############################
# With *scikit-learn*:
print(pipeline.predict(train_data[:1]))
print(pipeline.predict_proba(train_data[:1]))
###############################
# There are discrepencies for this model because
# the tokenization is not exactly the same.
# This is a work in progress.
##################################
# Display the ONNX graph
# ++++++++++++++++++++++
#
# Finally, let's see the graph converted with *sklearn-onnx*.
pydot_graph = GetPydotGraph(
model_onnx.graph, name=model_onnx.graph.name,
rankdir="TB", node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("pipeline_tfidf.dot")
os.system('dot -O -Gdpi=300 -Tpng pipeline_tfidf.dot')
image = plt.imread("pipeline_tfidf.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
print("onnx", results[2])
##################################
# It looks good.
#
# Display the ONNX graph
# ++++++++++++++++++++++
pydot_graph = GetPydotGraph(model_onnx.graph,
name=model_onnx.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("validator_classifier.dot")
os.system('dot -O -Gdpi=300 -Tpng validator_classifier.dot')
image = plt.imread("validator_classifier.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
#################################
# **Versions used for this example**
print("numpy:", np.__version__)
print("scikit-learn:", sklearn.__version__)
print("onnx: ", onnx.__version__)
print("onnxruntime: ", rt.__version__)
import numpy
sess = rt.InferenceSession("pipeline_titanic.onnx")
pred_onx = sess.run(None, inputs)
print("predict", pred_onx[0][:5])
print("predict_proba", pred_onx[1][:1])
##################################
# Display the ONNX graph
# ++++++++++++++++++++++
#
# Finally, let's see the graph converted with *sklearn-onnx*.
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer
pydot_graph = GetPydotGraph(model_onnx.graph,
name=model_onnx.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("pipeline_titanic.dot")
import os
os.system('dot -O -Gdpi=300 -Tpng pipeline_titanic.dot')
import matplotlib.pyplot as plt
image = plt.imread("pipeline_titanic.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
onx2 = to_onnx(woe2, X)
sess = InferenceSession(onx2.SerializeToString())
print(sess.run(None, {'X': X})[0])
################################################
# ONNX Graphs
# +++++++++++
#
# onehot=False
pydot_graph = GetPydotGraph(
onx1.graph, name=onx1.graph.name, rankdir="TB",
node_producer=GetOpNodeProducer(
"docstring", color="yellow", fillcolor="yellow", style="filled"))
pydot_graph.write_dot("woe1.dot")
os.system('dot -O -Gdpi=300 -Tpng woe1.dot')
image = plt.imread("woe1.dot.png")
fig, ax = plt.subplots(figsize=(10, 10))
ax.imshow(image)
ax.axis('off')
#######################################
# onehot=True
pydot_graph = GetPydotGraph(
onx2.graph, name=onx2.graph.name, rankdir="TB",
node_producer=GetOpNodeProducer(
"docstring", color="yellow", fillcolor="yellow", style="filled"))
def test_pipeline_column_transformer(self):
iris = datasets.load_iris()
X = iris.data[:, :3]
y = iris.target
X_train = pandas.DataFrame(X, columns=["vA", "vB", "vC"])
X_train["vcat"] = X_train["vA"].apply(lambda x: "cat1"
if x > 0.5 else "cat2")
X_train["vcat2"] = X_train["vB"].apply(lambda x: "cat3"
if x > 0.5 else "cat4")
y_train = y % 2
numeric_features = [0, 1, 2] # ["vA", "vB", "vC"]
categorical_features = [3, 4] # ["vcat", "vcat2"]
classifier = LogisticRegression(
C=0.01,
class_weight=dict(zip([False, True], [0.2, 0.8])),
n_jobs=1, max_iter=10, solver="lbfgs", tol=1e-3)
numeric_transformer = Pipeline(steps=[
("imputer", SimpleImputer(strategy="median")),
("scaler", StandardScaler()),
])
categorical_transformer = Pipeline(steps=[
(
"onehot",
OneHotEncoder(sparse=True, handle_unknown="ignore"),
),
(
"tsvd",
TruncatedSVD(n_components=1, algorithm="arpack", tol=1e-4),
),
])
preprocessor = ColumnTransformer(transformers=[
("num", numeric_transformer, numeric_features),
("cat", categorical_transformer, categorical_features),
])
model = Pipeline(steps=[("precprocessor",
preprocessor), ("classifier", classifier)])
model.fit(X_train, y_train)
initial_type = [
("numfeat", FloatTensorType([None, 3])),
("strfeat", StringTensorType([None, 2])),
]
X_train = X_train[:11]
model_onnx = convert_sklearn(model, initial_types=initial_type,
target_opset=TARGET_OPSET)
dump_data_and_model(
X_train, model, model_onnx,
basename="SklearnPipelineColumnTransformerPipeliner")
if __name__ == "__main__":
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer
pydot_graph = GetPydotGraph(
model_onnx.graph,
name=model_onnx.graph.name,
rankdir="TP",
node_producer=GetOpNodeProducer("docstring"))
pydot_graph.write_dot("graph.dot")
import os
os.system("dot -O -G=300 -Tpng graph.dot")
Y = predict_with_onnxruntime(model_def, X)
print(Y)
##################################
# Display the ONNX graph
# ++++++++++++++++++++++
pydot_graph = GetPydotGraph(model_def.graph,
name=model_def.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("pipeline_transpose2x.dot")
os.system('dot -O -Gdpi=300 -Tpng pipeline_transpose2x.dot')
image = plt.imread("pipeline_transpose2x.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
#################################
# **Versions used for this example**
import sklearn # noqa
print("numpy:", numpy.__version__)
print("scikit-learn:", sklearn.__version__)
import skl2onnx # noqa
with open("TfidfVectorizer.onnx", "wb") as f:
f.write(model_onnx.SerializeToString())
###########################
# Visualize
# +++++++++
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer # noqa
pydot_graph = GetPydotGraph(model_onnx.graph,
name=model_onnx.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("tfidfvectorizer.dot")
import os # noqa
os.system('dot -O -Gdpi=300 -Tpng tfidfvectorizer.dot')
import matplotlib.pyplot as plt # noqa
image = plt.imread("tfidfvectorizer.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
###########################
# Visualize intermediate outputs
# ++++++++++++++++++++++++++++++
from skonnxrt.sklapi import OnnxTransformer # noqa
##################################
# Display the ONNX graph
# ++++++++++++++++++++++
#
# Finally, let's see the graph converted with *sklearn-onnx*.
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer # noqa
pydot_graph = GetPydotGraph(onx.graph,
name=onx.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("pipeline_onnx_mixin.dot")
import os # noqa
os.system('dot -O -Gdpi=300 -Tpng pipeline_onnx_mixin.dot')
import matplotlib.pyplot as plt # noqa
image = plt.imread("pipeline_onnx_mixin.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
#################################
# **Versions used for this example**
import numpy, sklearn # noqa
print("numpy:", numpy.__version__)
from onnx import ModelProto
model = ModelProto()
with open(example1, "rb") as fid:
content = fid.read()
model.ParseFromString(content)
###################################
# We convert it into a graph.
from onnx.tools.net_drawer import GetOpNodeProducer, GetPydotGraph
pydot_graph = GetPydotGraph(model.graph,
name=model.graph.name,
rankdir="LR",
node_producer=GetOpNodeProducer("docstring"))
pydot_graph.write_dot("graph.dot")
#######################################
# Then into an image
import os
os.system("dot -O -Tpng graph.dot")
################################
# Which we display...
import matplotlib.pyplot as plt
image = plt.imread("graph.dot.png")
plt.imshow(image)
# Display the ONNX graph
# ++++++++++++++++++++++
#
# Finally, let's see the graph converted with *onnxmltools*.
import os
import matplotlib.pyplot as plt
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer
pydot_graph = GetPydotGraph(onx.graph,
name=onx.graph.name,
rankdir="TB",
node_producer=GetOpNodeProducer("docstring",
color="yellow",
fillcolor="yellow",
style="filled"))
pydot_graph.write_dot("model.dot")
os.system('dot -O -Gdpi=300 -Tpng model.dot')
image = plt.imread("model.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')
#################################
# **Versions used for this example**
print("numpy:", numpy.__version__)
print("scikit-learn:", sklearn.__version__)
print("onnx: ", onnx.__version__)
print("onnxruntime: ", rt.__version__)