From 10d2ab492b87e402ca42a5d3e4a90f9d8545a710 Mon Sep 17 00:00:00 2001
From: Samuel Brand <48288458+SamuelBrand1@users.noreply.github.com>
Date: Tue, 11 Feb 2025 18:30:20 +0000
Subject: [PATCH] Issue 66: simplify and split CI actions (#67)

* switch to more basic pre-commit from pyrenew

* remove concurrency

* Update .pre-commit-config.yaml

* Add back some hooks

* Update .pre-commit-config.yaml

* Delete .pre-commit-config_max.yaml

* add spelling pre-commit hook

* move script because not a "hook" anymore

* Create render-README.yaml

* Update render-README.yaml

* Update README.md

* Update .pre-commit-config.yaml

* revert pre-commit file minus readme render and with security hook

* pre-commit fixes

* minor test changes in quarto readme

---------

Co-authored-by: AFg6K7h4fhy2 <127630341+AFg6K7h4fhy2@users.noreply.github.com>
---
 .github/workflows/pre-commit.yaml          |   6 --
 .github/workflows/render-README.yaml       |  23 +++++
 .pre-commit-config.yaml                    |  77 ++++++++++----
 .secrets.baseline                          | 112 +++++++++++++++++++++
 README.md                                  |  29 ------
 README.qmd                                 |   2 +-
 forecasttools/__init__.py                  |   4 +-
 forecasttools/daily_to_epiweekly.py        |  18 +++-
 forecasttools/data.py                      |  64 +++++++++---
 forecasttools/idata_w_dates_to_df.py       |   5 +-
 forecasttools/recode_locations.py          |  24 +++--
 forecasttools/trajectories_to_quantiles.py |   4 +-
 forecasttools/utils.py                     |  12 ++-
 scripts/render-quarto-readme.sh            |  42 ++++++++
 tests/test_add_time_coords_to_idata.py     |   6 +-
 tests/test_recoding_locations.py           |  19 ++--
 16 files changed, 344 insertions(+), 103 deletions(-)
 create mode 100644 .github/workflows/render-README.yaml
 create mode 100644 .secrets.baseline
 create mode 100755 scripts/render-quarto-readme.sh

diff --git a/.github/workflows/pre-commit.yaml b/.github/workflows/pre-commit.yaml
index 800e852..bfe6623 100644
--- a/.github/workflows/pre-commit.yaml
+++ b/.github/workflows/pre-commit.yaml
@@ -13,10 +13,4 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: "3.12"
-    - name: Set up Quarto
-      uses: quarto-dev/quarto-actions/setup@v2
-    - name: Install Poetry
-      run: pip install poetry
-    - name: Install packages
-      run: poetry install --with dev
     - uses: pre-commit/action@v3.0.1
diff --git a/.github/workflows/render-README.yaml b/.github/workflows/render-README.yaml
new file mode 100644
index 0000000..c07803d
--- /dev/null
+++ b/.github/workflows/render-README.yaml
@@ -0,0 +1,23 @@
+name: render-readme
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  render-readme:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+      with:
+        python-version: "3.12"
+    - name: Set up Quarto
+      uses: quarto-dev/quarto-actions/setup@v2
+    - name: Install Poetry
+      run: pip install poetry
+    - name: Install packages
+      run: poetry install --with dev
+    - name: Render README
+      run: poetry run bash scripts/render-quarto-readme.sh
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index fd585c3..240ade7 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -13,7 +13,6 @@ repos:
     -   id: end-of-file-fixer
     -   id: mixed-line-ending
     -   id: trailing-whitespace
-
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0
     hooks:
@@ -56,41 +55,75 @@ repos:
     -   id: check-executables-have-shebangs
         files: \.sh$
 ################################################################################
-# QUARTO README RENDERING
+# PYTHON
 ################################################################################
--   repo: local
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.4
     hooks:
-    -   id: render-quarto-readme
-        name: "render README.qmd as README.md"
-        entry: "./scripts/hooks/render-quarto-readme.sh"
-        language: script
-        always_run: true
-        files: "README.(q|)md"
+    # "currently, the Ruff formatter does not sort imports.
+    # In order to both sort imports and format, call
+    # the Ruff linter and then the formatter:"
+    -   id: ruff
+        args: [
+          "check",
+          "--select",
+          # isort
+          "I",
+          "--fix"]
+    # run ruff linter; the Ruff Linter is an extremely fast Python linter
+    # designed as a drop-in replacement for Flake8 (plus dozens of plugins),
+    # isort, pydocstyle, pyupgrade, autoflake, and more
+    -   id: ruff
+        args: [
+          # ambiguous variable name: {name}
+          "--ignore=E741",
+          # do not assign a lambda expression, use a def
+          "--ignore=E731",
+          # found useless expression. ignore since .qmd displays
+          "--ignore=B018",
+          # {name} is too complex ({complexity} > {max_complexity})
+          # note: ignored on select repositories
+          "--ignore=C901",
+          # E and W: pycodestyle, standard PEP8 errors and pycodestyle warnings.
+          # F: pyflakes warnings (e.g., unused variables, undefined names).,
+          # B: flake8-bugbear (useful best practices).
+          # SIM: flake8-simplify
+          # C90: McCabe complexity (cyclomatic complexity).
+          # UP: pyupgrade, Python version compatibility
+          "--select=E,W,F,B,C90,UP,SIM",
+          # linter checks for lines, but doesn't fix, default is 88
+          "--line-length=79",
+          # lint all files in the current directory, and fix any fixable errors.
+          "--fix"]
+    # run the ruff-formatter; the Ruff formatter is an extremely fast
+    # Python code formatter designed as a drop-in replacement for Black
+    -   id: ruff-format
+        args: [
+          "--line-length=79",
+        ]
 ################################################################################
-# PYTHON
+# SECURITY
 ################################################################################
--   repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
-    hooks:
-    -   id: isort
-        args: ["--profile", "black", "--line-length", "79"]
--   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.3
+-   repo: https://github.com/Yelp/detect-secrets
+    rev: v1.5.0
     hooks:
-      - id: ruff
-        args: ["--ignore=E741", "--ignore=E731", "--fix"]
+    # must first run
+    # detect-secrets scan > .secrets.baseline
+    -   id: detect-secrets
+        args: ["--baseline", ".secrets.baseline"]
+        exclude: package.lock.json
 ################################################################################
 # GITHUB ACTIONS
 ################################################################################
 -   repo: https://github.com/rhysd/actionlint
-    rev: v1.7.4
+    rev: v1.7.7
     hooks:
     -   id: actionlint
 ################################################################################
 # SPELLING
 ################################################################################
 -   repo: https://github.com/crate-ci/typos
-    rev: typos-dict-v0.11.37
+    rev: typos-dict-v0.12.4
     hooks:
     -   id: typos
         args: ["--force-exclude"]
@@ -98,7 +131,7 @@ repos:
 # COMMIT MESSAGES
 ################################################################################
 -   repo: https://github.com/commitizen-tools/commitizen
-    rev: v4.1.0
+    rev: v4.1.1
     hooks:
     -   id: commitizen
 -   repo: https://github.com/jorisroovers/gitlint
diff --git a/.secrets.baseline b/.secrets.baseline
new file mode 100644
index 0000000..63f42f9
--- /dev/null
+++ b/.secrets.baseline
@@ -0,0 +1,112 @@
+{
+  "version": "1.4.0",
+  "plugins_used": [
+    {
+      "name": "ArtifactoryDetector"
+    },
+    {
+      "name": "AWSKeyDetector"
+    },
+    {
+      "name": "AzureStorageKeyDetector"
+    },
+    {
+      "name": "Base64HighEntropyString",
+      "limit": 4.5
+    },
+    {
+      "name": "BasicAuthDetector"
+    },
+    {
+      "name": "CloudantDetector"
+    },
+    {
+      "name": "DiscordBotTokenDetector"
+    },
+    {
+      "name": "GitHubTokenDetector"
+    },
+    {
+      "name": "HexHighEntropyString",
+      "limit": 3.0
+    },
+    {
+      "name": "IbmCloudIamDetector"
+    },
+    {
+      "name": "IbmCosHmacDetector"
+    },
+    {
+      "name": "JwtTokenDetector"
+    },
+    {
+      "name": "KeywordDetector",
+      "keyword_exclude": ""
+    },
+    {
+      "name": "MailchimpDetector"
+    },
+    {
+      "name": "NpmDetector"
+    },
+    {
+      "name": "PrivateKeyDetector"
+    },
+    {
+      "name": "SendGridDetector"
+    },
+    {
+      "name": "SlackDetector"
+    },
+    {
+      "name": "SoftlayerDetector"
+    },
+    {
+      "name": "SquareOAuthDetector"
+    },
+    {
+      "name": "StripeDetector"
+    },
+    {
+      "name": "TwilioKeyDetector"
+    }
+  ],
+  "filters_used": [
+    {
+      "path": "detect_secrets.filters.allowlist.is_line_allowlisted"
+    },
+    {
+      "path": "detect_secrets.filters.common.is_ignored_due_to_verification_policies",
+      "min_level": 2
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_indirect_reference"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_likely_id_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_lock_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_not_alphanumeric_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_potential_uuid"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_prefixed_with_dollar_sign"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_sequential_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_swagger_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_templated_secret"
+    }
+  ],
+  "results": {},
+  "generated_at": "2023-09-24T19:52:08Z"
+}
diff --git a/README.md b/README.md
index 0c0fea0..1d4c87c 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,6 @@
 render a GitHub README, see
 <https://quarto.org/docs/output-formats/gfm.html>
 -->
-
 <!-- ```{python}
 #| echo: false
 import polars as pl
@@ -34,9 +33,7 @@ Notes:
   [pyrenew-hew](https://github.com/CDCgov/pyrenew-hew).
 
 <details>
-
 <summary>
-
 A Tentative Utilities Diagram
 </summary>
 
@@ -384,9 +381,7 @@ given the expectation that no one would ever call it; however, for
 reproducibility’s sake, the following is included here)
 
 <details>
-
 <summary>
-
 Some Of The Forecast Code
 </summary>
 
@@ -762,9 +757,7 @@ CDC use of GitHub does not imply an endorsement of any one particular
 service, product, or enterprise.
 
 <details>
-
 <summary>
-
 Rules, Policy, And Collaboration
 </summary>
 
@@ -776,14 +769,10 @@ Rules, Policy, And Collaboration
 - [Code of Conduct](./rules-and-policies/code-of-conduct.md)
 
 </details>
-
 <details>
-
 <summary>
-
 Public Domain Standard Notice
 </summary>
-
 This repository constitutes a work of the United States Government and
 is not subject to domestic copyright protection under 17 USC § 105. This
 repository is in the public domain within the United States, and
@@ -794,11 +783,8 @@ contributions to this repository will be released under the CC0
 dedication. By submitting a pull request you are agreeing to comply with
 this waiver of copyright interest.
 </details>
-
 <details>
-
 <summary>
-
 License Standard Notice
 </summary>
 
@@ -821,25 +807,18 @@ http://www.apache.org/licenses/LICENSE-2.0.html
 The source code forked from other open source projects will inherit its
 license.
 </details>
-
 <details>
-
 <summary>
-
 Privacy Standard Notice
 </summary>
-
 This repository contains only non-sensitive, publicly available data and
 information. All material and community participation is covered by the
 [Disclaimer](DISCLAIMER.md) and [Code of Conduct](code-of-conduct.md).
 For more information about CDC’s privacy policy, please visit
 [http://www.cdc.gov/other/privacy.html](https://www.cdc.gov/other/privacy.html).
 </details>
-
 <details>
-
 <summary>
-
 Contributing Standard Notice
 </summary>
 
@@ -857,27 +836,19 @@ through CDC including this GitHub page may be subject to applicable
 federal law, including but not limited to the Federal Records Act, and
 may be archived. Learn more at <http://www.cdc.gov/other/privacy.html>.
 </details>
-
 <details>
-
 <summary>
-
 Records Management Standard Notice
 </summary>
-
 This repository is not a source of government records, but is a copy to
 increase collaboration and collaborative potential. All government
 records will be published through the [CDC web
 site](http://www.cdc.gov).
 </details>
-
 <details>
-
 <summary>
-
 Additional Standard Notices
 </summary>
-
 Please refer to [CDC’s Template
 Repository](https://github.com/CDCgov/template) for more information
 about [contributing to this
diff --git a/README.qmd b/README.qmd
index 1567f3f..2c717fc 100644
--- a/README.qmd
+++ b/README.qmd
@@ -230,7 +230,7 @@ print(idata_w_dates["observed_data"]["obs"]["obs_dim_0"][:15])
 ```{python}
 # idata without dates as coordinates
 idata_wo_dates = forecasttools.nhsn_flu_forecast_wo_dates
-print(idata_wo_dates["observed_data"]["obs"]["obs_dim_0"][:15])
+print(idata_wo_dates["observed_data"]["obs"]["obs_dim_0"][:20])
 ```
 
 The forecast was generated following the creation of `nhsn_hosp_flu.csv` (see previous section) by running `data.py` with the following added:
diff --git a/forecasttools/__init__.py b/forecasttools/__init__.py
index 023c3f3..b191a96 100644
--- a/forecasttools/__init__.py
+++ b/forecasttools/__init__.py
@@ -32,7 +32,9 @@
     "location_table.parquet"
 )
 location_table = pl.read_parquet(location_table_path)
-united_states = location_table.filter(pl.col("is_state")).get_column("long_name").to_list()
+united_states = (
+    location_table.filter(pl.col("is_state")).get_column("long_name").to_list()
+)
 
 # load example flusight submission
 example_flusight_submission_path = importlib.resources.files(
diff --git a/forecasttools/daily_to_epiweekly.py b/forecasttools/daily_to_epiweekly.py
index 4c1a013..7cd628e 100644
--- a/forecasttools/daily_to_epiweekly.py
+++ b/forecasttools/daily_to_epiweekly.py
@@ -31,7 +31,7 @@ def df_aggregate_to_epiweekly(
     df: pl.DataFrame,
     value_col: str = "value",
     date_col: str = "date",
-    id_cols: str | list[str] = ["draw"],
+    id_cols: list[str] = None,
     weekly_value_name: str = "weekly_value",
     strict: bool = True,
 ) -> pl.DataFrame:
@@ -72,6 +72,9 @@ def df_aggregate_to_epiweekly(
         A dataframe with value_col aggregated
         across epiweek and epiyear.
     """
+    # set default id_cols
+    if id_cols is None:
+        id_cols = ["draw"]
     id_cols = ensure_listlike(id_cols)
     # add epiweek and epiyear columns
     df = df.with_columns(
@@ -89,6 +92,16 @@ def df_aggregate_to_epiweekly(
     n_elements = grouped_df.agg(pl.count().alias("n_elements"))
     problematic_trajectories = n_elements.filter(pl.col("n_elements") > 7)
     if not problematic_trajectories.is_empty():
+        message = (
+            f"Problematic trajectories with more than"
+            f" 7 values per epiweek per year: {problematic_trajectories}"
+        )
+        raise ValueError(
+            f"At least one trajectory has more than 7 values for a given"
+            f" epiweek of a given year.\n{message}"
+        )
+    # check if any week has more than 7 dates
+    if not n_elements["n_elements"].to_numpy().max() <= 7:
         raise ValueError(
             "At least one trajectory has more than 7 values "
             "for a given epiweek of a given epiyear.\n"
@@ -96,7 +109,8 @@ def df_aggregate_to_epiweekly(
             "values: "
             f"{problematic_trajectories}"
         )
-
+    # if strict, filter out groups that do not have exactly 7
+    # contributing dates
     if strict:
         valid_groups = n_elements.filter(pl.col("n_elements") == 7)
         df = df.join(
diff --git a/forecasttools/data.py b/forecasttools/data.py
index b15bf23..8746f89 100644
--- a/forecasttools/data.py
+++ b/forecasttools/data.py
@@ -7,8 +7,6 @@
 an example FluSight submission.
 """
 
-
-
 import os
 import pathlib
 from urllib import error, request
@@ -64,7 +62,6 @@ def check_file_save_path(
         raise FileExistsError(f"File already exists at: {file_save_path}")
 
 
-
 def merge_pop_data_and_loc_data(
     file_save_path: str,
     population_file_path: str,
@@ -109,16 +106,56 @@ def merge_pop_data_and_loc_data(
         print(f"File already exists at {save_path}. Skipping writing.")
         return
     us_states = [
-        "Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado",
-        "Connecticut", "Delaware", "Florida", "Georgia", "Hawaii", "Idaho",
-        "Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana",
-        "Maine", "Maryland", "Massachusetts", "Michigan", "Minnesota",
-        "Mississippi", "Missouri", "Montana", "Nebraska", "Nevada",
-        "New Hampshire", "New Jersey", "New Mexico", "New York",
-        "North Carolina", "North Dakota", "Ohio", "Oklahoma", "Oregon",
-        "Pennsylvania", "Rhode Island", "South Carolina", "South Dakota",
-        "Tennessee", "Texas", "Utah", "Vermont", "Virginia", "Washington",
-        "West Virginia", "Wisconsin", "Wyoming"
+        "Alabama",
+        "Alaska",
+        "Arizona",
+        "Arkansas",
+        "California",
+        "Colorado",
+        "Connecticut",
+        "Delaware",
+        "Florida",
+        "Georgia",
+        "Hawaii",
+        "Idaho",
+        "Illinois",
+        "Indiana",
+        "Iowa",
+        "Kansas",
+        "Kentucky",
+        "Louisiana",
+        "Maine",
+        "Maryland",
+        "Massachusetts",
+        "Michigan",
+        "Minnesota",
+        "Mississippi",
+        "Missouri",
+        "Montana",
+        "Nebraska",
+        "Nevada",
+        "New Hampshire",
+        "New Jersey",
+        "New Mexico",
+        "New York",
+        "North Carolina",
+        "North Dakota",
+        "Ohio",
+        "Oklahoma",
+        "Oregon",
+        "Pennsylvania",
+        "Rhode Island",
+        "South Carolina",
+        "South Dakota",
+        "Tennessee",
+        "Texas",
+        "Utah",
+        "Vermont",
+        "Virginia",
+        "Washington",
+        "West Virginia",
+        "Wisconsin",
+        "Wyoming",
     ]
     pop_df = pl.read_parquet(population_path).select(
         [
@@ -144,7 +181,6 @@ def merge_pop_data_and_loc_data(
     print(f"File successfully written to {save_path}")
 
 
-
 def make_census_dataset(
     file_save_path: str,
 ) -> None:
diff --git a/forecasttools/idata_w_dates_to_df.py b/forecasttools/idata_w_dates_to_df.py
index 661b657..6e14dcb 100644
--- a/forecasttools/idata_w_dates_to_df.py
+++ b/forecasttools/idata_w_dates_to_df.py
@@ -175,7 +175,7 @@ def add_time_coords_to_idata_dimension(
     )
     # will change when xarray supports
     # numpy.dtype("datetime64[D]")
-    if not interval_dates.dtype == np.dtype("datetime64[ns]"):
+    if interval_dates.dtype != np.dtype("datetime64[ns]"):
         interval_dates = interval_dates.astype("datetime64[ns]")
     idata_group = idata_group.assign_coords({dimension: interval_dates})
     setattr(idata, group, idata_group)
@@ -269,7 +269,8 @@ def add_time_coords_to_idata_dimensions(
             )
         except ValueError as e:
             raise ValueError(
-                f"Error for (group={group}, variable={variable}, dimension={dimension})."
+                f"Error for (group={group}, variable={variable},"
+                f" dimension={dimension})."
             ) from e
 
     return idata
diff --git a/forecasttools/recode_locations.py b/forecasttools/recode_locations.py
index 7db5268..44f5d08 100644
--- a/forecasttools/recode_locations.py
+++ b/forecasttools/recode_locations.py
@@ -51,7 +51,8 @@ def loc_abbr_to_hubverse_code(
     # in the inputted dataframe
     if location_col not in df.columns:
         raise ValueError(
-            f"Column '{location_col}' not found in the dataframe; got {df.columns}."
+            f"Column '{location_col}' not found in the dataframe;"
+            f" got {df.columns}."
         )
     # get location table from forecasttools
     loc_table = forecasttools.location_table
@@ -62,7 +63,8 @@ def loc_abbr_to_hubverse_code(
     difference = location_values.difference(valid_values)
     if difference:
         raise ValueError(
-            f"The following values in '{location_col}') are not valid jurisdictional codes: {difference}."
+            f"The following values in '{location_col}') are not valid"
+            f" jurisdictional codes: {difference}."
         )
     # recode existing location abbreviations
     # with location codes
@@ -117,7 +119,8 @@ def loc_hubverse_code_to_abbr(
     # in the inputted dataframe
     if location_col not in df.columns:
         raise ValueError(
-            f"Column '{location_col}' not found in the dataframe; got {df.columns}."
+            f"Column '{location_col}' not found in the dataframe;"
+            f" got {df.columns}."
         )
     # get location table from forecasttools
     loc_table = forecasttools.location_table
@@ -128,7 +131,8 @@ def loc_hubverse_code_to_abbr(
     difference = location_values.difference(valid_values)
     if difference:
         raise ValueError(
-            f"Some values in {difference} (in col '{location_col}') are not valid jurisdictional codes."
+            f"Some values in {difference} (in col '{location_col}')"
+            f" are not valid jurisdictional codes."
         )
     # recode existing location codes with
     # with location abbreviations
@@ -161,9 +165,9 @@ def to_location_table_column(location_format: str) -> str:
         from the location table.
     """
     # check inputted variable type
-    assert isinstance(
-        location_format, str
-    ), f"Expected a string; got {type(location_format)}."
+    assert isinstance(location_format, str), (
+        f"Expected a string; got {type(location_format)}."
+    )
     # return proper column name from input format
     col_dict = {
         "abbr": "short_name",
@@ -173,7 +177,8 @@ def to_location_table_column(location_format: str) -> str:
     col = col_dict.get(location_format)
     if col is None:
         raise KeyError(
-            f"Unknown location format {location_format}. Expected one of:\n{col_dict.keys()}."
+            f"Unknown location format {location_format}."
+            f" Expected one of:\n{col_dict.keys()}."
         )
     return col
 
@@ -224,7 +229,8 @@ def location_lookup(
     valid_formats = ["abbr", "hubverse", "long_name"]
     if location_format not in valid_formats:
         raise ValueError(
-            f"Invalid location format '{location_format}'. Expected one of: {valid_formats}."
+            f"Invalid location format '{location_format}'."
+            f" Expected one of: {valid_formats}."
         )
     # check that location vector not empty
     if not location_vector:
diff --git a/forecasttools/trajectories_to_quantiles.py b/forecasttools/trajectories_to_quantiles.py
index 4812a1f..301413d 100644
--- a/forecasttools/trajectories_to_quantiles.py
+++ b/forecasttools/trajectories_to_quantiles.py
@@ -10,7 +10,7 @@
 def trajectories_to_quantiles(
     trajectories: pl.DataFrame,
     quantiles: list[float] = None,
-    timepoint_cols: list[str] = ["timepoint"],
+    timepoint_cols: list[str] = None,
     value_col_name: str = "value",
     quantile_value_name: str = "quantile_value",
     quantile_level_name: str = "quantile_level",
@@ -67,6 +67,8 @@ def trajectories_to_quantiles(
             + [0.05 * elt for elt in range(1, 20)]
             + [0.975, 0.99]
         )
+    if timepoint_cols is None:
+        timepoint_cols = ["timepoint"]
 
     # group trajectories based on timepoint_cols and id_cols
     group_cols = (
diff --git a/forecasttools/utils.py b/forecasttools/utils.py
index 312e9b7..c64fe05 100644
--- a/forecasttools/utils.py
+++ b/forecasttools/utils.py
@@ -18,12 +18,14 @@ def validate_input_type(
     if isinstance(expected_type, tuple):
         if not any(isinstance(value, t) for t in expected_type):
             raise TypeError(
-                f"Parameter '{param_name}' must be one of the types {expected_type}; got {type(value)}"
+                f"Parameter '{param_name}' must be one of the types"
+                f" {expected_type}; got {type(value)}."
             )
     else:
         if not isinstance(value, expected_type):
             raise TypeError(
-                f"Parameter '{param_name}' must be of type '{expected_type.__name__}'; got {type(value)}"
+                f"Parameter '{param_name}' must be of type"
+                f" '{expected_type.__name__}'; got {type(value)}."
             )
 
 
@@ -55,7 +57,8 @@ def validate_idata_group_var_dim(variable_data: xr.DataArray, dimension: str):
     exists in the variable."""
     if dimension not in variable_data.dims:
         raise ValueError(
-            f"Dimension '{dimension}' not found in variable dimensions: '{variable_data.dims}'."
+            f"Dimension '{dimension}' not found in variable dimensions:"
+            f" '{variable_data.dims}'."
         )
 
 
@@ -69,7 +72,8 @@ def validate_iter_has_expected_types(
     """
     if not all(isinstance(item, expected_type) for item in iterable):
         raise TypeError(
-            f"All items in '{param_name}' must be of type '{expected_type.__name__}'."
+            f"All items in '{param_name}' must be of type"
+            f" '{expected_type.__name__}'."
         )
 
 
diff --git a/scripts/render-quarto-readme.sh b/scripts/render-quarto-readme.sh
new file mode 100755
index 0000000..4853daf
--- /dev/null
+++ b/scripts/render-quarto-readme.sh
@@ -0,0 +1,42 @@
+#!/bin/bash
+
+set -e # halt execution if non-zero status
+
+# is quarto command available?
+if ! command -v quarto &> /dev/null; then
+  echo "Quarto is not installed. Please install it to use this hook."
+  exit 1
+fi
+
+# is poetry command available?
+if ! command -v poetry &> /dev/null; then
+  echo "Poetry is not installed. Please install it to use this hook."
+  exit 1
+fi
+
+echo "Rendering README.md from README.qmd..."
+poetry run quarto render README.qmd
+
+# prompt user to stage/commit README
+# if there is a change
+if [[ -f README.md ]]; then
+
+  # make sure considered in diff but not
+  # actually staged
+  git add --intent-to-add README.md
+
+  # dont want --cached because want unstaged
+  # stages to show up as a diff
+  if ! git diff --quiet --exit-code README.md; then
+
+    echo "README.md has been modified by this hook."
+    echo "Changes staged. Please commit the updated README.md."
+    # the presence of "exit 1" here has been
+    # debated
+  else
+    echo "README.md is up to date."
+  fi
+else
+  echo "README.md not found. Something went wrong."
+  exit 1
+fi
diff --git a/tests/test_add_time_coords_to_idata.py b/tests/test_add_time_coords_to_idata.py
index 512d56a..4006eda 100644
--- a/tests/test_add_time_coords_to_idata.py
+++ b/tests/test_add_time_coords_to_idata.py
@@ -373,9 +373,9 @@ def test_ensure_listlike(input_value, expected_output):
     unchanged.
     """
     out = forecasttools.ensure_listlike(input_value)
-    assert (
-        out == expected_output
-    ), f"Expected {expected_output}, but got {out}."
+    assert out == expected_output, (
+        f"Expected {expected_output}, but got {out}."
+    )
 
 
 @pytest.mark.parametrize(
diff --git a/tests/test_recoding_locations.py b/tests/test_recoding_locations.py
index 37ffe7f..d8107bd 100644
--- a/tests/test_recoding_locations.py
+++ b/tests/test_recoding_locations.py
@@ -36,9 +36,9 @@ def test_recode_valid_location_correct_input(
     """
     df_w_loc_recoded = function(df=df, location_col=location_col)
     loc_output = df_w_loc_recoded["location"].to_list()
-    assert (
-        loc_output == expected_output
-    ), f"Expected {expected_output}, Got: {loc_output}"
+    assert loc_output == expected_output, (
+        f"Expected {expected_output}, Got: {loc_output}"
+    )
 
 
 @pytest.mark.parametrize(
@@ -138,9 +138,10 @@ def test_to_location_table_column_correct_input(
     when given different location formats.
     """
     result_column = forecasttools.to_location_table_column(location_format)
-    assert (
-        result_column == expected_column
-    ), f"Expected column '{expected_column}' for format '{location_format}', but got '{result_column}'"
+    assert result_column == expected_column, (
+        f"Expected column '{expected_column}'"
+        f" for format '{location_format}', but got '{result_column}'."
+    )
 
 
 @pytest.mark.parametrize(
@@ -194,6 +195,6 @@ def test_location_lookup_exceptions(
         result = forecasttools.location_lookup(
             location_vector, location_format
         )
-        assert isinstance(
-            result, pl.DataFrame
-        ), "Expected a Polars DataFrame as output."
+        assert isinstance(result, pl.DataFrame), (
+            "Expected a Polars DataFrame as output."
+        )