates how to compute p-values using different statistical tests like Gehan-Breslow, Tarone-Ware, and Peto-Peto by specifying the 'method' argument. Supports weight notation for methods.

```r
# Fit survival curves
fit <- survfit(Surv(time, status) ~ sex, data = colon)

# Log-rank (default)
surv_pvalue(fit, colon, method = "survdiff")

# Gehan-Breslow (good for early differences)
surv_pvalue(fit, colon, method = "n")

# Tarone-Ware
surv_pvalue(fit, colon, method = "sqrtN")

# Peto-Peto
surv_pvalue(fit, colon, method = "S1")

# By weight notation
surv_pvalue(fit, colon, method = "1")  # Log-rank
surv_pvalue(fit, colon, method = "n")  # Gehan-Breslow
```

--------------------------------

### Adjusting Minimal Proportion for Cutpoint Analysis

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_cutpoint.md

Demonstrates how to adjust the `minprop` argument in `surv_cutpoint` to control the minimum proportion of observations in each group. A lower `minprop` allows for more flexibility, while a higher `minprop` imposes a stricter requirement. The output compares the cutpoints generated with different `minprop` values.

```r
# Default: 10% minimum per group
res.cut1 <- surv_cutpoint(
  myeloma,
  time = "time",
  event = "event",
  variables = c("DEPDC1"),
  minprop = 0.1
)

# More stringent: 20% minimum per group
res.cut2 <- surv_cutpoint(
  myeloma,
  time = "time",
  event = "event",
  variables = c("DEPDC1"),
  minprop = 0.2
)

# Compare cutpoints
print(summary(res.cut1))
print(summary(res.cut2))
```

--------------------------------

### Large-scale Gene Expression Analysis with surv_cutpoint

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_cutpoint.md

This snippet shows how to load a dataset with multiple gene expression variables, find optimal cutpoints for all genes using `surv_cutpoint`, categorize genes based on these cutpoints using `surv_categorize`, fit survival curves for selected genes, and visualize them with `ggsurvplot`. It requires the `survminer` and `survival` libraries.

```r
library("survminer")
library("survival")

# Load data with many genes
data(myeloma)

# Find optimal cutpoints for all genes
gene_vars <- colnames(myeloma)[-(1:2)]  # Exclude time and event columns
res.cut <- surv_cutpoint(
  myeloma,
  time = "time",
  event = "event",
  variables = gene_vars,
  minprop = 0.1,
  progressbar = TRUE
)

# Categorize all genes
res.cat <- surv_categorize(res.cut)

# Fit survival curves for each gene
fit.list <- surv_fit(
  Surv(time, event) ~ DEPDC1 + WHSC1 + CRIM1 + FAM46C + FAM4C + FAM46D,
  data = res.cat
)

# Visualize
ggsubplot(fit.list, data = res.cat)
```

--------------------------------

### Fit Cox Model and Plot Adjusted Curves

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/cox-forest-adjusted.md

Demonstrates fitting a Cox proportional hazards model and then plotting adjusted survival curves for a specified variable using the 'average' method. Requires the survival and survminer libraries.

```r
library("survival")
library("survminer")

# Fit Cox model
fit <- coxph(Surv(time, status) ~ sex + log(inst) + log(nodes), 
             data = cancer)

# Adjusted curves for sex (adjusted for other covariates)
ggadjustedcurves(fit, variable = "sex", data = cancer, method = "average")
```

--------------------------------

### Group Survival Data by Variables

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/utility-functions.md

Prepares survival data for grouped analysis by creating a list of datasets based on specified grouping variables. Requires the 'survival' and 'survminer' libraries.

```r
library("survival")
library("survminer")

# Group by treatment and gender
grouped.data <- surv_group_by(colon, grouping.vars = c("rx", "sex"))

# Fit survival curves for each group
fit <- surv_fit(Surv(time, status) ~ adhere, data = grouped.data)

# Plot stratified by group variables
ggsurvplot(fit, data = colon)
```

--------------------------------

### Fit Complex Survival Curves and Visualize with Faceting

Source: https://github.com/kassambara/survminer/blob/master/NEWS.md

Demonstrates fitting a complex survival model using the survival package and visualizing the results with ggsurvplot, applying faceting by multiple factors. Requires 'survival' and 'survminer' packages.

```r
require("survival")
fit3 <- survfit( Surv(time, status) ~ sex + rx + adhere,
                data = colon )
                
# Visualize by faceting
# Plots are survival curves by sex faceted by rx and adhere factors.
require("survminer")  
ggsurv$plot +theme_bw() + facet_grid(rx ~ adhere)
```

--------------------------------

### Exporting Survival Summary Data

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

This scenario demonstrates how to export the survival summary data generated by surv_summary to a CSV file. It also shows how to print the summary statistics table.

```r
fit <- survfit(Surv(time, status) ~ sex, data = lung)
res <- surv_summary(fit)

# Write to CSV
write.csv(res, file = "survival_summary.csv")

# Summary statistics
print(attr(res, "table"))
```

--------------------------------

### Basic Cutpoint Determination with surv_cutpoint

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_cutpoint.md

Find optimal cutpoints for multiple genes using the surv_cutpoint function. This requires loading the survminer library and a dataset like 'myeloma'.

```r
library("survminer")
data(myeloma)

# Find optimal cutpoints for multiple genes
res.cut <-
  surv_cutpoint(
    myeloma,
    time = "time",
    event = "event",
    variables = c("DEPDC1", "WHSC1", "CRIM1")
  )

# View summary of cutpoints
summary(res.cut)

# Print results
print(res.cut)
```

--------------------------------

### List of Formulas and Single Dataset

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Apply multiple formulas to the same dataset. Returns a named list of survfit objects in the order of the formulas provided.

```r
formulas <- list(
  sex = Surv(time, status) ~ sex,
  rx = Surv(time, status) ~ rx,
  adhere = Surv(time, status) ~ adhere
)
fit <- surv_fit(formulas, data = colon)
```

--------------------------------

### Define Survival Formula Syntax

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/types.md

Shows standard R formula syntax for survival analysis, including basic survival formulas, Cox model formulas, and stratified analysis.

```r
# Survival formula (left side)
Surv(time, event) ~ group

# Cox model formula
Surv(time, event) ~ covariate1 + covariate2

# Stratified analysis
Surv(time, event) ~ group + strata(institution)
```

--------------------------------

### Grouped Data (group.by option)

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Create separate fits for each variable combination using the group.by option. Returns a named list of survfit objects, grouped by strata.

```r
fit <- surv_fit(
  Surv(time, status) ~ sex,
  data = colon,
  group.by = "rx"
)
# Creates separate sex stratification for each rx level
```

--------------------------------

### surv_fit for Grouped Analysis

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Shows how to perform a grouped survival analysis using the `group.by` argument in surv_fit. This allows fitting curves for subgroups within a dataset.

```r
fit5 <- surv_fit(
  Surv(time, status) ~ sex,
  data = colon,
  group.by = "rx"
)
ggsurvplot(fit5, data = colon, facet.by = "rx")
```

--------------------------------

### Load survminer library

Source: https://github.com/kassambara/survminer/blob/master/README.md

Load the survminer package into your R session to use its functions.

```r
library("survminer")
```

--------------------------------

### surv_fit with Multiple Formulas

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Shows how to use surv_fit with a list of formulas applied to the same dataset. The function returns a named list of survfit objects.

```r
formulas <- list(
  sex = Surv(time, status) ~ sex,
  rx = Surv(time, status) ~ rx,
  adhere = Surv(time, status) ~ adhere
)
fits <- surv_fit(formulas, data = colon)
ggsurvplot(fits, data = colon)
surv_pvalue(fits)
```

--------------------------------

### Configure Confidence Interval Display

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/configuration.md

Control the visibility, style, fill color, and transparency of confidence intervals. Use 'conf.int.style' to choose between 'ribbon' and 'step'.

```r
# Show confidence interval
conf.int = TRUE

# Confidence interval style: "ribbon" or "step"
conf.int.style = "ribbon"

# CI fill color
conf.int.fill = "lightblue"

# CI transparency (0 = transparent, 1 = opaque)
conf.int.alpha = 0.15
```

--------------------------------

### Single Formula and Single Dataset

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Use this for the simplest case, equivalent to standard survival::survfit(). Returns one survfit object.

```r
fit <- surv_fit(Surv(time, status) ~ sex, data = colon)
```

--------------------------------

### Fit survival curves

Source: https://github.com/kassambara/survminer/blob/master/README.md

Fit survival curves using the `survfit` function from the survival package. Requires the survival package to be loaded.

```r
require("survival")
fit <- survfit(Surv(time, status) ~ sex, data = lung)
```

--------------------------------

### Single Formula and List of Datasets

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Apply the same formula across multiple cohorts. Returns a named list of survfit objects in the order of the datasets provided.

```r
fit <- surv_fit(
  Surv(time, status) ~ sex,
  data = list(colon = colon, lung = lung, breast = breast)
)
```

--------------------------------

### Print survminer plots to ReporteRs PowerPoint

Source: https://github.com/kassambara/survminer/blob/master/NEWS.md

Demonstrates how to integrate survminer plots into a PowerPoint presentation using the ReporteRs package. Ensure 'newpage = FALSE' is used when printing the plot to avoid creating a new slide for each plot.

```r
require(survival)
require(ReporteRs)
require(survminer)

fit <- survfit(Surv(time, status) ~ rx + adhere, data =colon)
survplot <- ggsurvplot(fit, pval = TRUE,
                       break.time.by = 400,
                       risk.table = TRUE,
                       risk.table.col = "strata",
                       risk.table.height = 0.5, # Useful when you have multiple groups
                       palette = "Dark2")


require(ReporteRs)
doc = pptx(title = "Survival plots")
doc = addSlide(doc, slide.layout = "Title and Content")
doc = addTitle(doc, "First try")
doc = addPlot(doc, function() print(survplot, newpage = FALSE), vector.graphic = TRUE)
writeDoc(doc, "test.pptx")
```

--------------------------------

### Formula-Data Matching

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_fit.md

Apply formulas to matching data by position (formula[i] to data[i]) using match.fd = TRUE. Returns a named list of survfit objects.

```r
formulas <- list(
  Surv(time, status) ~ sex,
  Surv(time, status) ~ rx
)
datasets <- list(
  subset1 = dplyr::sample_frac(colon, 0.5),
  subset2 = dplyr::sample_frac(colon, 0.5)
)
fit <- surv_fit(formulas, data = datasets, match.fd = TRUE)
# formula[1] applied to datasets[1], formula[2] to datasets[2]
```

--------------------------------

### Summarize Standard Kaplan-Meier Fit

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/api-reference/surv_summary.md

Use this to summarize a standard Kaplan-Meier fit object created with survfit. Ensure the input is a valid survfit object.

```r
fit <- survfit(Surv(time, status) ~ sex, data = lung)
surv_summary(fit)
```

--------------------------------

### Configure Risk Table in R

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/quick-reference.md

Control the display and appearance of the risk table. Options include showing the table, its position, coloring by strata, and its height proportion.

```r
risk.table = TRUE           # Show table
risk.table.pos = "out"      # Outside plot
risk.table.col = "strata"   # Color by groups
risk.table.height = 0.2     # Height proportion
```

--------------------------------

### surv_cutpoint Parameters

Source: https://github.com/kassambara/survminer/blob/master/_autodocs/quick-reference.md

Identify optimal cut-points for survival analysis based on specified variables. Requires time and event columns.

```r
surv_cutpoint(
  data,                          # dataset
  time = "time",                 # time column
  event = "event",               # event column
  variables,                     # variable names
  minprop = 0.1                  # min proportion
)
```