def test_predict(self):
self.required_plugins("dffml-model-scikit")
# Import SciKit modules
dffml_model_scikit = importlib.import_module("dffml_model_scikit")
# Instantiate the model
model = dffml_model_scikit.LinearRegressionModel(
directory=self.mktempdir(),
predict=Feature("Salary", int, 1),
features=Features(
Feature("Years", int, 1),
Feature("Expertise", int, 1),
Feature("Trust", float, 1),
),
)
training_data = CSVSource(filename=self.train_filename)
test_data = CSVSource(filename=self.test_filename)
predict_data = CSVSource(filename=self.predict_filename)
# Train the model
train(model, training_data)
# Assess accuracy
accuracy(model, test_data)
# Make prediction
predictions = [
prediction for prediction in predict(model, predict_data)
]
self.assertEqual(round(predictions[0][2]["Salary"]["value"]), 70)
self.assertEqual(round(predictions[1][2]["Salary"]["value"]), 80)
def main():
# Train the model
train(model, "train.csv")
# Assess accuracy
print("Accuracy:", accuracy(model, "test.csv"))
# Make prediction
for i, features, prediction in predict(model, "predict.csv"):
features["TARGET"] = prediction["TARGET"]["value"]
print(features)
from dffml import CSVSource, Features, Feature
from dffml.noasync import train, accuracy, predict
from dffml_model_scratch.logisticregression import LogisticRegression
model = LogisticRegression(
features=Features(Feature("f1", float, 1)),
predict=Feature("ans", int, 1),
)
# Train the model
train(model, "dataset.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="dataset.csv")))
# Make prediction
for i, features, prediction in predict(model, {"f1": 0.8, "ans": 0}):
features["ans"] = prediction["ans"]["value"]
print(features)
from dffml import CSVSource, DefFeature
from dffml.noasync import train, accuracy, predict
from dffml_model_transformers.ner.ner_model import NERModel
model = NERModel(
sid=DefFeature("SentenceId", int, 1),
words=DefFeature("Words", str, 1),
predict=DefFeature("Tag", str, 1),
model_architecture_type="distilbert",
model_name_or_path="distilbert-base-cased",
epochs=1,
no_cuda=True,
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="train.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{"SentenceID": 1, "Words": "DFFML models can do NER",},
{"SentenceID": 2, "Words": "DFFML models can do regression",},
):
features["Tag"] = prediction["Tag"]["value"]
print(features)
from dffml import Features, DefFeature
from dffml.noasync import train, accuracy, predict
from dffml.model.slr import SLRModel
model = SLRModel(
features=Features(DefFeature("f1", float, 1)),
predict=DefFeature("ans", int, 1),
)
# Train the model
train(model, "dataset.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, "dataset.csv"))
# Make prediction
for i, features, prediction in predict(model, {"f1": 0.8, "ans": 0}):
features["ans"] = prediction["ans"]["value"]
print(features)
"Trust": 0.4,
"Salary": 40
},
)
# Assess accuracy
print(
"Accuracy:",
accuracy(
model,
{
"Years": 4,
"Expertise": 9,
"Trust": 0.5,
"Salary": 50
},
{
"Years": 5,
"Expertise": 11,
"Trust": 0.6,
"Salary": 60
},
),
)
# Make prediction
for i, features, prediction in predict(
model,
{
"Years": 6,
"Expertise": 13,
from dffml import Feature
from dffml.noasync import train, accuracy, predict
from myslr import MySLRModel
# Configure the model
model = MySLRModel(
feature=Feature("Years", int, 1),
predict=Feature("Salary", int, 1),
directory="model",
)
# Train the model
train(model, "train.csv")
# Assess accuracy
print("Accuracy:", accuracy(model, "test.csv"))
# Make predictions
for i, features, prediction in predict(model, "predict.csv"):
features["Salary"] = prediction["Salary"]["value"]
print(features)
predict=Feature("target", float, 1),
directory="model",
max_depth=3,
learning_rate=0.01,
n_estimators=200,
reg_lambda=1,
reg_alpha=0,
gamma=0,
colsample_bytree=0,
subsample=1,
))
# Train the model
train(model, *[{"data": x, "target": y} for x, y in zip(trainX, trainy)])
# Assess accuracy
print(
"Test accuracy:",
accuracy(model, *[{
"data": x,
"target": y
} for x, y in zip(testX, testy)]),
)
print(
"Training accuracy:",
accuracy(model, *[{
"data": x,
"target": y
} for x, y in zip(trainX, trainy)]),
)
DefFeature("SepalWidth", float, 1),
DefFeature("PetalLength", float, 1),
DefFeature("PetalWidth", float, 1),
),
predict=DefFeature("classification", int, 1),
epochs=3000,
steps=20000,
classifications=[0, 1, 2],
clstype=int,
)
# Train the model
train(model, "iris_training.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="iris_test.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{
"PetalLength": 4.2,
"PetalWidth": 1.5,
"SepalLength": 5.9,
"SepalWidth": 3.0,
},
{
"PetalLength": 5.4,
"PetalWidth": 2.1,
"SepalLength": 6.9,
"SepalWidth": 3.1,
from dffml import Feature, Features
from dffml.noasync import accuracy, predict, train
from dffml_model_scratch.anomalydetection import AnomalyModel
# Configure the model
model = AnomalyModel(
features=Features(Feature("A", int, 2),),
predict=Feature("Y", int, 1),
directory="model",
)
# Train the model
train(model, "trainex.csv")
# Assess accuracy for test set
print("Test set F1 score :", accuracy(model, "testex.csv"))
# Assess accuracy for training set
print("Training set F1 score :", accuracy(model, "trainex.csv"))
