Snowflakeモデルレジストリ¶

import pandas as pd
import numpy as np
from sklearn import datasets
from snowflake.ml.modeling.xgboost import XGBClassifier

iris = datasets.load_iris()
df = pd.DataFrame(data=np.c_[iris["data"], iris["target"]], columns=iris["feature_names"] + ["target"])
df.columns = [s.replace(" (CM)", "").replace(" ", "") for s in df.columns.str.upper()]

input_cols = ["SEPALLENGTH", "SEPALWIDTH", "PETALLENGTH", "PETALWIDTH"]
label_cols = "TARGET"
output_cols = "PREDICTED_TARGET"

clf_xgb = XGBClassifier(
        input_cols=input_cols, output_cols=output_cols, label_cols=label_cols, drop_input_cols=True
)
clf_xgb.fit(df)
model_ref = registry.log_model(
    clf_xgb,
    model_name="XGBClassifier",
    version_name="v1",
)
model_ref.run(df.drop(columns=label_cols).head(10), function_name='predict_proba')

from sklearn import datasets, ensemble

iris_X, iris_y = datasets.load_iris(return_X_y=True, as_frame=True)
clf = ensemble.RandomForestClassifier(random_state=42)
clf.fit(iris_X, iris_y)
model_ref = registry.log_model(
    clf,
    model_name="RandomForestClassifier",
    version_name="v1",
    sample_input_data=iris_X,
    options={
        "method_options": {
            "predict": {"case_sensitive": True},
            "predict_proba": {"case_sensitive": True},
            "predict_log_proba": {"case_sensitive": True},
        }
    },
)
model_ref.run(iris_X[-10:], function_name='"predict_proba"')

import xgboost
from sklearn import datasets, model_selection

cal_X, cal_y = datasets.load_breast_cancer(as_frame=True, return_X_y=True)
cal_X_train, cal_X_test, cal_y_train, cal_y_test = model_selection.train_test_split(cal_X, cal_y)
params = dict(n_estimators=100, reg_lambda=1, gamma=0, max_depth=3, objective="binary:logistic")
regressor = xgboost.train(params, xgboost.DMatrix(data=cal_X_train, label=cal_y_train))
model_ref = registry.log_model(
    regressor,
    model_name="xgBooster",
    version_name="v1",
    sample_input_data=cal_X_test,
    options={
        "target_methods": ["predict"],
        "method_options": {
            "predict": {"case_sensitive": True},
        },
    },
)
model_ref.run(cal_X_test[-10:])

import torch
import numpy as np

class TorchModel(torch.nn.Module):
        def __init__(self, n_input: int, n_hidden: int, n_out: int, dtype: torch.dtype = torch.float32) -> None:
                super().__init__()
                self.model = torch.nn.Sequential(
                        torch.nn.Linear(n_input, n_hidden, dtype=dtype),
                        torch.nn.ReLU(),
                        torch.nn.Linear(n_hidden, n_out, dtype=dtype),
                        torch.nn.Sigmoid(),
                )

        def forward(self, tensor: torch.Tensor) -> torch.Tensor:
                return self.model(tensor)

n_input, n_hidden, n_out, batch_size, learning_rate = 10, 15, 1, 100, 0.01
dtype = torch.float32
x = np.random.rand(batch_size, n_input)
data_x = torch.from_numpy(x).to(dtype=dtype)
data_y = (torch.rand(size=(batch_size, 1)) < 0.5).to(dtype=dtype)

model = TorchModel(n_input, n_hidden, n_out, dtype=dtype)
loss_function = torch.nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
for _epoch in range(100):
        pred_y = model.forward(data_x)
        loss = loss_function(pred_y, data_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()


model_ref = registry.log_model(
    model,
    model_name="torchModel",
    version_name="v1",
    sample_input_data=[data_x],
)
model_ref.run([data_x])

import tensorflow as tf
import numpy as np

class KerasModel(tf.keras.Model):
        def __init__(self, n_hidden: int, n_out: int) -> None:
                super().__init__()
                self.fc_1 = tf.keras.layers.Dense(n_hidden, activation="relu")
                self.fc_2 = tf.keras.layers.Dense(n_out, activation="sigmoid")

        def call(self, tensor: tf.Tensor) -> tf.Tensor:
                input = tensor
                x = self.fc_1(input)
                x = self.fc_2(x)
                return x

n_input, n_hidden, n_out, batch_size, learning_rate = 10, 15, 1, 100, 0.01
dtype = tf.float32
x = np.random.rand(batch_size, n_input)
data_x = tf.convert_to_tensor(x, dtype=dtype)
raw_data_y = tf.random.uniform((batch_size, 1))
raw_data_y = tf.where(raw_data_y > 0.5, tf.ones_like(raw_data_y), tf.zeros_like(raw_data_y))
data_y = tf.cast(raw_data_y, dtype=dtype)

model = KerasModel(n_hidden, n_out)
model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=learning_rate), loss=tf.keras.losses.MeanSquaredError())
model.fit(data_x, data_y, batch_size=batch_size, epochs=100)

model_ref = registry.log_model(
    model,
    model_name="tfModel",
    version_name="v1",
    sample_input_data=[data_x],
)
model_ref.run([data_x])

import mlflow
from sklearn import datasets, model_selection, ensemble

db = datasets.load_diabetes(as_frame=True)
X_train, X_test, y_train, y_test = model_selection.train_test_split(db.data, db.target)
with mlflow.start_run() as run:
    rf = ensemble.RandomForestRegressor(n_estimators=100, max_depth=6, max_features=3)
    rf.fit(X_train, y_train)

    # Use the model to make predictions on the test dataset.
    predictions = rf.predict(X_test)
    signature = mlflow.models.signature.infer_signature(X_test, predictions)
    mlflow.sklearn.log_model(
        rf,
        "model",
        signature=signature,
    )
    run_id = run.info.run_id


model_ref = registry.log_model(
    mlflow.pyfunc.load_model(f"runs:/{run_id}/model"),
    model_name="mlflowModel",
    version_name="v1",
    conda_dependencies=["mlflow<=2.4.0", "scikit-learn", "scipy"],
    options={"ignore_mlflow_dependencies": True}
)
model_ref.run(X_test)

# Prepare model
import transformers
import pandas as pd

finbert_model = transformers.pipeline(
    task="text-classification",
    model="ProsusAI/finbert",
    top_k=2,
)

# Log the model
mv = registry.log_model(
    finbert_model,
    model_name="finbert",
    version_name="v1",
)

# Use the model
mv.run(pd.DataFrame(
        [
            ["I have a problem with my Snowflake that needs to be resolved asap!!", ""],
            ["I would like to have udon for today's dinner.", ""],
        ]
    )
)