classify landcover level34 by class def and code csv

docker/env.yaml

@@ -109,6 +109,7 @@ dependencies:
   - rsa
   - ruamel.yaml
   - ruamel.yaml.clib
+  - s3fs
   - s3transfer
   - scikit-image
   - scipy

odc/stats/plugins/_registry.py

@@ -40,7 +40,6 @@ def import_all():
     # TODO: make that more automatic
     modules = [
         "odc.stats.plugins.lc_treelite_cultivated",
-        "odc.stats.plugins.lc_level3",
         "odc.stats.plugins.lc_treelite_woody",
         "odc.stats.plugins.lc_tf_urban",
         "odc.stats.plugins.lc_level34",

odc/stats/plugins/_utils.py

@@ -1,3 +1,5 @@
+import re
+import operator
 import dask
 from osgeo import gdal, ogr, osr
 
@@ -42,3 +44,99 @@ def rasterize_vector_mask(
             return dask.array.ones(dst_shape, name=False)
 
     return dask.array.from_array(mask.reshape(dst_shape), name=False)
+
+
+OPERATORS = {
+    ">": operator.gt,
+    ">=": operator.ge,
+    "<": operator.lt,
+    "<=": operator.le,
+    "==": operator.eq,
+    "!=": operator.ne,
+}
+
+BRACKETS = {
+    "[": operator.ge,  # Inclusive lower bound
+    "(": operator.gt,  # Exclusive lower bound
+    "]": operator.le,  # Inclusive upper bound
+    ")": operator.lt,  # Exclusive upper bound
+}
+
+
+def parse_rule(rule):
+    """
+    Parse a single condition or range condition.
+    Supports range notations like '[]', '[)', '(]', and '()',
+    and treats standalone numbers as '=='.
+    """
+    # Special case for 255 (rule doesn't apply)
+    if (rule == "255") | (rule == "nan"):
+        return None
+
+    # Check for range conditions like '[a, b)' or '(a, b]'
+    range_pattern = r"([\[\(])(-?\d+\.?\d*),\s*(-?\d+\.?\d*)([\]\)])"
+    match = re.match(range_pattern, rule)
+    if match:
+        # Extract the bounds and the bracket types
+        lower_bracket, lower_value, upper_value, upper_bracket = match.groups()
+        return [
+            (BRACKETS[lower_bracket], float(lower_value)),
+            (BRACKETS[upper_bracket], float(upper_value)),
+        ]
+
+    ordered_operators = sorted(OPERATORS.items(), key=lambda x: -len(x[0]))
+
+    # Single condition (no range notation, no explicit operator)
+    for op_str, op_func in ordered_operators:
+        if op_str in rule:
+            value = float(rule.replace(op_str, "").strip())
+            return [(op_func, value)]
+
+    # Default to equality (==) if no operator is found
+    return [(operator.eq, int(rule.strip()))]
+
+
+def generate_numexpr_expressions(rules_df, final_class_column, previous):
+    """
+    Generate a list of numexpr-compatible expressions for classification rules.
+    :param rules_df: DataFrame containing the classification rules
+    :param final_class_column: Name of the column containing the final class values
+    :return: List of expressions (one for each rule)
+    """
+    expressions = []
+
+    for _, rules in rules_df.iterrows():
+        conditions = []
+
+        for col in rules.index:
+            if col == final_class_column:
+                continue
+            subconditions = parse_rule(rules[col])
+            if subconditions is None:  # Skip rule if it's None
+                continue
+            for op_func, value in subconditions:
+                if op_func is operator.eq:
+                    conditions.append(f"({col}=={value})")
+                elif op_func is operator.gt:
+                    conditions.append(f"({col}>{value})")
+                elif op_func is operator.ge:
+                    conditions.append(f"({col}>={value})")
+                elif op_func is operator.lt:
+                    conditions.append(f"({col}<{value})")
+                elif op_func is operator.le:
+                    conditions.append(f"({col}<={value})")
+                elif op_func is operator.ne:
+                    conditions.append(f"({col}!={value})")
+
+        if not conditions:
+            continue
+
+        condition = "&".join(conditions)
+
+        final_class = rules[final_class_column]
+        expressions.append(f"where({condition}, {final_class}, {previous})")
+
+    expressions = list(set(expressions))
+    expressions = sorted(expressions, key=len)
+
+    return expressions