diff --git a/analysis/dataset_definition.py b/analysis/dataset_definition.py
deleted file mode 100644
index 18824f6..0000000
--- a/analysis/dataset_definition.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from ehrql import create_dataset
-from ehrql.tables.tpp import patients, practice_registrations
-
-dataset = create_dataset()
-
-index_date = "2020-03-31"
-
-has_registration = practice_registrations.for_patient_on(
-    index_date
-).exists_for_patient()
-
-dataset.define_population(has_registration)
-
-dataset.sex = patients.sex
diff --git a/analysis/stata.do b/analysis/stata.do
deleted file mode 100644
index 0983157..0000000
--- a/analysis/stata.do
+++ /dev/null
@@ -1 +0,0 @@
-capture noisily import delimited ./output/output/dataset.csv, clear
diff --git a/lib/functions/function_plot_measures.R b/lib/functions/function_plot_measures.R
new file mode 100644
index 0000000..01bec02
--- /dev/null
+++ b/lib/functions/function_plot_measures.R
@@ -0,0 +1,31 @@
+plot_measures <- function(
+    data,
+    title = NULL,
+    x_label = NULL,
+    y_label = NULL) {
+
+  # Create plot
+  plot <- ggplot(
+    data,
+    aes(
+      x = interval_end,
+      y = numerator,
+      color = measure,
+      group = measure
+    )
+  ) +
+    geom_line() +
+    labs(
+      title = title,
+      x = x_label,
+      y = y_label,
+      color = "Condition"
+    ) +
+    # Setting the minimum y-value
+    ylim(y_min, NA) +
+    # Applying the minimal theme
+    theme_minimal()
+
+  # Return plot
+  plot
+}
diff --git a/lib/functions/graph_func.R b/lib/functions/graph_func.R
deleted file mode 100644
index e12a73d..0000000
--- a/lib/functions/graph_func.R
+++ /dev/null
@@ -1,18 +0,0 @@
-plot_pharmacy_first_conditions <- function(data,
-title = "Number of Consultations for each Pharmacy First Clinical Condition per month",
-                                           x_label = "Date",
-                                           y_label = "Number of Consultations",
-                                           y_min = 0) {
-  ggplot(data, 
-  aes(x = interval_end,
-  y = numerator,
-  color = measure,
-  group = measure)) +
-    geom_line() +
-    labs(title = title,
-         x = x_label,
-         y = y_label,
-         color = "Condition") +
-    ylim(y_min, NA) +  # Setting the minimum y-value
-    theme_minimal()    # Applying the minimal theme
-}
diff --git a/lib/functions/visualise_data.R b/lib/functions/sketch.R
similarity index 51%
rename from lib/functions/visualise_data.R
rename to lib/functions/sketch.R
index 2d0b2fe..d4a3725 100644
--- a/lib/functions/visualise_data.R
+++ b/lib/functions/sketch.R
@@ -1,20 +1,23 @@
+# In this file we're trying out some code
 library(tidyverse)
 library(ggplot2)
-library(gridExtra)  # For arranging multiple plots
+library(gridExtra) # For arranging multiple plots
 
 # Load data
 df_measures <- readr::read_csv(
   here::here("output", "report", "conditions_measures.csv")
 )
+
+# Develop plotting function 
 p <- ggplot(df_measures, aes(x = interval_end, y = numerator, color = measure, group = measure)) +
-    geom_line() +
-    labs(title = paste("Number of Consultations for each Pharmacy First Clinical Condition per month"),
-         x = "Date",
-         y = "Number of Consultations",
-         color = "Condition") +
-         ylim(0, NA)
-    theme_minimal()
-  
+  geom_line() +
+  labs(
+    title = paste("Number of Consultations for each Pharmacy First Clinical Condition per month"),
+    x = "Date",
+    y = "Number of Consultations",
+    color = "Condition"
+  ) +
+  ylim(0, NA)
+
 source(here::here("lib", "functions", "graph_func.R"))
 plot1_conditions <- plot_pharmacy_first_conditions(df_measures)
-  
\ No newline at end of file
diff --git a/project.yaml b/project.yaml
index 2cc1508..d7250b9 100644
--- a/project.yaml
+++ b/project.yaml
@@ -5,12 +5,6 @@ expectations:
   population_size: 1000
 
 actions:
-  generate_dataset:
-    run: ehrql:v1 generate-dataset analysis/dataset_definition.py --output output/dataset.csv.gz
-    outputs:
-      highly_sensitive:
-        dataset: output/dataset.csv.gz
-
   generate_pf_measures:
     run: >
       ehrql:v1 generate-measures analysis/report_measures.py