diff --git a/finetune.py b/finetune.py
index d986903..079de6d 100644
--- a/finetune.py
+++ b/finetune.py
@@ -17,17 +17,17 @@
 from sklearn.model_selection import train_test_split
 from torch.utils.data import DataLoader
 
-from lib.data import FinetuneDataset
-from lib.tokenizer import ConceptTokenizer
-from lib.utils import (
+from odyssey.data.dataset import FinetuneDataset
+from odyssey.data.tokenizer import ConceptTokenizer
+from odyssey.models.cehr_big_bird.model import BigBirdFinetune, BigBirdPretrain
+from odyssey.models.cehr_bert.model import BertFinetune, BertPretrain
+from odyssey.models.utils import (
     get_latest_checkpoint,
     get_run_id,
     load_config,
     load_finetune_data,
     seed_everything,
 )
-from models.big_bird_cehr.model import BigBirdFinetune, BigBirdPretrain
-from models.cehr_bert.model import BertFinetune, BertPretrain
 
 
 def main(
diff --git a/models/__init__.py b/models/__init__.py
deleted file mode 100644
index 923ee6a..0000000
--- a/models/__init__.py
+++ /dev/null
@@ -1,6 +0,0 @@
-"""
-models.py.
-
-Includes different model implementation such as XGBoost, Bi-LSTM,
-CEHR-BERT, and BigBird on the MIMIC-IV FHIR dataset.
-"""
diff --git a/odyssey/__init__.py b/odyssey/__init__.py
new file mode 100644
index 0000000..c94d3eb
--- /dev/null
+++ b/odyssey/__init__.py
@@ -0,0 +1 @@
+"""Odyssey package."""
diff --git a/odyssey/data/__init__.py b/odyssey/data/__init__.py
new file mode 100644
index 0000000..6ca91a7
--- /dev/null
+++ b/odyssey/data/__init__.py
@@ -0,0 +1 @@
+"""Data sub-package."""
diff --git a/data/bigbird_data/DataChecker.ipynb b/odyssey/data/bigbird_data/DataChecker.ipynb
similarity index 100%
rename from data/bigbird_data/DataChecker.ipynb
rename to odyssey/data/bigbird_data/DataChecker.ipynb
diff --git a/lib/data.py b/odyssey/data/dataset.py
similarity index 99%
rename from lib/data.py
rename to odyssey/data/dataset.py
index 8a6dbed..d46a90a 100644
--- a/lib/data.py
+++ b/odyssey/data/dataset.py
@@ -6,7 +6,7 @@
 import torch
 from torch.utils.data import Dataset
 
-from lib.tokenizer import ConceptTokenizer
+from odyssey.data.tokenizer import ConceptTokenizer
 
 
 class PretrainDataset(Dataset):
diff --git a/odyssey/data/mimiciv/__init__.py b/odyssey/data/mimiciv/__init__.py
new file mode 100644
index 0000000..a8885a4
--- /dev/null
+++ b/odyssey/data/mimiciv/__init__.py
@@ -0,0 +1 @@
+"""MIMICIV specific data processing module."""
diff --git a/data/collect.py b/odyssey/data/mimiciv/collect.py
similarity index 89%
rename from data/collect.py
rename to odyssey/data/mimiciv/collect.py
index 61b2f15..ce5d6a2 100644
--- a/data/collect.py
+++ b/odyssey/data/mimiciv/collect.py
@@ -1,6 +1,7 @@
 """Collect data from the FHIR database and save to csv files."""
 
 import json
+import logging
 import os
 from ast import literal_eval
 from typing import Any, Dict, List, Optional
@@ -17,6 +18,13 @@
 from sqlalchemy import MetaData, Table, create_engine, select
 from tqdm import tqdm
 
+from odyssey.utils.log import setup_logging
+
+
+# Logging.
+LOGGER = logging.getLogger(__name__)
+setup_logging(print_level="INFO", logger=LOGGER)
+
 
 PATIENT = "patient"
 ENCOUNTER = "encounter"
@@ -212,7 +220,8 @@ def get_patient_data(self) -> None:
         )
         buffer = []
         results = self.execute_query(DATA_COLLECTION_CONFIG[PATIENT]["table_name"])
-        for p in tqdm(results, desc="Processing patients", unit=PATIENT):
+        LOGGER.info("Fetching patient data ...")
+        for p in tqdm(results, desc="Processing patients", unit="patients"):
             patient = Patient(p)
             patient_data = {
                 "patient_id": patient.id,
@@ -239,7 +248,7 @@ def get_patient_data(self) -> None:
     def get_encounter_data(self) -> None:
         """Get encounter data from the database and save to a csv file."""
         try:
-            patients = pd.read_csv(self.csv_dir + "/patients.csv")
+            patients = pd.read_csv(os.path.join(self.csv_dir, "patients.csv"))
         except FileNotFoundError:
             print("Patients file not found. Please run get_patient_data() first.")
             return
@@ -249,10 +258,11 @@ def get_encounter_data(self) -> None:
         )
         buffer = []
         outpatient_ids = []
+        LOGGER.info("Fetching encounter data ...")
         for _, patient_id in tqdm(
             patients["patient_id"].items(),
             desc="Processing patients",
-            unit="patient",
+            unit="patients",
         ):
             results = self.execute_query(
                 DATA_COLLECTION_CONFIG[ENCOUNTER]["table_name"],
@@ -295,12 +305,12 @@ def get_encounter_data(self) -> None:
             flush=True,
         )
         patients = patients[~patients["patient_id"].isin(outpatient_ids)]
-        patients.to_csv(self.csv_dir + "/inpatient.csv", index=False)
+        patients.to_csv(os.path.join(self.csv_dir, "inpatient.csv"), index=False)
 
     def get_procedure_data(self) -> None:
         """Get procedure data from the database and save to a csv file."""
         try:
-            patients = pd.read_csv(self.csv_dir + "/inpatient.csv")
+            patients = pd.read_csv(os.path.join(self.csv_dir, "inpatient.csv"))
         except FileNotFoundError:
             print(
                 "Encounters (inpatient) file not found. Please run get_encounter_data() first.",
@@ -312,10 +322,11 @@ def get_procedure_data(self) -> None:
         )
         procedure_vocab = set()
         buffer = []
+        LOGGER.info("Fetching procedure data ...")
         for _, patient_id in tqdm(
             patients["patient_id"].items(),
             desc="Processing patients",
-            unit="patient",
+            unit="patients",
         ):
             results = self.execute_query("procedure", patient_id)
             proc_codes = []
@@ -358,13 +369,13 @@ def get_procedure_data(self) -> None:
             save_path,
             flush=True,
         )
-        with open(self.vocab_dir + "/procedure_vocab.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "procedure_vocab.json"), "w") as f:
             json.dump(list(procedure_vocab), f)
 
     def get_medication_data(self) -> None:
         """Get medication data from the database and save to a csv file."""
         try:
-            patients = pd.read_csv(self.csv_dir + "/inpatient.csv")
+            patients = pd.read_csv(os.path.join(self.csv_dir, "inpatient.csv"))
         except FileNotFoundError:
             print("Patients file not found. Please run get_encounter_data() first.")
             return
@@ -377,11 +388,12 @@ def get_medication_data(self) -> None:
         save_path = os.path.join(self.csv_dir, "med_requests.csv")
         med_vocab = set()
         buffer = []
+        LOGGER.info("Fetching medication data ...")
         with self.engine.connect() as connection:
             for _, patient_id in tqdm(
                 patients["patient_id"].items(),
                 desc="Processing patients",
-                unit="patient",
+                unit="patients",
             ):
                 results = self.execute_query(
                     DATA_COLLECTION_CONFIG[MEDICATION]["table_name"],
@@ -437,13 +449,13 @@ def get_medication_data(self) -> None:
             save_path,
             flush=True,
         )
-        with open(self.vocab_dir + "/med_vocab.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "med_vocab.json"), "w") as f:
             json.dump(list(med_vocab), f)
 
     def get_lab_data(self) -> None:
         """Get lab data from the database and save to a csv file."""
         try:
-            patients = pd.read_csv(self.csv_dir + "/inpatient.csv")
+            patients = pd.read_csv(os.path.join(self.csv_dir, "inpatient.csv"))
         except FileNotFoundError:
             print("Patients file not found. Please run get_encounter_data() first.")
             return
@@ -451,10 +463,11 @@ def get_lab_data(self) -> None:
         lab_vocab = set()
         all_units = {}
         buffer = []
+        LOGGER.info("Fetching lab data ...")
         for _, patient_id in tqdm(
             patients["patient_id"].items(),
             desc="Processing patients",
-            unit="patient",
+            unit="patients",
         ):
             results = self.execute_query(
                 DATA_COLLECTION_CONFIG[LAB]["table_name"],
@@ -506,10 +519,10 @@ def get_lab_data(self) -> None:
             save_path,
             flush=True,
         )
-        with open(self.vocab_dir + "/lab_vocab.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "lab_vocab.json"), "w") as f:
             json.dump(list(lab_vocab), f)
         all_units = {k: list(v) for k, v in all_units.items()}
-        with open(self.vocab_dir + "/lab_units.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "lab_units.json"), "w") as f:
             json.dump(all_units, f)
 
     def filter_lab_data(
@@ -517,20 +530,21 @@ def filter_lab_data(
     ) -> None:
         """Filter out lab codes that have more than one units."""
         try:
-            labs = pd.read_csv(self.csv_dir + "/labs.csv")
-            with open(self.vocab_dir + "/lab_vocab.json", "r") as f:
+            labs = pd.read_csv(os.path.join(self.csv_dir, "labs.csv"))
+            with open(os.path.join(self.vocab_dir, "lab_vocab.json"), "r") as f:
                 lab_vocab = json.load(f)
-            with open(self.vocab_dir + "/lab_units.json", "r") as f:
+            with open(os.path.join(self.vocab_dir, "lab_units.json"), "r") as f:
                 lab_units = json.load(f)
         except FileNotFoundError:
             print("Labs file not found. Please run get_lab_data() first.")
             return
+        LOGGER.info("Filtering lab data ...")
         for code, units in lab_units.items():
             if len(units) > 1:
                 lab_vocab.remove(code)
         labs = labs.apply(lambda x: filter_lab_codes(x, lab_vocab), axis=1)
-        labs.to_csv(self.csv_dir + "/filtered_labs.csv", index=False)
-        with open(self.vocab_dir + "/lab_vocab.json", "w") as f:
+        labs.to_csv(os.path.join(self.csv_dir, "filtered_labs.csv"), index=False)
+        with open(os.path.join(self.vocab_dir, "lab_vocab.json"), "w") as f:
             json.dump(list(lab_vocab), f)
 
     def process_lab_values(self, num_bins: int = 5) -> None:
@@ -540,10 +554,11 @@ def process_lab_values(self, num_bins: int = 5) -> None:
         ----------
         num_bins : int, optional
             number of bins, by default 5
+
         """
         try:
-            labs = pd.read_csv(self.csv_dir + "/filtered_labs.csv")
-            with open(self.vocab_dir + "/lab_vocab.json", "r") as f:
+            labs = pd.read_csv(os.path.join(self.csv_dir, "filtered_labs.csv"))
+            with open(os.path.join(self.vocab_dir, "lab_vocab.json"), "r") as f:
                 lab_vocab = json.load(f)
         except FileNotFoundError:
             print("Labs file not found. Please run get_lab_data() first.")
@@ -565,6 +580,7 @@ def assign_to_quantile_bins(row: pd.Series) -> pd.Series:
             row["binned_values"] = binned_values
             return row
 
+        LOGGER.info("Processing lab values ...")
         labs = labs.apply(apply_eval, axis=1)
         quantile_bins = {}
         for code in lab_vocab:
@@ -582,19 +598,19 @@ def assign_to_quantile_bins(row: pd.Series) -> pd.Series:
             ).categories
 
         labs = labs.apply(assign_to_quantile_bins, axis=1)
-        labs.to_csv(self.csv_dir + "/processed_labs.csv", index=False)
+        labs.to_csv(os.path.join(self.csv_dir, "processed_labs.csv"), index=False)
 
         lab_vocab_binned = []
         lab_vocab_binned.extend(
             [f"{code}_{i}" for code in lab_vocab for i in range(num_bins)],
         )
-        with open(self.vocab_dir + "/lab_vocab.json", "w") as f:
+        with open(os.path.join(self.vocab_dir + "lab_vocab.json"), "w") as f:
             json.dump(lab_vocab_binned, f)
 
     def get_condition_data(self) -> None:
         """Get condition data from the database and save to a csv file."""
         try:
-            patients = pd.read_csv(self.csv_dir + "/inpatient.csv")
+            patients = pd.read_csv(os.path.join(self.csv_dir, "inpatient.csv"))
         except FileNotFoundError:
             print("Patients file not found. Please run get_encounter_data() first.")
             return
@@ -603,10 +619,11 @@ def get_condition_data(self) -> None:
         condition_counts = {}
         condition_systems = {}
         buffer = []
+        LOGGER.info("Fetching condition data ...")
         for _, patient_id in tqdm(
             patients["patient_id"].items(),
             desc="Processing patients",
-            unit="patient",
+            unit="patients",
         ):
             patient_conditions_counted = set()
             results = self.execute_query(
@@ -650,7 +667,7 @@ def get_condition_data(self) -> None:
             save_path,
             flush=True,
         )
-        with open(self.vocab_dir + "/condition_vocab.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "condition_vocab.json"), "w") as f:
             json.dump(list(condition_vocab), f)
         sorted_conditions = sorted(
             condition_counts.items(),
@@ -658,18 +675,18 @@ def get_condition_data(self) -> None:
             reverse=True,
         )
         sorted_dict = dict(sorted_conditions)
-        with open(self.vocab_dir + "/condition_counts.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "condition_counts.json"), "w") as f:
             json.dump(sorted_dict, f)
-
-        with open(self.vocab_dir + "/condition_systems.json", "w") as f:
+        with open(os.path.join(self.vocab_dir, "condition_systems.json"), "w") as f:
             json.dump(condition_systems, f)
 
     def group_conditions(self) -> None:
         """Group conditions into categories."""
-        with open(self.vocab_dir + "/condition_counts.json", "r") as file:
+        with open(os.path.join(self.vocab_dir, "condition_counts.json"), "r") as file:
             data = json.load(file)
-        with open(self.vocab_dir + "/condition_systems.json", "r") as file:
+        with open(os.path.join(self.vocab_dir, "condition_systems.json"), "r") as file:
             systems = json.load(file)
+        LOGGER.info("Grouping conditions ...")
         grouped_data = {}
         for code, info in data.items():
             prefix = code[:3]
@@ -686,7 +703,10 @@ def group_conditions(self) -> None:
                 reverse=True,
             ),
         )
-        with open(self.vocab_dir + "condition_categories.json", "w") as file:
+        with open(
+            os.path.join(self.vocab_dir, "condition_categories.json"),
+            "w",
+        ) as file:
             json.dump(sorted_grouped_data, file, indent=4)
 
 
diff --git a/data/sequence.py b/odyssey/data/sequence.py
similarity index 83%
rename from data/sequence.py
rename to odyssey/data/sequence.py
index 32cb814..e11aa8d 100644
--- a/data/sequence.py
+++ b/odyssey/data/sequence.py
@@ -1,14 +1,22 @@
 """Create patient sequences from the events dataframes."""
 
-import ast
 import json
+import logging
 import os
+import time
+from ast import literal_eval
 from datetime import datetime
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd
 from dateutil import parser
+from odyssey.utils.log import setup_logging
+
+
+# Logging.
+LOGGER = logging.getLogger(__name__)
+setup_logging(print_level="INFO", logger=LOGGER)
 
 
 class SequenceGenerator:
@@ -160,13 +168,13 @@ def _get_valid_encounters(
         -------
         pd.DataFrame
         """
-        proc_encounters = set(eval(procedure_row["encounter_ids"]))
-        med_encounters = set(eval(medication_row["encounter_ids"]))
-        lab_encounters = set(eval(lab_row["encounter_ids"]))
+        proc_encounters = set(literal_eval(procedure_row["encounter_ids"]))
+        med_encounters = set(literal_eval(medication_row["encounter_ids"]))
+        lab_encounters = set(literal_eval(lab_row["encounter_ids"]))
         valid_encounters = proc_encounters.union(med_encounters, lab_encounters)
 
         for c_name in ["encounter_ids", "starts", "ends"]:
-            encounter_row[c_name] = eval(encounter_row[c_name])
+            encounter_row[c_name] = literal_eval(encounter_row[c_name])
         encounter_ids = encounter_row["encounter_ids"]
         encounter_starts = encounter_row["starts"]
         encounter_ends = encounter_row["ends"]
@@ -348,13 +356,13 @@ def _edit_datetimes(
                 "lab_values",
                 "lab_units",
             ]:
-                row[name] = eval(row[name])
+                row[name] = literal_eval(row[name])
         elif concept_name == "med":
             for name in ["encounter_ids", "med_dates", "med_codes"]:
-                row[name] = eval(row[name])
+                row[name] = literal_eval(row[name])
         elif concept_name == "proc":
             for name in ["encounter_ids", "proc_dates", "proc_codes"]:
-                row[name] = eval(row[name])
+                row[name] = literal_eval(row[name])
         if row["length"] == 0:
             return row
         dates = []
@@ -743,7 +751,7 @@ def _get_mortality_label(
         death_code = death_date - last_code_date
 
         if death_code.days < 0:
-            print("after death events", row["patient_id"])
+            LOGGER.info(f"After death events {row['patient_id']}")
             self.after_death_events.append(row["patient_id"])
 
         row["deceased"] = 1
@@ -978,163 +986,153 @@ def create_patient_sequence(
             f"{self.data_dir}/conditions.csv",
         ]
         rounds = 0
+        more_chunks = True
         readers = [pd.read_csv(path, chunksize=chunksize) for path in file_paths]
-        while True:
+        while more_chunks:
             try:
-                # read dataframes
-                if rounds <= 8:
-                    dataframes = [
-                        next(reader).reset_index(drop=True) for reader in readers
-                    ]
-                    rounds += 1
-                    continue
                 dataframes = [next(reader).reset_index(drop=True) for reader in readers]
-                patients, encounters, procedures, medications, labs, conditions = (
-                    dataframes
-                )
-
-                ## process encounters
-                # keep valid encounters
-                encounters = encounters.apply(
-                    lambda row: self._get_valid_encounters(
-                        row,
-                        procedures.iloc[row.name],
-                        medications.iloc[row.name],
-                        labs.iloc[row.name],
-                    ),
-                    axis=1,
-                )
-                # keep valid rows with at least one encounter
-                valid_indices = encounters[encounters["length"] > 0].index
-                encounters = encounters.loc[valid_indices].reset_index(drop=True)
-                patients = patients.loc[valid_indices].reset_index(drop=True)
-                # sort encounters by start time
-                encounters = encounters.apply(self._sort_encounters, axis=1)
-                # get ages of the patients at the time of the encounters
-                encounters = encounters.apply(
-                    lambda row: self._get_encounters_age(row, patients.iloc[row.name]),
-                    axis=1,
-                )
-                # get time of the encounters in weeks with respect to a reference time
-                encounters = encounters.apply(
-                    lambda row: self._get_encounters_time(row),
-                    axis=1,
-                )
-                # calculate intervals between encounters
-                encounters = encounters.apply(self._calculate_intervals, axis=1)
-                ## process events
-                # keep valid rows and edit the datetimes of the events
-                # procedures
-                procedures = procedures.loc[valid_indices].reset_index(drop=True)
-                procedures = procedures.apply(
-                    lambda row: self._edit_datetimes(
-                        row,
-                        encounters.iloc[row.name],
-                        "proc",
-                    ),
-                    axis=1,
-                )
-                # medications
-                medications = medications.loc[valid_indices].reset_index(drop=True)
-                medications = medications.apply(
-                    lambda row: self._edit_datetimes(
-                        row,
-                        encounters.iloc[row.name],
-                        "med",
-                    ),
-                    axis=1,
-                )
-                # labs
-                labs = labs.loc[valid_indices].reset_index(drop=True)
-                labs = labs.apply(
-                    lambda row: self._edit_datetimes(
-                        row,
-                        encounters.iloc[row.name],
-                        "lab",
-                    ),
-                    axis=1,
-                )
-                # conditions
-                conditions = conditions.loc[valid_indices].reset_index(drop=True)
-                conditions["encounter_conditions"] = conditions[
-                    "encounter_conditions"
-                ].apply(ast.literal_eval)
-
-                # combine events
-                combined_events = self._concat_concepts(
-                    procedures,
-                    medications,
-                    labs,
-                    encounters,
-                    conditions=conditions if condition_per_encounter else None,
-                )
-                # filter patients based on min_events
-                combined_events = combined_events[
-                    combined_events["length"] > min_events
-                ]
-                # add elapsed time after admission for all events
-                combined_events = combined_events.apply(
-                    lambda row: self._time_after_admission(
-                        row,
-                        encounters.iloc[row.name],
-                    ),
-                    axis=1,
-                )
-                # add special tokens to the events
-                combined_events = combined_events.apply(
-                    lambda row: self._add_tokens(row, encounters.iloc[row.name]),
-                    axis=1,
-                )
-                # filter patients based on min_visits
-                combined_events = combined_events[
-                    combined_events["num_visits"] > min_visits
-                ]
-                # get mortality label
-                combined_events = combined_events.apply(
-                    lambda row: self._get_mortality_label(
-                        row,
-                        patients.iloc[row.name],
-                        encounters.iloc[row.name],
-                    ),
-                    axis=1,
-                )
-                combined_events = combined_events[
-                    ~combined_events["patient_id"].isin(self.after_death_events)
-                ]
-                combined_events = combined_events.apply(
-                    lambda row: self._truncate_or_pad(row, pad_events=pad_events),
-                    axis=1,
-                )
-                # get condition label for common and rare conditions
-                combined_events = combined_events.apply(
-                    lambda row: self._get_condition_label(
-                        row,
-                        conditions.iloc[row.name],
-                    ),
-                    axis=1,
-                )
-                # drop rows with nan values for events if any
-                combined_events = combined_events.dropna(
-                    subset=[f"event_tokens_{self.max_seq_length}"],
-                )
-                # save the combined events
-                combined_events_all = combined_events[self.get_all_column_names]
-                combined_events_max = combined_events[self.get_max_column_names]
-
-                combined_events_all.to_parquet(
-                    self.all_dir + f"/patient_sequences_{rounds}.parquet",
-                    engine="pyarrow",
-                )
-                combined_events_max.to_parquet(
-                    self.max_dir
-                    + f"/patient_sequences_{self.max_seq_length}_{rounds}.parquet",
-                    engine="pyarrow",
-                )
-                print(f"Round {rounds} done")
-                rounds += 1
-
             except StopIteration:
+                more_chunks = False
                 break
+            patients, encounters, procedures, medications, labs, conditions = dataframes
+            ## Process encounters
+            # Keep valid encounters
+            encounters = encounters.apply(
+                lambda row: self._get_valid_encounters(
+                    row,
+                    procedures.iloc[row.name],
+                    medications.iloc[row.name],
+                    labs.iloc[row.name],
+                ),
+                axis=1,
+            )
+            # keep valid rows with at least one encounter
+            start = time.time()
+            valid_indices = encounters[encounters["length"] > 0].index
+            encounters = encounters.loc[valid_indices].reset_index(drop=True)
+            patients = patients.loc[valid_indices].reset_index(drop=True)
+            # sort encounters by start time
+            encounters = encounters.apply(self._sort_encounters, axis=1)
+            # get ages of the patients at the time of the encounters
+            encounters = encounters.apply(
+                lambda row: self._get_encounters_age(row, patients.iloc[row.name]),
+                axis=1,
+            )
+            # get time of the encounters in weeks with respect to a reference time
+            encounters = encounters.apply(
+                lambda row: self._get_encounters_time(row),
+                axis=1,
+            )
+            # calculate intervals between encounters
+            encounters = encounters.apply(self._calculate_intervals, axis=1)
+            ## process events
+            # keep valid rows and edit the datetimes of the events
+            # procedures
+            procedures = procedures.loc[valid_indices].reset_index(drop=True)
+            procedures = procedures.apply(
+                lambda row: self._edit_datetimes(
+                    row,
+                    encounters.iloc[row.name],
+                    "proc",
+                ),
+                axis=1,
+            )
+            # medications
+            medications = medications.loc[valid_indices].reset_index(drop=True)
+            medications = medications.apply(
+                lambda row: self._edit_datetimes(
+                    row,
+                    encounters.iloc[row.name],
+                    "med",
+                ),
+                axis=1,
+            )
+            # labs
+            labs = labs.loc[valid_indices].reset_index(drop=True)
+            labs = labs.apply(
+                lambda row: self._edit_datetimes(
+                    row,
+                    encounters.iloc[row.name],
+                    "lab",
+                ),
+                axis=1,
+            )
+            # conditions
+            conditions = conditions.loc[valid_indices].reset_index(drop=True)
+            conditions["encounter_conditions"] = conditions[
+                "encounter_conditions"
+            ].apply(literal_eval)
+
+            # combine events
+            combined_events = self._concat_concepts(
+                procedures,
+                medications,
+                labs,
+                encounters,
+                conditions=conditions if condition_per_encounter else None,
+            )
+            # filter patients based on min_events
+            combined_events = combined_events[combined_events["length"] > min_events]
+            # add elapsed time after admission for all events
+            combined_events = combined_events.apply(
+                lambda row: self._time_after_admission(
+                    row,
+                    encounters.iloc[row.name],
+                ),
+                axis=1,
+            )
+            # add special tokens to the events
+            combined_events = combined_events.apply(
+                lambda row: self._add_tokens(row, encounters.iloc[row.name]),
+                axis=1,
+            )
+            # filter patients based on min_visits
+            combined_events = combined_events[
+                combined_events["num_visits"] > min_visits
+            ]
+            # get mortality label
+            combined_events = combined_events.apply(
+                lambda row: self._get_mortality_label(
+                    row,
+                    patients.iloc[row.name],
+                    encounters.iloc[row.name],
+                ),
+                axis=1,
+            )
+            combined_events = combined_events[
+                ~combined_events["patient_id"].isin(self.after_death_events)
+            ]
+            combined_events = combined_events.apply(
+                lambda row: self._truncate_or_pad(row, pad_events=pad_events),
+                axis=1,
+            )
+            # get condition label for common and rare conditions
+            combined_events = combined_events.apply(
+                lambda row: self._get_condition_label(
+                    row,
+                    conditions.iloc[row.name],
+                ),
+                axis=1,
+            )
+            # drop rows with nan values for events if any
+            combined_events = combined_events.dropna(
+                subset=[f"event_tokens_{self.max_seq_length}"],
+            )
+            # save the combined events
+            combined_events_all = combined_events[self.get_all_column_names]
+            combined_events_max = combined_events[self.get_max_column_names]
+
+            combined_events_all.to_parquet(
+                self.all_dir + f"/patient_sequences_{rounds}.parquet",
+                engine="pyarrow",
+            )
+            combined_events_max.to_parquet(
+                self.max_dir
+                + f"/patient_sequences_{self.max_seq_length}_{rounds}.parquet",
+                engine="pyarrow",
+            )
+            LOGGER.info(f"Round {rounds} done")
+            rounds += 1
 
     def reapply_truncation(
         self,
@@ -1176,9 +1174,9 @@ def reapply_truncation(
 if __name__ == "__main__":
     generator = SequenceGenerator(
         max_seq_length=2048,
-        data_dir="/mnt/data/odyssey/mimiciv_fhir/csv_files",
-        json_dir="/mnt/data/odyssey/mimiciv_fhir/json_files",
-        save_dir="/mnt/data/odyssey/mimiciv_fhir/parquet_files",
+        data_dir="/mnt/data/odyssey/mimiciv_fhir1/csv_files",
+        json_dir="/mnt/data/odyssey/mimiciv_fhir1/vocab",
+        save_dir="/mnt/data/odyssey/mimiciv_fhir1/parquet_files",
     )
     generator.create_patient_sequence(
         chunksize=20000,
diff --git a/lib/tokenizer.py b/odyssey/data/tokenizer.py
similarity index 59%
rename from lib/tokenizer.py
rename to odyssey/data/tokenizer.py
index a2f9619..f5b16ce 100644
--- a/lib/tokenizer.py
+++ b/odyssey/data/tokenizer.py
@@ -1,8 +1,4 @@
-"""
-file: tokenizer.py.
-
-Custom HuggingFace tokenizer for medical concepts in MIMIC-IV FHIR dataset.
-"""
+"""Tokenizer module."""
 
 import glob
 import json
@@ -15,7 +11,47 @@
 
 
 class ConceptTokenizer:
-    """Tokenizer for event concepts using HuggingFace Library."""
+    """Tokenizer for event concepts using HuggingFace Library.
+
+    Parameters
+    ----------
+    pad_token: str
+        Padding token.
+    mask_token: str
+        Mask token.
+    start_token: str
+        Sequence Start token.
+    end_token: str
+        Sequence End token.
+    class_token: str
+        Class token.
+    reg_token: str
+        Registry token.
+    unknown_token: str
+        Unknown token.
+    data_dir: str
+        Directory containing the data.
+    tokenizer_object: Optional[Tokenizer]
+        Tokenizer object.
+    tokenizer: Optional[PreTrainedTokenizerFast]
+        Tokenizer object.
+
+    Attributes
+    ----------
+    pad_token: str
+        Padding token.
+    mask_token: str
+        Mask token.
+    unknown_token: str
+        Unknown token.
+    special_tokens: List[str]
+        Special tokens.
+    tokenizer: PreTrainedTokenizerFast
+        Tokenizer object.
+    tokenizer_object: Tokenizer
+        Tokenizer object.
+
+    """
 
     def __init__(
         self,
@@ -100,7 +136,19 @@ def create_tokenizer(
         self,
         tokenizer_obj: Tokenizer,
     ) -> PreTrainedTokenizerFast:
-        """Load the tokenizer from a JSON file on disk."""
+        """Load the tokenizer from a JSON file on disk.
+
+        Parameters
+        ----------
+        tokenizer_obj: Tokenizer
+            Tokenizer object.
+
+        Returns
+        -------
+        PreTrainedTokenizerFast
+            Tokenizer object.
+
+        """
         self.tokenizer = PreTrainedTokenizerFast(
             tokenizer_object=tokenizer_obj,
             bos_token="[VS]",
@@ -121,7 +169,29 @@ def __call__(
         padding: str = "max_length",
         max_length: int = 2048,
     ) -> BatchEncoding:
-        """Return the tokenized dictionary of input batch."""
+        """Return the tokenized dictionary of input batch.
+
+        Parameters
+        ----------
+        batch: Union[str, List[str]]
+            Input batch.
+        return_attention_mask: bool
+            Return attention mask.
+        return_token_type_ids: bool
+            Return token type ids.
+        truncation: bool
+            Truncate the input.
+        padding: str
+            Padding strategy.
+        max_length: int
+            Maximum length of the input.
+
+        Returns
+        -------
+        BatchEncoding
+            Tokenized dictionary of input batch.
+
+        """
         return self.tokenizer(
             batch,
             return_attention_mask=return_attention_mask,
@@ -133,23 +203,83 @@ def __call__(
         )
 
     def encode(self, concept_tokens: str) -> List[int]:
-        """Encode the concept tokens into token ids."""
+        """Encode the concept tokens into token ids.
+
+        Parameters
+        ----------
+        concept_tokens: str
+            Concept tokens.
+
+        Returns
+        -------
+        List[int]
+            Token ids.
+
+        """
         return self.tokenizer_object.encode(concept_tokens).ids
 
     def decode(self, concept_ids: List[int]) -> str:
-        """Decode the concept sequence token id into token concept."""
+        """Decode the concept sequence token id into token concept.
+
+        Parameters
+        ----------
+        concept_ids: List[int]
+            Concept ids.
+
+        Returns
+        -------
+        str
+            Concept sequence.
+
+        """
         return self.tokenizer_object.decode(concept_ids)
 
     def token_to_id(self, token: str) -> int:
-        """Return the id corresponding to token."""
+        """Return the id corresponding to token.
+
+        Parameters
+        ----------
+        token: str
+            Token.
+
+        Returns
+        -------
+        int
+            Token id.
+
+        """
         return self.tokenizer_object.token_to_id(token)
 
     def id_to_token(self, token_id: int) -> str:
-        """Return the token corresponding to id."""
+        """Return the token corresponding to id.
+
+        Parameters
+        ----------
+        token_id: int
+            Token id.
+
+        Returns
+        -------
+        str
+            Token.
+
+        """
         return self.tokenizer_object.id_to_token(token_id)
 
     def get_all_token_indexes(self, with_special_tokens: bool = True) -> Set[int]:
-        """Return a set of all possible token ids."""
+        """Return a set of all possible token ids.
+
+        Parameters
+        ----------
+        with_special_tokens: bool
+            Include special tokens.
+
+        Returns
+        -------
+        Set[int]
+            Set of all token ids.
+
+        """
         all_token_ids = set(self.tokenizer_vocab.values())
         special_token_ids = set(self.get_special_token_ids())
 
@@ -158,27 +288,69 @@ def get_all_token_indexes(self, with_special_tokens: bool = True) -> Set[int]:
         )
 
     def get_first_token_index(self) -> int:
-        """Return the smallest token id in vocabulary."""
+        """Return the smallest token id in vocabulary.
+
+        Returns
+        -------
+        int
+            First token id.
+
+        """
         return min(self.tokenizer_vocab.values())
 
     def get_last_token_index(self) -> int:
-        """Return the largest token id in vocabulary."""
+        """Return the largest token id in vocabulary.
+
+        Returns
+        -------
+        int
+            Largest token id.
+
+        """
         return max(self.tokenizer_vocab.values())
 
     def get_vocab_size(self) -> int:
-        """Return the number of possible tokens in vocabulary."""
+        """Return the number of possible tokens in vocabulary.
+
+        Returns
+        -------
+        int
+            Number of tokens in vocabulary.
+
+        """
         return len(self.tokenizer)
 
     def get_pad_token_id(self) -> int:
-        """Return the token id of PAD token."""
+        """Return the token id of PAD token.
+
+        Returns
+        -------
+        int
+            Token id of PAD token.
+
+        """
         return self.token_to_id(self.pad_token)
 
     def get_mask_token_id(self) -> int:
-        """Return the token id of MASK token."""
+        """Return the token id of MASK token.
+
+        Returns
+        -------
+        int
+            Token id of MASK token.
+
+        """
         return self.token_to_id(self.mask_token)
 
     def get_special_token_ids(self) -> List[int]:
-        """Get a list of ids representing special tokens."""
+        """Get a list of ids representing special tokens.
+
+        Returns
+        -------
+        List[int]
+            List of special token ids.
+
+        """
         self.special_token_ids = []
 
         for special_token in self.special_tokens:
@@ -188,5 +360,12 @@ def get_special_token_ids(self) -> List[int]:
         return self.special_token_ids
 
     def save_tokenizer_to_disk(self, save_dir: str) -> None:
-        """Save the tokenizer object to disk as a JSON file."""
+        """Save the tokenizer object to disk as a JSON file.
+
+        Parameters
+        ----------
+        save_dir: str
+            Directory to save the tokenizer.
+
+        """
         self.tokenizer.save(path=save_dir)
diff --git a/odyssey/models/__init__.py b/odyssey/models/__init__.py
new file mode 100644
index 0000000..9e94c8d
--- /dev/null
+++ b/odyssey/models/__init__.py
@@ -0,0 +1 @@
+"""Models sub-package."""
diff --git a/models/baseline/Bi-LSTM.ipynb b/odyssey/models/baseline/Bi-LSTM.ipynb
similarity index 100%
rename from models/baseline/Bi-LSTM.ipynb
rename to odyssey/models/baseline/Bi-LSTM.ipynb
diff --git a/models/baseline/Bi-LSTM.py b/odyssey/models/baseline/Bi-LSTM.py
similarity index 97%
rename from models/baseline/Bi-LSTM.py
rename to odyssey/models/baseline/Bi-LSTM.py
index 93739f6..8e20a38 100644
--- a/models/baseline/Bi-LSTM.py
+++ b/odyssey/models/baseline/Bi-LSTM.py
@@ -1,8 +1,4 @@
-"""
-File: Bi-LSTM.ipynb.
-
-Code to train and evaluate a bi-directional LSTM model on MIMIC-IV FHIR dataset.
-"""
+"""Bi-directional LSTM model implementation."""
 
 import os
 import sys
@@ -21,9 +17,9 @@
 from torch.utils.data import DataLoader, Dataset
 from tqdm import tqdm
 
-from models.big_bird_cehr.data import FinetuneDataset
-from models.big_bird_cehr.embeddings import Embeddings
-from models.big_bird_cehr.tokenizer import HuggingFaceConceptTokenizer
+from odyssey.models.big_bird_cehr.data import FinetuneDataset
+from odyssey.models.big_bird_cehr.embeddings import Embeddings
+from odyssey.models.big_bird_cehr.tokenizer import HuggingFaceConceptTokenizer
 
 
 ROOT = "/fs01/home/afallah/odyssey/odyssey"
diff --git a/models/baseline/XGBoost.ipynb b/odyssey/models/baseline/XGBoost.ipynb
similarity index 100%
rename from models/baseline/XGBoost.ipynb
rename to odyssey/models/baseline/XGBoost.ipynb
diff --git a/models/cehr_bert/embeddings.py b/odyssey/models/cehr_bert/embeddings.py
similarity index 100%
rename from models/cehr_bert/embeddings.py
rename to odyssey/models/cehr_bert/embeddings.py
diff --git a/models/cehr_bert/model.py b/odyssey/models/cehr_bert/model.py
similarity index 99%
rename from models/cehr_bert/model.py
rename to odyssey/models/cehr_bert/model.py
index a1334dd..9af880d 100644
--- a/models/cehr_bert/model.py
+++ b/odyssey/models/cehr_bert/model.py
@@ -22,7 +22,7 @@
     BertPooler,
 )
 
-from .embeddings import Embeddings
+from odyssey.models.cehr_bert.embeddings import Embeddings
 
 
 class BertPretrain(pl.LightningModule):
diff --git a/odyssey/models/cehr_big_bird/__init__.py b/odyssey/models/cehr_big_bird/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/models/big_bird_cehr/embeddings.py b/odyssey/models/cehr_big_bird/embeddings.py
similarity index 97%
rename from models/big_bird_cehr/embeddings.py
rename to odyssey/models/cehr_big_bird/embeddings.py
index 2e9f328..da43b44 100644
--- a/models/big_bird_cehr/embeddings.py
+++ b/odyssey/models/cehr_big_bird/embeddings.py
@@ -266,8 +266,21 @@ def cache_input(
         visit_orders: torch.Tensor,
         visit_segments: torch.Tensor,
     ) -> None:
-        """Cache values for time_stamps, ages, visit_orders & visit_segments inside the class object.
+        """Cache values for time_stamps, ages, visit_orders & visit_segments.
+
         These values will be used by the forward pass to change the final embedding.
+
+        Parameters
+        ----------
+        time_stamps : torch.Tensor
+            Time stamps of the input data.
+        ages : torch.Tensor
+            Ages of the input data.
+        visit_orders : torch.Tensor
+            Visit orders of the input data.
+        visit_segments : torch.Tensor
+            Visit segments of the input data.
+
         """
         self.time_stamps = time_stamps
         self.ages = ages
diff --git a/models/big_bird_cehr/model.py b/odyssey/models/cehr_big_bird/model.py
similarity index 98%
rename from models/big_bird_cehr/model.py
rename to odyssey/models/cehr_big_bird/model.py
index e8ee05b..2c5cf67 100644
--- a/models/big_bird_cehr/model.py
+++ b/odyssey/models/cehr_big_bird/model.py
@@ -1,8 +1,4 @@
-"""
-File: model.py.
-
-Implement BigBird using HuggingFace for pretraining and finetuning.
-"""
+"""Big Bird transformer model."""
 
 from typing import Any, Dict, Optional, Tuple, Union
 
@@ -25,7 +21,7 @@
     BigBirdForSequenceClassification,
 )
 
-from .embeddings import BigBirdEmbeddingsForCEHR
+from odyssey.models.cehr_big_bird.embeddings import BigBirdEmbeddingsForCEHR
 
 
 class BigBirdPretrain(pl.LightningModule):
@@ -305,7 +301,10 @@ def forward(
         """Forward pass for the model."""
         concept_ids, type_ids, time_stamps, ages, visit_orders, visit_segments = inputs
         self.model.bert.embeddings.cache_input(
-            time_stamps, ages, visit_orders, visit_segments
+            time_stamps,
+            ages,
+            visit_orders,
+            visit_segments,
         )
 
         if attention_mask is None:
diff --git a/models/big_bird_cehr/playground.ipynb b/odyssey/models/cehr_big_bird/playground.ipynb
similarity index 100%
rename from models/big_bird_cehr/playground.ipynb
rename to odyssey/models/cehr_big_bird/playground.ipynb
diff --git a/models/big_bird_cehr/tokenizer.ipynb b/odyssey/models/cehr_big_bird/tokenizer.ipynb
similarity index 100%
rename from models/big_bird_cehr/tokenizer.ipynb
rename to odyssey/models/cehr_big_bird/tokenizer.ipynb
diff --git a/models/configs/cehr_bert.yaml b/odyssey/models/configs/cehr_bert.yaml
similarity index 100%
rename from models/configs/cehr_bert.yaml
rename to odyssey/models/configs/cehr_bert.yaml
diff --git a/models/configs/cehr_bigbird.yaml b/odyssey/models/configs/cehr_bigbird.yaml
similarity index 100%
rename from models/configs/cehr_bigbird.yaml
rename to odyssey/models/configs/cehr_bigbird.yaml
diff --git a/models/exbehrt/playground.ipynb b/odyssey/models/exbehrt/playground.ipynb
similarity index 100%
rename from models/exbehrt/playground.ipynb
rename to odyssey/models/exbehrt/playground.ipynb
diff --git a/lib/prediction.py b/odyssey/models/prediction.py
similarity index 93%
rename from lib/prediction.py
rename to odyssey/models/prediction.py
index 630ee37..2d66e4f 100644
--- a/lib/prediction.py
+++ b/odyssey/models/prediction.py
@@ -4,8 +4,8 @@
 
 import torch
 
-from lib.tokenizer import ConceptTokenizer
-from models.big_bird_cehr.model import BigBirdFinetune, BigBirdPretrain
+from odyssey.models.big_bird_cehr.model import BigBirdFinetune, BigBirdPretrain
+from odyssey.tokenizer import ConceptTokenizer
 
 
 def load_finetuned_model(
@@ -23,7 +23,8 @@ def load_finetuned_model(
 
     Parameters
     ----------
-    model_path: Path to the finetuned model to load
+    model_path: str
+        Path to the finetuned model to load
     tokenizer: Loaded tokenizer object
     pre_model_config: Optional config to override default values of a pretrained model
     fine_model_config: Optional config to override default values of a finetuned model
diff --git a/lib/utils.py b/odyssey/models/utils.py
similarity index 100%
rename from lib/utils.py
rename to odyssey/models/utils.py
diff --git a/odyssey/utils/log.py b/odyssey/utils/log.py
new file mode 100644
index 0000000..05e8e69
--- /dev/null
+++ b/odyssey/utils/log.py
@@ -0,0 +1,138 @@
+"""Python logging function."""
+
+import logging
+from typing import Optional, Union
+
+
+LOG_FORMAT = "%(asctime)-15s %(levelname)-5s %(name)-15s - %(message)s"
+
+# https://stackoverflow.com/questions/384076/how-can-i-color-python-logging-output
+BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE = range(8)
+COLORS = {
+    "WARNING": YELLOW,
+    "INFO": WHITE,
+    "DEBUG": BLUE,
+    "CRITICAL": YELLOW,
+    "ERROR": RED,
+}
+
+# The background is set with 40 plus the number of the color, and the foreground 30.
+# These are the sequences need to get colored output.
+RESET_SEQ = "\033[0m"
+COLOR_SEQ = "\033[1;%dm"
+BOLD_SEQ = "\033[1m"
+
+
+def formatter_message(message: str, use_color: Optional[bool] = True) -> str:
+    """Format message.
+
+    Parameters
+    ----------
+    message: str
+        Message format.
+    use_color: bool, optional
+        Use colored logging.
+
+    Returns
+    -------
+    str
+        Formatted message.
+
+    """
+    if use_color:
+        message = message.replace("$RESET", RESET_SEQ).replace("$BOLD", BOLD_SEQ)
+    else:
+        message = message.replace("$RESET", "").replace("$BOLD", "")
+    return message
+
+
+class Formatter(logging.Formatter):
+    """Formatter.
+
+    Attributes
+    ----------
+    use_color: bool
+        Flag to toggle use of color.
+
+    """
+
+    def __init__(
+        self,
+        msg: Optional[str] = None,
+        use_color: bool = True,
+    ) -> None:
+        """Instantiate.
+
+        Parameters
+        ----------
+        msg: str
+            Message format.
+        use_color: bool
+            Flag to set using colored formatting.
+
+        """
+        if msg is None:
+            msg = formatter_message(LOG_FORMAT, True)
+        logging.Formatter.__init__(self, msg)
+        self.use_color = use_color
+
+    def format(self, record: logging.LogRecord) -> str:  # noqa: A003
+        """Apply formatting.
+
+        Parameters
+        ----------
+        record: logging.LogRecord
+            Record object for logging.
+
+        Returns
+        -------
+        str
+            Formatted string for log.
+
+        """
+        levelname = record.levelname
+        if self.use_color and levelname in COLORS:
+            levelname_color = (
+                COLOR_SEQ % (30 + COLORS[levelname]) + levelname + RESET_SEQ
+            )
+            record.levelname = levelname_color
+        return logging.Formatter.format(self, record)
+
+
+def setup_logging(
+    log_path: Optional[str] = None,
+    log_level: Union[int, str] = "DEBUG",
+    print_level: Union[int, str] = "INFO",
+    logger: Optional[logging.Logger] = None,
+    use_color: bool = True,
+) -> None:
+    """Create logger, and set it up.
+
+    Parameters
+    ----------
+    log_path : str, optional
+        Path to output log file.
+    log_level : str, optional
+        Log level for logging, defaults to DEBUG.
+    print_level : str, optional
+        Print level for logging, defaults to INFO.
+    logger : logging.Logger, optional
+        Pass logger if already exists, else a new logger object is created.
+    use_color: bool, optional
+        Use colored logging.
+
+    """
+    fmt = formatter_message(LOG_FORMAT, use_color)
+    logger = logger if logger else logging.getLogger()
+    logger.setLevel(log_level)
+    logger.handlers = []
+
+    stream_handler = logging.StreamHandler()
+    stream_handler.setFormatter(Formatter(fmt, use_color=use_color))
+    stream_handler.setLevel(print_level)
+    logger.addHandler(stream_handler)
+
+    if log_path:
+        file_handler = logging.FileHandler(log_path)
+        file_handler.setFormatter(Formatter(fmt, use_color=use_color))
+        logger.addHandler(file_handler)
diff --git a/poetry.lock b/poetry.lock
index 5e0dc20..df9c043 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -588,18 +588,18 @@ test = ["coverage", "pytest (>5.4.0)", "pytest-cov (>=2.10.0)", "pytest-runner"]
 
 [[package]]
 name = "filelock"
-version = "3.13.1"
+version = "3.13.3"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "filelock-3.13.1-py3-none-any.whl", hash = "sha256:57dbda9b35157b05fb3e58ee91448612eb674172fab98ee235ccb0b5bee19a1c"},
-    {file = "filelock-3.13.1.tar.gz", hash = "sha256:521f5f56c50f8426f5e03ad3b281b490a87ef15bc6c526f168290f0c7148d44e"},
+    {file = "filelock-3.13.3-py3-none-any.whl", hash = "sha256:5ffa845303983e7a0b7ae17636509bc97997d58afeafa72fb141a17b152284cb"},
+    {file = "filelock-3.13.3.tar.gz", hash = "sha256:a79895a25bbefdf55d1a2a0a80968f7dbb28edcd6d4234a0afb3f37ecde4b546"},
 ]
 
 [package.extras]
-docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.24)"]
-testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
+docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
 typing = ["typing-extensions (>=4.8)"]
 
 [[package]]
@@ -706,13 +706,13 @@ files = [
 
 [[package]]
 name = "fsspec"
-version = "2024.3.0"
+version = "2024.3.1"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "fsspec-2024.3.0-py3-none-any.whl", hash = "sha256:779001bd0122c9c4975cf03827d5e86c3afb914a3ae27040f15d341ab506a693"},
-    {file = "fsspec-2024.3.0.tar.gz", hash = "sha256:f13a130c0ed07e15c4e1aeb0472a823e9c426b0b5792a1f40d902b0a71972d43"},
+    {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
+    {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
 ]
 
 [package.dependencies]
@@ -1131,13 +1131,13 @@ test = ["click (==8.1.7)", "cloudpickle (>=1.3,<3.0)", "coverage (==7.3.1)", "fa
 
 [[package]]
 name = "lightning-utilities"
-version = "0.10.1"
+version = "0.11.2"
 description = "Lightning toolbox for across the our ecosystem."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "lightning-utilities-0.10.1.tar.gz", hash = "sha256:362755023dcf93b8fa519bc002ae41794943a3ffbc5318e40804d36aa14bf1fd"},
-    {file = "lightning_utilities-0.10.1-py3-none-any.whl", hash = "sha256:e67be3f328b1c14f2b36cc09e84642db5b50afeab94e7704969b2130fe6a3bda"},
+    {file = "lightning-utilities-0.11.2.tar.gz", hash = "sha256:adf4cf9c5d912fe505db4729e51d1369c6927f3a8ac55a9dff895ce5c0da08d9"},
+    {file = "lightning_utilities-0.11.2-py3-none-any.whl", hash = "sha256:541f471ed94e18a28d72879338c8c52e873bb46f4c47644d89228faeb6751159"},
 ]
 
 [package.dependencies]
@@ -1409,13 +1409,13 @@ test = ["pep440", "pre-commit", "pytest", "testpath"]
 
 [[package]]
 name = "nbqa"
-version = "1.8.4"
+version = "1.8.5"
 description = "Run any standard Python code quality tool on a Jupyter Notebook"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "nbqa-1.8.4-py3-none-any.whl", hash = "sha256:0e2acd73320ad1aa56f15200f9ea517c0ecb5ac388d217aee97fab66272c604b"},
-    {file = "nbqa-1.8.4.tar.gz", hash = "sha256:ca983e115d81f5cf149f70c4bf5b8baa36694a3eaf0783fe508dbf05b9767e07"},
+    {file = "nbqa-1.8.5-py3-none-any.whl", hash = "sha256:fe59ccb66f29bda2912c75cacf9cdbd34504923effb58ae1c88211d075213eff"},
+    {file = "nbqa-1.8.5.tar.gz", hash = "sha256:91624e9c747bbe38ff14ebf75d17cfb838b5c0432b039bcb7e8ad0bb423ef7ef"},
 ]
 
 [package.dependencies]
@@ -1620,7 +1620,10 @@ files = [
 ]
 
 [package.dependencies]
-numpy = {version = ">=1.22.4,<2", markers = "python_version < \"3.11\""}
+numpy = [
+    {version = ">=1.22.4,<2", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2,<2", markers = "python_version == \"3.11\""},
+]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
 tzdata = ">=2022.7"
@@ -1864,47 +1867,47 @@ tests = ["pytest"]
 
 [[package]]
 name = "pyarrow"
-version = "15.0.1"
+version = "15.0.2"
 description = "Python library for Apache Arrow"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pyarrow-15.0.1-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:c2ddb3be5ea938c329a84171694fc230b241ce1b6b0ff1a0280509af51c375fa"},
-    {file = "pyarrow-15.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7543ea88a0ff72f8e6baaf9bfdbec2c62aeabdbede9e4a571c71cc3bc43b6302"},
-    {file = "pyarrow-15.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1519e218a6941fc074e4501088d891afcb2adf77c236e03c34babcf3d6a0d1c7"},
-    {file = "pyarrow-15.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28cafa86e1944761970d3b3fc0411b14ff9b5c2b73cd22aaf470d7a3976335f5"},
-    {file = "pyarrow-15.0.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:be5c3d463e33d03eab496e1af7916b1d44001c08f0f458ad27dc16093a020638"},
-    {file = "pyarrow-15.0.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:47b1eda15d3aa3f49a07b1808648e1397e5dc6a80a30bf87faa8e2d02dad7ac3"},
-    {file = "pyarrow-15.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:e524a31be7db22deebbbcf242b189063ab9a7652c62471d296b31bc6e3cae77b"},
-    {file = "pyarrow-15.0.1-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:a476fefe8bdd56122fb0d4881b785413e025858803cc1302d0d788d3522b374d"},
-    {file = "pyarrow-15.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:309e6191be385f2e220586bfdb643f9bb21d7e1bc6dd0a6963dc538e347b2431"},
-    {file = "pyarrow-15.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83bc586903dbeb4365cbc72b602f99f70b96c5882e5dfac5278813c7d624ca3c"},
-    {file = "pyarrow-15.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:07e652daac6d8b05280cd2af31c0fb61a4490ec6a53dc01588014d9fa3fdbee9"},
-    {file = "pyarrow-15.0.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:abad2e08652df153a72177ce20c897d083b0c4ebeec051239e2654ddf4d3c996"},
-    {file = "pyarrow-15.0.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:cde663352bc83ad75ba7b3206e049ca1a69809223942362a8649e37bd22f9e3b"},
-    {file = "pyarrow-15.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:1b6e237dd7a08482a8b8f3f6512d258d2460f182931832a8c6ef3953203d31e1"},
-    {file = "pyarrow-15.0.1-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:7bd167536ee23192760b8c731d39b7cfd37914c27fd4582335ffd08450ff799d"},
-    {file = "pyarrow-15.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7c08bb31eb2984ba5c3747d375bb522e7e536b8b25b149c9cb5e1c49b0ccb736"},
-    {file = "pyarrow-15.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0f9c1d630ed2524bd1ddf28ec92780a7b599fd54704cd653519f7ff5aec177a"},
-    {file = "pyarrow-15.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5186048493395220550bca7b524420471aac2d77af831f584ce132680f55c3df"},
-    {file = "pyarrow-15.0.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:31dc30c7ec8958da3a3d9f31d6c3630429b2091ede0ecd0d989fd6bec129f0e4"},
-    {file = "pyarrow-15.0.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:3f111a014fb8ac2297b43a74bf4495cc479a332908f7ee49cb7cbd50714cb0c1"},
-    {file = "pyarrow-15.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:a6d1f7c15d7f68f08490d0cb34611497c74285b8a6bbeab4ef3fc20117310983"},
-    {file = "pyarrow-15.0.1-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:9ad931b996f51c2f978ed517b55cb3c6078272fb4ec579e3da5a8c14873b698d"},
-    {file = "pyarrow-15.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:738f6b53ab1c2f66b2bde8a1d77e186aeaab702d849e0dfa1158c9e2c030add3"},
-    {file = "pyarrow-15.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c1c3fc16bc74e33bf8f1e5a212938ed8d88e902f372c4dac6b5bad328567d2f"},
-    {file = "pyarrow-15.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1fa92512128f6c1b8dde0468c1454dd70f3bff623970e370d52efd4d24fd0be"},
-    {file = "pyarrow-15.0.1-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:b4157f307c202cbbdac147d9b07447a281fa8e63494f7fc85081da351ec6ace9"},
-    {file = "pyarrow-15.0.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:b75e7da26f383787f80ad76143b44844ffa28648fcc7099a83df1538c078d2f2"},
-    {file = "pyarrow-15.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:3a99eac76ae14096c209850935057b9e8ce97a78397c5cde8724674774f34e5d"},
-    {file = "pyarrow-15.0.1-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:dd532d3177e031e9b2d2df19fd003d0cc0520d1747659fcabbd4d9bb87de508c"},
-    {file = "pyarrow-15.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ce8c89848fd37e5313fc2ce601483038ee5566db96ba0808d5883b2e2e55dc53"},
-    {file = "pyarrow-15.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:862eac5e5f3b6477f7a92b2f27e560e1f4e5e9edfca9ea9da8a7478bb4abd5ce"},
-    {file = "pyarrow-15.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f0ea3a29cd5cb99bf14c1c4533eceaa00ea8fb580950fb5a89a5c771a994a4e"},
-    {file = "pyarrow-15.0.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bb902f780cfd624b2e8fd8501fadab17618fdb548532620ef3d91312aaf0888a"},
-    {file = "pyarrow-15.0.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:4f87757f02735a6bb4ad2e1b98279ac45d53b748d5baf52401516413007c6999"},
-    {file = "pyarrow-15.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:efd3816c7fbfcbd406ac0f69873cebb052effd7cdc153ae5836d1b00845845d7"},
-    {file = "pyarrow-15.0.1.tar.gz", hash = "sha256:21d812548d39d490e0c6928a7c663f37b96bf764034123d4b4ab4530ecc757a9"},
+    {file = "pyarrow-15.0.2-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:88b340f0a1d05b5ccc3d2d986279045655b1fe8e41aba6ca44ea28da0d1455d8"},
+    {file = "pyarrow-15.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:eaa8f96cecf32da508e6c7f69bb8401f03745c050c1dd42ec2596f2e98deecac"},
+    {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23c6753ed4f6adb8461e7c383e418391b8d8453c5d67e17f416c3a5d5709afbd"},
+    {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f639c059035011db8c0497e541a8a45d98a58dbe34dc8fadd0ef128f2cee46e5"},
+    {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:290e36a59a0993e9a5224ed2fb3e53375770f07379a0ea03ee2fce2e6d30b423"},
+    {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:06c2bb2a98bc792f040bef31ad3e9be6a63d0cb39189227c08a7d955db96816e"},
+    {file = "pyarrow-15.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:f7a197f3670606a960ddc12adbe8075cea5f707ad7bf0dffa09637fdbb89f76c"},
+    {file = "pyarrow-15.0.2-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:5f8bc839ea36b1f99984c78e06e7a06054693dc2af8920f6fb416b5bca9944e4"},
+    {file = "pyarrow-15.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f5e81dfb4e519baa6b4c80410421528c214427e77ca0ea9461eb4097c328fa33"},
+    {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3a4f240852b302a7af4646c8bfe9950c4691a419847001178662a98915fd7ee7"},
+    {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e7d9cfb5a1e648e172428c7a42b744610956f3b70f524aa3a6c02a448ba853e"},
+    {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2d4f905209de70c0eb5b2de6763104d5a9a37430f137678edfb9a675bac9cd98"},
+    {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:90adb99e8ce5f36fbecbbc422e7dcbcbed07d985eed6062e459e23f9e71fd197"},
+    {file = "pyarrow-15.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:b116e7fd7889294cbd24eb90cd9bdd3850be3738d61297855a71ac3b8124ee38"},
+    {file = "pyarrow-15.0.2-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:25335e6f1f07fdaa026a61c758ee7d19ce824a866b27bba744348fa73bb5a440"},
+    {file = "pyarrow-15.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:90f19e976d9c3d8e73c80be84ddbe2f830b6304e4c576349d9360e335cd627fc"},
+    {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a22366249bf5fd40ddacc4f03cd3160f2d7c247692945afb1899bab8a140ddfb"},
+    {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2a335198f886b07e4b5ea16d08ee06557e07db54a8400cc0d03c7f6a22f785f"},
+    {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:3e6d459c0c22f0b9c810a3917a1de3ee704b021a5fb8b3bacf968eece6df098f"},
+    {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:033b7cad32198754d93465dcfb71d0ba7cb7cd5c9afd7052cab7214676eec38b"},
+    {file = "pyarrow-15.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:29850d050379d6e8b5a693098f4de7fd6a2bea4365bfd073d7c57c57b95041ee"},
+    {file = "pyarrow-15.0.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:7167107d7fb6dcadb375b4b691b7e316f4368f39f6f45405a05535d7ad5e5058"},
+    {file = "pyarrow-15.0.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e85241b44cc3d365ef950432a1b3bd44ac54626f37b2e3a0cc89c20e45dfd8bf"},
+    {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:248723e4ed3255fcd73edcecc209744d58a9ca852e4cf3d2577811b6d4b59818"},
+    {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ff3bdfe6f1b81ca5b73b70a8d482d37a766433823e0c21e22d1d7dde76ca33f"},
+    {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:f3d77463dee7e9f284ef42d341689b459a63ff2e75cee2b9302058d0d98fe142"},
+    {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:8c1faf2482fb89766e79745670cbca04e7018497d85be9242d5350cba21357e1"},
+    {file = "pyarrow-15.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:28f3016958a8e45a1069303a4a4f6a7d4910643fc08adb1e2e4a7ff056272ad3"},
+    {file = "pyarrow-15.0.2-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:89722cb64286ab3d4daf168386f6968c126057b8c7ec3ef96302e81d8cdb8ae4"},
+    {file = "pyarrow-15.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cd0ba387705044b3ac77b1b317165c0498299b08261d8122c96051024f953cd5"},
+    {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ad2459bf1f22b6a5cdcc27ebfd99307d5526b62d217b984b9f5c974651398832"},
+    {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58922e4bfece8b02abf7159f1f53a8f4d9f8e08f2d988109126c17c3bb261f22"},
+    {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:adccc81d3dc0478ea0b498807b39a8d41628fa9210729b2f718b78cb997c7c91"},
+    {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:8bd2baa5fe531571847983f36a30ddbf65261ef23e496862ece83bdceb70420d"},
+    {file = "pyarrow-15.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:6669799a1d4ca9da9c7e06ef48368320f5856f36f9a4dd31a11839dda3f6cc8c"},
+    {file = "pyarrow-15.0.2.tar.gz", hash = "sha256:9c9bc803cb3b7bfacc1e96ffbfd923601065d9d3f911179d81e72d99fd74a3d9"},
 ]
 
 [package.dependencies]
@@ -1961,7 +1964,10 @@ files = [
 [package.dependencies]
 astroid = ">=3.1.0,<=3.2.0-dev0"
 colorama = {version = ">=0.4.5", markers = "sys_platform == \"win32\""}
-dill = {version = ">=0.2", markers = "python_version < \"3.11\""}
+dill = [
+    {version = ">=0.2", markers = "python_version < \"3.11\""},
+    {version = ">=0.3.6", markers = "python_version >= \"3.11\""},
+]
 isort = ">=4.2.5,<5.13.0 || >5.13.0,<6"
 mccabe = ">=0.6,<0.8"
 platformdirs = ">=2.2.0"
@@ -2071,13 +2077,13 @@ files = [
 
 [[package]]
 name = "pyupgrade"
-version = "3.15.1"
+version = "3.15.2"
 description = "A tool to automatically upgrade syntax for newer versions."
 optional = false
 python-versions = ">=3.8.1"
 files = [
-    {file = "pyupgrade-3.15.1-py2.py3-none-any.whl", hash = "sha256:c5e005de2805edcd333d1deb04553200ec69da85e4bc9db37b16345ed9e27ed9"},
-    {file = "pyupgrade-3.15.1.tar.gz", hash = "sha256:7690857cae0f6253f39241dcd2e57118c333c438b78609fc3c17a5aa61227b7d"},
+    {file = "pyupgrade-3.15.2-py2.py3-none-any.whl", hash = "sha256:ce309e0ff8ecb73f56a45f12570be84bbbde9540d13697cacb261a7f595fb1f5"},
+    {file = "pyupgrade-3.15.2.tar.gz", hash = "sha256:c488d6896c546d25845712ef6402657123008d56c1063174e27aabe15bd6b4e5"},
 ]
 
 [package.dependencies]
@@ -2311,28 +2317,28 @@ files = [
 
 [[package]]
 name = "ruff"
-version = "0.3.3"
+version = "0.3.4"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.3.3-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:973a0e388b7bc2e9148c7f9be8b8c6ae7471b9be37e1cc732f8f44a6f6d7720d"},
-    {file = "ruff-0.3.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:cfa60d23269d6e2031129b053fdb4e5a7b0637fc6c9c0586737b962b2f834493"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1eca7ff7a47043cf6ce5c7f45f603b09121a7cc047447744b029d1b719278eb5"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e7d3f6762217c1da954de24b4a1a70515630d29f71e268ec5000afe81377642d"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b24c19e8598916d9c6f5a5437671f55ee93c212a2c4c569605dc3842b6820386"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:5a6cbf216b69c7090f0fe4669501a27326c34e119068c1494f35aaf4cc683778"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:352e95ead6964974b234e16ba8a66dad102ec7bf8ac064a23f95371d8b198aab"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d6ab88c81c4040a817aa432484e838aaddf8bfd7ca70e4e615482757acb64f8"},
-    {file = "ruff-0.3.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79bca3a03a759cc773fca69e0bdeac8abd1c13c31b798d5bb3c9da4a03144a9f"},
-    {file = "ruff-0.3.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:2700a804d5336bcffe063fd789ca2c7b02b552d2e323a336700abb8ae9e6a3f8"},
-    {file = "ruff-0.3.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:fd66469f1a18fdb9d32e22b79f486223052ddf057dc56dea0caaf1a47bdfaf4e"},
-    {file = "ruff-0.3.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:45817af234605525cdf6317005923bf532514e1ea3d9270acf61ca2440691376"},
-    {file = "ruff-0.3.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:0da458989ce0159555ef224d5b7c24d3d2e4bf4c300b85467b08c3261c6bc6a8"},
-    {file = "ruff-0.3.3-py3-none-win32.whl", hash = "sha256:f2831ec6a580a97f1ea82ea1eda0401c3cdf512cf2045fa3c85e8ef109e87de0"},
-    {file = "ruff-0.3.3-py3-none-win_amd64.whl", hash = "sha256:be90bcae57c24d9f9d023b12d627e958eb55f595428bafcb7fec0791ad25ddfc"},
-    {file = "ruff-0.3.3-py3-none-win_arm64.whl", hash = "sha256:0171aab5fecdc54383993389710a3d1227f2da124d76a2784a7098e818f92d61"},
-    {file = "ruff-0.3.3.tar.gz", hash = "sha256:38671be06f57a2f8aba957d9f701ea889aa5736be806f18c0cd03d6ff0cbca8d"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:60c870a7d46efcbc8385d27ec07fe534ac32f3b251e4fc44b3cbfd9e09609ef4"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6fc14fa742e1d8f24910e1fff0bd5e26d395b0e0e04cc1b15c7c5e5fe5b4af91"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d3ee7880f653cc03749a3bfea720cf2a192e4f884925b0cf7eecce82f0ce5854"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf133dd744f2470b347f602452a88e70dadfbe0fcfb5fd46e093d55da65f82f7"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3f3860057590e810c7ffea75669bdc6927bfd91e29b4baa9258fd48b540a4365"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:986f2377f7cf12efac1f515fc1a5b753c000ed1e0a6de96747cdf2da20a1b369"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fd98e85869603e65f554fdc5cddf0712e352fe6e61d29d5a6fe087ec82b76c"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:64abeed785dad51801b423fa51840b1764b35d6c461ea8caef9cf9e5e5ab34d9"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df52972138318bc7546d92348a1ee58449bc3f9eaf0db278906eb511889c4b50"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:98e98300056445ba2cc27d0b325fd044dc17fcc38e4e4d2c7711585bd0a958ed"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:519cf6a0ebed244dce1dc8aecd3dc99add7a2ee15bb68cf19588bb5bf58e0488"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:bb0acfb921030d00070539c038cd24bb1df73a2981e9f55942514af8b17be94e"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:cf187a7e7098233d0d0c71175375c5162f880126c4c716fa28a8ac418dcf3378"},
+    {file = "ruff-0.3.4-py3-none-win32.whl", hash = "sha256:af27ac187c0a331e8ef91d84bf1c3c6a5dea97e912a7560ac0cef25c526a4102"},
+    {file = "ruff-0.3.4-py3-none-win_amd64.whl", hash = "sha256:de0d5069b165e5a32b3c6ffbb81c350b1e3d3483347196ffdf86dc0ef9e37dd6"},
+    {file = "ruff-0.3.4-py3-none-win_arm64.whl", hash = "sha256:6810563cc08ad0096b57c717bd78aeac888a1bfd38654d9113cb3dc4d3f74232"},
+    {file = "ruff-0.3.4.tar.gz", hash = "sha256:f0f4484c6541a99862b693e13a151435a279b271cff20e37101116a21e2a1ad1"},
 ]
 
 [[package]]
@@ -2421,13 +2427,13 @@ test = ["asv", "gmpy2", "hypothesis", "mpmath", "pooch", "pytest", "pytest-cov",
 
 [[package]]
 name = "sentry-sdk"
-version = "1.42.0"
+version = "1.43.0"
 description = "Python client for Sentry (https://sentry.io)"
 optional = false
 python-versions = "*"
 files = [
-    {file = "sentry-sdk-1.42.0.tar.gz", hash = "sha256:4a8364b8f7edbf47f95f7163e48334c96100d9c098f0ae6606e2e18183c223e6"},
-    {file = "sentry_sdk-1.42.0-py2.py3-none-any.whl", hash = "sha256:a654ee7e497a3f5f6368b36d4f04baeab1fe92b3105f7f6965d6ef0de35a9ba4"},
+    {file = "sentry-sdk-1.43.0.tar.gz", hash = "sha256:41df73af89d22921d8733714fb0fc5586c3461907e06688e6537d01a27e0e0f6"},
+    {file = "sentry_sdk-1.43.0-py2.py3-none-any.whl", hash = "sha256:8d768724839ca18d7b4c7463ef7528c40b7aa2bfbf7fe554d5f9a7c044acfd36"},
 ]
 
 [package.dependencies]
@@ -2441,6 +2447,7 @@ asyncpg = ["asyncpg (>=0.23)"]
 beam = ["apache-beam (>=2.12)"]
 bottle = ["bottle (>=0.12.13)"]
 celery = ["celery (>=3)"]
+celery-redbeat = ["celery-redbeat (>=2)"]
 chalice = ["chalice (>=1.16.0)"]
 clickhouse-driver = ["clickhouse-driver (>=0.2.0)"]
 django = ["django (>=1.8)"]
@@ -2605,60 +2612,60 @@ files = [
 
 [[package]]
 name = "sqlalchemy"
-version = "2.0.28"
+version = "2.0.29"
 description = "Database Abstraction Library"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e0b148ab0438f72ad21cb004ce3bdaafd28465c4276af66df3b9ecd2037bf252"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:bbda76961eb8f27e6ad3c84d1dc56d5bc61ba8f02bd20fcf3450bd421c2fcc9c"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:feea693c452d85ea0015ebe3bb9cd15b6f49acc1a31c28b3c50f4db0f8fb1e71"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5da98815f82dce0cb31fd1e873a0cb30934971d15b74e0d78cf21f9e1b05953f"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:4a5adf383c73f2d49ad15ff363a8748319ff84c371eed59ffd0127355d6ea1da"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:56856b871146bfead25fbcaed098269d90b744eea5cb32a952df00d542cdd368"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-win32.whl", hash = "sha256:943aa74a11f5806ab68278284a4ddd282d3fb348a0e96db9b42cb81bf731acdc"},
-    {file = "SQLAlchemy-2.0.28-cp310-cp310-win_amd64.whl", hash = "sha256:c6c4da4843e0dabde41b8f2e8147438330924114f541949e6318358a56d1875a"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:46a3d4e7a472bfff2d28db838669fc437964e8af8df8ee1e4548e92710929adc"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:0d3dd67b5d69794cfe82862c002512683b3db038b99002171f624712fa71aeaa"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c61e2e41656a673b777e2f0cbbe545323dbe0d32312f590b1bc09da1de6c2a02"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0315d9125a38026227f559488fe7f7cee1bd2fbc19f9fd637739dc50bb6380b2"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:af8ce2d31679006e7b747d30a89cd3ac1ec304c3d4c20973f0f4ad58e2d1c4c9"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:81ba314a08c7ab701e621b7ad079c0c933c58cdef88593c59b90b996e8b58fa5"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-win32.whl", hash = "sha256:1ee8bd6d68578e517943f5ebff3afbd93fc65f7ef8f23becab9fa8fb315afb1d"},
-    {file = "SQLAlchemy-2.0.28-cp311-cp311-win_amd64.whl", hash = "sha256:ad7acbe95bac70e4e687a4dc9ae3f7a2f467aa6597049eeb6d4a662ecd990bb6"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d3499008ddec83127ab286c6f6ec82a34f39c9817f020f75eca96155f9765097"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9b66fcd38659cab5d29e8de5409cdf91e9986817703e1078b2fdaad731ea66f5"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bea30da1e76cb1acc5b72e204a920a3a7678d9d52f688f087dc08e54e2754c67"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:124202b4e0edea7f08a4db8c81cc7859012f90a0d14ba2bf07c099aff6e96462"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e23b88c69497a6322b5796c0781400692eca1ae5532821b39ce81a48c395aae9"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b6303bfd78fb3221847723104d152e5972c22367ff66edf09120fcde5ddc2e2"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-win32.whl", hash = "sha256:a921002be69ac3ab2cf0c3017c4e6a3377f800f1fca7f254c13b5f1a2f10022c"},
-    {file = "SQLAlchemy-2.0.28-cp312-cp312-win_amd64.whl", hash = "sha256:b4a2cf92995635b64876dc141af0ef089c6eea7e05898d8d8865e71a326c0385"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e91b5e341f8c7f1e5020db8e5602f3ed045a29f8e27f7f565e0bdee3338f2c7"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45c7b78dfc7278329f27be02c44abc0d69fe235495bb8e16ec7ef1b1a17952db"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3eba73ef2c30695cb7eabcdb33bb3d0b878595737479e152468f3ba97a9c22a4"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5df5d1dafb8eee89384fb7a1f79128118bc0ba50ce0db27a40750f6f91aa99d5"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2858bbab1681ee5406650202950dc8f00e83b06a198741b7c656e63818633526"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-win32.whl", hash = "sha256:9461802f2e965de5cff80c5a13bc945abea7edaa1d29360b485c3d2b56cdb075"},
-    {file = "SQLAlchemy-2.0.28-cp37-cp37m-win_amd64.whl", hash = "sha256:a6bec1c010a6d65b3ed88c863d56b9ea5eeefdf62b5e39cafd08c65f5ce5198b"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:843a882cadebecc655a68bd9a5b8aa39b3c52f4a9a5572a3036fb1bb2ccdc197"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:dbb990612c36163c6072723523d2be7c3eb1517bbdd63fe50449f56afafd1133"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bd7e4baf9161d076b9a7e432fce06217b9bd90cfb8f1d543d6e8c4595627edb9"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e0a5354cb4de9b64bccb6ea33162cb83e03dbefa0d892db88a672f5aad638a75"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:fffcc8edc508801ed2e6a4e7b0d150a62196fd28b4e16ab9f65192e8186102b6"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:aca7b6d99a4541b2ebab4494f6c8c2f947e0df4ac859ced575238e1d6ca5716b"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-win32.whl", hash = "sha256:8c7f10720fc34d14abad5b647bc8202202f4948498927d9f1b4df0fb1cf391b7"},
-    {file = "SQLAlchemy-2.0.28-cp38-cp38-win_amd64.whl", hash = "sha256:243feb6882b06a2af68ecf4bec8813d99452a1b62ba2be917ce6283852cf701b"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fc4974d3684f28b61b9a90fcb4c41fb340fd4b6a50c04365704a4da5a9603b05"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:87724e7ed2a936fdda2c05dbd99d395c91ea3c96f029a033a4a20e008dd876bf"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68722e6a550f5de2e3cfe9da6afb9a7dd15ef7032afa5651b0f0c6b3adb8815d"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:328529f7c7f90adcd65aed06a161851f83f475c2f664a898af574893f55d9e53"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:df40c16a7e8be7413b885c9bf900d402918cc848be08a59b022478804ea076b8"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:426f2fa71331a64f5132369ede5171c52fd1df1bd9727ce621f38b5b24f48750"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-win32.whl", hash = "sha256:33157920b233bc542ce497a81a2e1452e685a11834c5763933b440fedd1d8e2d"},
-    {file = "SQLAlchemy-2.0.28-cp39-cp39-win_amd64.whl", hash = "sha256:2f60843068e432311c886c5f03c4664acaef507cf716f6c60d5fde7265be9d7b"},
-    {file = "SQLAlchemy-2.0.28-py3-none-any.whl", hash = "sha256:78bb7e8da0183a8301352d569900d9d3594c48ac21dc1c2ec6b3121ed8b6c986"},
-    {file = "SQLAlchemy-2.0.28.tar.gz", hash = "sha256:dd53b6c4e6d960600fd6532b79ee28e2da489322fcf6648738134587faf767b6"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4c142852ae192e9fe5aad5c350ea6befe9db14370b34047e1f0f7cf99e63c63b"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:99a1e69d4e26f71e750e9ad6fdc8614fbddb67cfe2173a3628a2566034e223c7"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5ef3fbccb4058355053c51b82fd3501a6e13dd808c8d8cd2561e610c5456013c"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d6753305936eddc8ed190e006b7bb33a8f50b9854823485eed3a886857ab8d1"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0f3ca96af060a5250a8ad5a63699180bc780c2edf8abf96c58af175921df847a"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c4520047006b1d3f0d89e0532978c0688219857eb2fee7c48052560ae76aca1e"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-win32.whl", hash = "sha256:b2a0e3cf0caac2085ff172c3faacd1e00c376e6884b5bc4dd5b6b84623e29e4f"},
+    {file = "SQLAlchemy-2.0.29-cp310-cp310-win_amd64.whl", hash = "sha256:01d10638a37460616708062a40c7b55f73e4d35eaa146781c683e0fa7f6c43fb"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:308ef9cb41d099099fffc9d35781638986870b29f744382904bf9c7dadd08513"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:296195df68326a48385e7a96e877bc19aa210e485fa381c5246bc0234c36c78e"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a13b917b4ffe5a0a31b83d051d60477819ddf18276852ea68037a144a506efb9"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f6d971255d9ddbd3189e2e79d743ff4845c07f0633adfd1de3f63d930dbe673"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:61405ea2d563407d316c63a7b5271ae5d274a2a9fbcd01b0aa5503635699fa1e"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:de7202ffe4d4a8c1e3cde1c03e01c1a3772c92858837e8f3879b497158e4cb44"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-win32.whl", hash = "sha256:b5d7ed79df55a731749ce65ec20d666d82b185fa4898430b17cb90c892741520"},
+    {file = "SQLAlchemy-2.0.29-cp311-cp311-win_amd64.whl", hash = "sha256:205f5a2b39d7c380cbc3b5dcc8f2762fb5bcb716838e2d26ccbc54330775b003"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d96710d834a6fb31e21381c6d7b76ec729bd08c75a25a5184b1089141356171f"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:52de4736404e53c5c6a91ef2698c01e52333988ebdc218f14c833237a0804f1b"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c7b02525ede2a164c5fa5014915ba3591730f2cc831f5be9ff3b7fd3e30958e"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0dfefdb3e54cd15f5d56fd5ae32f1da2d95d78319c1f6dfb9bcd0eb15d603d5d"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a88913000da9205b13f6f195f0813b6ffd8a0c0c2bd58d499e00a30eb508870c"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fecd5089c4be1bcc37c35e9aa678938d2888845a134dd016de457b942cf5a758"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-win32.whl", hash = "sha256:8197d6f7a3d2b468861ebb4c9f998b9df9e358d6e1cf9c2a01061cb9b6cf4e41"},
+    {file = "SQLAlchemy-2.0.29-cp312-cp312-win_amd64.whl", hash = "sha256:9b19836ccca0d321e237560e475fd99c3d8655d03da80c845c4da20dda31b6e1"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:87a1d53a5382cdbbf4b7619f107cc862c1b0a4feb29000922db72e5a66a5ffc0"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a0732dffe32333211801b28339d2a0babc1971bc90a983e3035e7b0d6f06b93"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90453597a753322d6aa770c5935887ab1fc49cc4c4fdd436901308383d698b4b"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:ea311d4ee9a8fa67f139c088ae9f905fcf0277d6cd75c310a21a88bf85e130f5"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:5f20cb0a63a3e0ec4e169aa8890e32b949c8145983afa13a708bc4b0a1f30e03"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-win32.whl", hash = "sha256:e5bbe55e8552019c6463709b39634a5fc55e080d0827e2a3a11e18eb73f5cdbd"},
+    {file = "SQLAlchemy-2.0.29-cp37-cp37m-win_amd64.whl", hash = "sha256:c2f9c762a2735600654c654bf48dad388b888f8ce387b095806480e6e4ff6907"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7e614d7a25a43a9f54fcce4675c12761b248547f3d41b195e8010ca7297c369c"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:471fcb39c6adf37f820350c28aac4a7df9d3940c6548b624a642852e727ea586"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:988569c8732f54ad3234cf9c561364221a9e943b78dc7a4aaf35ccc2265f1930"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dddaae9b81c88083e6437de95c41e86823d150f4ee94bf24e158a4526cbead01"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:334184d1ab8f4c87f9652b048af3f7abea1c809dfe526fb0435348a6fef3d380"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:38b624e5cf02a69b113c8047cf7f66b5dfe4a2ca07ff8b8716da4f1b3ae81567"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-win32.whl", hash = "sha256:bab41acf151cd68bc2b466deae5deeb9e8ae9c50ad113444151ad965d5bf685b"},
+    {file = "SQLAlchemy-2.0.29-cp38-cp38-win_amd64.whl", hash = "sha256:52c8011088305476691b8750c60e03b87910a123cfd9ad48576d6414b6ec2a1d"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3071ad498896907a5ef756206b9dc750f8e57352113c19272bdfdc429c7bd7de"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:dba622396a3170974f81bad49aacebd243455ec3cc70615aeaef9e9613b5bca5"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b184e3de58009cc0bf32e20f137f1ec75a32470f5fede06c58f6c355ed42a72"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c37f1050feb91f3d6c32f864d8e114ff5545a4a7afe56778d76a9aec62638ba"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bda7ce59b06d0f09afe22c56714c65c957b1068dee3d5e74d743edec7daba552"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:25664e18bef6dc45015b08f99c63952a53a0a61f61f2e48a9e70cec27e55f699"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-win32.whl", hash = "sha256:77d29cb6c34b14af8a484e831ab530c0f7188f8efed1c6a833a2c674bf3c26ec"},
+    {file = "SQLAlchemy-2.0.29-cp39-cp39-win_amd64.whl", hash = "sha256:04c487305ab035a9548f573763915189fc0fe0824d9ba28433196f8436f1449c"},
+    {file = "SQLAlchemy-2.0.29-py3-none-any.whl", hash = "sha256:dc4ee2d4ee43251905f88637d5281a8d52e916a021384ec10758826f5cbae305"},
+    {file = "SQLAlchemy-2.0.29.tar.gz", hash = "sha256:bd9566b8e58cabd700bc367b60e90d9349cd16f0984973f98a9a09f9c64e86f0"},
 ]
 
 [package.dependencies]
@@ -2725,13 +2732,13 @@ doc = ["reno", "sphinx", "tornado (>=4.5)"]
 
 [[package]]
 name = "threadpoolctl"
-version = "3.3.0"
+version = "3.4.0"
 description = "threadpoolctl"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "threadpoolctl-3.3.0-py3-none-any.whl", hash = "sha256:6155be1f4a39f31a18ea70f94a77e0ccd57dced08122ea61109e7da89883781e"},
-    {file = "threadpoolctl-3.3.0.tar.gz", hash = "sha256:5dac632b4fa2d43f42130267929af3ba01399ef4bd1882918e92dbc30365d30c"},
+    {file = "threadpoolctl-3.4.0-py3-none-any.whl", hash = "sha256:8f4c689a65b23e5ed825c8436a92b818aac005e0f3715f6a1664d7c7ee29d262"},
+    {file = "threadpoolctl-3.4.0.tar.gz", hash = "sha256:f11b491a03661d6dd7ef692dd422ab34185d982466c49c8f98c8f716b5c93196"},
 ]
 
 [[package]]
@@ -2820,13 +2827,13 @@ opt-einsum = ["opt-einsum (>=3.3)"]
 
 [[package]]
 name = "torchmetrics"
-version = "1.3.1"
+version = "1.3.2"
 description = "PyTorch native Metrics"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "torchmetrics-1.3.1-py3-none-any.whl", hash = "sha256:a44bd1edee629bbf463eb81bfba8300b3785d8b3b8d758bdcafa862b80955b4f"},
-    {file = "torchmetrics-1.3.1.tar.gz", hash = "sha256:8d371f7597a1a5eb02d5f2ed59642d6fef09093926997ce91e18b1147cc8defa"},
+    {file = "torchmetrics-1.3.2-py3-none-any.whl", hash = "sha256:44ca3a9f86dc050cb3f554836ef291698ea797778457195b4f685fce8e2e64a3"},
+    {file = "torchmetrics-1.3.2.tar.gz", hash = "sha256:0a67694a4c4265eeb54cda741eaf5cb1f3a71da74b7e7e6215ad156c9f2379f6"},
 ]
 
 [package.dependencies]
@@ -2836,14 +2843,14 @@ packaging = ">17.1"
 torch = ">=1.10.0"
 
 [package.extras]
-all = ["SciencePlots (>=2.0.0)", "ipadic (>=1.0.0)", "matplotlib (>=3.3.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "mypy (==1.8.0)", "nltk (>=3.6)", "piq (<=0.8.0)", "pycocotools (>2.0.0)", "pystoi (>=0.3.0)", "regex (>=2021.9.24)", "scipy (>1.0.0)", "sentencepiece (>=0.1.98)", "torch (==2.2.0)", "torch-fidelity (<=0.4.0)", "torchaudio (>=0.10.0)", "torchvision (>=0.8)", "tqdm (>=4.41.0)", "transformers (>4.4.0)", "transformers (>=4.10.0)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
+all = ["SciencePlots (>=2.0.0)", "ipadic (>=1.0.0)", "matplotlib (>=3.3.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "mypy (==1.8.0)", "nltk (>=3.6)", "piq (<=0.8.0)", "pycocotools (>2.0.0)", "pystoi (>=0.3.0)", "regex (>=2021.9.24)", "scipy (>1.0.0)", "sentencepiece (>=0.2.0)", "torch (==2.2.1)", "torch-fidelity (<=0.4.0)", "torchaudio (>=0.10.0)", "torchvision (>=0.8)", "tqdm (>=4.41.0)", "transformers (>4.4.0)", "transformers (>=4.10.0)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
 audio = ["pystoi (>=0.3.0)", "torchaudio (>=0.10.0)"]
 detection = ["pycocotools (>2.0.0)", "torchvision (>=0.8)"]
-dev = ["SciencePlots (>=2.0.0)", "bert-score (==0.3.13)", "dython (<=0.7.5)", "fairlearn", "fast-bss-eval (>=0.1.0)", "faster-coco-eval (>=1.3.3)", "huggingface-hub (<0.21)", "ipadic (>=1.0.0)", "jiwer (>=2.3.0)", "kornia (>=0.6.7)", "lpips (<=0.1.4)", "matplotlib (>=3.3.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "mir-eval (>=0.6)", "monai (==1.3.0)", "mypy (==1.8.0)", "netcal (>1.0.0)", "nltk (>=3.6)", "numpy (<1.25.0)", "pandas (>1.0.0)", "pandas (>=1.4.0)", "piq (<=0.8.0)", "pycocotools (>2.0.0)", "pystoi (>=0.3.0)", "pytorch-msssim (==1.0.0)", "regex (>=2021.9.24)", "rouge-score (>0.1.0)", "sacrebleu (>=2.3.0)", "scikit-image (>=0.19.0)", "scipy (>1.0.0)", "sentencepiece (>=0.1.98)", "sewar (>=0.4.4)", "statsmodels (>0.13.5)", "torch (==2.2.0)", "torch-complex (<=0.4.3)", "torch-fidelity (<=0.4.0)", "torchaudio (>=0.10.0)", "torchvision (>=0.8)", "tqdm (>=4.41.0)", "transformers (>4.4.0)", "transformers (>=4.10.0)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
+dev = ["SciencePlots (>=2.0.0)", "bert-score (==0.3.13)", "dython (<=0.7.5)", "fairlearn", "fast-bss-eval (>=0.1.0)", "faster-coco-eval (>=1.3.3)", "huggingface-hub (<0.22)", "ipadic (>=1.0.0)", "jiwer (>=2.3.0)", "kornia (>=0.6.7)", "lpips (<=0.1.4)", "matplotlib (>=3.3.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "mir-eval (>=0.6)", "monai (==1.3.0)", "mypy (==1.8.0)", "netcal (>1.0.0)", "nltk (>=3.6)", "numpy (<1.25.0)", "pandas (>1.0.0)", "pandas (>=1.4.0)", "piq (<=0.8.0)", "pycocotools (>2.0.0)", "pystoi (>=0.3.0)", "pytorch-msssim (==1.0.0)", "regex (>=2021.9.24)", "rouge-score (>0.1.0)", "sacrebleu (>=2.3.0)", "scikit-image (>=0.19.0)", "scipy (>1.0.0)", "sentencepiece (>=0.2.0)", "sewar (>=0.4.4)", "statsmodels (>0.13.5)", "torch (==2.2.1)", "torch-complex (<=0.4.3)", "torch-fidelity (<=0.4.0)", "torchaudio (>=0.10.0)", "torchvision (>=0.8)", "tqdm (>=4.41.0)", "transformers (>4.4.0)", "transformers (>=4.10.0)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
 image = ["scipy (>1.0.0)", "torch-fidelity (<=0.4.0)", "torchvision (>=0.8)"]
 multimodal = ["piq (<=0.8.0)", "transformers (>=4.10.0)"]
-text = ["ipadic (>=1.0.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "nltk (>=3.6)", "regex (>=2021.9.24)", "sentencepiece (>=0.1.98)", "tqdm (>=4.41.0)", "transformers (>4.4.0)"]
-typing = ["mypy (==1.8.0)", "torch (==2.2.0)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
+text = ["ipadic (>=1.0.0)", "mecab-ko (>=1.0.0)", "mecab-ko-dic (>=1.0.0)", "mecab-python3 (>=1.0.6)", "nltk (>=3.6)", "regex (>=2021.9.24)", "sentencepiece (>=0.2.0)", "tqdm (>=4.41.0)", "transformers (>4.4.0)"]
+typing = ["mypy (==1.8.0)", "torch (==2.2.1)", "types-PyYAML", "types-emoji", "types-protobuf", "types-requests", "types-setuptools", "types-six", "types-tabulate"]
 visual = ["SciencePlots (>=2.0.0)", "matplotlib (>=3.3.0)"]
 
 [[package]]
@@ -3111,5 +3118,5 @@ multidict = ">=4.0"
 
 [metadata]
 lock-version = "2.0"
-python-versions = ">=3.9, <3.11"
-content-hash = "975625efdd8f132df288096d8e51b302f49513b35566fc1e7cd1ae3fdb5ef741"
+python-versions = ">=3.9, <3.12"
+content-hash = "c46f4647f117a5280e8b74844b45f4ad00d5d93b7b95640b0b1a58728b8ec71d"
diff --git a/pretrain.py b/pretrain.py
index 55374f8..c123fd4 100644
--- a/pretrain.py
+++ b/pretrain.py
@@ -13,16 +13,16 @@
 from sklearn.model_selection import train_test_split
 from torch.utils.data import DataLoader
 
-from lib.data import PretrainDataset
-from lib.tokenizer import ConceptTokenizer
-from lib.utils import (
+from odyssey.data.dataset import PretrainDataset
+from odyssey.data.tokenizer import ConceptTokenizer
+from odyssey.models.cehr_big_bird.model import BigBirdPretrain
+from odyssey.models.cehr_bert.model import BertPretrain
+from odyssey.models.utils import (
     get_run_id,
     load_config,
     load_pretrain_data,
     seed_everything,
 )
-from models.big_bird_cehr.model import BigBirdPretrain
-from models.cehr_bert.model import BertPretrain
 
 
 def main(args: Dict[str, Any], model_config: Dict[str, Any]) -> None:
diff --git a/pyproject.toml b/pyproject.toml
index bb1ad82..f0b1939 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,15 +1,18 @@
 [tool.poetry]
 name = "odyssey"
 version = "0.1.0"
-description = "A library for developing generalizable patient representation models"
-authors = ["Vector AI Engineering <cyclops@vectorinstitute.ai>"]
+description = "A toolkit to develop clinical foundation models using electronic health records"
+authors = ["Vector AI Engineering <odyssey@vectorinstitute.ai>"]
 license = "Apache-2.0"
 repository = "https://github.com/VectorInstitute/odyssey"
 documentation = "https://vectorinstitute.github.io/odyssey/"
+packages = [
+    { include = "odyssey" },
+]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.9, <3.11"
+python = ">=3.9, <3.12"
 keras = "2.15.0"
 lightning = "2.2.0"
 scikit-learn = "^1.2.2"
@@ -102,7 +105,7 @@ ignore = [
 "__init__.py" = ["E402", "F401", "F403", "F811"]
 
 [tool.ruff.lint.pep8-naming]
-ignore-names = ["X*", "setUp"]
+ignore-names = ["X*", "setUp", "tearDown"]
 
 [tool.ruff.lint.isort]
 lines-after-imports = 2
@@ -113,6 +116,11 @@ convention = "numpy"
 [tool.ruff.lint.pycodestyle]
 max-doc-length = 88
 
+[tool.coverage]
+    [tool.coverage.run]
+    source=["odyssey"]
+    omit=["tests/*", "*__init__.py"]
+
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
diff --git a/tests/data/test_collect.py b/tests/odyssey/data/mimiciv/test_collect.py
similarity index 89%
rename from tests/data/test_collect.py
rename to tests/odyssey/data/mimiciv/test_collect.py
index 226c76d..31852c0 100644
--- a/tests/data/test_collect.py
+++ b/tests/odyssey/data/mimiciv/test_collect.py
@@ -4,7 +4,11 @@
 import shutil
 from unittest import TestCase
 
-from data.collect import DATA_COLLECTION_CONFIG, PATIENT, FHIRDataCollector
+from odyssey.data.mimiciv.collect import (
+    DATA_COLLECTION_CONFIG,
+    PATIENT,
+    FHIRDataCollector,
+)
 
 
 class TestFHIRDataCollector(TestCase):
@@ -20,7 +24,7 @@ def setUp(self) -> None:
             buffer_size=10,
         )
 
-    def tearDown(self) -> None:
+    def tearDown(self) -> None:  # noqa: N802
         """Tear down FHIRDataCollector."""
         if os.path.exists(self.save_dir):
             shutil.rmtree(self.save_dir)