Merge pull request #37 from zsarnoczay/master

azs - mostly updates related to water network damage simulation and working with custom DL models

.github/workflows/deploy_to_pypi.yaml

@@ -0,0 +1,32 @@
+name: Deploy to PyPI
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install setuptools wheel twine
+
+      - name: Build package
+        run: |
+          python setup.py sdist bdist_wheel
+
+      - name: Publish package to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: zsarnoczay
+          password: ${{ secrets.PELICUN_GITHUB_TOKEN }}

pelicun/__init__.py

@@ -41,7 +41,7 @@
 
 name = "pelicun"
 
-__version__ = '3.2b9'
+__version__ = '3.2'
 
 __copyright__ = ("Copyright (c) 2018 Leland Stanford "
                  "Junior University and The Regents "

pelicun/assessment.py

@@ -90,7 +90,7 @@ def __init__(self, config_options=None):
 
         self.options = base.Options(config_options, self)
 
-        self.unit_conversion_factors = file_io.parse_units(
+        self.unit_conversion_factors = base.parse_units(
             self.options.units_file)
 
         self.log = self.options.log

pelicun/base.py

@@ -57,12 +57,16 @@
     int_or_None
     process_loc
     dedupe_index
+    dict_raise_on_duplicates
+    parse_units
+    convert_units
 
     Options
     Logger
 
 """
 
+from __future__ import annotations
 import os
 import sys
 from datetime import datetime
@@ -1076,3 +1080,180 @@ def dedupe_index(dataframe, dtype=str):
     # Placeholder for advanced calculations
     'One':                            'ONE'
 }
+
+
+def dict_raise_on_duplicates(ordered_pairs):
+    """
+    Reject duplicate keys.
+
+    https://stackoverflow.com/questions/14902299/
+    json-loads-allows-duplicate-keys-
+    in-a-dictionary-overwriting-the-first-value
+
+    """
+    d = {}
+    for k, v in ordered_pairs:
+        if k in d:
+            raise ValueError(f"duplicate key: {k}")
+        d[k] = v
+    return d
+
+
+def parse_units(custom_file=None, preserve_categories=False):
+    """
+    Parse the unit conversion factor JSON file and return a dictionary.
+
+    Parameters
+    ----------
+    custom_file: str, optional
+        If a custom file is provided, only the units specified in the
+        custom file are used.
+
+    Raises
+    ------
+    KeyError
+        If a key is defined twice.
+    ValueError
+        If a unit conversion factor is not a float.
+    FileNotFoundError
+        If a file does not exist.
+    Exception
+        If a file does not have the JSON format.
+    """
+
+    def get_contents(file_path, preserve_categories=False):
+        try:
+            with open(file_path, 'r', encoding='utf-8') as f:
+                dictionary = json.load(f, object_pairs_hook=dict_raise_on_duplicates)
+        except FileNotFoundError as exc:
+            raise FileNotFoundError(f'{file_path} was not found.') from exc
+        except json.decoder.JSONDecodeError as exc:
+            raise ValueError(f'{file_path} is not a valid JSON file.') from exc
+        for category_dict in list(dictionary.values()):
+            # ensure all first-level keys point to a dictionary
+            if not isinstance(category_dict, dict):
+                raise ValueError(
+                    f'{file_path} contains first-level keys '
+                    'that don\'t point to a dictionary'
+                )
+            # convert values to float
+            for key, val in category_dict.items():
+                try:
+                    category_dict[key] = float(val)
+                except (ValueError, TypeError) as exc:
+                    raise type(exc)(
+                        f'Unit {key} has a value of {val} '
+                        'which cannot be interpreted as a float'
+                    ) from exc
+
+        if preserve_categories:
+            return dictionary
+
+        flattened = {}
+        for category in dictionary:
+            for unit_name, factor in dictionary[category].items():
+                if unit_name in flattened:
+                    raise ValueError(f'{unit_name} defined twice in {file_path}.')
+                flattened[unit_name] = factor
+
+        return flattened
+
+    if custom_file:
+        return get_contents(custom_file, preserve_categories)
+
+    return get_contents(
+        pelicun_path / "settings/default_units.json", preserve_categories
+    )
+
+
+def convert_units(
+    values: (float | list[float] | np.ndarray),
+    unit: str,
+    to_unit: str,
+    category: (str | None) = None
+) -> (float | list[float] | np.ndarray):
+    """
+    Converts numeric values between different units.
+
+    Supports conversion within a specified category of units and
+    automatically infers the category if not explicitly provided. It
+    maintains the type of the input in the output.
+
+    Parameters
+    ----------
+    values (float | list[float] | np.ndarray):
+      The numeric value(s) to convert.
+    unit (str):
+      The current unit of the values.
+    to_unit (str):
+      The target unit to convert the values into.
+    category (Optional[str]):
+      The category of the units (e.g., 'length', 'pressure'). If not
+      provided, the category will be inferred based on the provided
+      units.
+
+    Returns
+    -------
+    (float | list[float] | np.ndarray):
+      The converted value(s) in the target unit, in the same data type
+      as the input values.
+
+    Raises
+    ------
+    TypeError:
+      If the input `values` are not of type float, list, or
+      np.ndarray.
+    ValueError:
+      If the `unit`, `to_unit`, or `category` is unknown or if `unit`
+      and `to_unit` are not in the same category.
+
+    """
+
+    if isinstance(values, (float, list)):
+        vals = np.atleast_1d(values)
+    elif isinstance(values, np.ndarray):
+        vals = values
+    else:
+        raise TypeError('Invalid input type for `values`')
+
+    # load default units
+    all_units = parse_units(preserve_categories=True)
+
+    # if a category is given use it, otherwise try to determine it
+    if category:
+        if category not in all_units:
+            raise ValueError(f'Unknown category: `{category}`')
+        units = all_units[category]
+        for unt in unit, to_unit:
+            if unt not in units:
+                raise ValueError(
+                    f'Unknown unit: `{unt}`'
+                )
+    else:
+        unit_category: (str | None) = None
+        for key in all_units:
+            units = all_units[key]
+            if unit in units:
+                unit_category = key
+                break
+        if not unit_category:
+            raise ValueError(f'Unknown unit `{unit}`')
+        units = all_units[unit_category]
+        if to_unit not in units:
+            raise ValueError(
+                f'`{unit}` is a `{unit_category}` unit, but `{to_unit}` '
+                f'is not specified in that category.'
+            )
+
+    # convert units
+    from_factor = units[unit]
+    to_factor = units[to_unit]
+    new_values = vals * from_factor / to_factor
+
+    # return the results in the same type as that of the provided
+    # values
+    if isinstance(values, float):
+        return new_values[0]
+    if isinstance(values, list):
+        return new_values.tolist()
+    return new_values

pelicun/file_io.py

@@ -47,20 +47,17 @@
 
 .. autosummary::
 
-    dict_raise_on_duplicates
     get_required_resources
     save_to_csv
     load_data
     load_from_file
-    parse_units
 
 """
 
-import json
 from pathlib import Path
 import numpy as np
 import pandas as pd
-from . import base
+from pelicun import base
 
 
 convert_dv_name = {
@@ -94,23 +91,6 @@
 }
 
 
-def dict_raise_on_duplicates(ordered_pairs):
-    """
-    Reject duplicate keys.
-
-    https://stackoverflow.com/questions/14902299/
-    json-loads-allows-duplicate-keys-
-    in-a-dictionary-overwriting-the-first-value
-
-    """
-    d = {}
-    for k, v in ordered_pairs:
-        if k in d:
-            raise ValueError(f"duplicate key: {k}")
-        d[k] = v
-    return d
-
-
 def save_to_csv(data, filepath, units=None, unit_conversion_factors=None,
                 orientation=0, use_simpleindex=True, log=None):
     """
@@ -453,66 +433,3 @@ def load_from_file(filepath, log=None):
                          f'to load from csv: {filepath}')
 
     return data
-
-
-def parse_units(custom_file=None):
-    """
-    Parse the unit conversion factor JSON file and return a dictionary.
-
-    Parameters
-    ----------
-    custom_file: str, optional
-        If a custom file is provided, only the units specified in the
-        custom file are used.
-
-    Raises
-    ------
-    KeyError
-        If a key is defined twice.
-    ValueError
-        If a unit conversion factor is not a float.
-    FileNotFoundError
-        If a file does not exist.
-    Exception
-        If a file does not have the JSON format.
-    """
-
-    def get_contents(file_path):
-        try:
-            with open(file_path, 'r', encoding='utf-8') as f:
-                dictionary = json.load(
-                    f, object_pairs_hook=dict_raise_on_duplicates)
-        except FileNotFoundError as exc:
-            raise FileNotFoundError(
-                f'{file_path} was not found.') from exc
-        except json.decoder.JSONDecodeError as exc:
-            raise ValueError(
-                f'{file_path} is not a valid JSON file.') from exc
-        for category_dict in list(dictionary.values()):
-            # ensure all first-level keys point to a dictionary
-            if not isinstance(category_dict, dict):
-                raise ValueError(
-                    f'{file_path} contains first-level keys '
-                    'that don\'t point to a dictionary')
-            # convert values to float
-            for key, val in category_dict.items():
-                try:
-                    category_dict[key] = float(val)
-                except (ValueError, TypeError) as exc:
-                    raise type(exc)(
-                        f'Unit {key} has a value of {val} '
-                        'which cannot be interpreted as a float') from exc
-
-        flattened = {}
-        for category in dictionary:
-            for unit_name, factor in dictionary[category].items():
-                if unit_name in flattened:
-                    raise ValueError(f'{unit_name} defined twice in {file_path}.')
-                flattened[unit_name] = factor
-
-        return flattened
-
-    if custom_file:
-        return get_contents(custom_file)
-
-    return get_contents(base.pelicun_path / "settings/default_units.json")

pelicun/resources/SimCenterDBDL/damage_DB_Hazus_EQ_water.csv

@@ -0,0 +1,5 @@
+ID,Incomplete,Demand-Type,Demand-Unit,Demand-Offset,Demand-Directional,LS1-Family,LS1-Theta_0,LS1-DamageStateWeights
+PWP.B.GS,0,Peak Ground Velocity,cmps,0,0,multilinear_CDF,"0.1,2,3,4,5,6,8,10,15,20,30,40,50,60,80,100,150,200,300,400,500,579|0.00,0.00000290,0.00000722,0.00001379,0.00002279,0.00003435,0.00006561,0.00010840,0.00026993,0.00051566,0.00128401,0.00245290,0.00405254,0.00610781,0.01166803,0.01927724,0.04800100,0.09169855,0.22833253,0.43619425,0.72065511,1.00",0.8 | 0.2
+PWP.D.GS,0,Peak Ground Velocity,cmps,0,0,multilinear_CDF,"0.2,3,4,5,6,8,10,15,20,30,40,50,60,80,100,150,200,300,400,500,600,800,990|0.00,0.00000217,0.00000414,0.00000684,0.00001030,0.00001968,0.00003252,0.00008098,0.00015470,0.00038520,0.00073587,0.00121576,0.00183234,0.00350041,0.00578317,0.01440030,0.02750956,0.06849976,0.13085828,0.21619653,0.32584160,0.62247037,1.00",0.8 | 0.2
+PWP.B.GF,0,Permanent Ground Deformation,inch,0,0,multilinear_CDF,"0.008,0.1,0.2,0.3,0.4,0.5,0.6,0.8,1,2,3,4,5,6,8,10,15,20,30,40,50,60,80,100,150,200,300,400,500,600,800,1000,2000,3000,4000,5000,6000,8000,9050|0.00,0.00167898,0.00247527,0.00310622,0.00364921,0.00413493,0.00457941,0.00537991,0.00609600,0.00898715,0.01127802,0.01324947,0.01501302,0.01662684,0.01953329,0.02213324,0.02777513,0.03263035,0.04094802,0.04810592,0.05450899,0.06036840,0.07092108,0.08036093,0.10084539,0.11847365,0.14867326,0.17466205,0.19791019,0.21918441,0.25749888,0.29177290,0.43015181,0.53979998,0.63415957,0.71856848,0.79581049,0.93492194,1.00",0.2 | 0.8
+PWP.D.GF,0,Permanent Ground Deformation,inch,0,0,multilinear_CDF,"0.3,0.4,0.5,0.6,0.8,1,2,3,4,5,6,8,10,15,20,30,40,50,60,80,100,150,200,300,400,500,600,800,1000,2000,3000,4000,5000,6000,8000,10000,20000,30000,40000,50000,60000,80000|0.00,0.00109476,0.00124048,0.00137382,0.00161397,0.00182880,0.00269614,0.00338341,0.00397484,0.00450391,0.00498805,0.00585999,0.00663997,0.00833254,0.00978911,0.01228440,0.01443178,0.01635270,0.01811052,0.02127632,0.02410828,0.03025362,0.03554209,0.04460198,0.05239862,0.05937306,0.06575532,0.07724967,0.08753187,0.12904554,0.16193999,0.19024787,0.21557054,0.23874315,0.28047658,0.31780902,0.46853605,0.58796858,0.69074827,0.78268933,0.86682397,1.00",0.2 | 0.8