.. _l-BernoulliNB-m-cl-default--o17: BernoulliNB - m-cl - default - =============================== Fitted on a problem type *m-cl* (see :func:`find_suitable_problem `), method `predict_proba` matches output . :: BernoulliNB() +-----------------------------+----------+ | index | 0 | +=============================+==========+ | skl_nop | 1 | +-----------------------------+----------+ | onx_size | 1859 | +-----------------------------+----------+ | onx_nnodes | 22 | +-----------------------------+----------+ | onx_ninits | 9 | +-----------------------------+----------+ | onx_doc_string | | +-----------------------------+----------+ | onx_ir_version | 8 | +-----------------------------+----------+ | onx_domain | ai.onnx | +-----------------------------+----------+ | onx_model_version | 0 | +-----------------------------+----------+ | onx_producer_name | skl2onnx | +-----------------------------+----------+ | onx_producer_version | 1.13.1 | +-----------------------------+----------+ | onx_ | 13 | +-----------------------------+----------+ | onx_ai.onnx.ml | 1 | +-----------------------------+----------+ | onx_op_Cast | 4 | +-----------------------------+----------+ | onx_op_ZipMap | 1 | +-----------------------------+----------+ | onx_op_Reshape | 2 | +-----------------------------+----------+ | onx_size_optim | 1859 | +-----------------------------+----------+ | onx_nnodes_optim | 22 | +-----------------------------+----------+ | onx_ninits_optim | 9 | +-----------------------------+----------+ | fit_classes_.shape | 3 | +-----------------------------+----------+ | fit_class_count_.shape | 3 | +-----------------------------+----------+ | fit_feature_count_.shape | (3, 4) | +-----------------------------+----------+ | fit_feature_log_prob_.shape | (3, 4) | +-----------------------------+----------+ | fit_class_log_prior_.shape | 3 | +-----------------------------+----------+ .. gdot:: digraph{ size=7; ranksep=0.25; nodesep=0.05; orientation=portrait; X [shape=box color=red label="X\nfloat((0, 4))" fontsize=10]; output_label [shape=box color=green label="output_label\nint64((0,))" fontsize=10]; output_probability [shape=box color=green label="output_probability\n[{int64, {'kind': 'tensor', 'elem': 'float', 'shape': }}]" fontsize=10]; classes [shape=box label="classes\nint32((3,))\n[0 1 2]" fontsize=10]; feature_log_prob [shape=box label="feature_log_prob\nfloat32((4, 3))\n[[-0.02739897 -0.02469261 -0.02531781]\n [-0.027398..." fontsize=10]; class_log_prior [shape=box label="class_log_prior\nfloat32((1, 3))\n[[-1.1631508 -1.0549372 -1.0809127]]" fontsize=10]; constant [shape=box label="constant\nfloat32(())\n1.0" fontsize=10]; threshold [shape=box label="threshold\nfloat32((1,))\n[0.]" fontsize=10]; zero_tensor [shape=box label="zero_tensor\nfloat32((1, 4))\n[[0. 0. 0. 0.]]" fontsize=10]; axis [shape=box label="axis\nint64((1,))\n[0]" fontsize=10]; shape_tensor [shape=box label="shape_tensor\nint64((2,))\n[-1 1]" fontsize=10]; shape_tensor1 [shape=box label="shape_tensor1\nint64((1,))\n[-1]" fontsize=10]; exp_result [shape=box label="exp_result" fontsize=10]; Exp [shape=box style="filled,rounded" color=orange label="Exp\n(Exp)" fontsize=10]; feature_log_prob -> Exp; Exp -> exp_result; condition [shape=box label="condition" fontsize=10]; Greater [shape=box style="filled,rounded" color=orange label="Greater\n(Greater)" fontsize=10]; X -> Greater; threshold -> Greater; Greater -> condition; cast_values [shape=box label="cast_values" fontsize=10]; Cast [shape=box style="filled,rounded" color=orange label="Cast\n(Cast)\nto=1" fontsize=10]; condition -> Cast; Cast -> cast_values; sub_result [shape=box label="sub_result" fontsize=10]; Sub [shape=box style="filled,rounded" color=orange label="Sub\n(Sub)" fontsize=10]; constant -> Sub; exp_result -> Sub; Sub -> sub_result; binarised_input [shape=box label="binarised_input" fontsize=10]; Add [shape=box style="filled,rounded" color=orange label="Add\n(Add)" fontsize=10]; zero_tensor -> Add; cast_values -> Add; Add -> binarised_input; neg_prob [shape=box label="neg_prob" fontsize=10]; Log [shape=box style="filled,rounded" color=orange label="Log\n(Log)" fontsize=10]; sub_result -> Log; Log -> neg_prob; difference_matrix [shape=box label="difference_matrix" fontsize=10]; Sub1 [shape=box style="filled,rounded" color=orange label="Sub\n(Sub1)" fontsize=10]; feature_log_prob -> Sub1; neg_prob -> Sub1; Sub1 -> difference_matrix; sum_neg_prob [shape=box label="sum_neg_prob" fontsize=10]; ReduceSum [shape=box style="filled,rounded" color=orange label="ReduceSum\n(ReduceSum)" fontsize=10]; neg_prob -> ReduceSum; axis -> ReduceSum; ReduceSum -> sum_neg_prob; dot_prod [shape=box label="dot_prod" fontsize=10]; MatMul [shape=box style="filled,rounded" color=orange label="MatMul\n(MatMul)" fontsize=10]; binarised_input -> MatMul; difference_matrix -> MatMul; MatMul -> dot_prod; partial_sum_result [shape=box label="partial_sum_result" fontsize=10]; Add1 [shape=box style="filled,rounded" color=orange label="Add\n(Add1)" fontsize=10]; dot_prod -> Add1; sum_neg_prob -> Add1; Add1 -> partial_sum_result; sum_result [shape=box label="sum_result" fontsize=10]; Add2 [shape=box style="filled,rounded" color=orange label="Add\n(Add2)" fontsize=10]; partial_sum_result -> Add2; class_log_prior -> Add2; Add2 -> sum_result; argmax_output [shape=box label="argmax_output" fontsize=10]; ArgMax [shape=box style="filled,rounded" color=orange label="ArgMax\n(ArgMax)\naxis=1" fontsize=10]; sum_result -> ArgMax; ArgMax -> argmax_output; reduce_log_sum_exp_result [shape=box label="reduce_log_sum_exp_result" fontsize=10]; ReduceLogSumExp [shape=box style="filled,rounded" color=orange label="ReduceLogSumExp\n(ReduceLogSumExp)\naxes=[1]\nkeepdims=0" fontsize=10]; sum_result -> ReduceLogSumExp; ReduceLogSumExp -> reduce_log_sum_exp_result; reshaped_log_prob [shape=box label="reshaped_log_prob" fontsize=10]; Reshape [shape=box style="filled,rounded" color=orange label="Reshape\n(Reshape)" fontsize=10]; reduce_log_sum_exp_result -> Reshape; shape_tensor -> Reshape; Reshape -> reshaped_log_prob; array_feature_extractor_result [shape=box label="array_feature_extractor_result" fontsize=10]; ArrayFeatureExtractor [shape=box style="filled,rounded" color=orange label="ArrayFeatureExtractor\n(ArrayFeatureExtractor)" fontsize=10]; classes -> ArrayFeatureExtractor; argmax_output -> ArrayFeatureExtractor; ArrayFeatureExtractor -> array_feature_extractor_result; cast2_result [shape=box label="cast2_result" fontsize=10]; Cast1 [shape=box style="filled,rounded" color=orange label="Cast\n(Cast1)\nto=1" fontsize=10]; array_feature_extractor_result -> Cast1; Cast1 -> cast2_result; log_prob [shape=box label="log_prob" fontsize=10]; Sub2 [shape=box style="filled,rounded" color=orange label="Sub\n(Sub2)" fontsize=10]; sum_result -> Sub2; reshaped_log_prob -> Sub2; Sub2 -> log_prob; probabilities [shape=box label="probabilities" fontsize=10]; Exp1 [shape=box style="filled,rounded" color=orange label="Exp\n(Exp1)" fontsize=10]; log_prob -> Exp1; Exp1 -> probabilities; reshaped_result [shape=box label="reshaped_result" fontsize=10]; Reshape1 [shape=box style="filled,rounded" color=orange label="Reshape\n(Reshape1)" fontsize=10]; cast2_result -> Reshape1; shape_tensor1 -> Reshape1; Reshape1 -> reshaped_result; ZipMap [shape=box style="filled,rounded" color=orange label="ZipMap\n(ZipMap)\nclasslabels_int64s=[0 1 2]" fontsize=10]; probabilities -> ZipMap; ZipMap -> output_probability; label [shape=box label="label" fontsize=10]; Cast2 [shape=box style="filled,rounded" color=orange label="Cast\n(Cast2)\nto=7" fontsize=10]; reshaped_result -> Cast2; Cast2 -> label; Cast3 [shape=box style="filled,rounded" color=orange label="Cast\n(Cast3)\nto=7" fontsize=10]; label -> Cast3; Cast3 -> output_label; }