From 1eee5275b8afa5fd1dad62abbfb9bdf137c71193 Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Mon, 9 Dec 2024 16:43:02 -0500
Subject: [PATCH 1/6] Minor styling edits to `seeding.py`

* Added explicit exports,
* Reordered imports,
* Added general structure comments, and
* Refactored all lines to be less than 92 characters.
---
 flepimop/gempyor_pkg/src/gempyor/seeding.py | 44 +++++++++++++++------
 1 file changed, 31 insertions(+), 13 deletions(-)

diff --git a/flepimop/gempyor_pkg/src/gempyor/seeding.py b/flepimop/gempyor_pkg/src/gempyor/seeding.py
index bbfeaa07f..760da66bb 100644
--- a/flepimop/gempyor_pkg/src/gempyor/seeding.py
+++ b/flepimop/gempyor_pkg/src/gempyor/seeding.py
@@ -1,20 +1,27 @@
-from typing import Dict, TYPE_CHECKING
+# Exports
+__all__ = ("Seeding", "SeedingFactory")
 
+
+# Imports
+import logging
+
+import confuse
+import numba as nb
 import numpy as np
 import pandas as pd
-import confuse
-import logging
+
 from .simulation_component import SimulationComponent
 from . import utils
-import numba as nb
-import os
 
+
+# Globals
 logger = logging.getLogger(__name__)
 
 
 ## TODO: ideally here path_prefix should not be used and all files loaded from modinf
 
 
+# Internal functionality
 def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
     if not df["date"].is_monotonic_increasing:
         raise ValueError("The `df` given is not sorted by the 'date' column.")
@@ -40,7 +47,8 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
     for idx, (row_index, row) in enumerate(df.iterrows()):
         if row["subpop"] not in modinf.subpop_struct.subpop_names:
             logging.debug(
-                f"Invalid subpop '{row['subpop']}' in row {row_index + 1} of seeding::lambda_file. Not found in geodata... Skipping"
+                f"Invalid subpop '{row['subpop']}' in row {row_index + 1} of "
+                "seeding::lambda_file. Not found in geodata... Skipping"
             )
         elif (row["date"].date() - modinf.ti).days >= 0:
             if (row["date"].date() - modinf.ti).days < len(nb_seed_perday):
@@ -55,19 +63,24 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
                 }
                 seeding_dict["seeding_sources"][idx] = modinf.compartments.get_comp_idx(
                     source_dict,
-                    error_info=f"(seeding source at idx={idx}, row_index={row_index}, row=>>{row}<<)",
+                    error_info=(
+                        f"(seeding source at idx={idx}, "
+                        f"row_index={row_index}, row=>>{row}<<)"
+                    ),
                 )
                 seeding_dict["seeding_destinations"][idx] = (
                     modinf.compartments.get_comp_idx(
                         destination_dict,
-                        error_info=f"(seeding destination at idx={idx}, row_index={row_index}, row=>>{row}<<)",
+                        error_info=(
+                            f"(seeding destination at idx={idx}, "
+                            f"row_index={row_index}, row=>>{row}<<)"
+                        ),
                     )
                 )
                 seeding_dict["seeding_subpops"][idx] = (
                     modinf.subpop_struct.subpop_names.index(row["subpop"])
                 )
                 seeding_amounts[idx] = amounts[idx]
-                # id_seed+=1
             else:
                 n_seeding_ignored_after += 1
         else:
@@ -75,11 +88,13 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
 
     if n_seeding_ignored_before > 0:
         logging.critical(
-            f"Seeding ignored {n_seeding_ignored_before} rows because they were before the start of the simulation."
+            f"Seeding ignored {n_seeding_ignored_before} rows "
+            "because they were before the start of the simulation."
         )
     if n_seeding_ignored_after > 0:
         logging.critical(
-            f"Seeding ignored {n_seeding_ignored_after} rows because they were after the end of the simulation."
+            f"Seeding ignored {n_seeding_ignored_after} rows "
+            "because they were after the end of the simulation."
         )
 
     day_start_idx = np.zeros(modinf.n_days + 1, dtype=np.int64)
@@ -89,6 +104,7 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
     return seeding_dict, seeding_amounts
 
 
+# Exported functionality
 class Seeding(SimulationComponent):
     def __init__(self, config: confuse.ConfigView, path_prefix: str = "."):
         self.seeding_config = config
@@ -109,7 +125,8 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
             dupes = seeding[seeding.duplicated(["subpop", "date"])].index + 1
             if not dupes.empty:
                 raise ValueError(
-                    f"There are repeating subpop-date in rows '{dupes.tolist()}' of `seeding::lambda_file`."
+                    f"There are repeating subpop-date in rows '{dupes.tolist()}' "
+                    "of `seeding::lambda_file`."
                 )
         elif method == "FolderDraw":
             seeding = pd.read_csv(
@@ -154,7 +171,8 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
             amounts = np.random.poisson(seeding["amount"])
         elif method == "NegativeBinomialDistributed":
             raise ValueError(
-                "Seeding method 'NegativeBinomialDistributed' is not supported by flepiMoP anymore."
+                "Seeding method 'NegativeBinomialDistributed' "
+                "is not supported by flepiMoP anymore."
             )
         elif method == "FolderDraw" or method == "FromFile":
             amounts = seeding["amount"]

From 2d6885615482b9489d9b756053350685489b7181 Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Mon, 9 Dec 2024 17:15:39 -0500
Subject: [PATCH 2/6] Remove `modinf` arg from `_DataFrame2NumbaDict`

Remvoed the `modinf` arg from the `_DataFrame2NumbaDict` internal
utility and replaced it with the individual attributes from the `modinf`
object that are needed.
---
 flepimop/gempyor_pkg/src/gempyor/seeding.py | 69 ++++++++++++++-------
 1 file changed, 45 insertions(+), 24 deletions(-)

diff --git a/flepimop/gempyor_pkg/src/gempyor/seeding.py b/flepimop/gempyor_pkg/src/gempyor/seeding.py
index 760da66bb..4dbaa70b1 100644
--- a/flepimop/gempyor_pkg/src/gempyor/seeding.py
+++ b/flepimop/gempyor_pkg/src/gempyor/seeding.py
@@ -3,14 +3,18 @@
 
 
 # Imports
+from datetime import date
 import logging
 
 import confuse
 import numba as nb
 import numpy as np
+import numpy.typing as npt
 import pandas as pd
 
+from .compartments import Compartments
 from .simulation_component import SimulationComponent
+from .subpopulation_structure import SubpopulationStructure
 from . import utils
 
 
@@ -22,13 +26,18 @@
 
 
 # Internal functionality
-def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
+def _DataFrame2NumbaDict(
+    df: pd.DataFrame,
+    amounts: list[float],
+    compartments: Compartments,
+    subpop_struct: SubpopulationStructure,
+    n_days: int,
+    ti: date,
+) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
     if not df["date"].is_monotonic_increasing:
         raise ValueError("The `df` given is not sorted by the 'date' column.")
 
-    cmp_grp_names = [
-        col for col in modinf.compartments.compartments.columns if col != "name"
-    ]
+    cmp_grp_names = [col for col in compartments.compartments.columns if col != "name"]
     seeding_dict: nb.typed.Dict = nb.typed.Dict.empty(
         key_type=nb.types.unicode_type,
         value_type=nb.types.int64[:],
@@ -38,22 +47,22 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
     seeding_dict["seeding_subpops"] = np.zeros(len(amounts), dtype=np.int64)
     seeding_amounts = np.zeros(len(amounts), dtype=np.float64)
 
-    nb_seed_perday = np.zeros(modinf.n_days, dtype=np.int64)
+    nb_seed_perday = np.zeros(n_days, dtype=np.int64)
 
     n_seeding_ignored_before = 0
     n_seeding_ignored_after = 0
 
     # id_seed = 0
     for idx, (row_index, row) in enumerate(df.iterrows()):
-        if row["subpop"] not in modinf.subpop_struct.subpop_names:
+        if row["subpop"] not in subpop_struct.subpop_names:
             logging.debug(
                 f"Invalid subpop '{row['subpop']}' in row {row_index + 1} of "
                 "seeding::lambda_file. Not found in geodata... Skipping"
             )
-        elif (row["date"].date() - modinf.ti).days >= 0:
-            if (row["date"].date() - modinf.ti).days < len(nb_seed_perday):
-                nb_seed_perday[(row["date"].date() - modinf.ti).days] = (
-                    nb_seed_perday[(row["date"].date() - modinf.ti).days] + 1
+        elif (row["date"].date() - ti).days >= 0:
+            if (row["date"].date() - ti).days < len(nb_seed_perday):
+                nb_seed_perday[(row["date"].date() - ti).days] = (
+                    nb_seed_perday[(row["date"].date() - ti).days] + 1
                 )
                 source_dict = {
                     grp_name: row[f"source_{grp_name}"] for grp_name in cmp_grp_names
@@ -61,24 +70,22 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
                 destination_dict = {
                     grp_name: row[f"destination_{grp_name}"] for grp_name in cmp_grp_names
                 }
-                seeding_dict["seeding_sources"][idx] = modinf.compartments.get_comp_idx(
+                seeding_dict["seeding_sources"][idx] = compartments.get_comp_idx(
                     source_dict,
                     error_info=(
                         f"(seeding source at idx={idx}, "
                         f"row_index={row_index}, row=>>{row}<<)"
                     ),
                 )
-                seeding_dict["seeding_destinations"][idx] = (
-                    modinf.compartments.get_comp_idx(
-                        destination_dict,
-                        error_info=(
-                            f"(seeding destination at idx={idx}, "
-                            f"row_index={row_index}, row=>>{row}<<)"
-                        ),
-                    )
+                seeding_dict["seeding_destinations"][idx] = compartments.get_comp_idx(
+                    destination_dict,
+                    error_info=(
+                        f"(seeding destination at idx={idx}, "
+                        f"row_index={row_index}, row=>>{row}<<)"
+                    ),
                 )
-                seeding_dict["seeding_subpops"][idx] = (
-                    modinf.subpop_struct.subpop_names.index(row["subpop"])
+                seeding_dict["seeding_subpops"][idx] = subpop_struct.subpop_names.index(
+                    row["subpop"]
                 )
                 seeding_amounts[idx] = amounts[idx]
             else:
@@ -97,7 +104,7 @@ def _DataFrame2NumbaDict(df, amounts, modinf) -> nb.typed.Dict:
             "because they were after the end of the simulation."
         )
 
-    day_start_idx = np.zeros(modinf.n_days + 1, dtype=np.int64)
+    day_start_idx = np.zeros(n_days + 1, dtype=np.int64)
     day_start_idx[1:] = np.cumsum(nb_seed_perday)
     seeding_dict["day_start_idx"] = day_start_idx
 
@@ -149,7 +156,14 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
             )
         elif method == "NoSeeding":
             seeding = pd.DataFrame(columns=["date", "subpop"])
-            return _DataFrame2NumbaDict(df=seeding, amounts=[], modinf=modinf)
+            return _DataFrame2NumbaDict(
+                seeding,
+                [],
+                modinf.compartments,
+                modinf.subpop_struct,
+                modinf.n_days,
+                modinf.ti,
+            )
         else:
             raise ValueError(f"Unknown seeding method given, '{method}'.")
 
@@ -177,7 +191,14 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
         elif method == "FolderDraw" or method == "FromFile":
             amounts = seeding["amount"]
 
-        return _DataFrame2NumbaDict(df=seeding, amounts=amounts, modinf=modinf)
+        return _DataFrame2NumbaDict(
+            seeding,
+            amounts,
+            modinf.compartments,
+            modinf.subpop_struct,
+            modinf.n_days,
+            modinf.ti,
+        )
 
     def get_from_file(self, sim_id: int, modinf) -> nb.typed.Dict:
         """only difference with draw seeding is that the sim_id is now sim_id2load"""

From a12150c6127cea452fee05c1ee42957745eceb3d Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Tue, 10 Dec 2024 09:16:21 -0500
Subject: [PATCH 3/6] Add `ModelInfo.get_seeding_data`

Untangled the `Seeding` class from the `ModelInfo` class by adding a
method to `ModelInfo` that interfaces with the `Seeding` class.
---
 flepimop/gempyor_pkg/src/gempyor/inference.py | 11 ++--
 .../gempyor_pkg/src/gempyor/model_info.py     | 56 +++++++++++--------
 flepimop/gempyor_pkg/src/gempyor/seeding.py   | 42 ++++++--------
 flepimop/gempyor_pkg/src/gempyor/seir.py      |  8 +--
 .../gempyor_pkg/tests/seir/interface.ipynb    |  2 +-
 .../gempyor_pkg/tests/seir/test_seeding.py    | 13 ++++-
 flepimop/gempyor_pkg/tests/seir/test_seir.py  | 18 +++---
 7 files changed, 79 insertions(+), 71 deletions(-)

diff --git a/flepimop/gempyor_pkg/src/gempyor/inference.py b/flepimop/gempyor_pkg/src/gempyor/inference.py
index 525ce5cd6..28c7e5f30 100644
--- a/flepimop/gempyor_pkg/src/gempyor/inference.py
+++ b/flepimop/gempyor_pkg/src/gempyor/inference.py
@@ -164,7 +164,7 @@ def get_static_arguments(modinf: model_info.ModelInfo):
     )
 
     initial_conditions = modinf.initial_conditions.get_from_config(sim_id=0, modinf=modinf)
-    seeding_data, seeding_amounts = modinf.seeding.get_from_config(sim_id=0, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(0)
 
     # reduce them
     parameters = modinf.parameters.parameters_reduce(p_draw, npi_seir)
@@ -672,20 +672,17 @@ def one_simulation(
                 self.lastsim_parsed_parameters = parsed_parameters
 
             with Timer("onerun_SEIR.seeding"):
+                seeding_data, seeding_amounts = self.modinf.get_seeding_data(
+                    sim_id2load if load_ID else sim_id2write
+                )
                 if load_ID:
                     initial_conditions = self.modinf.initial_conditions.get_from_file(
                         sim_id2load, modinf=self.modinf
                     )
-                    seeding_data, seeding_amounts = self.modinf.seeding.get_from_file(
-                        sim_id2load, modinf=self.modinf
-                    )
                 else:
                     initial_conditions = self.modinf.initial_conditions.get_from_config(
                         sim_id2write, modinf=self.modinf
                     )
-                    seeding_data, seeding_amounts = self.modinf.seeding.get_from_config(
-                        sim_id2write, modinf=self.modinf
-                    )
                 self.lastsim_seeding_data = seeding_data
                 self.lastsim_seeding_amounts = seeding_amounts
                 self.lastsim_initial_conditions = initial_conditions
diff --git a/flepimop/gempyor_pkg/src/gempyor/model_info.py b/flepimop/gempyor_pkg/src/gempyor/model_info.py
index 2c0f88efa..d5e040f33 100644
--- a/flepimop/gempyor_pkg/src/gempyor/model_info.py
+++ b/flepimop/gempyor_pkg/src/gempyor/model_info.py
@@ -1,5 +1,14 @@
+import datetime
+import logging
+import os
+import pathlib
+
+import confuse
+import numba as nb
+import numpy as np
+import numpy.typing as npt
 import pandas as pd
-import datetime, os, logging, pathlib, confuse
+
 from . import (
     seeding,
     subpopulation_structure,
@@ -296,30 +305,15 @@ def get_output_filename(self, ftype: str, sim_id: int, extension_override: str =
     def get_filename(
         self, ftype: str, sim_id: int, input: bool, extension_override: str = ""
     ):
-        """return a CSP formated filename."""
-
-        if extension_override:  # empty strings are Falsy
-            extension = extension_override
-        else:  # Constructed like this because in some test, extension is not defined
-            extension = self.extension
-
-        if input:
-            run_id = self.in_run_id
-            prefix = self.in_prefix
-        else:
-            run_id = self.out_run_id
-            prefix = self.out_prefix
-
-        fn = self.path_prefix / file_paths.create_file_name(
-            run_id=run_id,
-            prefix=prefix,
-            index=sim_id + self.first_sim_index - 1,
+        return self.path_prefix / file_paths.create_file_name(
+            self.in_run_id if input else self.out_run_id,
+            self.in_prefix if input else self.out_prefix,
+            sim_id + self.first_sim_index - 1,
+            ftype,
+            extension=extension_override if extension_override else self.extension,
             inference_filepath_suffix=self.inference_filepath_suffix,
             inference_filename_prefix=self.inference_filename_prefix,
-            ftype=ftype,
-            extension=extension,
         )
-        return fn
 
     def get_setup_name(self):
         return self.setup_name
@@ -359,3 +353,21 @@ def write_simID(
             df=df,
         )
         return fname
+
+    def get_seeding_data(self, sim_id: int) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
+        return self.seeding.get_from_config(
+            self.compartments,
+            self.subpop_struct,
+            self.n_days,
+            self.ti,
+            self.tf,
+            (
+                None
+                if self.seeding_config is None
+                else self.get_input_filename(
+                    ftype=self.seeding_config["seeding_file_type"].get(),
+                    sim_id=sim_id,
+                    extension_override="csv",
+                )
+            ),
+        )
diff --git a/flepimop/gempyor_pkg/src/gempyor/seeding.py b/flepimop/gempyor_pkg/src/gempyor/seeding.py
index 4dbaa70b1..737e26aab 100644
--- a/flepimop/gempyor_pkg/src/gempyor/seeding.py
+++ b/flepimop/gempyor_pkg/src/gempyor/seeding.py
@@ -5,6 +5,7 @@
 # Imports
 from datetime import date
 import logging
+from typing import Any
 
 import confuse
 import numba as nb
@@ -117,7 +118,15 @@ def __init__(self, config: confuse.ConfigView, path_prefix: str = "."):
         self.seeding_config = config
         self.path_prefix = path_prefix
 
-    def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
+    def get_from_config(
+        self,
+        compartments: Compartments,
+        subpop_struct: SubpopulationStructure,
+        n_days: int,
+        ti: date,
+        tf: date,
+        input_filename: str | None,
+    ) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
         method = "NoSeeding"
         if self.seeding_config is not None and "method" in self.seeding_config.keys():
             method = self.seeding_config["method"].as_str()
@@ -137,12 +146,7 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
                 )
         elif method == "FolderDraw":
             seeding = pd.read_csv(
-                self.path_prefix
-                / modinf.get_input_filename(
-                    ftype=modinf.seeding_config["seeding_file_type"].get(),
-                    sim_id=sim_id,
-                    extension_override="csv",
-                ),
+                self.path_prefix / input_filename,
                 converters={"subpop": lambda x: str(x)},
                 parse_dates=["date"],
                 skipinitialspace=True,
@@ -157,12 +161,7 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
         elif method == "NoSeeding":
             seeding = pd.DataFrame(columns=["date", "subpop"])
             return _DataFrame2NumbaDict(
-                seeding,
-                [],
-                modinf.compartments,
-                modinf.subpop_struct,
-                modinf.n_days,
-                modinf.ti,
+                seeding, [], compartments, subpop_struct, n_days, ti
             )
         else:
             raise ValueError(f"Unknown seeding method given, '{method}'.")
@@ -171,9 +170,7 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
         # print(seeding.shape)
         seeding = seeding.sort_values(by="date", axis="index").reset_index()
         # print(seeding)
-        mask = (seeding["date"].dt.date > modinf.ti) & (
-            seeding["date"].dt.date <= modinf.tf
-        )
+        mask = (seeding["date"].dt.date > ti) & (seeding["date"].dt.date <= tf)
         seeding = seeding.loc[mask].reset_index()
         # print(seeding.shape)
         # print(seeding)
@@ -192,17 +189,14 @@ def get_from_config(self, sim_id: int, modinf) -> nb.typed.Dict:
             amounts = seeding["amount"]
 
         return _DataFrame2NumbaDict(
-            seeding,
-            amounts,
-            modinf.compartments,
-            modinf.subpop_struct,
-            modinf.n_days,
-            modinf.ti,
+            seeding, amounts, compartments, subpop_struct, n_days, ti
         )
 
-    def get_from_file(self, sim_id: int, modinf) -> nb.typed.Dict:
+    def get_from_file(
+        self, *args: Any, **kwargs: Any
+    ) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
         """only difference with draw seeding is that the sim_id is now sim_id2load"""
-        return self.get_from_config(sim_id=sim_id, modinf=modinf)
+        return self.get_from_config(*args, **kwargs)
 
 
 def SeedingFactory(config: confuse.ConfigView, path_prefix: str = "."):
diff --git a/flepimop/gempyor_pkg/src/gempyor/seir.py b/flepimop/gempyor_pkg/src/gempyor/seir.py
index 2492a3825..72a96bbe9 100644
--- a/flepimop/gempyor_pkg/src/gempyor/seir.py
+++ b/flepimop/gempyor_pkg/src/gempyor/seir.py
@@ -277,16 +277,12 @@ def onerun_SEIR(
             initial_conditions = modinf.initial_conditions.get_from_file(
                 sim_id2load, modinf=modinf
             )
-            seeding_data, seeding_amounts = modinf.seeding.get_from_file(
-                sim_id2load, modinf=modinf
-            )
+            seeding_data, seeding_amounts = modinf.get_seeding_data(sim_id2load)
         else:
             initial_conditions = modinf.initial_conditions.get_from_config(
                 sim_id2write, modinf=modinf
             )
-            seeding_data, seeding_amounts = modinf.seeding.get_from_config(
-                sim_id2write, modinf=modinf
-            )
+            seeding_data, seeding_amounts = modinf.get_seeding_data(sim_id2write)
 
     with Timer("onerun_SEIR.parameters"):
         # Draw or load parameters
diff --git a/flepimop/gempyor_pkg/tests/seir/interface.ipynb b/flepimop/gempyor_pkg/tests/seir/interface.ipynb
index 57bbea87d..6c14cce47 100644
--- a/flepimop/gempyor_pkg/tests/seir/interface.ipynb
+++ b/flepimop/gempyor_pkg/tests/seir/interface.ipynb
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "63618148-81db-4fe0-9395-7f21878c1372",
    "metadata": {
     "execution": {
diff --git a/flepimop/gempyor_pkg/tests/seir/test_seeding.py b/flepimop/gempyor_pkg/tests/seir/test_seeding.py
index 52d23e0e4..19bd7ad30 100644
--- a/flepimop/gempyor_pkg/tests/seir/test_seeding.py
+++ b/flepimop/gempyor_pkg/tests/seir/test_seeding.py
@@ -39,5 +39,16 @@ def test_Seeding_draw_success(self):
         sic = seeding.SeedingFactory(config=s.seeding_config)
         s.seeding_config["method"] = "NoSeeding"
 
-        seeding_result = sic.get_from_config(sim_id=100, modinf=s)
+        seeding_result = sic.get_from_config(
+            s.compartments,
+            s.subpop_struct,
+            s.n_days,
+            s.ti,
+            s.tf,
+            s.get_input_filename(
+                ftype=s.seeding_config["seeding_file_type"].get(),
+                sim_id=0,
+                extension_override="csv",
+            ),
+        )
         print(seeding_result)
diff --git a/flepimop/gempyor_pkg/tests/seir/test_seir.py b/flepimop/gempyor_pkg/tests/seir/test_seir.py
index 16bbd390c..8fc7ef024 100644
--- a/flepimop/gempyor_pkg/tests/seir/test_seir.py
+++ b/flepimop/gempyor_pkg/tests/seir/test_seir.py
@@ -73,7 +73,7 @@ def test_constant_population_legacy_integration():
     )
     integration_method = "legacy"
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -152,9 +152,7 @@ def test_constant_population_rk4jit_integration_fail():
         )
         modinf.seir_config["integration"]["method"] = "rk4.jit"
 
-        seeding_data, seeding_amounts = modinf.seeding.get_from_file(
-            sim_id=100, modinf=modinf
-        )
+        seeding_data, seeding_amounts = modinf.get_seeding_data(100)
         initial_conditions = modinf.initial_conditions.get_from_config(
             sim_id=100, modinf=modinf
         )
@@ -231,7 +229,7 @@ def test_constant_population_rk4jit_integration():
     # s.integration_method = "rk4.jit"
     assert modinf.seir_config["integration"]["method"].get() == "rk4"
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -306,7 +304,7 @@ def test_steps_SEIR_nb_simple_spread_with_txt_matrices():
         out_prefix=prefix,
     )
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -415,7 +413,7 @@ def test_steps_SEIR_nb_simple_spread_with_csv_matrices():
         out_prefix=prefix,
     )
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -492,7 +490,7 @@ def test_steps_SEIR_no_spread():
         out_prefix=prefix,
     )
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -769,7 +767,7 @@ def test_parallel_compartments_with_vacc():
         out_prefix=prefix,
     )
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )
@@ -863,7 +861,7 @@ def test_parallel_compartments_no_vacc():
         out_prefix=prefix,
     )
 
-    seeding_data, seeding_amounts = modinf.seeding.get_from_file(sim_id=100, modinf=modinf)
+    seeding_data, seeding_amounts = modinf.get_seeding_data(100)
     initial_conditions = modinf.initial_conditions.get_from_config(
         sim_id=100, modinf=modinf
     )

From 8ba5f0c8dc5c0415e054f77bbf6e644111220794 Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Tue, 10 Dec 2024 09:23:04 -0500
Subject: [PATCH 4/6] Update other references to `Seeding.get_from_*`

Updated remaining references in inactive code, notebooks and the
`gempyor.dev` module.
---
 flepimop/gempyor_pkg/docs/integration_benchmark.ipynb | 4 ++--
 flepimop/gempyor_pkg/docs/integration_doc.ipynb       | 4 ++--
 flepimop/gempyor_pkg/docs/interface.ipynb             | 9 ++-------
 flepimop/gempyor_pkg/src/gempyor/dev/dev_seir.py      | 2 +-
 flepimop/gempyor_pkg/tests/seir/interface.ipynb       | 7 +------
 5 files changed, 8 insertions(+), 18 deletions(-)

diff --git a/flepimop/gempyor_pkg/docs/integration_benchmark.ipynb b/flepimop/gempyor_pkg/docs/integration_benchmark.ipynb
index ce2880787..01513fb98 100644
--- a/flepimop/gempyor_pkg/docs/integration_benchmark.ipynb
+++ b/flepimop/gempyor_pkg/docs/integration_benchmark.ipynb
@@ -410,7 +410,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "07bfd952-5c42-4704-81cc-5de0c917c0ab",
    "metadata": {
     "execution": {
@@ -450,7 +450,7 @@
     "\n",
     "with Timer(\"onerun_SEIR.seeding\"):\n",
     "    initial_conditions = s.initial_conditions.get_from_config(sim_id, modinf=s)\n",
-    "    seeding_data, seeding_amounts = s.seeding.get_from_config(sim_id, modinf=s)\n",
+    "    seeding_data, seeding_amounts = s.get_seeding_data(sim_id)\n",
     "\n",
     "mobility_subpop_indices = s.mobility.indices\n",
     "mobility_data_indices = s.mobility.indptr\n",
diff --git a/flepimop/gempyor_pkg/docs/integration_doc.ipynb b/flepimop/gempyor_pkg/docs/integration_doc.ipynb
index cfbf2e5d9..763ae9d37 100644
--- a/flepimop/gempyor_pkg/docs/integration_doc.ipynb
+++ b/flepimop/gempyor_pkg/docs/integration_doc.ipynb
@@ -70,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "96230106-73e3-4681-b562-6a7269513375",
    "metadata": {
     "execution": {
@@ -109,7 +109,7 @@
     "\n",
     "\n",
     "initial_conditions = gempyor_inference.s.initial_conditions.get_from_config(sim_id2write, modinf=gempyor_inference.s)\n",
-    "seeding_data, seeding_amounts = gempyor_inference.s.seeding.get_from_config(sim_id2write, modinf=gempyor_inference.s)\n",
+    "seeding_data, seeding_amounts = gempyor_inference.s.get_seeding_data(sim_id2write)\n",
     "\n",
     "\n",
     "p_draw = gempyor_inference.s.parameters.parameters_quick_draw(\n",
diff --git a/flepimop/gempyor_pkg/docs/interface.ipynb b/flepimop/gempyor_pkg/docs/interface.ipynb
index 1b0de2e43..64c0850dd 100644
--- a/flepimop/gempyor_pkg/docs/interface.ipynb
+++ b/flepimop/gempyor_pkg/docs/interface.ipynb
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "63618148-81db-4fe0-9395-7f21878c1372",
    "metadata": {
     "execution": {
@@ -254,20 +254,15 @@
     "\n",
     "### Run every time:\n",
     "with Timer(\"onerun_SEIR.seeding\"):\n",
+    "    seeding_data, seeding_amounts = gempyor_inference.s.get_seeding_data(sim_id2load if load_ID else sim_id2write)\n",
     "    if load_ID:\n",
     "        initial_conditions = gempyor_inference.s.initial_conditions.get_from_file(\n",
     "            sim_id2load, modinf=gempyor_inference.s\n",
     "        )\n",
-    "        seeding_data, seeding_amounts = gempyor_inference.s.seeding.get_from_file(\n",
-    "            sim_id2load, modinf=gempyor_inference.s\n",
-    "        )\n",
     "    else:\n",
     "        initial_conditions = gempyor_inference.s.initial_conditions.get_from_config(\n",
     "            sim_id2write, modinf=gempyor_inference.s\n",
     "        )\n",
-    "        seeding_data, seeding_amounts = gempyor_inference.s.seeding.get_from_config(\n",
-    "            sim_id2write, modinf=gempyor_inference.s\n",
-    "        )\n",
     "\n",
     "with Timer(\"SEIR.parameters\"):\n",
     "    # Draw or load parameters\n",
diff --git a/flepimop/gempyor_pkg/src/gempyor/dev/dev_seir.py b/flepimop/gempyor_pkg/src/gempyor/dev/dev_seir.py
index 09745f44a..9a2219471 100644
--- a/flepimop/gempyor_pkg/src/gempyor/dev/dev_seir.py
+++ b/flepimop/gempyor_pkg/src/gempyor/dev/dev_seir.py
@@ -35,7 +35,7 @@
     out_prefix=prefix,
 )
 
-seeding_data = modinf.seeding.get_from_config(sim_id=100, modinf=modinf)
+seeding_data = modinf.get_seeding_data(100)
 initial_conditions = modinf.initial_conditions.get_from_config(sim_id=100, modinf=modinf)
 
 mobility_subpop_indices = modinf.mobility.indices
diff --git a/flepimop/gempyor_pkg/tests/seir/interface.ipynb b/flepimop/gempyor_pkg/tests/seir/interface.ipynb
index 6c14cce47..b331bd9e7 100644
--- a/flepimop/gempyor_pkg/tests/seir/interface.ipynb
+++ b/flepimop/gempyor_pkg/tests/seir/interface.ipynb
@@ -250,16 +250,11 @@
     "\n",
     "### Run every time:\n",
     "with Timer(\"onerun_SEIR.seeding\"):\n",
+    "    seeding_data, seeding_amounts = gempyor_inference.s.get_seeding_data(sim_id2load if load_ID else sim_id2write)\n",
     "    if load_ID:\n",
     "        initial_conditions = gempyor_inference.s.initial_conditions.get_from_file(sim_id2load, modinf=gempyor_inference.s)\n",
-    "        seeding_data, seeding_amounts = gempyor_inference.s.seeding.get_from_file(\n",
-    "            sim_id2load, modinf=gempyor_inference.s\n",
-    "        )\n",
     "    else:\n",
     "        initial_conditions = gempyor_inference.s.initial_conditions.get_from_config(sim_id2write, modinf=gempyor_inference.s)\n",
-    "        seeding_data, seeding_amounts = gempyor_inference.s.seeding.get_from_config(\n",
-    "            sim_id2write, modinf=gempyor_inference.s\n",
-    "        )\n",
     "\n",
     "with Timer(\"SEIR.parameters\"):\n",
     "    # Draw or load parameters\n",

From e31cac881c85504612c23a69e098a0d86dc8cb23 Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Tue, 10 Dec 2024 10:23:06 -0500
Subject: [PATCH 5/6] Add documentation to the `Seeding` class

---
 flepimop/gempyor_pkg/src/gempyor/seeding.py | 78 +++++++++++++++++----
 1 file changed, 66 insertions(+), 12 deletions(-)

diff --git a/flepimop/gempyor_pkg/src/gempyor/seeding.py b/flepimop/gempyor_pkg/src/gempyor/seeding.py
index 737e26aab..a06763b4a 100644
--- a/flepimop/gempyor_pkg/src/gempyor/seeding.py
+++ b/flepimop/gempyor_pkg/src/gempyor/seeding.py
@@ -6,6 +6,7 @@
 from datetime import date
 import logging
 from typing import Any
+import warnings
 
 import confuse
 import numba as nb
@@ -23,9 +24,6 @@
 logger = logging.getLogger(__name__)
 
 
-## TODO: ideally here path_prefix should not be used and all files loaded from modinf
-
-
 # Internal functionality
 def _DataFrame2NumbaDict(
     df: pd.DataFrame,
@@ -114,7 +112,22 @@ def _DataFrame2NumbaDict(
 
 # Exported functionality
 class Seeding(SimulationComponent):
+    """
+    Class to handle the seeding of the simulation.
+
+    Attributes:
+        seeding_config: The configuration for the seeding.
+        path_prefix: The path prefix to use when reading files.
+    """
+
     def __init__(self, config: confuse.ConfigView, path_prefix: str = "."):
+        """
+        Initialize a seeding instance.
+
+        Args:
+            config: The configuration for the seeding.
+            path_prefix: The path prefix to use when reading files.
+        """
         self.seeding_config = config
         self.path_prefix = path_prefix
 
@@ -127,6 +140,27 @@ def get_from_config(
         tf: date,
         input_filename: str | None,
     ) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
+        """
+        Get seeding data from the configuration.
+
+        Args:
+            compartments: The compartments for the simulation.
+            subpop_struct: The subpopulation structure for the simulation.
+            n_days: The number of days in the simulation.
+            ti: The start date of the simulation.
+            tf: The end date of the simulation.
+            input_filename: The input filename to use for seeding data. Only used if
+                the seeding method is 'FolderDraw'.
+
+        Returns:
+            A tuple containing the seeding data as a Numba dictionary and the seeding
+            amounts as a Numpy array. The seeding data is a dictionary with the
+            following keys:
+                - "seeding_sources": The source compartments for the seeding.
+                - "seeding_destinations": The destination compartments for the seeding.
+                - "seeding_subpops": The subpopulations for the seeding.
+                - "day_start_idx": The start index for each day in the seeding data.
+        """
         method = "NoSeeding"
         if self.seeding_config is not None and "method" in self.seeding_config.keys():
             method = self.seeding_config["method"].as_str()
@@ -166,16 +200,10 @@ def get_from_config(
         else:
             raise ValueError(f"Unknown seeding method given, '{method}'.")
 
-        # Sorting by date is very important here for the seeding format necessary !!!!
-        # print(seeding.shape)
+        # Sorting by date is important for the seeding format
         seeding = seeding.sort_values(by="date", axis="index").reset_index()
-        # print(seeding)
         mask = (seeding["date"].dt.date > ti) & (seeding["date"].dt.date <= tf)
         seeding = seeding.loc[mask].reset_index()
-        # print(seeding.shape)
-        # print(seeding)
-
-        # TODO: print.
 
         amounts = np.zeros(len(seeding))
         if method == "PoissonDistributed":
@@ -195,11 +223,37 @@ def get_from_config(
     def get_from_file(
         self, *args: Any, **kwargs: Any
     ) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
-        """only difference with draw seeding is that the sim_id is now sim_id2load"""
+        """
+        This method is deprecated. Use `get_from_config` instead.
+
+        Args:
+            *args: Positional arguments to pass to `get_from_config`.
+            **kwargs: Keyword arguments to pass to `get_from_config`.
+
+        Returns:
+            The result of `get_from_config`.
+        """
+        warnings.warn(
+            "The 'get_from_file' method is deprecated. Use 'get_from_config' instead.",
+            DeprecationWarning,
+        )
         return self.get_from_config(*args, **kwargs)
 
 
-def SeedingFactory(config: confuse.ConfigView, path_prefix: str = "."):
+def SeedingFactory(config: confuse.ConfigView, path_prefix: str = ".") -> Seeding:
+    """
+    Create a Seeding instance based on the given configuration.
+
+    This function will use the given configuration to either lookup a plugin class for
+    the seeding instance or fallback to the default Seeding class.
+
+    Args:
+        config: The configuration for the seeding.
+        path_prefix: The path prefix to use when reading files.
+
+    Returns:
+        A Seeding instance.
+    """
     if config is not None and "method" in config.keys():
         if config["method"].as_str() == "plugin":
             klass = utils.search_and_import_plugins_class(

From 692865fa2659b94dfb072634b555b7369e22775f Mon Sep 17 00:00:00 2001
From: Timothy Willard <9395586+TimothyWillard@users.noreply.github.com>
Date: Tue, 10 Dec 2024 10:24:36 -0500
Subject: [PATCH 6/6] Document `ModelInfo.get_seeding_data`

---
 flepimop/gempyor_pkg/src/gempyor/model_info.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/flepimop/gempyor_pkg/src/gempyor/model_info.py b/flepimop/gempyor_pkg/src/gempyor/model_info.py
index d5e040f33..459598ab6 100644
--- a/flepimop/gempyor_pkg/src/gempyor/model_info.py
+++ b/flepimop/gempyor_pkg/src/gempyor/model_info.py
@@ -355,6 +355,18 @@ def write_simID(
         return fname
 
     def get_seeding_data(self, sim_id: int) -> tuple[nb.typed.Dict, npt.NDArray[np.number]]:
+        """
+        Pull the seeding data for the info represented by this model info instance.
+
+        Args:
+            sim_id: The simulation ID to pull seeding data for.
+
+        Returns:
+            A tuple containing the seeding data dictionary and the seeding data array.
+
+        See Also:
+            `gempyor.seeding.Seeding.get_from_config`
+        """
         return self.seeding.get_from_config(
             self.compartments,
             self.subpop_struct,