Merge branch 'master' into exprs

BayesWitnesses · May 20, 2020 · eb470a1 · eb470a1
2 parents 3edb263 + 4869e00
commit eb470a1
Show file tree

Hide file tree

Showing 13 changed files with 75 additions and 64 deletions.
diff --git a/README.md b/README.md
@@ -47,7 +47,7 @@ pip install m2cgen
 | **Linear** | <ul><li>scikit-learn<ul><li>LogisticRegression</li><li>LogisticRegressionCV</li><li>PassiveAggressiveClassifier</li><li>Perceptron</li><li>RidgeClassifier</li><li>RidgeClassifierCV</li><li>SGDClassifier</li></ul></li><li>lightning<ul><li>AdaGradClassifier</li><li>CDClassifier</li><li>FistaClassifier</li><li>SAGAClassifier</li><li>SAGClassifier</li><li>SDCAClassifier</li><li>SGDClassifier</li></ul></li></ul> | <ul><li>scikit-learn<ul><li>ARDRegression</li><li>BayesianRidge</li><li>ElasticNet</li><li>ElasticNetCV</li><li>HuberRegressor</li><li>Lars</li><li>LarsCV</li><li>Lasso</li><li>LassoCV</li><li>LassoLars</li><li>LassoLarsCV</li><li>LassoLarsIC</li><li>LinearRegression</li><li>OrthogonalMatchingPursuit</li><li>OrthogonalMatchingPursuitCV</li><li>PassiveAggressiveRegressor</li><li>RANSACRegressor(only supported regression estimators can be used as a base estimator)</li><li>Ridge</li><li>RidgeCV</li><li>SGDRegressor</li><li>TheilSenRegressor</li></ul><li>StatsModels<ul><li>Generalized Least Squares (GLS)</li><li>Generalized Least Squares with AR Errors (GLSAR)</li><li>Generalized Linear Models (GLM)</li><li>Ordinary Least Squares (OLS)</li><li>[Gaussian] Process Regression Using Maximum Likelihood-based Estimation (ProcessMLE)</li><li>Quantile Regression (QuantReg)</li><li>Weighted Least Squares (WLS)</li></ul><li>lightning<ul><li>AdaGradRegressor</li><li>CDRegressor</li><li>FistaRegressor</li><li>SAGARegressor</li><li>SAGRegressor</li><li>SDCARegressor</li></ul></li></ul> |
 | **SVM** | <ul><li>scikit-learn<ul><li>LinearSVC</li><li>NuSVC</li><li>SVC</li></ul></li><li>lightning<ul><li>KernelSVC</li><li>LinearSVC</li></ul></li></ul> | <ul><li>scikit-learn<ul><li>LinearSVR</li><li>NuSVR</li><li>SVR</li></ul></li><li>lightning<ul><li>LinearSVR</li></ul></li></ul> |
 | **Tree** | <ul><li>DecisionTreeClassifier</li><li>ExtraTreeClassifier</li></ul> | <ul><li>DecisionTreeRegressor</li><li>ExtraTreeRegressor</li></ul> |
-| **Random Forest** | <ul><li>ExtraTreesClassifier</li><li>LGBMClassifier(rf booster only)</li><li>RandomForestClassifier</li><li>XGBRFClassifier(binary only, multiclass is not supported yet)</li></ul> | <ul><li>ExtraTreesRegressor</li><li>LGBMRegressor(rf booster only)</li><li>RandomForestRegressor</li><li>XGBRFRegressor</li></ul> |
+| **Random Forest** | <ul><li>ExtraTreesClassifier</li><li>LGBMClassifier(rf booster only)</li><li>RandomForestClassifier</li><li>XGBRFClassifier</li></ul> | <ul><li>ExtraTreesRegressor</li><li>LGBMRegressor(rf booster only)</li><li>RandomForestRegressor</li><li>XGBRFRegressor</li></ul> |
 | **Boosting** | <ul><li>LGBMClassifier(gbdt/dart/goss booster only)</li><li>XGBClassifier(gbtree/gblinear booster only)</li><ul> | <ul><li>LGBMRegressor(gbdt/dart/goss booster only)</li><li>XGBRegressor(gbtree/gblinear booster only)</li></ul> |
 
 You can find versions of packages with which compatibility is guaranteed by CI tests [here](https://github.com/BayesWitnesses/m2cgen/blob/master/requirements-test.txt#L1).

diff --git a/m2cgen/assemblers/boosting.py b/m2cgen/assemblers/boosting.py
@@ -10,6 +10,7 @@
 class BaseBoostingAssembler(ModelAssembler):
 
     classifier_names = {}
+    strided_layout_for_multiclass = True
 
     def __init__(self, model, estimator_params, base_score=0):
         super().__init__(model)
@@ -54,7 +55,8 @@ def _assemble_multi_class_output(self, estimator_params):
         # Multi-class output is calculated based on discussion in
         # https://github.com/dmlc/xgboost/issues/1746#issuecomment-295962863
         splits = _split_estimator_params_by_classes(
-            estimator_params, self._output_size)
+            estimator_params, self._output_size,
+            self.strided_layout_for_multiclass)
 
         base_score = self._base_score
         exprs = [
@@ -112,9 +114,8 @@ class XGBoostTreeModelAssembler(BaseTreeBoostingAssembler):
     classifier_names = {"XGBClassifier", "XGBRFClassifier"}
 
     def __init__(self, model):
-        if type(model).__name__ == "XGBRFClassifier" and model.n_classes_ > 2:
-            raise RuntimeError(
-                "Multiclass XGBRFClassifier is not supported yet")
+        if type(model).__name__ == "XGBRFClassifier":
+            self.strided_layout_for_multiclass = False
         feature_names = model.get_booster().feature_names
         self._feature_name_to_idx = {
             name: idx for idx, name in enumerate(feature_names or [])
@@ -243,7 +244,13 @@ def _assemble_tree(self, tree):
             self._assemble_tree(false_child))
 
 
-def _split_estimator_params_by_classes(values, n_classes):
-    # Splits are computed based on a comment
-    # https://github.com/dmlc/xgboost/issues/1746#issuecomment-267400592.
-    return [values[class_idx::n_classes] for class_idx in range(n_classes)]
+def _split_estimator_params_by_classes(values, n_classes, strided):
+    if strided:
+        # Splits are computed based on a comment
+        # https://github.com/dmlc/xgboost/issues/1746#issuecomment-267400592.
+        return [values[class_idx::n_classes] for class_idx in range(n_classes)]
+    else:
+        values_len = len(values)
+        block_len = values_len // n_classes
+        return [values[start_block_idx:start_block_idx + block_len]
+                for start_block_idx in range(0, values_len, block_len)]
diff --git a/m2cgen/interpreters/c/code_generator.py b/m2cgen/interpreters/c/code_generator.py
@@ -6,8 +6,8 @@
 
 class CCodeGenerator(CLikeCodeGenerator):
 
-    tpl_scalar_var_declare = CT("double ${var_name};")
-    tpl_vector_var_declare = CT("double ${var_name}[${size}];")
+    tpl_scalar_var_declare = CT("double {var_name};")
+    tpl_vector_var_declare = CT("double {var_name}[{size}];")
 
     scalar_type = "double"
     vector_type = "double *"

diff --git a/m2cgen/interpreters/code_generator.py b/m2cgen/interpreters/code_generator.py
@@ -1,19 +1,22 @@
 from io import StringIO
-from string import Template
 from weakref import finalize
 
 
 class CodeTemplate:
 
     def __init__(self, template):
-        self.template = Template(template)
         self.str_template = template
 
     def __str__(self):
         return self.str_template
 
     def __call__(self, *args, **kwargs):
-        return self.template.substitute(*args, **kwargs)
+        # Force calling str() representation
+        # because without it numpy gives the same output
+        # for different float types
+        return self.str_template.format(
+            *[str(i) for i in args],
+            **{k: str(v) for k, v in kwargs.items()})
 
 
 class BaseCodeGenerator:
@@ -187,12 +190,12 @@ class CLikeCodeGenerator(ImperativeCodeGenerator):
     have to provide logic for wrapping expressions into functions/classes/etc.
     """
 
-    tpl_num_value = CodeTemplate("${value}")
-    tpl_infix_expression = CodeTemplate("(${left}) ${op} (${right})")
-    tpl_var_declaration = CodeTemplate("${var_type} ${var_name};")
-    tpl_return_statement = CodeTemplate("return ${value};")
-    tpl_array_index_access = CodeTemplate("${array_name}[${index}]")
-    tpl_if_statement = CodeTemplate("if (${if_def}) {")
-    tpl_else_statement = CodeTemplate("} else {")
-    tpl_block_termination = CodeTemplate("}")
-    tpl_var_assignment = CodeTemplate("${var_name} = ${value};")
+    tpl_num_value = CodeTemplate("{value}")
+    tpl_infix_expression = CodeTemplate("({left}) {op} ({right})")
+    tpl_var_declaration = CodeTemplate("{var_type} {var_name};")
+    tpl_return_statement = CodeTemplate("return {value};")
+    tpl_array_index_access = CodeTemplate("{array_name}[{index}]")
+    tpl_if_statement = CodeTemplate("if ({if_def}) {{")
+    tpl_else_statement = CodeTemplate("}} else {{")
+    tpl_block_termination = CodeTemplate("}}")
+    tpl_var_assignment = CodeTemplate("{var_name} = {value};")
diff --git a/m2cgen/interpreters/go/code_generator.py b/m2cgen/interpreters/go/code_generator.py
@@ -5,15 +5,15 @@
 
 
 class GoCodeGenerator(ImperativeCodeGenerator):
-    tpl_num_value = CodeTemplate("${value}")
-    tpl_infix_expression = CodeTemplate("(${left}) ${op} (${right})")
-    tpl_array_index_access = CodeTemplate("${array_name}[${index}]")
-    tpl_else_statement = CodeTemplate("} else {")
-    tpl_block_termination = CodeTemplate("}")
-    tpl_var_declaration = CodeTemplate("var ${var_name} ${var_type}")
-    tpl_return_statement = CodeTemplate("return ${value}")
-    tpl_if_statement = CodeTemplate("if ${if_def} {")
-    tpl_var_assignment = CodeTemplate("${var_name} = ${value}")
+    tpl_num_value = CodeTemplate("{value}")
+    tpl_infix_expression = CodeTemplate("({left}) {op} ({right})")
+    tpl_array_index_access = CodeTemplate("{array_name}[{index}]")
+    tpl_else_statement = CodeTemplate("}} else {{")
+    tpl_block_termination = CodeTemplate("}}")
+    tpl_var_declaration = CodeTemplate("var {var_name} {var_type}")
+    tpl_return_statement = CodeTemplate("return {value}")
+    tpl_if_statement = CodeTemplate("if {if_def} {{")
+    tpl_var_assignment = CodeTemplate("{var_name} = {value}")
 
     scalar_type = "float64"
     vector_type = "[]float64"

diff --git a/m2cgen/interpreters/haskell/code_generator.py b/m2cgen/interpreters/haskell/code_generator.py
@@ -5,9 +5,9 @@
 
 
 class HaskellCodeGenerator(BaseCodeGenerator):
-    tpl_num_value = CodeTemplate("${value}")
-    tpl_infix_expression = CodeTemplate("(${left}) ${op} (${right})")
-    tpl_module_definition = CodeTemplate("module ${module_name} where")
+    tpl_num_value = CodeTemplate("{value}")
+    tpl_infix_expression = CodeTemplate("({left}) {op} ({right})")
+    tpl_module_definition = CodeTemplate("module {module_name} where")
 
     def __init__(self, *args, **kwargs):
         self._func_idx = 0

diff --git a/m2cgen/interpreters/php/code_generator.py b/m2cgen/interpreters/php/code_generator.py
@@ -7,7 +7,7 @@
 
 class PhpCodeGenerator(CLikeCodeGenerator):
 
-    tpl_array_index_access = CodeTemplate("$$${array_name}[${index}]")
+    tpl_array_index_access = CodeTemplate("${array_name}[{index}]")
 
     def __init__(self, *args, **kwargs):
         super(PhpCodeGenerator, self).__init__(*args, **kwargs)

diff --git a/m2cgen/interpreters/powershell/code_generator.py b/m2cgen/interpreters/powershell/code_generator.py
@@ -7,10 +7,10 @@
 
 class PowershellCodeGenerator(CLikeCodeGenerator):
 
-    tpl_var_declare = CT("${var_type}${var_name} = ${init_val}")
-    tpl_var_assignment = CT("${var_name} = ${value}")
-    tpl_array_index_access = CT("$$${array_name}[${index}]")
-    tpl_return_statement = CT("return ${value}")
+    tpl_var_declare = CT("{var_type}{var_name} = {init_val}")
+    tpl_var_assignment = CT("{var_name} = {value}")
+    tpl_array_index_access = CT("${array_name}[{index}]")
+    tpl_return_statement = CT("return {value}")
 
     scalar_type = "[double]"
     vector_type = "[double[]]"

diff --git a/m2cgen/interpreters/python/code_generator.py b/m2cgen/interpreters/python/code_generator.py
@@ -6,14 +6,14 @@
 
 class PythonCodeGenerator(ImperativeCodeGenerator):
 
-    tpl_num_value = CT("${value}")
-    tpl_infix_expression = CT("(${left}) ${op} (${right})")
-    tpl_return_statement = CT("return ${value}")
-    tpl_array_index_access = CT("${array_name}[${index}]")
-    tpl_array_convert_to_numpy = CT("np.asarray(${value})")
-    tpl_if_statement = CT("if ${if_def}:")
+    tpl_num_value = CT("{value}")
+    tpl_infix_expression = CT("({left}) {op} ({right})")
+    tpl_return_statement = CT("return {value}")
+    tpl_array_index_access = CT("{array_name}[{index}]")
+    tpl_array_convert_to_numpy = CT("np.asarray({value})")
+    tpl_if_statement = CT("if {if_def}:")
     tpl_else_statement = CT("else:")
-    tpl_var_assignment = CT("${var_name} = ${value}")
+    tpl_var_assignment = CT("{var_name} = {value}")
 
     tpl_var_declaration = CT("")
     tpl_block_termination = CT("")

diff --git a/m2cgen/interpreters/r/code_generator.py b/m2cgen/interpreters/r/code_generator.py
@@ -6,8 +6,8 @@
 
 class RCodeGenerator(CLikeCodeGenerator):
 
-    tpl_return_statement = CodeTemplate("return(${value})")
-    tpl_var_assignment = CodeTemplate("${var_name} <- ${value}")
+    tpl_return_statement = CodeTemplate("return({value})")
+    tpl_var_assignment = CodeTemplate("{var_name} <- {value}")
 
     def __init__(self, *args, **kwargs):
         super(RCodeGenerator, self).__init__(*args, **kwargs)

diff --git a/m2cgen/interpreters/ruby/code_generator.py b/m2cgen/interpreters/ruby/code_generator.py
@@ -7,14 +7,14 @@
 class RubyCodeGenerator(ImperativeCodeGenerator):
 
     tpl_var_declaration = CT("")
-    tpl_num_value = CT("${value}")
-    tpl_infix_expression = CT("(${left}) ${op} (${right})")
+    tpl_num_value = CT("{value}")
+    tpl_infix_expression = CT("({left}) {op} ({right})")
     tpl_return_statement = tpl_num_value
-    tpl_array_index_access = CT("${array_name}[${index}]")
-    tpl_if_statement = CT("if ${if_def}")
+    tpl_array_index_access = CT("{array_name}[{index}]")
+    tpl_if_statement = CT("if {if_def}")
     tpl_else_statement = CT("else")
     tpl_block_termination = CT("end")
-    tpl_var_assignment = CT("${var_name} = ${value}")
+    tpl_var_assignment = CT("{var_name} = {value}")
 
     def add_function_def(self, name, args):
         func_def = "def " + name + "("

diff --git a/m2cgen/interpreters/visual_basic/code_generator.py b/m2cgen/interpreters/visual_basic/code_generator.py
@@ -6,18 +6,18 @@
 
 
 class VisualBasicCodeGenerator(ImperativeCodeGenerator):
-    tpl_num_value = CodeTemplate("${value}")
-    tpl_infix_expression = CodeTemplate("(${left}) ${op} (${right})")
+    tpl_num_value = CodeTemplate("{value}")
+    tpl_infix_expression = CodeTemplate("({left}) {op} ({right})")
     tpl_var_declaration = \
-        CodeTemplate("Dim ${var_name}${type_modifier} As ${var_type}")
-    tpl_return_statement = CodeTemplate("${func_name} = ${value}")
-    tpl_if_statement = CodeTemplate("If ${if_def} Then")
+        CodeTemplate("Dim {var_name}{type_modifier} As {var_type}")
+    tpl_return_statement = CodeTemplate("{func_name} = {value}")
+    tpl_if_statement = CodeTemplate("If {if_def} Then")
     tpl_else_statement = CodeTemplate("Else")
-    tpl_block_termination = CodeTemplate("End ${block_name}")
-    tpl_array_index_access = CodeTemplate("${array_name}(${index})")
-    tpl_array_set_by_index = CodeTemplate("${array_name}(${index}) = ${value}")
-    tpl_var_assignment = CodeTemplate("${var_name} = ${value}")
-    tpl_module_definition = CodeTemplate("Module ${module_name}")
+    tpl_block_termination = CodeTemplate("End {block_name}")
+    tpl_array_index_access = CodeTemplate("{array_name}({index})")
+    tpl_array_set_by_index = CodeTemplate("{array_name}({index}) = {value}")
+    tpl_var_assignment = CodeTemplate("{var_name} = {value}")
+    tpl_module_definition = CodeTemplate("Module {module_name}")
 
     scalar_type = "Double"
 

diff --git a/tests/e2e/test_e2e.py b/tests/e2e/test_e2e.py
@@ -200,6 +200,7 @@ def regression_bounded(model, test_fraction=0.02):
 
         # XGBoost (RF)
         regression(xgboost.XGBRFRegressor(**XGBOOST_PARAMS_RF)),
+        classification(xgboost.XGBRFClassifier(**XGBOOST_PARAMS_RF)),
         classification_binary(xgboost.XGBRFClassifier(**XGBOOST_PARAMS_RF)),
 
         # XGBoost (Large Trees)