def test_classification(backbone, fields, tmpdir):
train_data_frame = TEST_DF_1.copy()
val_data_frame = TEST_DF_1.copy()
test_data_frame = TEST_DF_1.copy()
data = TabularClassificationData.from_data_frame(
**fields,
target_fields="label",
train_data_frame=train_data_frame,
val_data_frame=val_data_frame,
test_data_frame=test_data_frame,
num_workers=0,
batch_size=2,
)
model = TabularClassifier.from_data(datamodule=data, backbone=backbone)
trainer = pl.Trainer(fast_dev_run=True, default_root_dir=tmpdir)
trainer.fit(model, data)
def test_serve():
train_data = {
"num_col": [1.4, 2.5],
"cat_col": ["positive", "negative"],
"target": [1, 2]
}
datamodule = TabularData.from_data_frame(
"cat_col",
"num_col",
"target",
pd.DataFrame.from_dict(train_data),
)
model = TabularClassifier.from_data(datamodule)
# TODO: Currently only servable once a preprocess has been attached
model._preprocess = datamodule.preprocess
model.eval()
model.serve()
# 1. Download the data
download_data("https://pl-flash-data.s3.amazonaws.com/titanic.zip", "data/")
# 2. Load the data
datamodule = TabularData.from_csv(
["Sex", "Age", "SibSp", "Parch", "Ticket", "Cabin", "Embarked"],
["Fare"],
target_field="Survived",
train_file="./data/titanic/titanic.csv",
test_file="./data/titanic/test.csv",
val_split=0.25,
)
# 3. Build the model
model = TabularClassifier.from_data(
datamodule, metrics=[Accuracy(), Precision(),
Recall()])
# 4. Create the trainer
trainer = flash.Trainer(fast_dev_run=True)
# 5. Train the model
trainer.fit(model, datamodule=datamodule)
# 6. Test model
trainer.test(model)
# 7. Save it!
trainer.save_checkpoint("tabular_classification_model.pt")
import torch
import flash
from flash.core.data.utils import download_data
from flash.tabular import TabularClassificationData, TabularClassifier
# 1. Create the DataModule
download_data("https://pl-flash-data.s3.amazonaws.com/titanic.zip", "./data")
datamodule = TabularClassificationData.from_csv(
["Sex", "Age", "SibSp", "Parch", "Ticket", "Cabin", "Embarked"],
"Fare",
target_fields="Survived",
train_file="data/titanic/titanic.csv",
val_split=0.1,
)
# 2. Build the task
model = TabularClassifier.from_data(datamodule)
# 3. Create the trainer and train the model
trainer = flash.Trainer(max_epochs=3, gpus=torch.cuda.device_count())
trainer.fit(model, datamodule=datamodule)
# 4. Generate predictions from a CSV
predictions = model.predict("data/titanic/titanic.csv")
print(predictions)
# 5. Save the model!
trainer.save_checkpoint("tabular_classification_model.pt")
# 1. Create the DataModule
download_data("https://pl-flash-data.s3.amazonaws.com/titanic.zip", "./data")
datamodule = TabularClassificationData.from_csv(
categorical_fields=[
"Sex", "Age", "SibSp", "Parch", "Ticket", "Cabin", "Embarked"
],
numerical_fields="Fare",
target_fields="Survived",
train_file="data/titanic/titanic.csv",
val_split=0.1,
batch_size=8,
)
# 2. Build the task
model = TabularClassifier.from_data(datamodule, backbone="fttransformer")
# 3. Create the trainer and train the model
trainer = flash.Trainer(max_epochs=3, gpus=torch.cuda.device_count())
trainer.fit(model, datamodule=datamodule)
# 4. Generate predictions from a CSV
datamodule = TabularClassificationData.from_csv(
predict_file="data/titanic/titanic.csv",
parameters=datamodule.parameters,
batch_size=8,
)
predictions = trainer.predict(model, datamodule=datamodule, output="classes")
print(predictions)
# 5. Save the model!