Merge pull request #68 from hubverse-org/mc/pass-through-initial-xaxis-range/48

implements [add a pass-through initial_xaxis_range option to predtimechart-config.yml files]

Author: matthewcornell

src/hub_predtimechart/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.1"
+__version__ = "2.2.0"

src/hub_predtimechart/generate_options.py

@@ -78,6 +78,6 @@ def get_max_ref_date_or_first_config_ref_date(reference_dates):
         options['disclaimer'] = hub_config.disclaimer
 
     # set `initial_xaxis_range`
-    options['initial_xaxis_range'] = None
+    options['initial_xaxis_range'] = hub_config.initial_xaxis_range if hub_config.initial_xaxis_range else None
 
     return options

src/hub_predtimechart/hub_config_ptc.py

@@ -7,7 +7,7 @@
 import pandas as pd
 import polars as pl
 import yaml
-from jsonschema import ValidationError, validate
+from jsonschema import ValidationError, validate, FormatChecker
 
 from hub_predtimechart.hub_config import HubConfig
 from hub_predtimechart.ptc_schema import ptc_config_schema
@@ -23,6 +23,7 @@ class HubConfigPtc(HubConfig):
     - horizon_col_name: ""
     - initial_checked_models: ""
     - disclaimer: ""
+    - initial_xaxis_range: "", or None if not passed
     - task_id_text: "". optional (None if not passed). keys: task_ids, values: value-to-text dict. ex:
         {'location': {'US': 'United States', '01': 'Alabama', ..., '78': 'Virgin Islands'},  ...}
     - target_data_file_name: either None (if the hub implements our new time-series target data standard) which means to
@@ -60,8 +61,9 @@ def __init__(self, hub_dir: Path, ptc_config_file: Path):
         self.horizon_col_name: str = ptc_config['horizon_col_name']
         self.initial_checked_models: str = ptc_config['initial_checked_models']
         self.disclaimer: str | None = ptc_config.get('disclaimer')  # optional
-        self.task_id_text: dict | None = ptc_config.get('task_id_text')  # optional
-        self.target_data_file_name: str | None = ptc_config.get('target_data_file_name')  # optional
+        self.initial_xaxis_range: str | None = ptc_config.get('initial_xaxis_range')  # ""
+        self.task_id_text: dict | None = ptc_config.get('task_id_text')  # ""
+        self.target_data_file_name: str | None = ptc_config.get('target_data_file_name')  # ""
 
         # set model_id_to_metadata
         self.model_id_to_metadata: dict[str, dict] = {}
@@ -129,8 +131,9 @@ def _validate_predtimechart_config(ptc_config: dict, tasks: dict):
     :param tasks: dict loaded from a 'tasks.json' file
     :raises ValidationError: if `ptc_config` is not valid
     """
-    # validate against the JSON Schema and then do additional validations
-    validate(ptc_config, ptc_config_schema)
+    # validate against the JSON Schema and then do additional validations. enable format checking for
+    # `initial_xaxis_range` `date` format
+    validate(ptc_config, ptc_config_schema, format_checker=FormatChecker())
 
     # validate: `rounds_idx`
     try:
@@ -167,7 +170,8 @@ def _validate_hub_ptc_compatibility(hub_config_ptc: HubConfigPtc):
         raise ValidationError(f"'designated_model' not found in model metadata schema's 'required' section")
 
     # validate: all model_task entries have the same task_ids. frozenset lets us make a set of sets
-    task_ids_all_model_tasks = [frozenset(model_task.task['task_ids'].keys()) for model_task in hub_config_ptc.model_tasks]
+    task_ids_all_model_tasks = [frozenset(model_task.task['task_ids'].keys()) for model_task in
+                                hub_config_ptc.model_tasks]
     if len(set(task_ids_all_model_tasks)) != 1:
         raise ValidationError(f"not all model_task entries have the same task_ids")
 

src/hub_predtimechart/ptc_schema.py

@@ -35,10 +35,18 @@
             }
         },
         "disclaimer": {
-            "description": "text providing any important information users should know",
+            "description": "optional text providing any important information users should know",
             "type": "string",
             "minLength": 1
         },
+        "initial_xaxis_range": {
+            "description": "`array` of two dates in 'YYYY-MM-DD' format that specify the initial xaxis range to use. To not initialize the range, pass `null` for its value",
+            "type": ["array", "null"],
+            "minItems": 2,
+            "maxItems": 2,
+            "uniqueItems": True,
+            "items": {"type": "string", "format": "date"}
+        },
         "task_id_text": {
             "description": "optional mapping of predtimechart task id values to text. keys are task_ids and values are an object whose keys are ptc task_id `value`s and values are ptc task_id `text`s",
             "type": "object",

tests/hub_predtimechart/test_generate_options.py

@@ -54,3 +54,13 @@ def test_generate_options_task_id_text_covid19_forecast_hub():
         exp_options = json.load(fp)
     act_options = ptc_options_for_hub(hub_config)
     assert act_options == exp_options
+
+
+def test_generate_options_initial_xaxis_range_covid19_forecast_hub():
+    hub_dir = Path('tests/hubs/covid19-forecast-hub')
+    hub_config = HubConfigPtc(hub_dir, hub_dir / 'hub-config/predtimechart-config-xaxis.yml')
+    with open('tests/expected/covid19-forecast-hub/predtimechart-options.json') as fp:
+        exp_options = json.load(fp)
+    exp_options['initial_xaxis_range'] = hub_config.initial_xaxis_range
+    act_options = ptc_options_for_hub(hub_config)
+    assert act_options == exp_options

tests/hubs/covid19-forecast-hub/hub-config/predtimechart-config-xaxis.yml

@@ -0,0 +1,68 @@
+---
+rounds_idx: 0
+reference_date_col_name: 'reference_date'
+target_date_col_name: 'target_end_date'
+horizon_col_name: 'horizon'
+initial_checked_models: [ ]
+task_id_text:
+  location: # location,location_name
+    "US": "United States"
+    "01": "Alabama"
+    "02": "Alaska"
+    "04": "Arizona"
+    "05": "Arkansas"
+    "06": "California"
+    "08": "Colorado"
+    "09": "Connecticut"
+    "10": "Delaware"
+    "11": "District of Columbia"
+    "12": "Florida"
+    "13": "Georgia"
+    "15": "Hawaii"
+    "16": "Idaho"
+    "17": "Illinois"
+    "18": "Indiana"
+    "19": "Iowa"
+    "20": "Kansas"
+    "21": "Kentucky"
+    "22": "Louisiana"
+    "23": "Maine"
+    "24": "Maryland"
+    "25": "Massachusetts"
+    "26": "Michigan"
+    "27": "Minnesota"
+    "28": "Mississippi"
+    "29": "Missouri"
+    "30": "Montana"
+    "31": "Nebraska"
+    "32": "Nevada"
+    "33": "New Hampshire"
+    "34": "New Jersey"
+    "35": "New Mexico"
+    "36": "New York"
+    "37": "North Carolina"
+    "38": "North Dakota"
+    "39": "Ohio"
+    "40": "Oklahoma"
+    "41": "Oregon"
+    "42": "Pennsylvania"
+    "44": "Rhode Island"
+    "45": "South Carolina"
+    "46": "South Dakota"
+    "47": "Tennessee"
+    "48": "Texas"
+    "49": "Utah"
+    "50": "Vermont"
+    "51": "Virginia"
+    "53": "Washington"
+    "54": "West Virginia"
+    "55": "Wisconsin"
+    "56": "Wyoming"
+    "60": "American Samoa"
+    "66": "Guam"
+    "69": "Northern Mariana Islands"
+    "72": "Puerto Rico"
+    "74": "U.S. Minor Outlying Islands"
+    "78": "Virgin Islands"
+target_data_file_name: 'covid-hospital-admissions.csv'
+initial_xaxis_range: ['2024-10-22', '2025-10-22']